CN107424182B - Thermal imaging field monitoring device and method - Google Patents
Thermal imaging field monitoring device and method Download PDFInfo
- Publication number
- CN107424182B CN107424182B CN201710305806.5A CN201710305806A CN107424182B CN 107424182 B CN107424182 B CN 107424182B CN 201710305806 A CN201710305806 A CN 201710305806A CN 107424182 B CN107424182 B CN 107424182B
- Authority
- CN
- China
- Prior art keywords
- image
- thermal imaging
- images
- pixel
- pictures
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a thermal imaging on-site monitoring device and a thermal imaging on-site monitoring method, comprising the following steps: the thermal imaging module is used for shooting thermal imaging images within a preset angle range, and comprises: the device comprises a controller, a rotary type cradle head bracket and a thermal imaging camera arranged on the rotary type cradle head bracket, wherein the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera in each stage to form a thermal imaging picture, after the thermal imaging camera rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle to wait for photographing next time; the image synthesis module is used for splicing a plurality of pictures taken by the thermal imaging module from an initial angle to a final angle into a complete panoramic view. The panoramic image is formed by splicing the images, so that more comprehensive and more coherent visual information can be provided in a single image.
Description
Technical Field
The invention relates to the technical field of field monitoring, in particular to a thermal imaging field monitoring device and a thermal imaging field monitoring method.
Background
In the existing field monitoring device, a common camera is adopted to shoot field images, and an imaging photo cannot be used for obviously distinguishing people, objects or animals in the environment, so that when foreign matters invade, timely judgment cannot be made. And the shooting content of the common imaging pictures is independent and incoherent, and the accurate judgment of an administrator on the site environment is not facilitated.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks.
To this end, an object of the present invention is to propose a thermal imaging field monitoring device and method.
To achieve the above object, an embodiment of the present invention provides a thermal imaging field monitoring apparatus including: a thermal imaging module, an image synthesis module and an image analysis module, wherein,
the thermal imaging module is used for shooting thermal imaging images within a preset angle range, and comprises: the device comprises a controller, a rotary type cradle head bracket and a thermal imaging camera arranged on the rotary type cradle head bracket, wherein the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera in each stage to form a thermal imaging picture, after the thermal imaging camera rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle to wait for photographing next time;
the image synthesis module is used for splicing a plurality of pictures shot by the thermal imaging module from an initial angle to a final angle into a complete panoramic view;
the image analysis module is used for taking the spliced panoramic view as a training sample, cutting each sample image into small images and numbering the small images; taking the small pictures with the same numbers in all the sample pictures, calculating the average value of each pixel, generating a reference small picture, cutting the synthesized picture according to the same method when analyzing the new synthesized picture, comparing the synthesized picture with the corresponding reference picture,
the calculation criteria are as follows: d= Σ (p xy -p’ xy ) 2 ，x＝1，…，40，y＝1，…，40；
The image analysis module sets a threshold f according to a priori criterion 0 If d>f 0 And alarming the image area.
Further, the thermal imaging camera includes: the imaging device comprises an optical lens, an imaging sensor, an image processor and a power supply circuit, wherein the optical lens, the imaging sensor and the image processor are sequentially connected, and the power supply circuit is respectively connected with the optical lens, the imaging sensor and the image processor.
Further, the controller, the imaging sensor, the image processor and the power supply circuit adopt an explosion-proof design.
Further, the image synthesis module splices panoramic views, including:
calculating the maximum value of the difference between the temperature value of each pixel point in the image and the temperature values of 8 surrounding pixels as the new pixel value of the pixel, namely
t’＝max[(t-t Upper part )，(t-t Lower part(s) )，(t-t Left side )，(t-t Right side )，(t-t Left upper part )，(t-t Upper right )，(t-t Lower left )，(t-t Lower right )]
A binarization algorithm is adopted: binarizing the image subjected to difference, and setting a threshold t according to prior experience 0 The pixel value t 'of each pixel point is greater than t if t' > t 0 The pixel color is set to be black, if t' < t 0 The pixel color is set to white;
the binarized image is divided according to the distribution of black pixels as follows:
optionally selecting a black pixel point in the image, finding all black pixel points adjacent to the black pixel point, recording coordinates of each point, calculating and recording the average value of the coordinates of each point, and changing each point to be calculated into white;
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，...，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
The two images (original images) are translated, the left image is fixed, the right image is translated rightwards from the superposition position, and the translation distance a is calculated so that S (a) =min [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point is taken as the average value of the corresponding pixel points of the two original images in the overlapping area of the two images;
the splicing of the two adjacent images is completed in the mode, and the splicing pictures of all the images obtained by one rotation are completed in the same mode.
