CN110659551A - Motion state recognition method, device and vehicle - Google Patents

Abstract

The invention discloses a method for identifying a motion state, which comprises the following steps: acquiring an image of a surrounding environment through at least one camera; and analyzing the fuzzy state of the image to identify a motion area or a static area in the image. Therefore, the moving area or the static area can be identified through the single-frame image, the requirement on data quantity is low, the calculated quantity is small, the requirement on hardware is low, the result can be rapidly output, and the detection rate is effectively improved. The invention also discloses a motion state recognition device, a vehicle early warning method and device, a road monitoring method and device and a vehicle.

Description

Motion state recognition method, device and vehicle

technical field

The invention relates to the technical field of object recognition, and in particular to a method for identifying a motion state, a method for early warning of a vehicle, a method for road monitoring, a device for identifying a state of motion, a device for early warning of a vehicle, a road monitoring device and a a vehicle.

Background technique

At this stage, the detection of moving objects in machine vision is mainly based on the relative relationship of multiple frames of images to distinguish between static pixels and moving pixels, and then realize the detection of surrounding moving objects according to the moving pixels.

The specific detection process is: sorting the images captured by the camera, determining the time sequence relationship between each frame of images, and then judging the still pixels and moving pixels in the current frame image according to the pixels in the previous frame image. After the static pixels of the current frame are obtained, motion compensation is performed on them, the moving pixels are extracted, the feature analysis is performed on the moving pixels, and the moving objects in the image are detected by clustering.

The above-mentioned moving object detection method mainly detects the video stream, which requires joint detection of multiple frames of images. During the detection process, the previous frame image needs to be processed and analyzed, and then the current frame image is judged to obtain the current frame image. stationary and moving objects. The whole process requires a large amount of data and a large amount of calculation, which requires high hardware.

SUMMARY OF THE INVENTION

The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the first purpose of the present invention is to propose a method for identifying a motion state, which can identify a motion area or a static area through a single frame of image, requires small amount of data, small amount of calculation, and low requirement on hardware, And it can output results quickly, effectively improving the detection rate.

The second object of the present invention is to provide a vehicle early warning method.

The third object of the present invention is to provide a road monitoring method.

A fourth object of the present invention is to propose a non-transitory computer-readable storage medium.

The fifth object of the present invention is to provide a motion state identification device.

The sixth object of the present invention is to provide a vehicle warning device.

The seventh object of the present invention is to provide a road monitoring device.

An eighth object of the present invention is to propose a vehicle.

In order to achieve the above object, an embodiment of the first aspect of the present invention proposes a method for recognizing a motion state, which includes the following steps: acquiring an image of the surrounding environment through at least one camera; analyzing the fuzzy state of the image, and identifying the moving or still areas in the image.

According to the method for recognizing a motion state according to an embodiment of the present invention, an image of the surrounding environment is acquired through at least one camera, and the blurred state of the image is analyzed to identify a motion area or a static area in the image. As a result, a moving area or a static area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate.

In order to achieve the above object, an embodiment of the second aspect of the present invention provides a vehicle early warning method, including the following steps: obtaining an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle; The fuzzy state is analyzed to identify the motion area in the image; the first geographic location coordinates of the motion area are obtained; the motion is calculated according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle The distance between the object and the current vehicle; if the distance is less than the preset safety distance threshold, an alarm signal is issued.

According to the vehicle early warning method of the embodiment of the present invention, an image of the surrounding environment of the current vehicle is obtained by at least one camera installed on the current vehicle, and the blurred state of the image is analyzed to identify the moving area in the image. Then, the first geographic location coordinates of the motion area are acquired, and the distance between the moving object and the current vehicle is calculated according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle, if the distance is less than a preset safe distance threshold , an alarm signal will be issued. As a result, the motion area can be identified through a single frame of image, which requires small data volume, small calculation amount, low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a vehicle. The effective data of driving is convenient for the driving judgment of the vehicle, such as early warning to prevent the occurrence of dangerous accidents.

In order to achieve the above object, a third aspect of the present invention provides a road monitoring method, which includes the following steps: acquiring an image of the surrounding environment through at least one camera installed on the road; analyzing the fuzzy state of the image, Identifying the moving area in the image; determining the traffic congestion situation of the road according to the moving area.

According to the road monitoring method of the embodiment of the present invention, at least one camera installed on the road is used to obtain an image of the surrounding environment, and the fuzzy state of the image is analyzed to identify the motion area in the image, and according to the motion area, determine the road. of traffic congestion. As a result, the motion area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a road. The effective data of monitoring is convenient for the judgment of road congestion.

In order to achieve the above object, the fourth aspect of the present invention provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the first aspect of the present invention is implemented. The method for recognizing the motion state, or the vehicle early warning method described in the embodiment of the second aspect of the present invention, or the road monitoring method described in the embodiment of the third aspect of the present invention.

According to the non-transitory computer-readable storage medium according to the embodiment of the present invention, through the above-mentioned method for recognizing a motion state, a moving area or a static area can be identified through a single frame of image, which requires less data and requires less calculation, and requires less hardware. It has low requirements, and can output results quickly, which can effectively improve the detection rate; through the above-mentioned vehicle early warning method, the moving area can be identified through a single frame of image, which requires small amount of data, small amount of calculation, and low hardware requirements. It can output results quickly, effectively improve the detection rate, and the identified motion area can be used as effective data for vehicle driving, which is convenient for vehicle driving judgment, such as early warning to prevent dangerous accidents; through the above-mentioned road monitoring method through a single frame image The motion area can be identified, the data volume is small, the calculation amount is small, the hardware requirement is low, and the result can be quickly output, which can effectively improve the detection rate, and the identified motion area can be used as effective data for road monitoring, which is convenient for road monitoring. Judgment of congestion.

In order to achieve the above object, a fifth aspect of the present invention provides an apparatus for recognizing a motion state, including: a first image acquisition unit for acquiring an image of the surrounding environment through at least one camera; a first recognition unit for The blur state of the image is analyzed to identify moving or stationary areas in the image.

According to the apparatus for recognizing motion state according to the embodiment of the present invention, the image of the surrounding environment is acquired by the first image acquisition unit, and the blur state of the image is analyzed by the first recognition unit to recognize the motion area or the static area in the image. As a result, a moving area or a static area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate.

In order to achieve the above object, an embodiment of the sixth aspect of the present invention provides a vehicle early warning device, comprising: a second image acquisition unit configured to acquire an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle The second identification unit is used to analyze the fuzzy state of the image and identify the motion area in the image; the distance acquisition unit is used to obtain the first geographic location coordinates of the motion area, and according to the The first geographic location coordinates and the second geographic location coordinates of the current vehicle are calculated to obtain the distance between the moving object and the current vehicle; the alarm unit is used to issue a warning if the distance is less than a preset safety distance threshold Alarm.

According to the vehicle early warning device of the embodiment of the present invention, the image of the current surrounding environment of the vehicle is acquired by the second image acquisition unit, and the blurred state of the image is analyzed by the second recognition unit, the motion area in the image is recognized, and the distance is acquired by The unit obtains the first geographic location coordinates of the motion area, and calculates the distance between the moving object and the current vehicle according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle, where the distance is less than a preset safety distance When the threshold value is reached, an alarm signal is sent out through the alarm unit. As a result, the motion area can be identified through a single frame of image, which requires small data volume, small calculation amount, low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a vehicle. The effective data of driving is convenient for the driving judgment of the vehicle, such as early warning to prevent the occurrence of dangerous accidents.

In order to achieve the above object, a seventh aspect of the present invention provides a road monitoring device, including: a third image acquisition unit for acquiring images of the surrounding environment through at least one camera installed on the road; a third identification unit , which is used for analyzing the fuzzy state of the image and identifying the motion area in the image; the judgment unit is used for determining the traffic congestion situation of the road according to the motion area.

According to the road monitoring device of the embodiment of the present invention, the image of the surrounding environment is acquired by the third image acquisition unit, the blurred state of the image is analyzed by the third recognition unit, the motion area in the image is recognized, and the motion area is identified by the judgment unit according to the motion. area to determine the traffic congestion on the road. As a result, the motion area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a road. The effective data of monitoring is convenient for the judgment of road congestion.

In order to achieve the above object, the embodiment of the eighth aspect of the present invention provides a vehicle, which includes the vehicle early warning device described in the embodiment of the sixth aspect of the present invention.

