CN114331928B - High-temperature infrared image visualization enhancement method, device and equipment - Google Patents
High-temperature infrared image visualization enhancement method, device and equipment Download PDFInfo
- Publication number
- CN114331928B CN114331928B CN202210244689.7A CN202210244689A CN114331928B CN 114331928 B CN114331928 B CN 114331928B CN 202210244689 A CN202210244689 A CN 202210244689A CN 114331928 B CN114331928 B CN 114331928B
- Authority
- CN
- China
- Prior art keywords
- image
- img
- pseudo
- enhanced
- color
- 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
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012800 visualization Methods 0.000 title claims description 25
- 230000002708 enhancing effect Effects 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000003709 image segmentation Methods 0.000 claims abstract description 21
- 230000003044 adaptive effect Effects 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000005192 partition Methods 0.000 claims description 13
- 230000002194 synthesizing effect Effects 0.000 claims description 6
- 101100113998 Mus musculus Cnbd2 gene Proteins 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 abstract description 8
- 238000010791 quenching Methods 0.000 description 15
- 230000000171 quenching effect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/20—Recycling
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a method, a device and equipment for visually enhancing a high-temperature infrared image. The method comprises the following steps: acquiring an infrared gray image; carrying out contrast-limiting adaptive histogram equalization processing on the infrared gray level image to obtain a first enhanced image; training an image segmentation model by using the annotation data, segmenting the first enhanced image by using the image segmentation model to obtain a mask image, and enhancing the first enhanced image again by using the mask image to obtain a second enhanced image; and converting the second enhanced image into a color image by using a pseudo color mapping method. The method has the advantages of strong robustness and strong adaptability, and the enhanced high-temperature infrared image is more in line with the visual characteristics of human eyes.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method, a device and equipment for visually enhancing a high-temperature infrared image.
Background
In the field of high temperature technology, there are special requirements for image capture of a target object, which require high image visibility and the ability to distinguish between the background and the target object. For example, in the metal smelting industry, a quenching furnace is a furnace in which a workpiece is heated before quenching, and quenching operation is performed by putting the workpiece into the quenching furnace, heating the workpiece to a certain preset temperature and keeping the temperature for a period of time, and then taking the workpiece out of the furnace and quickly putting the workpiece into a quenching liquid (oil or water). The quenching process requires that the temperature of the workpiece heated by the quenching furnace is uniform and is within a certain range. Therefore, monitoring the temperature of the workpiece in the quenching furnace plays an important role in the quenching process, and meanwhile, visualization of the temperature image of the workpiece can also provide help for temperature monitoring of field process personnel and control of the quenching process.
After the workpiece is heated in the quenching furnace for a period of time, the difference between the background temperature in the quenching furnace and the temperature of the workpiece is smaller, and the direct output image of the infrared camera is a gray image formed by temperature mapping. The gray values of the workpiece and the background in the gray image are relatively small in difference, and the boundary between the workpiece and the background is not obvious, so that the monitoring of the position and the temperature state of the workpiece by human eyes is difficult.
In order to facilitate workers to directly monitor the workpiece state of the temperature equalizing section of the quenching furnace through images, the contrast of the gray level images output by the infrared camera needs to be enhanced so as to distinguish the background from the workpiece. The conventional solution generally adopts linear or non-linear pixel region stretching to enhance an image, but due to the existence of noise on the image, the image enhancement effect is not good, and the effect of convenient distinguishing cannot be achieved, so how to assist in enhancing workpiece position information on the image and display the workpiece position information in an image form more sensitive to human eyes is an urgent problem to be solved in the field.
Disclosure of Invention
In order to solve the above problems, in one aspect, the present invention provides a method for enhancing visualization of a high temperature infrared image, where the method includes:
acquiring an infrared gray image;
the acquired image is subjected to contrast-limiting self-adaptive histogram equalization processing to obtain a first enhanced imageimg clahe ；
Training an image segmentation model using the annotation data, and aligning the first enhanced image using the image segmentation modelimg clahe Segmenting to obtain a mask image, enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg ；
Mapping the second enhanced image by using a pseudo color mapping methodimg seg Converted into a color map.
Further, the limited contrast adaptive histogram equalization process includes:
counting the gray value characteristics of the image;
setting a limiting contrast threshold;
setting a partition number threshold value;
and carrying out contrast-limiting self-adaptive histogram equalization processing on the infrared gray level image.
Further, the threshold value of limiting contrast is set according to the statistical result of the gray-scale features of the image, and the threshold value of the number of the subareas is set according to the size features of the interested object in the input image and the statistical result of the live image.
Further, the process of performing contrast-limited adaptive histogram equalization on the infrared grayscale image specifically includes:
based on the set limit contrast threshold and the partition number threshold, the original gray level image is subjected to limit contrast self-adaptive histogram equalization processing to obtain a first enhanced imageimg clahe 。
Further, the first enhanced image is subjected to image segmentation modelimg clahe The segmentation is specifically as follows:
first enhanced image using Mask R-CNN modelimg clahe Dividing to obtain a form ofCnt 1 ，Cnt 2 ，...，Cnt N A polygon outline of { right arrow over } polygon;
wherein,Cnt n is as followsnA set of convex polygon vertices of the outline of the region of interest,Nthe number of the segmented interesting objects is shown.
Further, the process of enhancing again by using the mask image specifically includes:
subjecting the pixel coordinates of the first enhanced image to a contour map of a polygonCnt 1 ,Cnt 2 ...,Cnt N Uniformly subtracting a specific value from the pixel gray value of each area in the image to obtain a second enhanced imageimg seg 。
Further, the second enhanced image is mapped by a pseudo-color mapping methodimg seg The conversion into color map process is:
setting a pseudo-color coefficient;
establishing a pixel calculation model in the conversion process;
and performing pixel calculation according to the set pseudo-color coefficient and the pixel calculation model in the conversion process, and synthesizing the image.
Further, the pseudo-color coefficients include:cr、cgand, andcb；
wherein,cris the pseudo-color coefficient of the red channel,cgIs the pseudo-color coefficient of the green channel,cbIs the blue channel pseudo-color coefficient.
Further, the pixel calculation model of the conversion process is as follows:
wherein, represents the multiplication,
a matrix of pixel values for the second enhanced image,img r for the red channel image of the constructed pseudo-color image,img g for the green channel image of the constructed pseudo-color image,img b a blue channel image of the constructed pseudo-color image.
Using images of three channels, red, green and blueimg r 、img g Andimg b and (5) performing channel superposition to synthesize an RGB image.
In another aspect, a device for visually enhancing a high temperature infrared image comprises:
the image acquisition unit is used for acquiring an infrared gray image;
an equalization processing unit for performing contrast-limited adaptive histogram equalization processing on the acquired image to obtain a first enhanced imageimg clahe ；
An image segmentation unit for segmenting the first enhanced imageimg clahe Obtaining a mask image, and enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg ；
An image conversion unit for converting the second enhanced imageimg seg Converted into a color map.
Further, the equalization processing unit is used for counting the gray value distribution characteristics of the image and generating a gray histogram; setting a contrast limiting threshold and a partition number threshold; and based on the set limited contrast threshold and the set partition number threshold, carrying out the balanced treatment of the limited contrast histogram on each partition area on the gray level image and outputting a first enhanced imageimg clahe 。
Further, the image segmentation unit is configured to segment the first enhanced image using an image segmentation model trained by the annotated workpiece position dataimg clahe Segmenting to obtain a mask image, and enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg 。
Further, the image conversion unit is used for setting a pseudo color coefficient value; constructing a conversion process pixel calculation model; and performing pixel calculation according to the set pseudo-color coefficient and the pixel calculation model in the conversion process, and synthesizing the image.
Further, the pseudo color coefficients includecr、cgAnd, andcb；
wherein,cris the pseudo-color coefficient of the red channel,cgIs the pseudo-color coefficient of the green channel,cbIs the blue channel pseudo-color coefficient.
Further, the conversion process pixel calculation model is specifically as follows:
wherein, represents the multiplication,
a matrix of pixel values for the second enhanced image,img r for the red channel image of the constructed pseudo-color image,img g for the green channel image of the constructed pseudo-color image,img b a blue channel image of the constructed pseudo-color image.