The thermal imaging on-site monitoring method of the embodiment of the invention comprises the following steps: step S1: shooting a thermal imaging image within a preset angle range, comprising: the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera at each stage to form a thermal imaging picture, and after the cradle head rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle and wait for photographing next time;
step S2: splicing a plurality of pictures taken from an initial angle to a final angle into a complete panoramic view;
step S3: taking the spliced panoramic view as a training sample, cutting each sample image into small images, and numbering; taking the small pictures with the same numbers in all the sample pictures, calculating the average value of each pixel, generating a reference small picture, cutting the synthesized picture according to the same method when analyzing the new synthesized picture, comparing the synthesized picture with the corresponding reference picture,
the calculation criteria are as follows: d= Σ (p xy -p’ xy ) 2 ，x＝1，…，40，y＝1，…，40；
Setting a threshold f according to a priori criteria 0 If d > f 0 And alarming the image area.
Further, in the step S3, a maximum value of the difference between the temperature value of each pixel point in the image and the temperature values of 8 pixels around is calculated as a new pixel value of the pixel, that is
t’＝max[(t-t Upper part )，(t-t Lower part(s) )，(t-t Left side )，(t-t Right side )，(t-t Left upper part )，(t-t Upper right )，(t-t Lower left )，(t-t Lower right )]
A binarization algorithm is adopted: binarizing the image subjected to difference, and setting a threshold t according to prior experience 0 The pixel value t 'of each pixel point is greater than t if t' > t 0 The pixel color is set to be black, if t' < t 0 The pixel color is set to white;
the binarized image is divided according to the distribution of black pixels as follows:
optionally selecting a black pixel point in the image, finding all black pixel points adjacent to the black pixel point, recording coordinates of each point, calculating and recording the average value of the coordinates of each point, and changing each point to be calculated into white;
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，...，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
The two images (original images) are translated, the left image is fixed, the right image is translated rightwards from the superposition position, and the translation distance a is calculated so that S (a) =min [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point is taken as the average value of the corresponding pixel points of the two original images in the overlapping area of the two images;
the splicing of the two adjacent images is completed in the mode, and the splicing pictures of all the images obtained by one rotation are completed in the same mode.
According to the thermal imaging on-site monitoring device and the thermal imaging on-site monitoring method, the shooting of the thermal imaging pictures is helpful for distinguishing the environment from personnel and animals more obviously, so that personnel in a monitoring area and accidental entry of animals such as cats, dogs and rats can be found better; the panoramic image is formed by splicing a plurality of images, so that more comprehensive and more coherent visual information can be provided in a single image.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a block diagram of a thermal imaging field monitoring device according to an embodiment of the present invention;
fig. 2 is a block diagram of a thermal imaging module according to an embodiment of the invention.
Fig. 3 is a flow chart of a thermal imaging field monitoring method according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
As shown in fig. 1, a thermal imaging field monitoring apparatus according to an embodiment of the present invention includes: a thermal imaging module 1, an image synthesis module 2 and an image analysis module 3.
Specifically, the thermal imaging module 1 is configured to capture a thermal imaging image within a preset angle range, and includes: the camera comprises a controller, a rotary type cradle head support and a thermal imaging camera arranged on the rotary type cradle head support, wherein the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera in each stage to form a thermal imaging picture, after the thermal imaging camera rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle to wait for photographing next time.
As shown in fig. 2, the thermal imaging camera includes: the imaging device comprises an optical lens 11, an imaging sensor 12, an image processor 13 and a power supply circuit 14, wherein the optical lens 11, the imaging sensor 12 and the image processor 13 are sequentially connected, and the power supply circuit 14 is respectively connected with the optical lens 11, the imaging sensor 12 and the image processor 13. The thermal imaging camera employs a fixed-focus optical lens to ensure a stable image viewing angle is obtained.
In one embodiment of the invention, the controller, imaging sensor, image processor and power supply circuit are of explosion-proof design.
Specifically, the circuit part of the thermal imaging module 1, namely the imaging sensor, the image processor and the power supply circuit are subjected to explosion-proof design, a booster circuit is avoided, the power supply voltage of the control circuit is within 5V, and the total capacitance of the control circuit is within 600 uF.
The controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera at each stage to form a thermal imaging picture, and after the cradle head rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle and wait for photographing next time. The controller ensures that the starting angle of each shot remains consistent. And the shot pictures are transmitted back to the image processing center by the controller.
In addition, the circuit part of the controller is subjected to explosion-proof design, a booster circuit is avoided, the power supply voltage of the control circuit is within 4.5V, and the total capacitance of the control circuit is within 300 uF.
The image synthesis module 2 is used for splicing a plurality of pictures taken by the thermal imaging module from an initial angle to a final angle into a complete panoramic view.
Specifically, the image synthesizing module 2 is located in the image processing center, and is configured to stitch multiple pictures taken by rotating the pan-tilt from an initial angle to a final angle (one-step and multi-step rotation) into a complete panoramic view.
The stitching of images uses a series of image processing algorithms:
(1) Image difference:
calculating the maximum value of the difference between the temperature value (obtained by color value conversion) of each pixel point and the temperature values of 8 surrounding pixels in the image as the new pixel value of the pixel, namely
t’＝max[(t-t Upper part ),(t-t Lower part(s) ),(t-t Left side ),(t-t Right side ),(t-t Left upper part ),(t-t Upper right ),(t-t Lower left ),(t-t Lower right )]
Binarization algorithm: binarizing the image subjected to difference, and setting a threshold t according to prior experience 0 The pixel value t 'of each pixel point is t'>t 0 The pixel color is set to black, if t'<t 0 The pixel color is set to white.
(2) Dividing images:
the binarized image is divided according to the distribution of black pixels as follows:
1. optionally a black pixel in the image
2. Finding all black pixel points adjacent to the point, and recording coordinates of each point (the upper, lower, left and right four pixel points of one pixel point are defined as the adjacent pixel points of the point)
3. Calculating and recording the average value of the coordinates of each point
4. Changing the calculated points into white
5. Returning to step 1
(3) And (3) image stitching:
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，...，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
The two images (original images) are translated, the left image is fixed, the right image is translated rightwards from the superposition position, and the translation distance a is calculated so that S (a) =min [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point in the overlapping area of the two images is taken as the average value of the corresponding pixel points of the two original images.
And splicing the two adjacent images in the mode. And the splice map of all the images obtained by one rotation is completed in the same way.
The image analysis module 3 is implemented in an image processing center. Because each group of images has a fixed viewing angle range (focal length) and a fixed initial angle, the system can synthesize a relatively stable thermal imaging composite image.
The image analysis module 3 takes a plurality of synthetic images within a period of time (for example, 1 month) as training samples, and clips each sample image into small images of 40×40 pixels and numbers the small images. And taking the small images with the same numbers in all the sample images, calculating the average value of each pixel, and generating a reference small image.
When the image analysis module 3 analyzes the new synthetic image, the synthetic image is cut according to the same method and compared with the corresponding reference image, and the calculation criterion is d= Σ (p xy -p’ xy ) 2 X=1, …,40, y=1, …,40. Setting a threshold f according to a priori criteria 0 If d > f 0 And alarming the image area.
As shown in fig. 3, the thermal imaging field monitoring method according to the embodiment of the invention includes the following steps:
step S1: shooting a thermal imaging image within a preset angle range, comprising: the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera at each stage to form a thermal imaging picture, and after the cradle head rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle and wait for photographing next time;
step S2: splicing a plurality of pictures taken from an initial angle to a final angle into a complete panoramic view;
(1) Image difference:
calculating the maximum value of the difference between the temperature value (obtained by color value conversion) of each pixel point and the temperature values of 8 surrounding pixels in the image as the new pixel value of the pixel, namely
t’＝max[(t-t Upper part )，(t-t Lower part(s) )，(t-t Left side )，(t-t Right side )，(t-t Left upper part )，(t-t Upper right )，(t-t Lower left )，(t-t Lower right )]
Binarization algorithm: the image to be subjected to the differenceBinarization processing is carried out, and a threshold t is set according to prior experience 0 The pixel value t 'of each pixel point is greater than t if t' > t 0 The pixel color is set to be black, if t' < t 0 The pixel color is set to white.