According to the vehicle according to the embodiment of the present invention, through the above-mentioned vehicle early warning device, the moving area can be identified through a single frame of image, the requirement for data amount is small, the amount of calculation is small, the requirement for hardware is low, and the result can be quickly output, which effectively improves the The detection rate and the identified motion area can be used as effective data for vehicle driving, which is convenient for vehicle driving judgment, such as early warning to prevent dangerous accidents.

Description of drawings

1 is a flowchart of a method for identifying a motion state according to an embodiment of the present invention;

FIG. 2 is a flowchart of identifying a moving area or a static area in an image according to an embodiment of the present invention;

3 is a flowchart of a vehicle early warning method according to an embodiment of the present invention;

4 is a flowchart of a road monitoring method according to an embodiment of the present invention;

5 is a flowchart of a method for measuring vehicle speed according to an embodiment of the present invention;

6 is a flowchart of a method for measuring the speed of a moving object according to an embodiment of the present invention;

7 is a schematic block diagram of an apparatus for identifying a motion state according to an embodiment of the present invention;

FIG. 8 is a schematic block diagram of a vehicle early warning device according to an embodiment of the present invention;

9 is a schematic block diagram of a road monitoring device according to an embodiment of the present invention;

Figure 10 is a schematic block diagram of a vehicle according to one embodiment of the present invention;

11 is a schematic block diagram of a device for measuring vehicle speed according to an embodiment of the present invention;

12 is a block schematic diagram of a vehicle according to another embodiment of the present invention;

13a is a schematic block diagram of a device for measuring the velocity of a moving object according to an embodiment of the present invention;

13b is a schematic block diagram of a device for measuring the velocity of a moving object according to an embodiment of the present invention;

14 is a schematic block diagram of a vehicle according to yet another embodiment of the present invention.

Detailed ways

The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention and should not be construed as limiting the present invention.

FIG. 1 is a flowchart of a method for recognizing a motion state according to an embodiment of the present invention.

As shown in FIG. 1 , the method for identifying a motion state according to an embodiment of the present invention may include the following steps:

S11. Obtain an image of the surrounding environment through at least one camera.

According to an embodiment of the present invention, there are multiple cameras, and acquiring an image of the surrounding environment through at least one camera includes: acquiring a panoramic image of the surrounding environment through the multiple cameras.

In practical applications, the number of cameras can be determined according to actual needs. For example, when it is necessary to detect moving objects such as passing vehicles and pedestrians on the road, a camera can be set above or on one side of the road, and the image of the road can be obtained through the camera; when it is necessary to detect moving objects such as vehicles and pedestrians around the vehicle During detection, multiple cameras can be set up on the vehicle, and images from different angles can be taken through multiple cameras, and then stitched into a panoramic image, so that all the surrounding environment can be obtained through the analysis of a panoramic image, so as to facilitate the analysis of the surrounding environment. Moving objects around the vehicle are detected. The image captured by the camera may be a three-channel image (an image in an RGB data format), which is not specifically limited here.

S12, analyze the blurred state of the image, and identify a moving area or a static area in the image.

According to an embodiment of the present invention, as shown in FIG. 2 , the fuzzy state of the image is analyzed, and the moving area or the static area in the image is identified, including:

S121, performing block processing on the image to obtain a plurality of block images.

Specifically, the image may be divided into blocks according to the resolution of the image to obtain images of small blocks, wherein the number of obtained block images is proportional to the resolution. For example, the higher the resolution of the image, the greater the number of obtained block images, the lower the resolution of the image, the less the number of obtained block images, thus, it can effectively prevent when the image resolution When it is lower, the same block method will result in unclear block images, which will affect the correct analysis of block images.

S122, acquiring the blur scale of each block image in the plurality of block images.

According to one embodiment of the present invention, obtaining the fuzzy scale of each block image in the plurality of block images includes: performing frequency domain transformation on the block images to obtain a spectrogram of the block image; The direction angle and the spacing of the dark stripes are used to obtain the blur scale of the patch image.

According to an embodiment of the present invention, obtaining the blur scale of the block image according to the direction angle of the dark fringes and the spacing of the dark fringes in the spectrogram includes: using a first preset formula to calculate the blur scale, the first preset formula for:

Among them, L is the blur scale, M is the lateral size of the block image, D is the spacing of the dark stripes, θ is the direction angle of the dark stripes, and σ is the aspect ratio of the block image.

Specifically, after obtaining a plurality of block images, discrete Fourier transform can be used to perform frequency domain transformation on each block image to obtain a spectrogram of each block image, and then the frequency spectrum of each block image can be graph for analysis. Due to the different degrees of motion blur caused by the static part and the moving part in the image, there will be dark fringes (spectral lines) of different degrees in the spectrogram. Therefore, according to the direction angle θ of the dark fringes and the The distance D is to obtain the blur scale L of each block image.

When obtaining the fuzzy scale L of the block image according to the direction angle θ of the dark stripes in the spectrogram and the distance D of the dark stripes, also obtain the lateral size M of the block image and the aspect ratio σ of the block image (when the block When the horizontal size M of the image is greater than the vertical size N of the block image, σ=M/N; when the horizontal size M of the block image is smaller than or equal to the vertical size N of the block image, σ=N/M), then, According to the lateral size M of the block image, the aspect ratio σ of the block image, the distance D of the dark stripes, and the direction angle θ of the dark stripes, the blur scale L of the block image is obtained by calculating the above formula (1).

S123 , according to the fuzzy scale, perform clustering on a plurality of block images, and calculate the average value of the fuzzy scales in each category.

Specifically, after obtaining the blurring scale of each block image, the block images with similar blurring scales are divided into one category, and then the average value of the blurring scale of each category of block images is calculated.

For example, when there are 6 block images and the corresponding blur scales are L1, L2, L3, L4, L5 and L6, if L1-L2<L0 (the preset threshold), it means that L1 and L2 correspond to The fuzzy scales of the block images are similar, and the block images corresponding to L1 and L2 belong to one class. Assuming that the fuzzy scale of the corresponding block images of L1, L2, L3 and L4 is determined by the above-mentioned method, and the fuzzy scale of the corresponding block images of L5 and L6 is similar, then the corresponding block images of L1, L2, L3 and L4 are similar. The average value of the corresponding fuzzy scale is (L1+L2+L3+L4)/4; the block images corresponding to L5 and L6 are another type, and the average value of the corresponding fuzzy scale is (L5+L6) /2.

S124: Determine a moving area or a static area according to the average value of the blur scale.

According to an embodiment of the present invention, determining the moving area or the static area according to the average value of the blur scale includes: acquiring the moving speed of the camera, and obtaining the static blur scale under the moving speed; judging the average value of the blur scale and the static blur Whether the difference between the scales is greater than a preset threshold; if so, the region corresponding to the class with the average value of the fuzzy scale is determined as a moving region; if not, the region corresponding to the class with the average value of the fuzzy scale is determined as a static region. The preset threshold can be calibrated according to the actual situation.

计算出静止物体的静止模糊尺度，其中，V为摄像头的运动速度，H为静止物体至摄像头的距离，f为摄像头的焦距，T为摄像头的曝光时间，L为静止模糊尺度，s为摄像头拍摄的静止物体图像的像素大小。然后，将各个模糊尺度的平均值与静止模糊尺度进行对比分析，将差值大于预设阈值的区域判断为运动区域，而差值小于或等于预设阈值的区域判断为静止区域。That is to say, when determining the motion area according to the average value of the blur scale, it can be determined in combination with its own state. For example, when the camera is in a fixed state (such as the camera is set above or on the side of the road), the still blur scale of a stationary object (such as the ground) is zero; when the camera is in motion (such as the camera is set on a vehicle), it can be determined according to the The movement speed of the camera (when the camera is set on the vehicle, the movement speed is the speed of the vehicle), through the formula

Calculate the still blur scale of the stationary object, where V is the motion speed of the camera, H is the distance from the stationary object to the camera, f is the focal length of the camera, T is the exposure time of the camera, L is the still blur scale, and s is the camera shot The pixel size of the still object image. Then, the average value of each blur scale and the static blur scale are compared and analyzed, and the area with the difference greater than the preset threshold is judged as the moving area, and the area with the difference less than or equal to the preset threshold is judged as the static area.