Using images of three channels, red, green and blueimg r 、img g Andimg b and (5) performing channel superposition to synthesize an RGB image.
In yet another aspect, a high temperature infrared image visualization enhancing apparatus, the visualization enhancing apparatus comprising a memory and a processor, wherein:
the memory to store executable instructions;
the processor is used for reading and executing the executable instructions stored in the memory so as to realize the high-temperature infrared image visualization enhancing method.
Compared with the prior art, the invention has the following beneficial effects:
according to the visual enhancement method for the high-temperature infrared image, firstly, the contrast of the image is enhanced by a method of limiting contrast self-adaptive histogram equalization; and then, carrying out workpiece position marking on the enhanced image, training an image segmentation model, and further enhancing the contrast between the workpiece and the background based on a segmentation result so as to obviously improve the display effect. Setting a gray threshold according to the gray distribution characteristics of the image; according to the size characteristics of an interested object, partition parameters are defined so as to be convenient for carrying out equalization processing on the image and achieve an expected processing effect, then the image is segmented and enhanced, and finally the image is processed by adopting a pseudo-color mapping method to obtain an image with higher identification degree.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a technical flow chart of an embodiment of the infrared image visualization enhancement method of the present invention;
FIG. 2 is a block diagram of an embodiment of the infrared image visualization enhancing apparatus of the present invention;
FIG. 3 is a block diagram of an embodiment of an infrared image visualization enhancing apparatus of the present invention;
FIG. 4 is a graph of the original infrared gray scale of an industrial site obtained by the present invention;
FIG. 5 is an image resulting from a limited contrast adaptive histogram equalization process performed on FIG. 4;
FIG. 6a is a histogram of gray scale for the temperature equalization region of FIG. 4;
FIG. 6b is a histogram of gray scale for the temperature equalization region of FIG. 5;
FIG. 7 is a Mask diagram of the workpiece in the uniform temperature region obtained by dividing the graph of FIG. 5 by using Mask R-CNN;
fig. 8 is an image obtained by performing enhancement processing on fig. 7.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a high-temperature infrared image visualization enhancement method, which is characterized in that the image contrast is enhanced by a contrast-limiting adaptive histogram equalization processing method, then workpiece position marking is carried out on the enhanced image, an image segmentation model is trained, image segmentation is carried out, the contrast between a workpiece and a background is further enhanced based on a segmentation result, and finally, graph optimization is carried out, so that the image visibility is enhanced. The method has the advantages of strong robustness and strong adaptability, and the enhanced high-temperature infrared image is more in line with the visual characteristics of human eyes; fig. 1 shows a technical flowchart of an embodiment of the infrared image visualization enhancement method of the present invention, where the visualization enhancement method specifically includes the following steps:
s1, acquiring an infrared gray level image.
When a gray image of an infrared camera during quenching and stabilizing heating of a workpiece is acquired in the field, as shown in fig. 4, it can be seen that the visual effect of the original gray image is very poor.
And S2, carrying out contrast limiting adaptive histogram equalization processing on the acquired image.
And (4) counting the gray value distribution characteristics of the gray image to obtain a gray histogram of the infrared gray image, as shown in fig. 6 a. In this embodiment, the statistical results show: in the right uniform temperature workpiece area, the pixel proportion of the picture gray value distributed between 125-160 is 77.8%, the pixel proportion of the gray value more than 160 is 4.5%, and the pixel proportion of the gray value less than 125 is 17.7%.
Setting proper gray value as limit according to the gray value distribution characteristic statistical result of the gray histogramMaking a contrast threshold; setting a threshold value of the number of the subareas according to the size characteristics of the interested object in the image; in this embodiment, the object of interest refers to a target object, for example, the workpiece in fig. 4 may be the target object; carrying out contrast limiting self-adaptive histogram equalization processing on the gray level image of each partition to obtain a first enhanced imageimg clahe . The specific process is as follows:
in this embodiment, the limit contrast threshold is set to 10, and the expectation of the width of the workpiece in the temperature equalization section is 50 pixels; in the horizontal direction, the number of divisions is set to 21, and the number of divisions in the vertical direction is similarly set to 21. Then, the image is subjected to contrast-limited adaptive histogram equalization processing, and an equalized image is obtained, as shown in fig. 5. Then, the gray level distribution characteristics of the image after the equalization processing are counted to obtain a gray level histogram of the image after the equalization processing, as shown in fig. 6 b. By comparing fig. 4 and fig. 5, it is apparent that: the visual effect of the original gray level image is improved by the equalization processing; by comparing fig. 6a and 6b, it is apparent that: the gray value distribution characteristics of the image after the equalization processing are closer to normal distribution.