(2) Dividing images:
the binarized image is divided according to the distribution of black pixels as follows:
1. optionally a black pixel in the image
2. Finding all black pixel points adjacent to the point, and recording coordinates of each point (the upper, lower, left and right four pixel points of one pixel point are defined as the adjacent pixel points of the point)
3. Calculating and recording the average value of the coordinates of each point
4. Changing the calculated points into white
5. Returning to step 1
(3) And (3) image stitching:
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，...，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
For two picturesThe image (original image) is translated, the left image is fixed, the right image is translated rightwards from the superposition position, and the translation distance a is calculated so that S (a) =min [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point in the overlapping area of the two images is taken as the average value of the corresponding pixel points of the two original images.
And splicing the two adjacent images in the mode, and finishing the splicing pictures of all the images obtained by one rotation in the same mode.
Step S3: taking the spliced panoramic view as a training sample, cutting each sample image into small images, and numbering; taking the small pictures with the same numbers in all the sample pictures, calculating the average value of each pixel, generating a reference small picture, cutting the synthesized picture according to the same method when analyzing the new synthesized picture, comparing the synthesized picture with the corresponding reference picture,
the calculation criteria are as follows: d= Σ (p xy -p’ xy ) 2 X=1, …,40, y=1, …,40; setting a threshold f according to a priori criteria 0 If d>f 0 And alarming the image area.
According to the thermal imaging on-site monitoring device and the thermal imaging on-site monitoring method, the shooting of the thermal imaging pictures is helpful for distinguishing the environment from personnel and animals more obviously, so that personnel in a monitoring area and accidental entry of animals such as cats, dogs and rats can be found better; the panoramic image is formed by splicing a plurality of images, so that more comprehensive and more coherent visual information can be provided in a single image.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations may be made in the above embodiments by those skilled in the art without departing from the spirit and principles of the invention. The scope of the invention is defined by the appended claims and their equivalents.
Claims (4)
1. A thermal imaging field monitoring device, comprising: a thermal imaging module, an image synthesis module and an image analysis module, wherein,
the thermal imaging module is used for shooting thermal imaging images within a preset angle range, and comprises: the device comprises a controller, a rotary type cradle head bracket and a thermal imaging camera arranged on the rotary type cradle head bracket, wherein the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera in each stage to form a thermal imaging picture, after the thermal imaging camera rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle to wait for photographing next time;
the image synthesis module is used for splicing a plurality of pictures shot by the thermal imaging module from an initial angle to a final angle into a complete panoramic view;
the image analysis module is used for taking the spliced panoramic view as a training sample, cutting each sample image into small images and numbering the small images; taking the small pictures with the same numbers in all the sample pictures, calculating the average value of each pixel, generating a reference small picture, cutting the synthesized picture according to the same method when analyzing the new synthesized picture, comparing the synthesized picture with the corresponding reference picture,
the calculation criteria are as follows: d= Σ (p xy -p’ xy ) 2 ，x＝1，…，40，y＝1，…，40；
The image analysis module sets a threshold f according to a priori criterion 0 If d > f 0 Alarming the image area;
the image synthesis module splices panoramic views, including:
calculating the maximum value of the difference between the temperature value of each pixel point in the image and the temperature values of 8 surrounding pixels as the new pixel value of the pixel, namely
t’＝max[(t-t Upper part )，(t-t Lower part(s) )，(t-t Left side )，(t-t Right side )，(t-t Left upper part )，(t-t Upper right )，(t-t Lower left )，(t-t Lower right )]
A binarization algorithm is adopted: binarizing the image subjected to difference, and setting a threshold t according to prior experience 0 The pixel value t 'of each pixel point is greater than t if t' > t 0 The pixel color is set to be black, if t' < t 0 The pixel color is set to white;
the binarized image is divided according to the distribution of black pixels as follows:
optionally selecting a black pixel point in the image, finding all black pixel points adjacent to the black pixel point, recording coordinates of each point, calculating and recording the average value of the coordinates of each point, and changing each point to be calculated into white;
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
The two images (original images) are translated, the left image is fixed, the right image is translated rightwards from the superposition position, and the translation distance a is calculated so that S (a) =min [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point is taken as the average value of the corresponding pixel points of the two original images in the overlapping area of the two images;
the splicing of the two adjacent images is completed in the mode, and the splicing pictures of all the images obtained by one rotation are completed in the same mode.
