WO2022152107A1

WO2022152107A1 - Infrared image quality evaluation method, device, and storage medium

Info

Publication number: WO2022152107A1
Application number: PCT/CN2022/071242
Authority: WO
Inventors: 刘勇; 张涛; 陈美文; 何科君; 武金龙
Original assignee: 深圳市普渡科技有限公司
Priority date: 2021-01-12
Filing date: 2022-01-11
Publication date: 2022-07-21
Also published as: CN114764775A

Abstract

Disclosed are an infrared image quality evaluation method, a device, and a storage medium. The method comprises: obtaining an infrared image as an image to be evaluated; obtaining a target region on the basis of said image; calculating feature data of each target region on the basis of the target region, respectively, the feature data comprising a region brightness value of the target region and a definition value of the target region; and calculating, on the basis of the obtained feature data, a quality score of said image related to the feature data.

Description

Infrared image quality evaluation method, device and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application filed on January 12, 2021 with the application number 202110038494.2 and the application title is "Infrared Image Quality Evaluation Method, Device and Storage Medium", the entire contents of which are incorporated by reference in in this application.

technical field

The present application relates to the technical field of infrared image processing, and in particular, to an infrared image quality evaluation method, device and storage medium.

Background technique

The conventional infrared image quality evaluation scheme is generally based on the overall image. In the application scenario, only a specific area of the infrared image needs to be evaluated.

Therefore, if the conventional infrared image quality evaluation scheme is used to evaluate the local high-contrast infrared image scene, it is not conducive to the subsequent image algorithm processing, nor is it conducive to provide accurate early warning and reference for judging whether the field data is abnormal.

SUMMARY OF THE INVENTION

According to various embodiments of the present application, an infrared image quality evaluation method is provided, including:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

Based on the target area, the characteristic data of each target area is calculated respectively, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

Based on the acquired feature data, a quality score of the image to be evaluated related to the feature data is calculated.

An infrared image quality evaluation device, comprising:

an image acquisition module to be evaluated, configured to acquire an infrared image as an image to be evaluated;

a highlight area detection module, configured to acquire a target area based on the to-be-evaluated image;

The highlight area brightness and sharpness evaluation module, based on the target area, respectively calculates the characteristic data of each target area, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

The step module of outputting the quality evaluation result of the image to be evaluated is used for calculating the quality score of the image to be evaluated related to the characteristic data based on the acquired characteristic data.

A computer device includes a memory, a processor, and a readable storage medium stored in the memory and executable on the processor, and the processor implements the following steps when executing the readable storage medium:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

Based on the acquired feature data, a quality score of the image to be evaluated related to the feature data is calculated. One or more computer-readable storage media storing computer-readable instructions that store computer-readable instructions that, when executed by one or more processors, cause the One or more processors perform the following steps:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the present application will be apparent from the description, drawings and claims.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments of the present application or the prior art. The drawings are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

1 is a flowchart of a method for evaluating infrared image quality in an embodiment of the present application;

Fig. 2 is another flowchart of an infrared image quality evaluation method in an embodiment of the present application;

3 is another flowchart of an infrared image quality evaluation method in an embodiment of the present application;

4 is another flowchart of an infrared image quality evaluation method in an embodiment of the present application;

5 is a schematic diagram of an infrared image quality evaluation device in an embodiment of the present application;

FIG. 6 is a schematic diagram of a computer device in an embodiment of the present application.

Detailed ways

In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the related drawings. The preferred embodiments of the present application are shown in the accompanying drawings. However, the application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that a thorough and complete understanding of the disclosure of this application is provided.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field of the invention. The terms used herein in the description of the invention are for the purpose of describing particular embodiments only and are not intended to limit the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

An embodiment of the present application provides an infrared image quality evaluation method, as shown in FIG. 1 , including the following steps:

Step S1 of acquiring an image to be evaluated: acquiring an infrared image as an image to be evaluated.

Specifically, an infrared image is obtained as an image to be evaluated by adopting a high-reverse cooperation sign and a supplementary light enhancement method; the cooperation sign is an artificially set reflective sign.