And S3, segmenting the image processed in the S2, and further enhancing the image.
First, a first enhanced image is marked by using a marking toolimg clahe Marking the position of the workpiece, and based on the marked image, adopting a Mask R-CNN algorithm based on deep learning to segment the image subjected to equalization processing to obtain an interested object region image (Mask image), namely, the image in the form of a great mouthCnt 1 ，Cnt 2 ，...，Cnt N Figure i polygon outline. Wherein,Cnt n is as followsnA set of convex polygon vertices of the outline of the region of interest,Nthe number of the segmented interesting objects is shown.
In the embodiment, a training set of a Mask R-CNN model is set as 2000 images marked on the positions of workpieces in a uniform temperature region in the same scene, and the Mask R-CNN model is trained; the images in the training set are obtained after workpiece position marking is carried out on labelme; then use the trainingThe Mask R-CNN model divides the equalized image to obtain a workpiece Mask image only with a temperature equalizing region, and the corresponding polygonal contour map is a great curl as shown in FIG. 7
}. In order to distinguish the workpiece and the background in the uniform temperature region, the gray value of the pixel point of the coordinate in the mask of fig. 7 in fig. 5 is subtracted by a fixed value 5 to obtain a second enhanced image with further enhanced contrastimg seg As shown in fig. 8. Namely:
wherein,ithe coordinates of the pixel points in the horizontal direction in figure 5,jthe coordinates of the pixel points in the vertical direction in figure 5,g ij is a coordinate of (in FIG. 5)i,j) The gray value of the pixel point of (a),
is a coordinate of (in FIG. 7)i,j) The gray value of the pixel point of (a),Nthe number of the divided workpieces is equal to that of the workpieces,Wto be the width of the image,His the image height.
Obtaining a second enhanced image through the above processing procedureimg seg The process further enhances the contrast between the workpiece and the background; furthermore, since the pixel grayscale values in the workpiece region are all subtracted by the deterministic value, the grayscale values of the pixels in FIG. 8 can still reflect the local temperature of the region.
And S4, converting the gray-scale image obtained in the step S3 into a color image by using a pseudo-color mapping method.
Because the temperature in the quenching furnace is high, a warm color pseudo-color method with larger pseudo-color coefficient of a red channel is selected, and related parameters are setcr=3.5，cg=1.4，cb= 0.5; wherein,cris the pseudo-color coefficient of the red channel,cgIs the pseudo-color coefficient of the green channel,cbIs the blue channel pseudo-color coefficient. Multiplying the pixel value of each point in the graph 8 by a red channel pseudo-color coefficient, a green channel pseudo-color coefficient and a blue channel pseudo-color coefficient respectively to obtain a red channel image, a green channel image and a blue channel image, wherein the calculation formula is as follows:
wherein, represents the multiplication,
a matrix of pixel values for the second enhanced image,img r for the red channel image of the constructed pseudo-color image,img g for the green channel image of the constructed pseudo-color image,img b for the blue channel image of the constructed pseudo-color image, the gray value of each pixel point is limited to be not more than 255 because the gray value of the image pixel is stored by 8 bytes and ranges from 0 to 255.
Using red, green and blue three-channel imagesimg r 、img g Andimg b and (4) performing channel superposition, and synthesizing an RGB image to obtain a final enhanced image.
The invention provides a high-temperature infrared image visualization enhancing device, which is characterized in that the contrast of an original image is enhanced based on a contrast-limiting self-adaptive histogram equalization processing method; then marking the position of the workpiece on the enhanced image; then, segmenting the image by utilizing the trained segmentation model; enhancing the image contrast again based on the image segmentation result; and finally, carrying out optimization processing on the re-enhanced image to obtain an enhanced image which has better visual effect and is easily distinguished by human eyes. The visualization enhancing device is divided into an image acquisition unit, an equalization processing unit, an image segmentation unit and an image conversion unit according to functions; fig. 2 shows a frame diagram of an embodiment of the infrared image visualization enhancing apparatus of the present invention.
When a threshold value for limiting the contrast is set in the equalization processing unit, the statistical result of the image gray value distribution characteristics output by the statistical module is taken as a basis; when the threshold of the number of the subareas is set, the size characteristics of the workpiece in the input image and the statistical result of the field image are taken as the basis.
In an image segmentation unit, a trained Mask R-CNN model is used for a first enhanced imageimg clahe Is divided and obtained in the form of aCnt 1 ，Cnt 2 ，...，Cnt N A polygon outline of { right arrow over } polygon;
wherein,Cnt n is as followsnA set of convex polygon vertices of the outline of the region of interest,Nthe number of the segmented interesting objects is obtained.
The pixel gray value of each area of the pixel coordinates in the first enhanced image in the polygonal contour is uniformly subtracted by a specific value to further enhance the first enhanced image to obtain a second enhanced imageimg seg 。
The image conversion unit utilizes the second enhanced imageimg seg And the pixel pseudo-color coefficient and the conversion process pixel calculation model are used for carrying out pixel calculation to obtain images of three channels of red, green and blueimg r 、img g Andimg b (ii) a Thirdly, using the images of the red, green and blue channelsimg r ,img g Andimg b and synthesizing an RGB image to obtain a final enhanced image.
The invention provides a high-temperature infrared image visualization enhancing device which comprises a memory and a processor. The equipment firstly acquires an on-site infrared gray image, then enhances the contrast of the infrared gray image based on a contrast-limiting adaptive histogram equalization processing method, and then segments the enhanced image by utilizing a trained Mask R-CNN model to obtain a workpiece Mask image; enhancing the contrast of the image again based on the obtained workpiece mask image; finally, optimizing the image to obtain a final display image with better visual effect; fig. 3 shows a frame diagram of an embodiment of the infrared image visualization enhancing apparatus of the present invention.
And the memory is used for storing information such as a field image acquired by the visualization enhancing equipment, an intermediate image generated in the image processing process, set related parameter data, an image segmentation model, a pixel conversion calculation model, an execution instruction and the like.
And the processor is used for reading various image information and parameter data information stored in the memory and carrying out corresponding processing procedures according to the execution instruction information, so that an enhanced image with better visual effect is finally obtained.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (15)
1. A visualization enhancing method for high temperature infrared images is characterized by comprising the following steps:
acquiring an infrared gray image;
the acquired image is subjected to contrast-limiting self-adaptive histogram equalization processing to obtain a first enhanced imageimg clahe ；
Training an image segmentation model using the annotation data, and aligning the first enhanced image using the image segmentation modelimg clahe Segmenting to obtain a mask image, enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg ；
The first enhanced image is subjected to image segmentation modelimg clahe The segmentation is specifically as follows:
first enhanced image using Mask R-CNN modelimg clahe Dividing to obtain a form ofCnt 1 ，Cnt 2 ，...，Cnt n ，...，Cnt N A polygon outline of { right arrow over } polygon;
wherein,Cnt n is as followsnA set of convex polygon vertices of the outline of the region of interest,Nthe number of the segmented interesting objects is;
mapping the second enhanced image by using a pseudo color mapping methodimg seg Converted into a color map.
2. The method for visually enhancing the high temperature infrared image according to claim 1, wherein the process of limiting contrast adaptive histogram equalization comprises:
counting gray value characteristics of the image;
setting a limiting contrast threshold;
setting a partition number threshold value;
and carrying out contrast-limiting self-adaptive histogram equalization processing on the infrared gray level image.
3. The method of claim 2, wherein the threshold of contrast limit is set according to the statistical result of the gray scale features of the image, and the threshold of the number of partitions is set according to the size features of the object of interest in the input image and the statistical result of the live image.