Further, after the motion regions are obtained, one or more motion regions may be divided according to the average value of the blur scale. For example, when there are 5 different average values of blurring scales with a difference greater than a preset threshold, the moving area can be divided into 5, which indicates that there are 5 moving objects in the image. Therefore, by performing motion blur analysis on a single frame of image, the moving area in the image can be quickly identified. Fast output results, effectively improving the detection rate.

According to the method for recognizing a motion state according to an embodiment of the present invention, an image of the surrounding environment is acquired through at least one camera, and the blurred state of the image is analyzed to identify a motion area or a static area in the image. As a result, a moving area or a static area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate.

In practical applications, the method for recognizing a motion state according to the embodiment of the present invention may be applicable to multiple scenarios. For example, it can be applied to vehicles to identify the area where moving objects are located around the vehicle, and then carry out vehicle warning, etc.; in another example, it can be applied to the road to identify the area where moving objects are located on the road, and then determine traffic congestion.

Specifically, FIG. 3 is a flowchart of a vehicle early warning method according to an embodiment of the present invention.

As shown in FIG. 3 , the vehicle early warning method according to the embodiment of the present invention may include the following steps:

S31 , acquiring an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle.

According to an embodiment of the present invention, there are multiple cameras, and acquiring an image of the surrounding environment through at least one camera includes: acquiring a panoramic image of the surrounding environment through the multiple cameras.

Specifically, multiple cameras can be set up on the current vehicle, and images from different angles are captured by multiple cameras, and then stitched into a panoramic image, so that all the surrounding environment can be obtained by analyzing a panoramic image, so as to facilitate the analysis of the surrounding environment. Moving objects (eg, vehicles, pedestrians, etc.) around the vehicle are detected. In practical applications, there is usually a panoramic image on the vehicle for obtaining the surrounding environment of the vehicle, so as long as the panoramic image is analyzed, there is no need to add an additional camera, which reduces the hardware cost and improves the utilization rate of the current camera.

S32, analyze the blurred state of the image, and identify the motion area in the image.

According to an embodiment of the present invention, as shown in FIG. 2 , the fuzzy state of the image is analyzed, and the motion area in the image is identified, including:

S121, performing block processing on the image to obtain a plurality of block images.

S122, acquiring the blur scale of each block image in the plurality of block images.

According to one embodiment of the present invention, obtaining the fuzzy scale of each block image in the plurality of block images includes: performing frequency domain transformation on the block images to obtain a spectrogram of the block image; The direction angle and the spacing of the dark stripes are used to obtain the blur scale of the patch image.

According to an embodiment of the present invention, obtaining the blur scale of the block image according to the direction angle of the dark fringes and the spacing of the dark fringes in the spectrogram includes: using a first preset formula to calculate the blur scale, the first preset formula As shown in the above formula (1).

S123 , according to the fuzzy scale, perform clustering on a plurality of block images, and calculate the average value of the fuzzy scales in each category.

S124: Determine the motion area according to the average value of the blur scale.

According to an embodiment of the present invention, determining the motion area according to the average value of the blur scale includes: acquiring the motion speed of the camera, and obtaining the static blur scale at the motion speed; judging the difference between the average value of the blur scale and the static blur scale Whether the difference is greater than the preset threshold; if so, it is determined that the area corresponding to the class of the average value of the blur scale is a motion area. The preset threshold can be calibrated according to the actual situation.

S33, acquiring the first geographic location coordinates of the motion area.

S34: Calculate the distance between the moving object and the current vehicle according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle.

That is to say, by converting the moving area in the image and the corresponding actual position coordinates, the actual distance of the moving object relative to the current vehicle can be obtained. Specifically, the position coordinates of the moving area in the original image can be calculated first, and then the actual distance of the moving object relative to the current vehicle can be calculated according to the position and shooting range of the camera combined with the existing algorithm.

S35, if the distance is smaller than the preset safety distance threshold, an alarm signal is sent. Among them, the safety distance threshold can be calibrated according to the actual situation.

Specifically, an image of the surrounding environment of the vehicle can be obtained through a camera installed on the vehicle, and then the image of the surrounding environment can be analyzed to identify whether there are moving objects around the vehicle. When there is a moving object around the vehicle, identify the area where the moving object is located, calculate the location coordinates of the area where the moving object is located, and then determine the distance between the current vehicle and the moving object according to the location coordinates, and provide it to the vehicle, In order to provide effective data for the driving of the vehicle, it is convenient for the driving judgment of the vehicle.

For example, the obtained distance can be sent to the early warning system of the vehicle, and then the early warning system will judge the distance, and if the distance is smaller than the set safety distance threshold, an alarm signal will be issued. On the one hand, for a manned vehicle, the driver can be reminded by the alarm signal, so that the driver can take corresponding measures in time to realize advanced assisted intelligent driving; It directly performs deceleration processing, direction adjustment, and parking processing to realize automatic driving.

According to the vehicle early warning method of the embodiment of the present invention, an image of the surrounding environment of the current vehicle is obtained by at least one camera installed on the current vehicle, and the blurred state of the image is analyzed to identify the moving area in the image. Then, the first geographic location coordinates of the motion area are acquired, and the distance between the moving object and the current vehicle is calculated according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle, if the distance is less than a preset safe distance threshold , an alarm signal will be issued. As a result, the motion area can be identified through a single frame of image, which requires small data volume, small calculation amount, low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a vehicle. The effective data of driving is convenient for the driving judgment of the vehicle, such as early warning to prevent the occurrence of dangerous accidents.

FIG. 4 is a flowchart of a road monitoring method according to an embodiment of the present invention.

As shown in FIG. 4 , the road monitoring method according to the embodiment of the present invention may include the following steps:

S31, obtain an image of the surrounding environment through at least one camera installed on the road.

According to an embodiment of the present invention, there are multiple cameras, and acquiring an image of the surrounding environment through at least one camera includes: acquiring a panoramic image of the surrounding environment through the multiple cameras.

Specifically, when it is necessary to monitor the traffic conditions of the road, one or more cameras can be set above or on one side of the road, and images of the road can be obtained through the one or more cameras. For example, when it is necessary to monitor the traffic situation at the intersection, images in different directions can be taken by multiple cameras, and then stitched into a panoramic image, so that all the surrounding environment can be obtained through the analysis of one panoramic image, so that To monitor the traffic situation at the entire intersection. Of course, in practical applications, a panoramic camera can also be used to capture an image of the entire intersection, and there is no specific limitation here, as long as the required image can be obtained.

S32, analyze the blurred state of the image, and identify the motion area in the image.

According to an embodiment of the present invention, as shown in FIG. 2 , the fuzzy state of the image is analyzed, and the motion area in the image is identified, including:

S121, performing block processing on the image to obtain a plurality of block images.

S122, acquiring the blur scale of each block image in the plurality of block images.

According to one embodiment of the present invention, obtaining the fuzzy scale of each block image in the plurality of block images includes: performing frequency domain transformation on the block images to obtain a spectrogram of the block image; The direction angle and the spacing of the dark stripes are used to obtain the blur scale of the patch image.

According to an embodiment of the present invention, obtaining the blur scale of the block image according to the direction angle of the dark fringes and the spacing of the dark fringes in the spectrogram includes: using a first preset formula to calculate the blur scale, the first preset formula As shown in the above formula (1).

S123 , according to the fuzzy scale, perform clustering on a plurality of block images, and calculate the average value of the fuzzy scales in each category.

S124: Determine the motion area according to the average value of the blur scale.

According to an embodiment of the present invention, determining the motion area according to the average value of the blur scale includes: acquiring the motion speed of the camera, and obtaining the static blur scale at the motion speed; judging the difference between the average value of the blur scale and the static blur scale Whether the difference is greater than the preset threshold; if so, it is determined that the area corresponding to the class of the average value of the blur scale is a motion area. The preset threshold can be calibrated according to the actual situation.

S33, according to the movement area, determine the traffic congestion situation of the road.

Specifically, if there are many moving areas in the image, and the distance between the moving areas is relatively small, it can be considered that the current road is in a traffic jam situation; otherwise, the current road is considered to be unobstructed. Or, after obtaining the motion area, it can be determined whether the moving object corresponding to the motion area is a pedestrian or a vehicle. If it is a vehicle, it is included in the total number of vehicles. If the total number of vehicles on the road is greater than the traffic capacity of the road within a period of time, The current road is considered to be in a traffic jam situation; otherwise, the current road is considered to be clear. Thus, real-time monitoring of road traffic conditions can be achieved.

According to the road monitoring method of the embodiment of the present invention, at least one camera installed on the road is used to obtain an image of the surrounding environment, and the fuzzy state of the image is analyzed to identify the motion area in the image, and determine the motion area according to the motion area. Traffic congestion on the road. As a result, the motion area can be identified through a single frame of image, which requires small data volume, small calculation amount, and low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a road. The effective data of monitoring is convenient for the judgment of road congestion.

In practical applications, based on the above principles, the real-time measurement of the vehicle's own speed can be realized.

FIG. 5 is a flowchart of a method for measuring vehicle speed according to an embodiment of the present invention.

As shown in FIG. 5 , the method for measuring vehicle speed according to the embodiment of the present invention may include the following steps:

S41 , acquiring an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle, and determining a ground area image in the image according to the position of the at least one camera.

According to an embodiment of the present invention, there are multiple cameras, and obtaining an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle includes: obtaining the surrounding environment of the current vehicle through multiple cameras installed on the current vehicle panoramic image.

Specifically, when it is necessary to detect the own speed of the current vehicle, multiple cameras can be set on the current vehicle, and images from different angles are captured by the multiple cameras to obtain multiple images, and then the multiple images are spliced into a panorama image. For example, combining with the location information of the camera, the images captured by the camera can be distinguished according to the location of the camera, and then stitching multiple images through the calibration information of the camera to obtain a panoramic image. In this way, all the conditions of the surrounding environment can be obtained through the analysis of a panoramic image, so as to facilitate the monitoring of the surrounding environment of the vehicle, and the analysis of a panoramic image can effectively reduce the amount of data for subsequent processing and improve the calculation speed. Reducing computation time has a big effect.

Further, after the image of the current vehicle surrounding environment is obtained by the above method, since the range of the image captured by the camera is fixed after the installation is completed, the ground area image in the image can be obtained by combining the position information of the camera.

It is understandable that a camera can be specially set up to capture images of the ground area, but this will increase the hardware cost. In practical applications, there are usually already existing panoramic images on the vehicle for obtaining the surrounding environment of the vehicle. The image can be analyzed without adding an additional camera, which reduces the hardware cost and improves the utilization rate of the current camera.

S42 , performing frequency domain transformation on the ground area image to obtain a spectrogram of the ground area image.

Specifically, after obtaining the ground area image, discrete Fourier transform may be used to perform frequency domain transformation on the ground area image to obtain a spectrogram of the ground area image.

S43, obtain the movement direction of the current vehicle and the movement speed value of the current vehicle according to the spectrogram, and obtain the movement speed vector of the current vehicle according to the movement direction and the movement speed value.

Specifically, the present invention mainly uses the motion of the vehicle to make the image captured by the camera on the vehicle produce motion blur, and then inversely obtains the vehicle's own speed according to the motion blur. Among them, since the direction of the vehicle motion is basically the same, and the speed is within a certain range, the direction of the resulting motion blur remains unchanged as a whole, and there are certain rules, and the relationship between the amount of motion blur and the vehicle speed can be calculated through the imaging principle model, so the actual speed of the vehicle can be obtained from the motion blur. The specific process is: analyze the spectrogram of the ground area image to obtain the fuzzy direction and fuzzy scale of the ground area image, obtain the moving direction of the vehicle according to the fuzzy direction, and calculate the vehicle according to the fuzzy scale and the relationship model between the fuzzy scale and the speed of the vehicle. The movement speed value of , and finally the combination of the two can obtain the real-time speed of the vehicle.

According to an embodiment of the present invention, obtaining the moving direction of the current vehicle according to the spectrogram includes: obtaining the moving direction according to the direction angle of the dark stripes in the spectrogram.

According to an embodiment of the present invention, obtaining the motion direction according to the direction angle of the dark fringes in the spectrogram includes: using a first preset formula to calculate and obtain the motion direction, and the first preset formula is:

Among them, α is the movement direction, θ is the direction angle of the dark stripes, N is the vertical size of the ground area image, and M is the horizontal size of the ground area image.

Specifically, due to vehicle motion, dark fringes of different degrees will appear in the spectrogram. By analyzing and comparing the blurred directions of the dark fringes in the spectrogram, the moving direction of the current vehicle can be obtained. For example, according to the direction angle θ of the dark fringes in the spectrogram, the blurring direction of the dark fringes can be obtained, and then the moving direction α of the current vehicle can be obtained. According to the direction angle θ of the dark stripes in the spectrogram, the fuzzy direction of the dark stripes is obtained, and then the moving direction α of the current vehicle is obtained, and the horizontal size M and the vertical size N of the ground area image are also obtained. According to the horizontal size of the ground area image M, the longitudinal dimension N and the direction angle θ of the dark stripes are calculated by the above formula (2) to obtain the blurring direction of the ground area image, which is the current vehicle motion direction α.

According to an embodiment of the present invention, obtaining the moving speed value of the current vehicle according to the spectrogram includes: obtaining the fuzzy scale of the image of the ground area according to the direction angle of the dark stripes and the spacing of the dark stripes in the spectrogram; according to the fuzzy scale, obtaining Movement speed value.

According to an embodiment of the present invention, obtaining the blurring scale of the image of the ground area according to the direction angle of the dark fringes and the spacing of the dark fringes in the spectrogram includes: using a second preset formula to calculate the blurring scale, the second preset formula for:

Among them, L is the blur scale, M is the lateral size of the ground area image, D is the spacing of the dark stripes, θ is the direction angle of the dark stripes, and σ is the aspect ratio of the ground area image.

According to an embodiment of the present invention, obtaining the motion speed value according to the fuzzy scale includes: using a third preset formula to calculate the motion speed value, where the third preset formula is:

Among them, V is the motion speed value, H is the distance from the ground to the camera, f is the focal length of the camera, T is the exposure time of the camera, L is the blur scale, and s is the pixel size of the ground area image.

Specifically, by analyzing and comparing the fuzzy scale of the dark stripes in the spectrogram, the motion speed value of the current vehicle can be obtained. For example, the fuzzy scale L of the ground area image can be obtained first according to the direction angle θ of the dark stripes in the spectrogram and the distance D of the dark stripes, and then the current vehicle speed value V can be obtained according to the fuzzy scale L of the ground area image.

Among them, when the fuzzy scale L of the ground area image is obtained according to the direction angle θ of the dark fringes and the distance D of the dark fringes in the spectrogram, the lateral size M of the ground area image and the aspect ratio σ of the ground area image are also obtained, according to The horizontal size M of the ground area image, the aspect ratio σ of the ground area image, the distance D of the dark stripes, and the direction angle θ of the dark stripes are calculated by the above formula (3) to obtain the blurring scale L of the ground area image.

After the blurring scale L of the ground area image is obtained, the moving speed value V of the current vehicle can be obtained by calculation according to the blurring scale L and the relationship model between the blurring scale and the moving speed. Among them, the relationship model between the blur scale and the motion speed can be shown in the above formula (4), that is, according to the distance H from the ground to the camera, the focal length f of the camera, the exposure time T of the camera, the pixel size of the ground area image and the blur For the scale L, the motion speed value V of the current vehicle is obtained by calculating the above formula (4).

Finally, according to the movement direction and movement speed value of the current vehicle, the movement speed vector of the current vehicle can be determined, that is, the real-time vehicle speed.

Therefore, by analyzing the motion blur direction generated by the ground part in the image, the moving direction of the current vehicle can be obtained, and by analyzing the motion blur scale generated by the ground part in the image, the current vehicle speed value can be obtained. The process only needs to analyze a single frame of image, the amount of data is small, and the amount of calculation is small, which can effectively improve the efficiency of speed detection.

According to the vehicle speed measurement method of the embodiment of the present invention, an image of the surrounding environment of the current vehicle is obtained through at least one camera installed on the current vehicle, and according to the position of the at least one camera, the ground area image in the image is determined, and the ground The area image is transformed into the frequency domain to obtain the spectrogram of the ground area image. Then, according to the spectrogram, the movement direction of the current vehicle and the movement speed value of the current vehicle are obtained, and the movement speed vector of the current vehicle is obtained according to the movement direction and the movement speed value. In this way, the real-time detection of the vehicle's own vehicle speed can be realized, replacing some vehicle speed sensors, which plays a certain role in promoting the development of intelligent driving, and can perform data fusion with different sensors to output its own vehicle speed more accurately. The environmental perception part of the sensor forms a redundant design. For example, when the vehicle speed measurement sensor does not work, it can complete the speed measurement work independently to ensure the driving safety of the vehicle.