2. The thermal imaging field monitoring device of claim 1, wherein the thermal imaging camera comprises: the imaging device comprises an optical lens, an imaging sensor, an image processor and a power supply circuit, wherein the optical lens, the imaging sensor and the image processor are sequentially connected, and the power supply circuit is respectively connected with the optical lens, the imaging sensor and the image processor.
3. The thermal imaging field monitoring device of claim 2, wherein the controller, imaging sensor, image processor, and power supply circuit are of an explosion-proof design.
4. A thermal imaging field monitoring method, comprising the steps of:
step S1: shooting a thermal imaging image within a preset angle range, comprising: the controller controls the cradle head to rotate from an initial angle to a final angle in a plurality of stages, a photographing instruction is sent to the thermal imaging camera at each stage to form a thermal imaging picture, and after the cradle head rotates to the final angle, the thermal imaging camera photographs a plurality of pictures, and the controller controls the cradle head to reversely rotate to the initial angle and wait for photographing next time;
step S2: splicing a plurality of pictures taken from an initial angle to a final angle into a complete panoramic view;
step S3: taking the spliced panoramic view as a training sample, cutting each sample image into small images, and numbering; taking the small pictures with the same numbers in all the sample pictures, calculating the average value of each pixel, generating a reference small picture, cutting the synthesized picture according to the same method when analyzing the new synthesized picture, comparing the synthesized picture with the corresponding reference picture,
the calculation criteria are as follows: d= Σ (p xy -p’ xy ) 2 ，x＝1，…，40，y＝1，…，40；
Setting a threshold f according to a priori criteria 0 If d > f 0 Alarming the image area;
in the step S3, the maximum value of the difference between the temperature value of each pixel point in the image and the temperature values of 8 surrounding pixels is calculated as the new pixel value of the pixel, namely
t’＝max[(t-t Upper part )，(t-t Lower part(s) )，(t-t Left side )，(t-t Right side )，(t-t Left upper part )，(t-t Upper right )，(t-t Lower left )，(t-t Lower right )]
A binarization algorithm is adopted: binarizing the image subjected to difference, and setting a threshold t according to prior experience 0 The pixel value t 'of each pixel point is greater than t if t' > t 0 The pixel color is set to be black, if t' < t 0 The pixel color is set to white;
the binarized image is divided according to the distribution of black pixels as follows:
optionally selecting a black pixel point in the image, finding all black pixel points adjacent to the black pixel point, recording coordinates of each point, calculating and recording the average value of the coordinates of each point, and changing each point to be calculated into white;
after the image segmentation is completed, the obtained plurality of coordinate means are ordered according to the x-axis coordinates to form the following sequence
{[x 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}
According to the obtained sequence, matching the adjacent images:
the sequence of left image in 2 adjacent images is { [ x ] 1 ，y 1 ]，[x 2 ，y 2 ]，[x 3 ，y 3 ]，…，[x n ，y n ]}，
The right image sequence is { [ u ] 1 ，v 1 ]，[u 2 ，v 2 ]，[u 3 ，v 3 ]，…，[u m ，v m ]}；
Record d 0 ＝abs(y n 2 -v 1 2 )，d k ＝abs(y n-k 2 -v 1+k 2 )，d p ＝min(d 1 ，…，d k )；
The two images (original images) are translated, the left image is fixed, the right image is translated rightward from the superposition position, and the translation distance a is calculated so that S (a) =mn [ (x) n-p -u 1+p +a) 2 +(x n-p+1 -u 2+p +a) 2 +…+(x n -u m +a) 2 ]；
After the translation, the pixel value of each pixel point is taken as the average value of the corresponding pixel points of the two original images in the overlapping area of the two images;
the splicing of the two adjacent images is completed in the mode, and the splicing pictures of all the images obtained by one rotation are completed in the same mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305806.5A CN107424182B (en) | 2017-05-03 | 2017-05-03 | Thermal imaging field monitoring device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305806.5A CN107424182B (en) | 2017-05-03 | 2017-05-03 | Thermal imaging field monitoring device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107424182A CN107424182A (en) | 2017-12-01 |
| CN107424182B true CN107424182B (en) | 2024-04-12 |
Family