4. The method for visually enhancing the high-temperature infrared image according to claim 2, wherein the process of performing the contrast-limited adaptive histogram equalization on the infrared gray image specifically comprises:
based on the set limit contrast threshold and the partition number threshold, the original gray level image is subjected to limit contrast self-adaptive histogram equalization processing to obtain a first enhanced imageimg clahe 。
5. The method for enhancing visualization of a high-temperature infrared image according to claim 1, wherein the process of enhancing again by using the mask image is specifically as follows:
subjecting the pixel coordinates of the first enhanced image to a contour map of a polygonCnt 1 ,Cnt 2 ...,Cnt N Uniformly subtracting a specific value from the pixel gray value of each area in the image to obtain a second enhanced imageimg seg 。
6. The method for visually enhancing a high temperature infrared image according to claim 1, wherein the second enhanced image is obtained by a pseudo color mapping methodimg seg The conversion into color map process is:
setting a pseudo-color coefficient;
establishing a pixel calculation model in the conversion process;
and performing pixel calculation according to the set pseudo-color coefficient and the pixel calculation model in the conversion process, and synthesizing the image.
7. The method for visually enhancing a high temperature infrared image according to claim 6, wherein the pseudo color coefficients comprise:cr、cgand, andcb；
wherein,cris the pseudo-color coefficient of the red channel,cgPseudo-color coefficient of green channel,cbIs the blue channel pseudo-color coefficient.
8. The method for visually enhancing the high temperature infrared image according to claim 7, wherein the pixel calculation model of the conversion process is:
wherein, represents the multiplication,
a matrix of pixel values for the second enhanced image,img r for the red channel image of the constructed pseudo-color image,img g for the green channel image of the constructed pseudo-color image,img b a blue channel image of the constructed pseudo-color image;
using images of three channels, red, green and blueimg r 、img g Andimg b and (5) performing channel superposition to synthesize an RGB image.
9. A high temperature infrared image visualization enhancing apparatus, comprising:
the image acquisition unit is used for acquiring an infrared gray image;
an equalization processing unit for performing contrast-limited adaptive histogram equalization processing on the acquired image to obtain a first enhanced imageimg clahe ；
An image segmentation unit for segmenting the first enhanced imageimg clahe Obtaining a mask image, and enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg ；
The segmenting the first enhanced imageimg clahe The method specifically comprises the following steps:
first enhanced image using Mask R-CNN modelimg clahe Dividing to obtain a form ofCnt 1 ，Cnt 2 ，...，Cnt n ，...，Cnt N A polygonal outline map of { circle;
wherein,Cnt n is as followsnA set of convex polygon vertices of the outline of the region of interest,Nthe number of the segmented interesting objects is;
an image conversion unit for converting the second enhanced imageimg seg Converted into a color map.
10. The device for visually enhancing the high-temperature infrared image according to claim 9, wherein the equalization processing unit is configured to count gray-scale value distribution characteristics of the image and generate a gray-scale histogram; setting a limiting contrast threshold and a partition number threshold; and based on the set limited contrast threshold and the set partition number threshold, carrying out the balanced treatment of the limited contrast histogram on each partition area on the gray level image and outputting a first enhanced imageimg clahe 。
11. The device of claim 9, wherein the image segmentation unit is configured to apply the first enhanced image to the image using an image segmentation model trained by the annotated workpiece position dataimg clahe Segmenting to obtain a mask image, and enhancing the first enhanced image again by using the mask image to obtain a second enhanced imageimg seg 。
12. The device for enhancing visualization of a high temperature infrared image as claimed in any one of claims 9 to 11, wherein the image conversion unit is configured to set a pseudo color coefficient value; constructing a conversion process pixel calculation model; and performing pixel calculation according to the set pseudo-color coefficient and the pixel calculation model in the conversion process, and synthesizing the image.
13. The device of claim 12, wherein the pseudo-color coefficients comprisecr、cgAnd, andcb；
wherein,cris the pseudo-color coefficient of the red channel,cgIs the pseudo-color coefficient of the green channel,cbIs the blue channel pseudo-color coefficient.
14. The device for visually enhancing a high temperature infrared image according to claim 13, wherein the conversion process pixel calculation model is specifically as follows:
wherein, represents the multiplication,
a matrix of pixel values for the second enhanced image,img r for the red channel image of the constructed pseudo-color image,img g for the green channel image of the constructed pseudo-color image,img b a blue channel image of the constructed pseudo-color image;
using images of three channels, red, green and blueimg r 、img g Andimg b and (5) performing channel superposition to synthesize an RGB image.
15. A high temperature infrared image visualization enhancing apparatus, comprising a memory and a processor, wherein:
the memory to store executable instructions;
the processor is used for reading and executing the executable instructions stored in the memory to realize the high-temperature infrared image visualization enhancing method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210244689.7A CN114331928B (en) | 2022-03-14 | 2022-03-14 | High-temperature infrared image visualization enhancement method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210244689.7A CN114331928B (en) | 2022-03-14 | 2022-03-14 | High-temperature infrared image visualization enhancement method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114331928A CN114331928A (en) | 2022-04-12 |
| CN114331928B true CN114331928B (en) | 2022-08-09 |
Family
ID=81033308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210244689.7A Active CN114331928B (en) | 2022-03-14 | 2022-03-14 | High-temperature infrared image visualization enhancement method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331928B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0318039B1 (en) * | 1987-11-26 | 1995-02-01 | Fujitsu Limited | An emergency watching system using an infrared image processing |
| CN104252700B (en) * | 2014-09-18 | 2017-06-20 | 电子科技大学 | A kind of histogram equalization method of infrared image |
| CN106952246A (en) * | 2017-03-14 | 2017-07-14 | 北京理工大学 | Visible-infrared image enhancement color fusion method based on visual attention characteristics |
| CN109147005B (en) * | 2018-08-24 | 2023-02-28 | 电子科技大学 | Self-adaptive dyeing method and system for infrared image, storage medium and terminal |
| CN112561835A (en) * | 2020-12-15 | 2021-03-26 | 南京邮电大学 | Adaptive inverse histogram equalization detail enhancement method and system |
-
2022
- 2022-03-14 CN CN202210244689.7A patent/CN114331928B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114331928A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767354B (en) | An Image Dehazing Algorithm Based on Dark Primitive Color Prior | |
| CN110490896B (en) | Video frame image processing method and device | |
| EP3477931A1 (en) | Image processing method and device, readable storage medium and electronic device | |
| CN108229276B (en) | Neural network training and image processing method and device and electronic equipment | |
| CN108537749B (en) | Image processing method, image processing device, mobile terminal and computer readable storage medium | |
| CN111028137B (en) | Image processing method, apparatus, electronic device, and computer-readable storage medium | |
| CN105118027B (en) | A kind of defogging method of image | |
| CN104166967B (en) | Method for improving definition of video image | |
| US10565741B2 (en) | System and method for light field correction of colored surfaces in an image | |
| CN103886565B (en) | Nighttime color image enhancement method based on purpose optimization and histogram equalization | |
| CN113822830B (en) | Multi-exposure image fusion method based on depth perception enhancement | |
| CN107368806B (en) | Image rectification method, image rectification device, computer-readable storage medium and computer equipment | |
| CN107993209A (en) | Image processing method, device, computer-readable recording medium and electronic equipment | |
| CN107730444A (en) | Image processing method, device, readable storage medium storing program for executing and computer equipment | |
| WO2019056549A1 (en) | Image enhancement method, and image processing device | |
| CN107833189A (en) | The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast | |
| CN111369478A (en) | Face image enhancement method and device, computer equipment and storage medium | |
| CN114022383A (en) | Moire pattern removing method and device for character image and electronic equipment | |
| AU2013258866A1 (en) | Reducing the dynamic range of image data | |
| CN112287765B (en) | Face living body detection method, device, equipment and readable storage medium | |
| CN107909542A (en) | Image processing method, device, computer-readable recording medium and electronic equipment | |
| CN114119433B (en) | A dark image processing method based on Bezier curve | |
| CN111080754B (en) | Character animation production method and device for connecting characteristic points of head and limbs | |
| CN114331928B (en) | High-temperature infrared image visualization enhancement method, device and equipment | |
| CN119068091B (en) | Three-dimensional head model texture generation method and device and electronic equipment |
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 |