In practical applications, based on the above principles, the measurement of the speed of the moving object can be realized, and specifically, the real-time measurement of the vehicle speed around the current vehicle during the driving process can be realized.

FIG. 6 is a flowchart of a method for measuring the speed of a moving object according to an embodiment of the present invention.

As shown in FIG. 6 , the method for measuring the speed of a moving object according to the embodiment of the present invention may include the following steps:

S51 , acquiring an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle.

According to an embodiment of the present invention, there are multiple cameras, and obtaining an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle includes: obtaining the surrounding environment of the current vehicle through multiple cameras installed on the current vehicle panoramic image.

Specifically, when it is necessary to measure the speed of moving objects (such as vehicles, pedestrians, etc.) around the vehicle, multiple cameras can be set on the current vehicle, and images from different angles are captured by the multiple cameras to obtain multiple images. , and then stitch multiple images into a panoramic image, so that all the conditions of the surrounding environment can be obtained by analyzing a panoramic image, so as to measure the speed of moving objects around the vehicle. In practical applications, there is usually a panoramic image on the vehicle for obtaining the surrounding environment of the vehicle, so as long as the panoramic image is analyzed, there is no need to add an additional camera, which reduces the hardware cost and improves the utilization rate of the current camera.

S52, performing frequency domain transformation on the image to obtain a first spectrogram of the image.

Specifically, after the current image of the surrounding environment of the vehicle is obtained, discrete Fourier transform may be used to transform the image in the frequency domain, so as to obtain the first spectrogram of the image.

S53: Determine a region where the difference between the fuzzy scale and the static fuzzy scale in the first spectrogram is greater than a preset threshold as the second spectrogram corresponding to the moving object around the current vehicle.

Specifically, when a moving object appears in the image, because the moving object has a speed, the degree of blurring produced by the moving object is different from that of the stationary object in the image. The specific embodiment is the dark stripes with different distances. The scale determines the area in which the moving object is located. For example, the blur scale of a stationary object (eg, the ground) can be obtained as the still blur scale, and then it is determined whether the difference between the blur scale and the still blur scale in the first spectrogram is greater than a preset threshold, and if so, then Determined as the area where the moving object is located. In simple terms, it is through the speed difference between a moving object and a stationary object (such as the ground), inversely deduce the difference in the fuzzy scale between the two, and then distinguish the position of the two from the image according to the difference, so as to locate out the area where the moving object is located.

According to an embodiment of the present invention, the above-mentioned method for measuring the speed of a moving object may further include: determining the ground area image in the image according to the position of at least one camera; converting the ground area image in the frequency domain to obtain the ground area image Spectrogram; obtains the blur scale of the spectrogram of the ground area image to obtain the still blur scale.

Specifically, after the camera is installed, the image range it captures is fixed, so after obtaining the image of the surrounding environment of the current vehicle, the position information of the camera can be combined to obtain the image of the ground area in the image, and then the discrete Fourier image can be obtained. The leaf transform transforms the ground area image in the frequency domain to obtain the spectrogram of the ground area image, and obtains the fuzzy scale of the spectrogram to obtain the static blur scale, and then determines the number corresponding to the moving objects around the current vehicle according to the static blur scale. Two spectrograms.

S54, obtain the relative movement direction and relative movement speed value of the moving object relative to the current vehicle according to the second spectrogram, and obtain the relative movement speed vector of the moving object relative to the current vehicle according to the relative movement direction and the relative movement speed value.

According to an embodiment of the present invention, obtaining the relative motion direction of the moving object relative to the current vehicle according to the second spectrogram includes: obtaining the relative motion direction according to the direction angle of the dark fringes in the second spectrogram.

According to an embodiment of the present invention, obtaining the relative motion direction according to the direction angle of the dark fringes in the second spectrogram includes: using a first preset formula to calculate and obtain the relative motion direction, and the first preset formula is:

Among them, α is the relative motion direction, θ is the direction angle of the dark fringes, N is the vertical size of the image corresponding to the second spectrogram, and M is the horizontal size of the image corresponding to the second spectrogram.

Specifically, by analyzing and comparing the blurred direction of the dark stripes in the spectrogram, the relative motion direction of the moving object relative to the current vehicle can be obtained. For example, according to the direction angle θ of the dark fringes in the second spectrogram, the relative motion direction α of the moving object relative to the current vehicle can be obtained. When the relative motion direction α of the moving object relative to the current vehicle is obtained according to the direction angle θ of the dark stripes in the second spectrogram, the horizontal size M and the vertical size N of the image corresponding to the second spectrogram are also obtained. According to the second spectrogram Corresponding to the horizontal size M of the image, the vertical size N and the direction angle θ of the dark stripes, the blurring direction of the second spectrogram is obtained by calculating the above formula (5), and the blurring direction is the relative motion direction α of the moving object relative to the current vehicle. .

According to an embodiment of the present invention, obtaining the relative motion velocity value of the moving object according to the second spectrogram includes: obtaining the fuzzy scale of the second spectrogram according to the direction angle of the dark fringes and the spacing of the dark fringes in the second spectrogram ; According to the fuzzy scale, get the relative motion speed value.

According to an embodiment of the present invention, obtaining the fuzzy scale of the second spectrogram according to the direction angle of the dark fringes and the spacing of the dark fringes in the second spectrogram includes: using a second preset formula to calculate the fuzzy scale, and the second The default formula is:

Among them, L is the blur scale, M is the horizontal size of the image corresponding to the second spectrogram, D is the spacing of the dark fringes, θ is the direction angle of the dark fringes, and σ is the aspect ratio of the image corresponding to the second spectrogram.

According to an embodiment of the present invention, obtaining the relative motion speed value according to the fuzzy scale includes: using a third preset formula to calculate and obtain the relative motion speed value, where the third preset formula is:

Among them, V is the relative motion speed value, H is the distance between the moving object and the camera, f is the focal length of the camera, T is the exposure time of the camera, L is the blur scale, and s is the pixel size of the image corresponding to the second spectrogram.

Specifically, by analyzing and comparing the blurring scale of the dark fringes in the second spectrogram, the relative motion velocity value of the moving object can be obtained. For example, the fuzzy scale L of the second spectrogram can be obtained first according to the direction angle θ of the dark fringes and the distance D of the dark fringes in the second spectrogram, and then the relative motion of the moving object can be obtained according to the fuzzy scale L of the second spectrogram. Velocity value V.

Wherein, when the fuzzy scale L of the second spectrogram is obtained according to the direction angle θ of the dark fringes and the distance D of the dark fringes in the second spectrogram, the lateral size M of the image corresponding to the second spectrogram and the second spectrogram are also obtained. Corresponding to the aspect ratio σ of the image, according to the lateral dimension M of the image corresponding to the second spectrogram, the aspect ratio σ of the second spectrogram corresponding to the image, the distance D of the dark fringes and the direction angle θ of the dark fringes, through the above formula (6 ) to obtain the fuzzy scale L of the second spectrogram.

After the fuzzy scale L of the second spectrogram is obtained, the relative motion speed value V of the moving object can be obtained by calculation according to the fuzzy scale L and the relationship model between the fuzzy scale and the motion speed. The relationship model between the blur scale and the motion speed can be shown in the above formula (7), that is, according to the distance H between the moving object and the camera, the focal length f of the camera, the exposure time T of the camera, and the second spectrogram corresponding to the image. The pixel size and the blur scale L are calculated by the above formula (7) to obtain the relative motion speed value V of the moving object.

Finally, according to the relative motion direction and the relative motion speed value, the relative motion speed vector of the moving object relative to the current vehicle is obtained.

S55, obtain the motion speed vector of the moving object according to the relative motion speed vector and the current motion speed vector of the vehicle.

Specifically, the movement speed value of the current vehicle can be obtained through the vehicle speed sensor, or the movement speed value of the current vehicle can be obtained through the aforementioned vehicle speed measurement method, and at the same time, the movement direction of the current vehicle can be obtained through the aforementioned vehicle speed measurement method, or according to When obtaining the area where the moving object is located, the blurring direction of the area where the stationary object is located (eg, the blurring direction of the ground area image) is used to obtain the moving direction of the current vehicle, and the motion velocity vector of the current vehicle can be obtained by combining the two. Finally, perform vector calculation on the relative motion speed vector and the motion speed vector of the current vehicle to obtain the motion speed vector of the moving object.

According to an embodiment of the present invention, the above-mentioned method for measuring the speed of a moving object may further include: judging whether the moving object is a moving vehicle; if the moving object is a moving vehicle, the obtained moving speed vector of the moving object is the moving speed of the moving vehicle vector.

Specifically, the moving objects around the current vehicle are usually uncertain, which may be pedestrians or vehicles. Therefore, during or after obtaining the motion velocity vector of the moving object, it is also possible to determine whether the moving object is a pedestrian or a vehicle. If it is a pedestrian, the obtained moving speed vector is the moving speed vector of the pedestrian; if it is a vehicle, the obtained moving speed vector is the moving speed vector of the vehicle. Wherein, when judging whether the moving object is a pedestrian or a vehicle, it can be realized by adopting the existing technology, which is not limited here.

According to the method for measuring the speed of a moving object according to the embodiment of the present invention, an image of the surrounding environment of the current vehicle is acquired through at least one camera installed on the current vehicle, and the image is converted in the frequency domain to obtain the first spectrogram of the image, and the An area in the first spectrogram where the difference between the fuzzy scale and the static fuzzy scale is greater than the preset threshold is determined as the second spectrogram corresponding to the moving objects around the current vehicle. Then, according to the second spectrogram, the relative movement direction and relative movement speed value of the moving object relative to the current vehicle are obtained, and the relative movement speed vector of the moving object relative to the current vehicle is obtained according to the relative movement direction and the relative movement speed value, and According to the relative motion speed vector and the current vehicle motion speed vector, the motion speed vector of the moving object is obtained. Thereby, the moving speed of the surrounding moving objects can be sensed accurately in real time. Among them, when the moving object is a vehicle, it can sense the speed of moving vehicles around the current vehicle in real time and accurately, and can replace some millimeter-wave radars to locate, detect and track vehicles within the field of view. It plays a certain role in promoting the development of intelligent driving. It can perform data fusion with different sensors to output information about the surrounding environment more accurately. For example, it can more accurately perceive obstacles around the vehicle and detect the movement of obstacles. status and speed. In addition, a redundant design can be formed for some sensors of environmental perception. For example, when the millimeter-wave radar suddenly stops working, the corresponding work can be completed independently to ensure the driving safety of the vehicle.

To sum up, the present invention can realize the recognition of moving objects, the measurement of the speed of moving objects, and the measurement of the vehicle's own speed by analyzing the motion blur of a single frame of image, which requires less data and requires less calculation. It has a small amount, low hardware requirements, and can form a redundant design with some sensors to ensure the driving safety of the vehicle, and can be used in a variety of scenarios.

In order to achieve the above object, the present invention also proposes a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for recognizing the motion state, or the above-mentioned vehicle warning method is realized. , or the above-mentioned road monitoring method.

According to the non-transitory computer-readable storage medium according to the embodiment of the present invention, through the above-mentioned method for recognizing a motion state, a moving area or a static area can be identified through a single frame of image, which requires less data and requires less calculation, and requires less hardware. It has low requirements, and can output results quickly, which can effectively improve the detection rate; through the above-mentioned vehicle early warning method, the moving area can be identified through a single frame of image, which requires small amount of data, small amount of calculation, and low hardware requirements. It can output results quickly, effectively improve the detection rate, and the identified motion area can be used as effective data for vehicle driving, which is convenient for vehicle driving judgment, such as early warning to prevent dangerous accidents; through the above-mentioned road monitoring method through a single frame image The motion area can be identified, the data volume is small, the calculation amount is small, the hardware requirement is low, and the result can be quickly output, which can effectively improve the detection rate, and the identified motion area can be used as effective data for road monitoring, which is convenient for road monitoring. Judgment of congestion.

In order to achieve the above object, the present invention also provides another non-transitory computer-readable storage medium, which stores a computer program, and when the program is executed by the processor, realizes the above-mentioned vehicle speed measurement method.

According to the non-transitory computer-readable storage medium of the embodiment of the present invention, the vehicle's real-time detection of its own vehicle speed can be realized through the above-mentioned vehicle speed measurement method.

To achieve the above object, the present invention also proposes another non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for measuring the speed of a moving object is implemented.

According to the non-transitory computer-readable storage medium of the embodiment of the present invention, through the above-mentioned method for measuring the speed of a moving object, the moving speed of surrounding moving objects can be sensed in real time and accurately. to perceive the speed of moving vehicles around the current vehicle.

FIG. 7 is a schematic block diagram of an apparatus for identifying a motion state according to an embodiment of the present invention.

As shown in FIG. 7 , the apparatus for identifying a motion state according to the embodiment of the present invention may include: a first image acquiring unit 11 and a first identifying unit 12 .

Wherein, the first image acquisition unit 11 is used to acquire images of the surrounding environment through at least one camera; the first recognition unit 12 is used to analyze the blurred state of the image, and identify the moving area or the static area in the image.

According to an embodiment of the present invention, there are multiple cameras, and the first image acquisition unit 11 is specifically configured to acquire panoramic images of the surrounding environment through the multiple cameras.

According to an embodiment of the present invention, the first identification unit 12 is specifically configured to perform block processing on the image to obtain multiple block images; obtain the blur scale of each block image in the multiple block images; according to the blur scale, Cluster images of multiple blocks, and calculate the average value of fuzzy scales in each category; according to the average value of fuzzy scales, determine the moving area or static area.

According to an embodiment of the present invention, the first identification unit 12 is specifically used to perform frequency domain conversion on the block image to obtain a spectrogram of the block image; The blur scale of the block image.

According to an embodiment of the present invention, the first identification unit 12 is specifically configured to use a first preset formula to calculate the fuzzy scale, and the first preset formula is:

Among them, L is the blur scale, M is the lateral size of the block image, D is the spacing of the dark stripes, θ is the direction angle of the dark stripes, and σ is the aspect ratio of the block image.

According to an embodiment of the present invention, the first identification unit 12 is specifically configured to obtain the moving speed of the camera, and obtain the static blur scale under the moving speed; determine whether the difference between the average value of the blur scale and the static blur scale is greater than a predetermined value. Set the threshold value; if yes, the region corresponding to the class with the average value of the fuzzy scale is determined to be a moving region; if not, the region corresponding to the class with the average value of the fuzzy scale is determined to be a static region.

It should be noted that, for details that are not disclosed in the apparatus for recognizing the motion state of the embodiment of the present invention, please refer to the details disclosed in the method for recognizing the motion state of the embodiment of the present invention, which will not be repeated here.

According to the apparatus for recognizing motion state according to the embodiment of the present invention, the image of the surrounding environment is acquired by the first image acquisition unit, and the blur state of the image is analyzed by the first recognition unit to recognize the motion area or the static area in the image. As a result, a moving area or a static area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate.

FIG. 8 is a schematic block diagram of a vehicle early warning device according to an embodiment of the present invention.

As shown in FIG. 8 , the vehicle early warning device according to the embodiment of the present invention may include: a second image acquisition unit 21 , a second identification unit 22 , a distance acquisition unit 23 and an alarm unit 24 .

Wherein, the second image acquisition unit 21 is used to acquire an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle; the second recognition unit 22 is used to analyze the blurred state of the image and identify the motion in the image area; the distance acquisition unit 23 is used to obtain the first geographic location coordinates of the motion area, and calculates the distance between the moving object and the current vehicle according to the first geographic location coordinates and the second geographic location coordinates of the current vehicle; the alarm unit 24 Used to issue an alarm signal if the distance is less than the preset safe distance threshold.

It should be noted that, for details not disclosed in the vehicle early warning device of the embodiment of the present invention, please refer to the details disclosed in the vehicle early warning method of the embodiment of the present invention, which will not be repeated here.

According to the vehicle early warning device of the embodiment of the present invention, the image of the current surrounding environment of the vehicle is acquired by the second image acquisition unit, and the blurred state of the image is analyzed by the second recognition unit, the motion area in the image is recognized, and the distance is acquired by The unit acquires the first geographic location coordinates of the motion area, and calculates the distance between the moving object and the current vehicle according to the first geographic location coordinates and the first geographic location coordinates of the current vehicle, wherein the distance is less than the preset safety distance When the threshold value is reached, an alarm signal is sent out through the alarm unit. As a result, the motion area can be identified through a single frame of image, which requires small data volume, small calculation amount, low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a vehicle. The effective data of driving is convenient for the driving judgment of the vehicle, such as early warning to prevent the occurrence of dangerous accidents.

FIG. 9 is a schematic block diagram of a road monitoring device according to an embodiment of the present invention.

As shown in FIG. 9 , the road monitoring device according to the embodiment of the present invention may include: a third image acquisition unit 31 , a third identification unit 32 and a judgment unit 33 .

Wherein, the third image acquisition unit 31 is used to acquire the image of the surrounding environment through at least one camera installed on the road; the third recognition unit 32 is used to analyze the blurred state of the image, and identify the motion area in the image; determine The unit 33 is used for determining the traffic congestion situation of the road according to the movement area.

It should be noted that, for details not disclosed in the road monitoring device in the embodiment of the present invention, please refer to the details disclosed in the road monitoring method in the embodiment of the present invention, and details are not repeated here.

According to the road monitoring device of the embodiment of the present invention, the image of the surrounding environment is acquired by the third image acquisition unit, the blurred state of the image is analyzed by the third recognition unit, the motion area in the image is recognized, and the motion area is identified by the judgment unit according to the motion. area to determine the traffic congestion on the road. As a result, the motion area can be identified through a single frame of image, which requires less data volume, less calculation, and low hardware requirements, and can output results quickly, effectively improving the detection rate, and the identified motion area can be used as a road. The effective data of monitoring is convenient for the judgment of road congestion.

10 is a schematic block diagram of a vehicle according to one embodiment of the present invention.

As shown in FIG. 10 , the vehicle 40 according to the embodiment of the present invention includes the above-mentioned vehicle early warning device 41 .

According to the vehicle according to the embodiment of the present invention, through the above-mentioned vehicle early warning device, the moving area can be identified through a single frame of image, the requirement for data amount is small, the amount of calculation is small, the requirement for hardware is low, and the result can be quickly output, which effectively improves the The detection rate and the identified motion area can be used as effective data for vehicle driving, which is convenient for vehicle driving judgment, such as early warning to prevent dangerous accidents.

FIG. 11 is a schematic block diagram of a vehicle speed measuring apparatus according to an embodiment of the present invention.

As shown in FIG. 11 , the apparatus for measuring vehicle speed according to the embodiment of the present invention may include: a first image acquisition unit 51 , a second image acquisition unit 52 , a conversion unit 53 and a vehicle speed acquisition unit 54 .

Wherein, the first image acquisition unit 51 is used to acquire an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle; the second image acquisition unit 52 is used to determine the ground in the image according to the position of the at least one camera area image; the conversion unit 53 is used to transform the ground area image in the frequency domain to obtain the spectrogram of the ground area image; the vehicle speed acquisition unit 54 is used to obtain the motion direction of the current vehicle and the motion speed value of the current vehicle according to the spectrogram, and According to the movement direction and the movement speed value, the movement speed vector of the current vehicle is obtained.

According to an embodiment of the present invention, there are multiple cameras, and the first image obtaining unit 51 is specifically configured to obtain a panoramic image of the surrounding environment of the current vehicle through multiple cameras installed on the current vehicle.

According to an embodiment of the present invention, the vehicle speed obtaining unit 54 is specifically configured to obtain the movement direction according to the direction angle of the dark fringes in the spectrogram.

According to an embodiment of the present invention, the vehicle speed obtaining unit 54 is specifically configured to use a first preset formula to calculate the movement direction, and the first preset formula is:

Among them, α is the movement direction, θ is the direction angle of the dark stripes, N is the vertical size of the ground area image, and M is the horizontal size of the ground area image.

According to an embodiment of the present invention, the vehicle speed obtaining unit 54 is specifically configured to obtain the blur scale of the image of the ground area according to the direction angle of the dark fringes and the spacing of the dark streaks in the spectrogram; and obtain the motion speed value according to the blur scale.

According to an embodiment of the present invention, the vehicle speed obtaining unit 54 is specifically configured to use a second preset formula to calculate the fuzzy scale, and the second preset formula is:

Among them, L is the blur scale, M is the lateral size of the ground area image, D is the spacing of the dark stripes, θ is the direction angle of the dark stripes, and σ is the aspect ratio of the ground area image.

According to an embodiment of the present invention, the vehicle speed obtaining unit 54 is specifically configured to obtain the motion speed value by using a third preset formula, and the third preset formula is:

Among them, V is the motion speed value, H is the distance from the ground to the camera, f is the focal length of the camera, T is the exposure time of the camera, L is the blur scale, and s is the pixel size of the ground area image.

It should be noted that, for details not disclosed in the vehicle speed measuring device of the embodiment of the present invention, please refer to the details disclosed in the vehicle speed measuring method of the embodiment of the present invention, and details are not repeated here.

According to the vehicle speed measurement device of the embodiment of the present invention, the image of the current surrounding environment of the vehicle is acquired by the first image acquisition unit, the ground area image in the image is determined by the second image acquisition unit, and the conversion unit is used for the image of the ground area. Frequency domain transformation to obtain the spectrogram of the ground area image. Then, the vehicle speed obtaining unit obtains the current vehicle motion direction and the current vehicle motion speed value according to the spectrogram, and obtains the current vehicle motion speed vector according to the motion direction and the motion speed value. In this way, the real-time detection of the vehicle's own vehicle speed can be realized.

12 is a schematic block diagram of a vehicle according to another embodiment of the present invention.

As shown in FIG. 12 , the vehicle 60 according to the embodiment of the present invention includes the above-mentioned vehicle speed measuring device 61 .

According to the vehicle of the embodiment of the present invention, through the above-mentioned vehicle speed measuring device, the vehicle can realize real-time detection of its own vehicle speed.

Fig. 13a is a schematic block diagram of an apparatus for measuring the velocity of a moving object according to an embodiment of the present invention.

As shown in FIG. 13a, the apparatus for measuring the speed of a moving object according to the embodiment of the present invention may include: a first image acquisition unit 71, a conversion unit 72, a second image acquisition unit 73, a first speed acquisition unit 74, and a second speed acquisition unit 75.

The first image acquisition unit 71 is used to acquire an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle; the conversion unit 72 is used to convert the image in the frequency domain to obtain the first spectrogram of the image; the second image The acquiring unit 73 is used to determine the area where the difference between the fuzzy scale and the static fuzzy scale in the first spectrogram is greater than the preset threshold as the second spectrogram corresponding to the moving objects around the current vehicle; the first speed acquiring unit 74 It is used to obtain the relative movement direction and relative movement speed value of the moving object relative to the current vehicle according to the second spectrogram, and obtain the relative movement speed vector of the moving object relative to the current vehicle according to the relative movement direction and relative movement speed value; The second speed obtaining unit 75 is configured to obtain the moving speed vector of the moving object according to the relative moving speed vector and the moving speed vector of the current vehicle.

According to an embodiment of the present invention, there are multiple cameras, and the first image acquisition unit 71 is specifically configured to acquire a panoramic image of the surrounding environment of the current vehicle through multiple cameras installed on the current vehicle.

According to an embodiment of the present invention, as shown in FIG. 13b, the above-mentioned apparatus for measuring the speed of a moving object may further include: a third image acquisition unit 76, configured to determine the ground area image in the image according to the position of at least one camera The frequency acquisition unit 77 is used to transform the ground area image in the frequency domain to obtain the spectrogram of the ground area image, and obtain the fuzzy scale of the spectrogram of the ground area image to obtain the static fuzzy scale.

According to an embodiment of the present invention, the first speed obtaining unit 74 is specifically configured to obtain the relative motion direction according to the direction angle of the dark fringes in the second spectrogram.

According to an embodiment of the present invention, the first speed obtaining unit 74 is specifically configured to use a first preset formula to calculate and obtain the relative motion direction, and the first preset formula is:

Among them, α is the relative motion direction, θ is the direction angle of the dark fringes, N is the vertical size of the image corresponding to the second spectrogram, and M is the horizontal size of the image corresponding to the second spectrogram.

According to an embodiment of the present invention, the first velocity obtaining unit 74 is specifically configured to obtain the fuzzy scale of the second spectrogram according to the direction angle of the dark fringes and the spacing of the dark fringes in the second spectrogram; according to the fuzzy scale, obtain the relative motion speed value.

According to an embodiment of the present invention, the first speed obtaining unit 74 is specifically configured to use a second preset formula to calculate the blur scale, and the second preset formula is:

Among them, L is the blur scale, M is the horizontal size of the image corresponding to the second spectrogram, D is the spacing of the dark fringes, θ is the direction angle of the dark fringes, and σ is the aspect ratio of the image corresponding to the second spectrogram.

According to an embodiment of the present invention, the first speed obtaining unit 74 is specifically configured to use a third preset formula to calculate the relative motion speed value, and the third preset formula is:

Among them, V is the relative motion speed value, H is the distance from the moving object to the camera, f is the focal length of the camera, T is the exposure time of the camera, L is the blur scale, and s is the pixel size of the image corresponding to the second spectrogram.

According to an embodiment of the present invention, as shown in FIG. 13b, the above-mentioned apparatus for measuring the speed of a moving object may further include: a judgment unit 78 for judging whether the moving object is a moving vehicle, wherein, if the moving object is a moving vehicle, then The obtained motion speed vector of the moving object is the motion speed vector of the moving vehicle.

It should be noted that, for details not disclosed in the apparatus for measuring the velocity of a moving object in the embodiment of the present invention, please refer to the details disclosed in the method for measuring the velocity of a moving object in the embodiment of the present invention, and details are not repeated here.

According to the device for measuring the speed of a moving object according to the embodiment of the present invention, the image of the current surrounding environment of the vehicle is acquired by the first image acquisition unit, and the image is converted in the frequency domain by the conversion unit to obtain the first spectrogram of the image, and the second The image acquisition unit determines an area in the first spectrogram where the difference between the blurring scale and the static blurring scale is greater than a preset threshold as the second spectrogram corresponding to the moving objects around the current vehicle. Then, the relative movement direction and relative movement speed value of the moving object relative to the current vehicle are obtained by the first speed obtaining unit according to the second frequency spectrum, and the relative movement direction and relative movement speed value of the moving object are obtained according to the relative movement direction and relative movement speed value. The relative motion speed vector, and the motion speed vector of the moving object is obtained by the second speed obtaining unit according to the relative motion speed vector and the motion speed vector of the current vehicle. Thereby, the moving speed of the surrounding moving objects can be sensed in real time and accurately, wherein when the moving object is a vehicle, the vehicle speed of the moving vehicles around the current vehicle can be sensed in real time and accurately.

14 is a schematic block diagram of a vehicle according to yet another embodiment of the present invention.

As shown in FIG. 14 , the vehicle 80 according to the embodiment of the present invention includes the above-mentioned measuring device 81 for the speed of the moving object.

According to the vehicle according to the embodiment of the present invention, through the above-mentioned device for measuring the speed of the moving object, the moving speed of the surrounding moving objects can be sensed in real time and accurately, wherein when the moving object is a vehicle, the surrounding of the current vehicle can be sensed in real time and accurately. speed of the moving vehicle.

It should be understood that various parts of the present invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

In addition, in the description of the present invention, the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "Left", "Right", "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise", "Axial", "Radial" ”, “circumferential” and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation, construction and operation in a particular orientation, and therefore should not be construed as a limitation of the present invention.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

In the present invention, unless otherwise expressly specified and limited, the terms "installed", "connected", "connected", "fixed" and other terms should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between the two elements, unless otherwise specified limit. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

In the present invention, unless otherwise expressly specified and limited, a first feature "on" or "under" a second feature may be in direct contact between the first and second features, or the first and second features indirectly through an intermediary touch. Also, the first feature being "above", "over" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is level higher than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature has a lower level than the second feature.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

Although the embodiments of the present invention have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present invention. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (15)

1. A method for identifying a motion state is characterized by comprising the following steps:

acquiring an image of a surrounding environment through at least one camera;

and analyzing the fuzzy state of the image, and identifying a motion area or a static area in the image.

2. The identification method according to claim 1, wherein the number of the cameras is plural, and the acquiring the image of the surrounding environment by at least one camera comprises:

and acquiring a panoramic image of the surrounding environment through a plurality of cameras.

3. The identification method according to claim 1, wherein the analyzing the blur state of the image to identify a motion region or a static region in the image comprises:

carrying out blocking processing on the image to obtain a plurality of block images;

acquiring a fuzzy scale of each block image in the plurality of block images;

clustering the block images according to the fuzzy scale, and calculating the average value of the fuzzy scale in each class;

and determining the motion area or the static area according to the average value of the fuzzy scale.

4. The identification method according to claim 3, wherein said obtaining the blur scale of each block image of the plurality of block images comprises:

performing frequency domain conversion on the block image to obtain a spectrogram of the block image;

and obtaining the fuzzy scale of the block image according to the direction angle of the dark stripes in the spectrogram and the distance of the dark stripes.

5. The identification method according to claim 4, wherein the obtaining the blur scale of the block image according to the direction angle of the dark stripes and the distance between the dark stripes in the spectrogram comprises:

calculating to obtain the fuzzy scale by adopting a first preset formula, wherein the first preset formula is as follows:

wherein L is the blur scale, M is the lateral size of the block image, D is the distance between the dark stripes, θ is the direction angle of the dark stripes, and σ is the aspect ratio of the block image.

6. The identification method according to claim 3, wherein the determining the motion region or the stationary region according to the average value of the blur scale comprises:

acquiring the movement speed of the camera and acquiring a static fuzzy scale at the movement speed;

judging whether the difference value between the average value of the fuzzy scales and the static fuzzy scale is larger than a preset threshold value or not;

if so, judging that the area corresponding to the class of the average value of the fuzzy scale is the motion area;

if not, judging that the area corresponding to the class of the average value of the fuzzy scale is the static area.

7. A vehicle early warning method is characterized by comprising the following steps:

acquiring an image of the surrounding environment of a current vehicle through at least one camera mounted on the current vehicle;

analyzing the fuzzy state of the image, and identifying a motion area in the image;

acquiring a first geographical position coordinate of the motion area;

calculating to obtain the distance between the moving object and the current vehicle according to the first geographical position coordinate and the second geographical position coordinate of the current vehicle;

and if the distance is smaller than a preset safety distance threshold value, sending an alarm signal.

8. A method of road monitoring, comprising the steps of:

acquiring an image of a surrounding environment through at least one camera installed on a road;

analyzing the fuzzy state of the image, and identifying a motion area in the image;

and determining the traffic jam condition of the road according to the motion area.

9. A non-transitory computer-readable storage medium on which a computer program is stored, which, when being executed by a processor, implements a method of identifying a state of motion according to any one of claims 1 to 6, or a vehicle warning method according to claim 7, or a road monitoring method according to claim 8.

10. An apparatus for recognizing a motion state, comprising:

the first image acquisition unit is used for acquiring images of the surrounding environment through at least one camera;

and the first identification unit is used for analyzing the fuzzy state of the image and identifying a motion area or a static area in the image.

11. Identification device according to claim 10, characterized in that the first identification unit is specifically adapted to,

carrying out blocking processing on the image to obtain a plurality of block images;

acquiring a fuzzy scale of each block image in the plurality of block images;

clustering the block images according to the fuzzy scale, and calculating the average value of the fuzzy scale in each class;

and determining the motion area or the static area according to the average value of the fuzzy scale.

12. Identification device according to claim 11, characterized in that the first identification unit is specifically adapted to,

acquiring the movement speed of the camera and acquiring a static fuzzy scale at the movement speed;

judging whether the difference value between the average value of the fuzzy scales and the static fuzzy scale is larger than a preset threshold value or not;

if so, judging that the area corresponding to the class of the average value of the fuzzy scale is the motion area;

if not, judging that the area corresponding to the class of the average value of the fuzzy scale is the static area.

13. A vehicle warning device, comprising:

the second image acquisition unit is used for acquiring an image of the surrounding environment of the current vehicle through at least one camera installed on the current vehicle;

the second identification unit is used for analyzing the fuzzy state of the image and identifying a motion area in the image;

the distance acquisition unit is used for acquiring a first geographical position coordinate of the moving area and calculating to obtain the distance between the moving object and the current vehicle according to the first geographical position coordinate and a second geographical position coordinate of the current vehicle;

and the alarm unit is used for sending an alarm signal if the distance is smaller than a preset safety distance threshold value.

14. A road monitoring device, comprising:

a third image acquisition unit for acquiring an image of a surrounding environment through at least one camera installed on a road;

the third identification unit is used for analyzing the fuzzy state of the image and identifying a motion area in the image;

and the judging unit is used for determining the traffic jam condition of the road according to the motion area.

15. A vehicle characterized by comprising the vehicle warning device according to claim 13.

Images