ID=60424369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710305806.5A Active CN107424182B (en) | 2017-05-03 | 2017-05-03 | Thermal imaging field monitoring device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107424182B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109640042A (en) * | 2018-12-19 | 2019-04-16 | 成都森和电子科技有限公司 | High-precision holder infrared panorama camera based on FPGA |
| CN109596630A (en) * | 2019-01-25 | 2019-04-09 | 上海东震冶金工程技术有限公司 | A kind of hot detection method of flame machine slab upper and lower surface imaging rear clearly |
| CN110192845B (en) * | 2019-05-09 | 2021-10-01 | 广州番禺职业技术学院 | A pig body temperature detection device and system |
| CN112598865B (en) * | 2020-12-14 | 2023-03-03 | 深圳供电局有限公司 | A monitoring method and system for preventing external force damage of cable lines |
| CN113899574B (en) * | 2021-09-26 | 2024-11-15 | 中国纺织科学研究院有限公司 | Fault detection method for cooling and blowing equipment and spinning equipment |
| CN116193228B (en) * | 2023-04-24 | 2023-08-22 | 深圳市龙之源科技股份有限公司 | Outdoor monitoring device, control method thereof and hunting equipment |
| CN119402729B (en) * | 2025-01-02 | 2025-04-22 | 合肥埃科光电科技股份有限公司 | Image sensor splicing judging method, system, adjusting method and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004295361A (en) * | 2003-03-26 | 2004-10-21 | Canon Inc | Image processing method |
| CN101242542A (en) * | 2008-02-26 | 2008-08-13 | 北京中星微电子有限公司 | An image detection method and device |
| CN105264439A (en) * | 2013-08-09 | 2016-01-20 | 热成像雷达有限责任公司 | Method for analyzing thermal imaging data using multiple virtual devices and method for associating depth values with image pixels |
| CN105376522A (en) * | 2015-02-10 | 2016-03-02 | 山东华光光电子有限公司 | Infrared thermal imager with optical warning device and application thereof |
-
2017
- 2017-05-03 CN CN201710305806.5A patent/CN107424182B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004295361A (en) * | 2003-03-26 | 2004-10-21 | Canon Inc | Image processing method |
| CN101242542A (en) * | 2008-02-26 | 2008-08-13 | 北京中星微电子有限公司 | An image detection method and device |
| CN105264439A (en) * | 2013-08-09 | 2016-01-20 | 热成像雷达有限责任公司 | Method for analyzing thermal imaging data using multiple virtual devices and method for associating depth values with image pixels |
| CN105376522A (en) * | 2015-02-10 | 2016-03-02 | 山东华光光电子有限公司 | Infrared thermal imager with optical warning device and application thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107424182A (en) | 2017-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107424182B (en) | Thermal imaging field monitoring device and method | |
| US20070030363A1 (en) | Image capture method and apparatus | |
| EP4116462A3 (en) | Method and apparatus of processing image, electronic device, storage medium and program product | |
| CN109034185A (en) | A kind of street view image contrast difference method and device | |
| CN110278366B (en) | A panoramic image blurring method, terminal and computer-readable storage medium | |
| CN1854887A (en) | Method and apparatus for forming a panoramic image | |
| WO2019161814A3 (en) | Panoramic imaging system and method | |
| US10019639B2 (en) | Determining a boundary associated with image data | |
| CN104135926A (en) | Image processing device, image processing system, image processing method, and program | |
| CN103501409A (en) | Ultrahigh resolution panorama speed dome AIO (All-In-One) system | |
| CN102645837A (en) | A panoramic image shooting and processing method applied to a mobile handheld device equipped with front and rear cameras | |
| CN109451240B (en) | Focusing method, focusing device, computer equipment and readable storage medium | |
| CN109360150A (en) | A kind of joining method and device of the panorama depth map based on depth camera | |
| WO2021168804A1 (en) | Image processing method, image processing apparatus and image processing system | |
| CN113627385A (en) | Sight direction detection method, device, detection system, and readable storage medium | |
| CN110581950B (en) | Camera, system and method for selecting camera settings | |
| JP2006191524A (en) | Automatic framing device and photographing device | |
| CN107995408A (en) | A kind of 360 ° of panoramic shooting systems and method | |
| CN106791456A (en) | A kind of photographic method and electronic equipment | |
| CN106131498B (en) | Panoramic video joining method and device | |
| KR102138333B1 (en) | Apparatus and method for generating panorama image | |
| JP2008005110A5 (en) | ||
| CN105467741A (en) | Panoramic shooting method and terminal | |
| Chew et al. | Panorama stitching using overlap area weighted image plane projection and dynamic programming for visual localization | |
| CN111242107B (en) | Method and electronic device for setting virtual object in space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |