KR102585066B1 - Combined fire alarm system using stand-alone fire alarm and visible light camera - Google Patents

Abstract

The convergence fire alarm system according to the present invention includes a fire detection sensor that detects at least one of flame, smoke, gas, or temperature generated when a fire occurs; a fire signal processing unit that receives a detection signal from the fire detection sensor and determines whether a fire has occurred; a fire warning unit that receives a fire detection signal from the fire signal processing unit and generates a fire warning signal when a predetermined condition is met; and a short-range communication fire alarm having a short-range communication module, and a visible light camera that photographs an area where the short-range communication fire alarm is installed; an image analysis unit that analyzes the image received from the visible light camera and determines whether there is a fire; an image and data storage unit that stores images captured by the visible light camera and image information generated by the image analysis unit; a short-range communication unit that communicates with the short-range communication module to receive the fire detection signal; and a camera system including a long-distance communication unit that communicates with an external terminal and transmits a value for determining whether a fire has occurred to the terminal.

Description

Combined fire alarm system using stand-alone fire alarm and visible light camera}

The present invention relates to a convergence fire alarm system using a stand-alone fire alarm and a visible light camera.

Fire alarms are generally stand-alone devices that use at least one of the following sensors: IR sensor, temperature sensor, smoke sensor, and gas detection sensor. Such a stand-alone fire alarm can provide both an auditory alarm such as a beacon and visual information such as a flashing LED light when a signal exceeding the threshold set in the preceding sensors is generated.

However, it has been found that a significant portion of erroneous dispatches by firefighters are caused by malfunctions of fire alarms, and it is known that the largest proportion of them are malfunctions of stand-alone fire alarms. There are many attempts to reduce malfunctions and increase reliability of stand-alone fire alarms.

For example, in order to increase accuracy compared to a stand-alone fire alarm, a separate IR thermal imaging camera was added to reduce the occurrence of malfunctions. A complex fire alarm was also invented. In this case, the stand-alone fire alarm and the IR thermal imaging camera are integrated with each other, or In some cases, a stand-alone fire alarm and an IR thermal imaging camera are connected wirelessly to increase the reliability of the fire alarm.

Nevertheless, IR thermal imaging cameras have the disadvantage of being difficult to apply because they are quite expensive, so there is a need to develop technology that can increase the reliability of fire alarms while using inexpensive visible light cameras.

The present invention uses a visible light camera, which is cheaper than an IR heat detection camera, and uses an image signal processing technique to extract a color temperature histogram from a general RGB image, thereby not only increasing the reliability of fire alarms, but also improving the reliability of CCTV cameras using the same camera. It is possible to provide a convergence fire alarm system that can also serve as a security function.

A convergence fire alarm system according to an embodiment of the present invention includes a fire detection sensor that detects at least one of flame, smoke, gas, or temperature generated when a fire occurs; a fire signal processing unit that receives a detection signal from the fire detection sensor and determines whether a fire has occurred; a fire warning unit that receives a fire detection signal from the fire signal processing unit and generates a fire warning signal when a predetermined condition is met; and a short-range communication fire alarm having a short-range communication module, and a visible light camera that photographs an area where the short-range communication fire alarm is installed; an image analysis unit that analyzes the image received from the visible light camera and determines whether there is a fire; an image and data storage unit that stores images captured by the visible light camera and image information generated by the image analysis unit; a short-range communication unit that communicates with the short-range communication module to receive the fire detection signal; and a camera system including a long-distance communication unit that communicates with an external terminal and transmits a value for determining whether a fire has occurred to the terminal.

In one embodiment, the image analysis unit includes an image signal processor that classifies images and image information into at least one group and generates an index according to the classification result; And when a fire detection signal is received through the short-range communication unit, it may include an accident determination unit that determines whether there is a fire based on the image information.

According to an embodiment of the present disclosure, a reliable fire alarm can be generated by significantly reducing the malfunction range of a single fire alarm. In addition, it allows you to check image information in the area of interest, allowing you to take active follow-up measures.

Figure 1 is a diagram schematically showing the configuration of a convergence-type fire alarm system according to an embodiment of the present invention.
FIG. 2 is a block diagram showing the configuration of the short-range communication fire alarm of FIG. 1.
FIG. 3 is a block diagram showing the configuration of the camera system of FIG. 1.
FIG. 4 relates to the real-time information/corresponding stored information comparison process of the components of the image and data storage unit and the image analysis unit of the camera system of FIG. 2.
FIG. 5 is a flowchart showing the configuration of a fire alarm method using the integrated fire alarm system of FIG. 1.
FIG. 6 is a flowchart showing the configuration of a method for obtaining color temperature information in the image signal processor of FIG. 3.
Figure 7 shows an example of a CIE Chromaticity Diagram for estimating the color and color temperature of light by combustion according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings to clarify the technical idea of the present invention. In describing the present invention, if it is determined that a detailed description of related known functions or components may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. Components having substantially the same functional configuration among the drawings are given the same reference numbers and symbols as much as possible, even if they are shown in different drawings. For convenience of explanation, if necessary, the device and method should be described together.

Figure 1 is a diagram schematically showing the configuration of a convergence-type fire alarm system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the configuration of the short-range communication fire alarm of FIG. 1. FIG. 3 is a block diagram showing the configuration of the camera system of FIG. 1. FIG. 4 relates to the real-time information/corresponding stored information comparison process of the components of the image and data storage unit and the image analysis unit of the camera system of FIG. 2. FIG. 5 is a flowchart showing the configuration of a fire alarm method using the integrated fire alarm system of FIG. 1.

In one embodiment, the image and data storage unit of the camera system according to an embodiment of the present invention stores images by time of day, time information of the stored images, image processing information of the stored images, fire alarm image comparison history, and fire threshold. It may include values, etc.

Referring to Figures 1 to 5, the convergence fire alarm system according to an embodiment of the present invention includes a short-range communication fire alarm and a camera system.

A short-range communication fire alarm can detect a fire and transmit a fire detection signal to a camera system. The camera system that receives the fire detection signal can analyze the image of the area where the fire occurred and transmit the analysis results to an electronic terminal (PC, smart phone) outside the camera system. For example, the external electronic terminal may be an electronic device owned by a person involved in a fire incident, such as a registered user, a fire department, or a manager. Additionally, the camera system can transmit the analysis results to a short-range communication fire alarm.

A short-range communication fire alarm may include an IR (Infrared Ray Sensor) sensor, a fire detection sensor, a fire signal processing unit, a fire warning unit, a short-range communication module, and a power supply unit.

IR sensors can detect infrared rays. The IR sensor can transmit the detected infrared signal to the fire signal processing unit. For example, an IR sensor can regularly and repeatedly transmit detected infrared signals to a fire signal processor at preset time intervals. Alternatively, the IR sensor can transmit infrared signals detected in real time to a fire detection signal processing unit.

Fire detection sensors can detect heat, flame, smoke, gas, etc. that occur when a fire occurs. For example, the fire detection sensor may include at least one of a heat detector, a heat detector, a flame detector, a smoke detector, a gas detector, or a temperature sensor. A heat detector can detect heat or temperature using a heat sensor such as a thermistor or thermocouple. A smoke detector can detect smoke generated during a fire by using the correlation between smoke concentration and optical phenomena such as light absorption or scattering that occur when light passes through a gas containing smoke particles. Flame detectors can detect infrared or ultraviolet rays contained in the light emitted from sparks caused by a fire.

The fire detection sensor can transmit a fire detection signal in real time to the fire signal processing unit when heat, flame, smoke, gas, etc. are detected.

The fire presence signal processing unit may determine whether a fire has occurred by receiving and analyzing detection signals detected by the IR sensor and/or the fire detection sensor. For example, the fire signal processing unit detects a fire when at least one of the fire detection signals such as IR, flame, smoke, gas, and/or temperature signals received from the IR sensor and/or the fire detection sensor exceeds the fire detection threshold. It can be determined that has occurred. The fire signal processing unit may generate a fire detection signal when it is determined that a fire has occurred, and transmit the generated fire detection signal to the fire warning unit and the short-distance communication module.

The fire warning unit may generate a fire warning signal when it receives a fire detection signal from the fire presence signal processing unit. In one embodiment, the fire warning unit receives a fire detection signal from the fire presence signal processing unit, and generates a fire warning signal when receiving a fire situation verification signal from the camera system within a certain time from receiving the fire detection signal. You can. Additionally, the fire warning unit may generate a fire warning signal even when no signal is received from the camera system within a certain period of time from the time the fire detection signal is received. For example, fire warning signals may be visual and/or auditory. When generating a fire warning signal, the fire warning unit may repeatedly generate the warning signal at least once or more at regular time intervals.

The short-range communication module can receive a fire detection signal received from the fire signal processing unit and transmit it to the camera system. For example, the short-range communication module includes at least one of a Near Field Communication (NFC) module, a Bluetooth module, a Wi-Fi module, a Zigbee communication module, and an Infra-red communication module. It can be done, but it is not limited to this.

The power supply unit may supply power for operation of a short-distance communication fire alarm. For example, the power supply unit may be comprised of a battery, but is not limited thereto.

The camera system may include a camera, an image analysis unit, a short-range communication unit, a long-distance communication unit, a camera, and an image and data storage unit.

The camera can capture areas where short-range communication fire alarms are installed. For example, the camera may be a visible light camera, but is not limited thereto. For example, the camera can transmit the captured video to the video analysis unit in real time. Alternatively, the camera may transmit the captured image to the image analysis unit when a specific signal is received from the image analysis unit. Alternatively, the camera may capture an image in response to a remote control signal through a long-distance communication unit and transmit the captured image to the image analysis unit. Additionally, the camera can transmit captured images to the image and data storage unit.

The video analysis unit may include a video signal processing unit, a terminal control unit, and an accident determination unit. The video analysis unit can determine whether there is an accident (fire or not) by analyzing the video received from the camera.

The video signal processing unit can convert and process the video received from the camera. In one embodiment, the image signal processor may generate image information by regularly converting and processing images received from a camera according to a preset cycle. The video signal processing unit may transmit the image received from the camera and the generated image information corresponding to the image to the image and data storage unit.

In one embodiment, the video signal processor may convert and process the video received from the camera according to a pre-designated terminal control algorithm. For example, the terminal control algorithm used by the video signal processing unit may be determined according to the terminal control command of the terminal control unit.

In one embodiment, the image signal processor may classify images and image information into at least one system and/or group, and create an index according to the classification results. The video signal processing unit can transmit the video and video information along with the index to the video and video data storage unit.

For example, the image information obtained by the image signal processing unit converting and/or processing the image received from the camera is at least one of the average brightness of the image of interest, histogram, integral image, color temperature, color temperature histogram, and information index. may include.

The image and data storage unit can store images captured by a camera, image information generated by the image analysis unit, and index information. The image and data storage unit may receive a fire detection signal from the accident determination unit of the image analysis unit and, in response, transmit the stored video and/or video information to the accident determination unit. For example, the image and data storage unit may store information such as stored images for each time of day, time information of the stored images, image processing information of the stored images, fire alarm image comparison history, and fire threshold values.

When a fire detection signal is received through the short-distance communication unit, the accident determination unit can determine whether there is an accident, that is, whether there is a fire, based on the image information. In one embodiment, the accident determination unit may extract the fire occurrence time from the fire detection signal and receive real-time captured images of the fire occurrence area from the fire occurrence time from the camera.

The accident determination unit may generate fire occurrence video information by converting and/or processing the real-time captured video received from the camera. The accident determination unit can compare and analyze the generated fire occurrence video information and the video information stored in the video data storage unit.

The accident determination unit can calculate the probability (%) of whether an accident occurred using the comparative analysis results. The accident determination unit may determine whether an accident has occurred by comparing the calculated probability value with a pre-specified or selected threshold value (%). The accident determination unit may generate a final judgment value corresponding to the occurrence or non-occurrence of an accident according to the judgment result.

In one embodiment, if it is determined that an accident has occurred, the accident determination unit may transmit the determination value to a short-distance fire alarm through the short-range communication unit. In addition, the accident determination unit may transmit the determination value (at least one generated image and at least one text) to a preset recipient at least once or more through the remote communication unit.

The short-range communication unit may receive a fire detection signal from the short-range communication module of the short-range communication fire alarm. The short-range communication unit may transmit the judgment value of whether an accident has occurred received from the video analysis unit to the short-range communication module of the short-range communication fire alarm. For example, the short-range communication module includes at least one of a Near Field Communication (NFC) module, a Bluetooth module, a Wi-Fi module, a Zigbee communication module, and an Infra-red communication module. It can be done, but it is not limited to this.

The remote communication unit may transmit the image received from the video analysis unit and/or the judgment value received as to whether an accident has occurred to a terminal owned by a relevant person such as a registered user, fire department, or manager. The remote communication unit may transmit information through at least one communication means among E-mail, SMS, MMS, and SNS, depending on the receiving device of the recipient receiving the fire information. For example, the Department of Telecommunications includes Wireless LAN (WLAN), Wireless-Fidelity (Wi-Fi), Wireless Fidelity (Wi-Fi) Direct, Digital Living Network Alliance (DLNA), Wireless Broadband (WiBro), and World Interoperability for WiMAX (WiMAX). It may be a communication module that uses at least one of wireless communication technologies such as Microwave Access, HSDPA, HSUPA, LTE, and LTE-A.

The power supply unit may supply power for operation of the camera system. For example, the power supply unit may include, but is not limited to, a charging port and/or a battery.

FIG. 6 is a flowchart showing the configuration of a method for obtaining color temperature information in the image signal processor of FIG. 3.

Referring to FIG. 6, a method of obtaining color temperature information may include calculating a color temperature value and generating a color temperature histogram.

In general, visible light cameras rather than IR thermal imaging cameras are not appropriate for extracting color and color temperature due to combustion, making it very difficult to find the temperature of the image. To overcome this difficulty, the image signal processing unit of the present invention can use a color temperature estimation algorithm that calculates the color temperature from the image acquired by the visible light camera.

In one embodiment, the color temperature value calculation step may include a first conversion step, a second conversion step, an averaging step, a chromaticity value acquisition step, and a color temperature value extraction step. For example, an algorithm for estimating color temperature in images is described by K. Wnukowicz and W. Skarbek in color temperature estimation algorithm for digital images properties and convergence. Optoelectronics Review. The method announced in 2003 can be used.

In the first conversion step, the RGB image may be converted to sRGB format. That is, in the first conversion step, a pixel image can be extracted from RGB, and the extracted pixel images can be aligned in sRGB format.

In the second conversion step, the sRGB format can be converted to the XYZ color space. (Color temperature calculation performed on CIE1960) This is because color temperature calculation must be performed in pure UV chromaticity form.

In the averaging step, colors that are irrelevant in calculating the color temperature value can be erased and then pixels, etc., can be averaged. (CIE1931) For example, colors that are not relevant in calculating color temperature values are black and pseudo-black. In one embodiment, in the averaging step, black and pixels close to black can be erased by checking the Y component.

In the averaging step, black and pseudo-black are erased and the remaining pixels can be averaged. The output value output as a result of averaging may be in the form of Xa, Yb, or Za. These output values in the form of Xa, Yb, and Za can be used to calculate the X and Y planes of chromaticity values. The chromaticity value of the pixel (Xs, Ys) of the Xa, Ya, and Za are calculated as chromatocity values (Xs, Ys) on the CIE (1931) chromatocity diagram.

In the chromaticity value acquisition step, CIE 1960 chromaticity values can be acquired. In one embodiment, the ( It is for this purpose. CIE (1960) Chromatocity can be calculated using Robertson’s method by finding two adjacent same-color temperature lines adjacent to the pixel (Us, Vs) points on the diagram. The output from this calculation can be expressed as Mega Kelvin (MK-1).

In the color temperature value extraction step, 1,000,000 is divided by the color temperature to obtain the Kelvin color temperature, and the divided value is the Mega Kelvin value. In other words, the color temperature is 1,000,000/Mega Kelvin.

In one embodiment, the color temperature histogram generation step may include a segmentation step, an estimation step, a separation step, a classification step, and a histogram generation step.

The color temperature histogram is a combination of the color temperature methodology in video and the histogram methodology. This method is close to recognition with the human eye. The color temperature histogram consists of 46 bins. Each bin represents an interval of color temperature values. Color temperature values can be calculated and derived from the color gamut. Each bin of the histogram shows the frequency value of the same color temperature portion of the image.

In the segmentation step, since the image has various color temperatures, the image can be segmented into blocks. For example, one block can be 4x4 pixels. This block size can produce more accurate results in experiments and save computing power.

In the estimation step, the color temperature of each block can be calculated through a color temperature extraction algorithm. This method cannot be used with black images with an RGB value of 0. So, if the block is black, set TRc = beta (the beta value is outside of 0-600) and set the parameter to 3.

In the separation step, if the RGB values are the same, the parameter gamma value can be set to black = 0, gray = 1, and white = 2 to separate gray/white/black.

In the classification step, the parameter This is because color temperature is not suitable for describing the color perceived by humans, and all colors express one color temperature value.

In the histogram creation step, you can count the number of segments with the same color temperature value and the same parameter x to create a color temperature histogram and place it in a bin. The areas of the bins are in Table II.

In one embodiment, classification (clustering) of images can be done by creating a database by converting images into color temperature histogram vectors, and then using a hierarchical method to group the images to classify each region with a certain threshold. This method can split one large classification (cluster) into the most different smaller classifications by comparing the distance between groups and the average value of the groups.

Figure 7 shows an example of a CIE Chromaticity Diagram for estimating the color and color temperature of light by combustion according to an embodiment of the present invention.

Referring to Figure 7, the color of light caused by the main combustion occurring in the human living environment has the form of dark red/red/light red/yellow red/white red/white white, and the temperature is 700 degrees Celsius/850 degrees Celsius/950 degrees Celsius, respectively. It is known to form around /1100 degrees/1300 degrees/1500 degrees. Among the video signal processing methods described above, in the process of generating color temperature and color temperature histogram, mega Kelvin (MK-1: 1,0000,000/Kelvin temperature) is estimated and a portion of the color temperature value of 970 to 1770 ^o K due to combustion Alternatively, the method of finding everything can be used in thinking and judgment. Additionally, the maximum/minimum values of image information and the duration of similar signals can be used as variables for fire detection.

Figure 8 relates to other accident determination algorithms other than the color temperature histogram according to an embodiment of the present invention.

In one embodiment, the equation representing the framework of accident detection variables is as Equation 1 below.

: Change variable of camera image information Change in time until reset (if there are no accidents based on 24 hours, it is considered that there is a certain pattern in the environment even if there are changes in seasons and lighting)

: Variable indicating Min/Max of image information on xy plane experienced from camera image information, the maximum value is min/max values reset after (sec)

: Accident (fire/smoke) level Time elapsed after becoming greater than %, fire (smoke) warning event The setting value is set to 1. Fire (smoke) event Variable when it becomes more than % has a binary value and is the level detected during the image processing process. If it is greater than %, it is assumed to be 1, otherwise it is assumed to be 0. From here % is continuously experimented and adjusted based on, for example, 70%)

: Fire (smoke) detection level Elapsed time when maintaining the status below %, threshold variable Is If it is above %, set to 1, otherwise assume to be 0.

: variable Time taken from 1 to 0

: Minimum % value of image processing information to determine accident situation detection

: Minimum % value required to respond to fire (smoke) detection variable

: Minimum % value to determine accident situation detection

: Longest time (sec) to maintain a state lower than the %threshold value, is the threshold at which the incident detection algorithm determines activation/deactivation.

The accident detection function is

Accident judgment is 0 or 1

: Weighting factor for accident detection (accident detection based on the correlation between the relative value of image processing information and fire (smoke) detection information)

: Accident detection threshold

The present invention can also be implemented as computer-readable code on a computer-readable recording medium. Computer-readable recording media include all storage media such as magnetic storage media, optically readable media, and carrier wave (eg, transmission via the Internet). Additionally, it is possible to record the data format of the message used in the present invention on a recording medium.

So far, the present invention has been examined in detail, focusing on the preferred embodiments shown in the drawings. These embodiments are not intended to limit the invention but are merely illustrative and should be considered from an illustrative rather than a limiting perspective. The true technical protection scope of the present invention should be determined by the technical spirit of the appended claims rather than the foregoing description. Although specific terms are used in this specification, they are used only for the purpose of explaining the concept of the present invention and are not used to limit the meaning or scope of the present invention described in the claims. Each step of the present invention does not necessarily have to be performed in the order described, but may be performed in parallel, selectively, or individually. Those skilled in the art to which the present invention pertains will understand that various modifications and other equivalent embodiments are possible without departing from the essential technical spirit of the present invention as claimed in the patent claims. Equivalents should be understood to include not only currently known equivalents but also equivalents developed in the future, that is, all components invented to perform the same function regardless of structure.

Claims (2)

A fire detection sensor that detects at least one of flame, smoke, gas, or temperature generated when a fire occurs;
a fire signal processing unit that receives a detection signal from the fire detection sensor and determines whether a fire has occurred;
a fire warning unit that receives a fire detection signal from the fire signal processing unit and generates a fire warning signal when a predetermined condition is met; and
A short-range communication fire alarm having a short-range communication module,
A visible light camera that photographs an area where the short-range communication fire alarm is installed;
an image analysis unit that analyzes the image received from the visible light camera and determines whether there is a fire;
an image and data storage unit that stores images captured by the visible light camera and image information generated by the image analysis unit;
a short-range communication unit that communicates with the short-range communication module to receive the fire detection signal; and
It includes a camera system including a long-distance communication unit that communicates with an external terminal and transmits a value for determining whether a fire has occurred to the terminal,
The video analysis unit,
a video signal processor that classifies images and image information into at least one group and creates an index according to the classification results; and
When receiving a fire detection signal through the short-distance communication unit, it includes an accident determination unit that determines whether there is a fire based on the image information,
The image information includes at least one of average brightness, color temperature, and color temperature histogram of the captured image,
The accident determination unit receives real-time captured images of the fire area from the time of fire occurrence from the camera, generates fire occurrence image information, and compares and analyzes the image information with the image information. delete