Highlight region detection step S2: based on the to-be-evaluated image, acquire a target region.

Specifically, based on the to-be-evaluated image, dividing several target areas includes preprocessing the to-be-evaluated image, that is, performing adaptive threshold segmentation on the to-be-evaluated image to obtain a corresponding binary map, wherein the to-be-evaluated image It is obtained by using a number of high-reverse cooperation signs and fill lights to enhance the acquisition.

judging whether the cooperation sign can be identified in the binary image;

If the cooperation logo is identified in the binary image, the circumscribed rectangle of each cooperative logo is obtained, and the circumscribed rectangle of each cooperative logo is expanded by several pixels to obtain a plurality of expanded logo circumscribed rectangles area, and a rectangular area circumscribing each mark is used as the target area. In other embodiments, the circumscribed rectangle of each cooperation sign may also be expanded in a preset area ratio, for example, the target area is obtained by expanding the circumscribed rectangle of each cooperation sign by 25%.

If the cooperation sign is not recognized, a rectangular area of N*M pixels in the central area of the image to be evaluated is used as the target area. Wherein, in order to facilitate the calculation, the rectangular area of the N*M pixel points is generally taken as a square. Specifically, the rectangular area may be a square area of 200×200 pixels, and in other embodiments, it may also be an area of other numbers of pixels, which is not limited here.

Brightness and sharpness evaluation step S3 of the highlighted area: Based on the target area, calculate the characteristic data of each target area respectively, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area.

Specifically, to calculate the feature data of each target area separately, a two-dimensional Gaussian distribution proportional to the height and width of the image to be evaluated needs to be generated. When it is located at the center position (x, y) of the image to be evaluated, the The two-dimensional Gaussian distribution obtains the maximum value; the two-dimensional Gaussian distribution is multiplied by a preset scale coefficient lamda to obtain a template showing the brightness distribution of the image to be evaluated;

calculating the average brightness value of several pixels whose brightness value is a preset top ratio on each of the target areas, and using the average brightness value as the first brightness value of the corresponding target area;

Obtain the position coordinates of the center point of each target area, query the brightness value of the corresponding position of each of the position coordinates from the template, and use the brightness value as the second brightness value corresponding to the target area;

Taking the absolute value of the difference between the first brightness value and the second brightness value of each target area as the regional brightness value of the target area;

Calculate the average gradient of luminance values for each target area;

The sharpness value for each of the target regions is calculated based on the average gradient of the luminance values by the following formula:

C=(x*x+y*y)*D;

Wherein, the C is the sharpness value, and the D is the average gradient of the luminance value.

The regional brightness value and sharpness value of the target area are characteristic data used for image quality evaluation.

Outputting the quality evaluation result of the image to be evaluated Step S4: Based on the acquired feature data, calculate a quality score of the image to be evaluated related to the feature data.

Specifically, calculating the brightness average value of the regional brightness values of all the target regions;

calculating a sharpness average of sharpness values of all said target regions;

The quality score is obtained by weighting the brightness average value and the sharpness average value by using a preset weight ratio.

The quality score of the image to be evaluated is calculated by the following formula:

Score=exp(average value/alpha of area luminance values of all target areas)+exp(average value/beta of sharpness of all target areas), where exp represents the index, alpha and beta are variance coefficients, and Score is the quality Score.

The sharpness value and the brightness value of the target area are adjusted to obtain the quality evaluation result of the image to be evaluated.

In the embodiment of the present application, as shown in FIG. 1 , the highlight area detection step S2 is to obtain the target area based on the image to be evaluated, which specifically includes the following steps:

S21: Adopt adaptive threshold segmentation to obtain a binary image corresponding to the image to be evaluated.

Specifically, adaptive threshold segmentation refers to a method of using image local thresholds to replace global thresholds for image calculation, specifically for pictures with excessive changes in light and shadow, or pictures with less obvious color differences within the range. Adaptive means to ensure that the computer can obtain the average threshold value of the image area through judgment and calculation to iterate. In the process of image processing, when performing binarization and other operations before the shop, we hope to be able to provide and retain all the information in the corresponding area of the image. In the laboratory environment, the corresponding material is templated, but when the laboratory method is applied to the real environment, we will find that the light and shadow environment has a great influence on the effect. Processing in this case will result in unsatisfactory results: a block of black, a block of white, and the features of the black area cannot be extracted. At this time, the adaptive threshold algorithm is particularly important. Different from the global threshold, it pays more attention to the context relationship, divides the original image into smaller areas for judgment, and greatly reduces the influence of shadows on the image itself.

S22: Determine whether the cooperation flag can be identified in the binary image.

Specifically, the cooperation flag is step S1, and an infrared image is acquired as the image to be evaluated, and the cooperation flag is used when acquiring the infrared image. In the image to be evaluated, that is, the original image, the location of the cooperation sign can be directly observed. Using adaptive threshold segmentation, a binary image corresponding to the image to be evaluated is obtained, and it is judged whether the cooperation sign can be recognized in the binary image.

S23: If the cooperation logo is identified, then obtain the circumscribed rectangle of each of the cooperative logos, and expand the circumscribed rectangle of each of the cooperative logos by several pixels to obtain a plurality of expanded logo circumscribed rectangle areas, so that the Each marked circumscribed rectangular area in the image to be evaluated is used as the target area.

Specifically, if the cooperation flag is identified in the binary map, first obtain the circumscribed rectangle of each of the cooperation flags, and then expand the circumscribed rectangle of each of the cooperation flags, generally by 25%. , other arbitrary pixel point range values can also be selected for expansion to obtain a number of expanded logo circumscribed rectangular areas, and then these several logo circumscribed rectangular areas are corresponding to the original image to be evaluated, with the Each mark circumscribes a rectangular area as the target area.

S24: If the cooperation sign is not recognized, use a rectangular area of N*M pixels in the central area of the image to be evaluated as the target area.

Specifically, if the cooperation sign is not identified in the binary image, a rectangular area of N*M pixels in the central area of the image to be evaluated is selected as the target area, that is, the area to be evaluated. Wherein, for the rectangular area, in order to facilitate the calculation, an N*N square area is generally selected.

In the embodiment of the present application, as shown in FIG. 1 , the step S3 of evaluating the brightness and sharpness of the highlighted area is to calculate the characteristic data of each target area based on the target area, and the characteristic data includes the area of the target area. The brightness value and the sharpness value of the target area specifically include the following steps:

S31: Perform Gaussian blurring on the image to be evaluated to obtain a template showing the brightness distribution of the image to be evaluated.

Specifically, Gaussian blurring is performed on the image to be evaluated, that is, a two-dimensional Gaussian distribution proportional to the height and width of the image to be evaluated is generated. The two-dimensional Gaussian distribution function value is the brightness value of the image to be evaluated, based on the two-dimensional Gaussian distribution. The characteristic of , when the coordinates of the center of the image to be evaluated are located, the two-dimensional Gaussian distribution obtains the maximum value. Obtaining a template for displaying the brightness distribution of the image to be evaluated, that is, multiplying the two-dimensional Gaussian distribution by a proportional coefficient lamda to obtain a template for displaying the brightness distribution of the image to be evaluated.

S32: Calculate, based on the template, an area brightness value and a sharpness value of each of the target areas.

Specifically, the regional brightness value of each of the target areas is calculated, that is, the average brightness value of several pixels whose brightness value is a preset top ratio on each of the target areas is calculated, and the average brightness value is used as the corresponding The first brightness value of the target area, wherein when calculating the average brightness value of the target area, the selected pixels are based on the brightness value of the pixel points, generally taking the first 80%, and other range of pixels. Obtain the position coordinates of the center point of each target area, and query the brightness value of the corresponding position of each of the position coordinates from the template, that is, query the brightness value of the position that is the same as the position coordinates of the target center point from the template, and use the template. The luminance value is used as the second luminance value corresponding to the target area, and the absolute value of the difference between the first luminance value and the second luminance value of each target area is used as the area of the target area brightness value;

The template is obtained through step S31, that is, performing Gaussian blurring on the image to be evaluated to obtain a template that displays the brightness distribution of the image to be evaluated. The position (x, y) of the center point of the target area refers to the coordinates of the intersection of the diagonal lines of the marked circumscribed rectangular area.

Specifically, to calculate the sharpness value of each described target area, the average gradient D of the luminance value of each described target area needs to be calculated first, and the luminance value gradient d(i, j) of the image to be evaluated is calculated as follows:

dx(i,j)=I(i+1,j)-I(i,j);

dy(i,j)=I(i,j+1)-I(i,j);

d(i,j)=abs(dx(i,j))+abs(dy(i,j));

Average gradient D=sum(d(i,j))/counts(pixels);

Wherein, I refers to the pixel brightness value of the image to be evaluated, (i, j) is the coordinate of the pixel in the specified area, and counts(pixels) is the number of pixels in the target area;

The sharpness value C of each target area is calculated according to the average gradient D of luminance values, C=(x*x+y*y)*D.

In the embodiment of the present application, as shown in FIG. 1 , the step S4 of outputting the quality evaluation result of the image to be evaluated is to calculate the quality score of the image to be evaluated related to the characteristic data based on the acquired characteristic data, which specifically includes the following steps:

S41: Calculate the image quality score to be evaluated comprehensively related to the sharpness value and the regional brightness value;

Specifically, to calculate the image quality score to be evaluated comprehensively related to the sharpness and brightness, it is necessary to first calculate the brightness average value of the regional brightness values of all the target areas and the sharpness average value of the sharpness values of all the target areas. ;

Optionally, the quality score of the image to be evaluated can be calculated by the following formula:

Score=exp(average value/alpha of the area brightness values of all target areas)+exp(average value/beta of the sharpness of all target areas), where exp represents the exponent, alpha and beta are variance coefficients, and Score is the quality Score.

S42: Adjust the sharpness value and the regional brightness value of the target area, and obtain the quality evaluation result of the image to be evaluated.

Specifically, the sharpness value and the area brightness value of the target area are adjusted, wherein the sharpness value of the target area can be adjusted by adjusting the brightness value of the pixel points of the image to be evaluated, and the sharpness value of the target area can be adjusted by adjusting the first brightness value or the second brightness value. The sharpness value of the target area is adjusted based on the brightness value, and based on empirical adjustment, the impact of different sharpness values and regional brightness values of the target area on the image quality score to be evaluated is analyzed, and the image quality evaluation result to be evaluated is obtained.

An infrared image quality evaluation device, further comprising:

The to-be-evaluated image acquisition module 51 is configured to acquire an infrared image as the to-be-evaluated image.

The highlight area detection module 52 is configured to acquire a target area based on the image to be evaluated.

The highlight area brightness and sharpness evaluation module 53 is used to calculate the characteristic data of each target area based on the target area, and the characteristic data includes the area brightness value of the target area and the sharpness of the target area value.

The step module 54 of outputting the quality evaluation result of the image to be evaluated is configured to calculate, based on the acquired feature data, a quality score of the image to be evaluated related to the feature data.

Preferably, the highlight area detection module 52, that is, to acquire the target area based on the image to be evaluated, includes: an image preprocessing unit, an identification unit, a first judgment unit, and a second judgment unit.

The image preprocessing unit is used for adopting adaptive threshold segmentation to obtain the binary image corresponding to the image to be evaluated.

An identification unit, configured to judge whether the cooperation sign can be identified in the binary image.

The first judging unit is used to obtain the circumscribed rectangle of each of the cooperative signs if the cooperative sign is recognized, and to expand the circumscribed rectangle of each of the cooperative signs by a number of pixels, and obtain a number of expanded signs circumscribed. A rectangular area, a rectangular area circumscribing each mark in the image to be evaluated is used as the target area.

The second judging unit is configured to use a rectangular area of N*M pixels in the central area of the image to be evaluated as a target area if the cooperation sign is not recognized.

Preferably, the highlight area brightness and sharpness evaluation module 53 calculates the characteristic data of each target area based on the target area, and the characteristic data includes the area brightness value of the target area and the target area Definition value, including: template establishment unit, feature data acquisition unit.

The template establishment unit is configured to perform Gaussian blurring on the image to be evaluated to obtain a template showing the brightness distribution of the image to be evaluated.

A feature data acquisition unit, configured to calculate, based on the template, an area brightness value and a sharpness value of each of the target areas.

Preferably, the step module 54 of outputting the image quality evaluation result to be evaluated, that is, based on the acquired feature data, calculates the image quality score to be evaluated related to the feature data, including: an image quality score calculation unit, and an image quality evaluation result acquisition unit.

An image quality score calculation unit, configured to calculate a to-be-evaluated image quality score comprehensively related to the sharpness value and the regional brightness value.

Image quality evaluation result obtaining unit: used to adjust the sharpness value and the regional brightness value of the target area, and obtain the image quality evaluation result to be evaluated.

In one embodiment, a computer device is provided, the computer device can be a terminal, and its internal structure diagram is shown in FIG. 6 , the computer device includes a processor, a memory, a network interface, a display screen and a input device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the execution of the operating system and computer-readable instructions in the readable storage medium. The network interface of the computer device is used to communicate with an external server over a network connection. The computer-readable instructions, when executed by a processor, implement a method for evaluating infrared image quality. The readable storage medium provided by this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, and the processor implements the above embodiments when executing the computer-readable instructions The steps of the infrared image quality evaluation method, such as steps S1-S4 shown in FIG. 1 , or steps shown in FIG. 2 to FIG. 4 , are not repeated here in order to avoid repetition. Or, when the processor executes the computer program, the functions of each module/unit in this embodiment of the user interface automatic testing device are realized, for example, the image acquisition module 51 to be evaluated, the highlight region detection module 52, the highlight region shown in FIG. 5 The functions of the brightness and sharpness evaluation module 53 and the step module 54 for outputting the evaluation result of the image quality to be evaluated are not repeated here in order to avoid repetition.

In one embodiment, a computer-readable storage medium is provided, and the readable storage medium provided by this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium, the computer-readable storage medium The medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the infrared image quality evaluation method in the above-mentioned embodiment are implemented, for example, steps S1-S4 shown in FIG. 1 , or steps S1-S4 shown in FIG. The steps shown, in order to avoid repetition, are not repeated here. Or, when the processor executes the computer program, the functions of each module/unit in this embodiment of the user interface automatic testing device are realized, for example, the image acquisition module 51 to be evaluated, the highlight region detection module 52, the highlight region shown in FIG. 5 The functions of the brightness and sharpness evaluation module 53 and the step module 54 for outputting the evaluation result of the image quality to be evaluated are not repeated here in order to avoid repetition.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile computer. In the read storage medium or the volatile readable storage medium, the computer-readable instructions, when executed, may include the processes of the foregoing method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated to different functional units, Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above-described embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be regarded as the scope described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent application. It should be noted that, for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

An infrared image quality evaluation method, comprising:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

Based on the target area, the characteristic data of each target area is calculated respectively, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

Based on the acquired feature data, a quality score of the image to be evaluated related to the feature data is calculated.
The infrared image quality evaluation method according to claim 1, wherein acquiring the target area based on the to-be-evaluated image comprises:

Adopt adaptive threshold segmentation to obtain the binary image corresponding to the image to be evaluated, wherein the image to be evaluated is obtained by using several highly inverse cooperation signs and supplementary lights to enhance the acquisition;

judging whether the cooperation sign can be identified in the binary image;

If the cooperation logo is identified, the circumscribed rectangle of each cooperation logo is obtained, and the circumscribed rectangle of each cooperation logo is expanded by several pixels to obtain a plurality of expanded logo circumscribed rectangle areas, so that Each marked circumscribed rectangular area in the image to be evaluated is used as the target area;

If the cooperation sign is not recognized, a rectangular area of N*M pixels in the central area of the image to be evaluated is used as the target area.
The infrared image quality evaluation method according to claim 2, comprising: the rectangular area of the N*M pixel points is a square.
The infrared image quality evaluation method according to claim 1, wherein the characteristic data of each target area is calculated separately based on the target area, comprising:

Generate a two-dimensional Gaussian distribution proportional to the height and width of the image to be evaluated, and when positioned at the center of the image to be evaluated, the two-dimensional Gaussian distribution obtains a maximum value;

Multiply the two-dimensional Gaussian distribution by the scale coefficient lamda to obtain a template showing the brightness distribution of the image to be evaluated;

calculating the average brightness value of several pixels whose brightness value is a preset top ratio on each of the target areas, and using the average brightness value as the first brightness value of the corresponding target area;

Obtain the position coordinates of the center point of each target area, query the brightness value of the corresponding position of each of the position coordinates from the template, and use the brightness value as the second brightness value corresponding to the target area;

Taking the absolute value of the difference between the first brightness value and the second brightness value of each target area as the regional brightness value of the target area;

Calculate the average gradient of luminance values for each target area;

The sharpness value for each of the target regions is calculated based on the average gradient of the luminance values by the following formula:

C=(x*x+y*y)*D;

Wherein, the C is the sharpness value, and the D is the average gradient of the luminance value.
The method for evaluating the quality of an infrared image according to claim 1, wherein calculating the image quality score to be evaluated related to the feature data based on the acquired feature data, comprising:

Calculate the brightness average value of the regional brightness values of all the target areas;

calculating a sharpness average of sharpness values of all said target regions;

The quality score is obtained by weighting the brightness average value and the sharpness average value by using a preset weight ratio.
An infrared image quality evaluation device, comprising:

an image acquisition module to be evaluated, configured to acquire an infrared image as an image to be evaluated;

a highlight area detection module, configured to acquire a target area based on the to-be-evaluated image;

The highlight area brightness and sharpness evaluation module, based on the target area, respectively calculates the characteristic data of each target area, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

The step module of outputting the quality evaluation result of the image to be evaluated is used for calculating the quality score of the image to be evaluated related to the characteristic data based on the acquired characteristic data.
A computer device includes a memory, a processor, and a readable storage medium stored in the memory and executable on the processor, and the processor implements the following steps when executing the readable storage medium:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

Based on the target area, the characteristic data of each target area is calculated respectively, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

Based on the acquired feature data, a quality score of the image to be evaluated related to the feature data is calculated.
The computer device according to claim 7, wherein the acquisition of the target area based on the image to be evaluated comprises:

Adopt adaptive threshold segmentation to obtain the binary image corresponding to the image to be evaluated, wherein the image to be evaluated is obtained by using several highly inverse cooperation signs and supplementary lights to enhance the acquisition;

judging whether the cooperation sign can be identified in the binary image;

If the cooperation logo is identified, the circumscribed rectangle of each of the cooperative logos is obtained, and the circumscribed rectangle of each of the cooperative logos is expanded by several pixels to obtain a number of expanded logo circumscribed rectangle areas, so that Each marked circumscribed rectangular area in the image to be evaluated is used as the target area;

If the cooperation sign is not recognized, a rectangular area of N*M pixels in the central area of the image to be evaluated is used as the target area.
The computer device according to claim 8, wherein the rectangular area of the N*M pixel points is a square.
The computer device according to claim 7, wherein based on the target area, the characteristic data of each target area is calculated separately, comprising:

Generate a two-dimensional Gaussian distribution proportional to the height and width of the image to be evaluated, and when located at the center of the image to be evaluated, the two-dimensional Gaussian distribution obtains a maximum value;

Multiply the two-dimensional Gaussian distribution by the scale coefficient lamda to obtain a template showing the brightness distribution of the image to be evaluated;

calculating the average brightness value of several pixels whose brightness value is a preset top ratio on each of the target areas, and using the average brightness value as the first brightness value of the corresponding target area;

Obtain the position coordinates of the center point of each target area, query the brightness value of the corresponding position of each of the position coordinates from the template, and use the brightness value as the second brightness value corresponding to the target area;

Taking the absolute value of the difference between the first brightness value and the second brightness value of each target area as the regional brightness value of the target area;

Calculate the average gradient of luminance values for each target area;

The sharpness value for each of the target regions is calculated based on the average gradient of the luminance values by the following formula:

C=(x*x+y*y)*D;

Wherein, the C is the sharpness value, and the D is the average gradient of the luminance value.
The computer device according to claim 7, wherein, based on the acquired feature data, calculating a quality score of an image to be evaluated related to the feature data, comprising:

Calculate the brightness average value of the regional brightness values of all the target areas;

calculating a sharpness average of sharpness values of all said target regions;

The quality score is obtained by weighting the brightness average value and the sharpness average value by using a preset weight ratio.
One or more computer-readable storage media storing computer-readable instructions that store computer-readable instructions that, when executed by one or more processors, cause the One or more processors perform the following steps:

acquiring an infrared image as the image to be evaluated;

Based on the to-be-evaluated image, obtain a target area;

Based on the target area, the characteristic data of each target area is calculated respectively, and the characteristic data includes the area brightness value of the target area and the sharpness value of the target area;

Based on the acquired feature data, a quality score of the image to be evaluated related to the feature data is calculated.
The computer-readable storage medium of claim 12, wherein the acquiring a target area based on the to-be-evaluated image comprises:

Adopt adaptive threshold segmentation to obtain the binary image corresponding to the image to be evaluated, wherein the image to be evaluated is obtained by using several highly inverse cooperation signs and supplementary lights to enhance the acquisition;

judging whether the cooperation sign can be identified in the binary image;

If the cooperation logo is identified, the circumscribed rectangle of each of the cooperative logos is obtained, and the circumscribed rectangle of each of the cooperative logos is expanded by several pixels to obtain a number of expanded logo circumscribed rectangle areas, so that Each marked circumscribed rectangular area in the image to be evaluated is used as the target area;

If the cooperation sign is not recognized, a rectangular area of N*M pixels in the central area of the image to be evaluated is used as the target area.
The computer-readable storage medium of claim 13, comprising: the rectangular area of the N*M pixel points is a square.
The computer-readable storage medium according to claim 12, wherein the characteristic data of each target area is calculated separately based on the target area, comprising:

Generate a two-dimensional Gaussian distribution proportional to the height and width of the image to be evaluated, and when located at the center of the image to be evaluated, the two-dimensional Gaussian distribution obtains a maximum value;

Multiply the two-dimensional Gaussian distribution by the scale coefficient lamda to obtain a template showing the brightness distribution of the image to be evaluated;

calculating the average brightness value of several pixels whose brightness value is a preset top ratio on each of the target areas, and using the average brightness value as the first brightness value of the corresponding target area;

Obtain the position coordinates of the center point of each target area, query the brightness value of the corresponding position of each of the position coordinates from the template, and use the brightness value as the second brightness value corresponding to the target area;

Taking the absolute value of the difference between the first brightness value and the second brightness value of each target area as the regional brightness value of the target area;

Calculate the average gradient of luminance values for each target area;

The sharpness value for each of the target regions is calculated based on the average gradient of the luminance values by the following formula:

C=(x*x+y*y)*D;

Wherein, the C is the sharpness value, and the D is the average gradient of the luminance value.
The computer-readable storage medium according to claim 12, wherein, based on the acquired feature data, calculating a quality score of an image to be evaluated related to the feature data, comprising:

Calculate the brightness average value of the regional brightness values of all the target areas;

calculating a sharpness average of sharpness values of all said target regions;

The quality score is obtained by weighting the brightness average value and the sharpness average value by using a preset weight ratio.