Monitoring video deblurring method and system
By performing frame image splitting, dark channel image calculation and atmospheric light intensity estimation on the monitoring video, combined with the guide filtered transmission map for image enhancement, the problem of unstable fog removal effect in the existing technology is solved, and the problem of unstable fog removal effect of monitoring video is realized More efficient defuzzing and fog removal effects.
Patent Information
- Application Number
- CN202410928014.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing surveillance video defog removal method has unstable effects when processing blurred images and has poor adaptability to different scenes, making it difficult to effectively improve the contrast and clarity of the video.
By reading the monitoring video and splitting it into frame images, inverting color transformation and dark channel image calculations are performed, regions are divided to estimate atmospheric light intensity, image enhancement is performed in combination with the guide filtered transmission map, and defuzzy video is synthesized.
It improves the deblurring effect of surveillance video, enhances the contrast and clarity of the image, and improves the stability and adaptability of the processing effect.
Smart Images

Figure HDA0004938802150000011 
Figure HDA0004938802150000012 
Figure HDA0004938802150000013
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing, and in particular to a monitoring video deblurring method and system. Background Art
[0002] Surveillance video systems have been widely used in the fields of public security, traffic management, and environmental monitoring. As an important means of obtaining information, surveillance video has the advantages of real-time, continuity, and comprehensiveness. However, in practical applications, due to the influence of weather conditions, such as haze, smoke, etc., surveillance videos are often severely degraded, resulting in blurred images, low contrast, and poor visibility, which affects the effectiveness and reliability of video surveillance. At present, research on video defogging is mainly concentrated in the fields of image processing and computer vision. Traditional defogging methods include histogram equalization, contrast enhancement, and multi-scale Retinex. These methods can improve the contrast and clarity of images to a certain extent, but often have problems such as unstable processing effects and poor adaptability to different scenes. . Summary of the invention
[0003] In order to solve the above problem, the present invention provides a surveillance video deblurring method, the method comprising the following steps:
[0004] Reading a surveillance video and splitting the surveillance video into frame images, performing an inverse color transformation on the frame image to obtain an inverse frame image, respectively calculating dark channel images of the frame image and the inverse frame image, and obtaining a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel image;
[0005] Dividing the dark channel image of the frame image into a plurality of regions, selecting at least one region from the plurality of regions based on the dark channel image of the frame image and a coarse transmittance map of the frame image, and estimating the atmospheric light intensity based on a pixel value of the at least one region in the frame image;
[0006] A refined transmittance map is obtained based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, an enhanced frame image is obtained using the atmospheric light intensity and the refined transmittance map, and the enhanced frame images are synthesized into a surveillance video in the order of the frame images.
[0007] Preferably, the obtaining of the coarse transmittance map of the frame image and the coarse transmittance map of the inverse frame image according to the dark channel image is specifically as follows:
[0008] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image;
[0009] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
[0010] Preferably, the selecting at least one region from the plurality of regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically:
[0011] Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
[0012] Preferably, filtering the selected area based on the average value to obtain at least one area is specifically:
[0013] The selected areas are ranked in ascending order according to the average values, and the first several selected areas are taken as at least one area.
[0014] Preferably, the rough transmittance map of the frame image after the guided filtering and the rough transmittance map of the inverse frame image are used to obtain the refined transmittance map, specifically:
[0015] The rough transmittance map of the frame image and the rough transmittance map of the inverse frame image are compared pixel by pixel, and the one with the largest pixel value at each position is selected as the pixel value of the position in the fine transmittance map.
[0016] In another aspect, the present invention further provides a surveillance video deblurring system, the system comprising the following modules:
[0017] A transmittance calculation module, used to read the surveillance video and split the surveillance video into frame images, perform inverse color transformation on the frame image to obtain an inverse frame image, calculate dark channel images of the frame image and the inverse frame image respectively, and obtain a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel image;
[0018] an atmospheric light intensity calculation module, configured to divide the dark channel image of the frame image into a plurality of regions, select at least one region from the plurality of regions based on the dark channel image of the frame image and a coarse transmittance map of the frame image, and estimate the atmospheric light intensity based on a pixel value of the at least one region in the frame image;
[0019] The video enhancement module is used to obtain a fine transmittance map based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, obtain an enhanced frame image using the atmospheric light intensity and the fine transmittance map, and synthesize the enhanced frame images into a surveillance video in the order of the frame images.
[0020] Preferably, the obtaining of the coarse transmittance map of the frame image and the coarse transmittance map of the inverse frame image according to the dark channel image is specifically as follows:
[0021] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image;
[0022] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
[0023] Preferably, the selecting at least one region from the plurality of regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically:
[0024] Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
[0025] Preferably, filtering the selected area based on the average value to obtain at least one area is specifically:
[0026] The selected areas are ranked in ascending order according to the average values, and the first several selected areas are taken as at least one area.
[0027] Preferably, the rough transmittance map of the frame image after the guided filtering and the rough transmittance map of the inverse frame image are used to obtain the refined transmittance map, specifically:
[0028] The rough transmittance map of the frame image and the rough transmittance map of the inverse frame image are compared pixel by pixel, and the one with the largest pixel value at each position is selected as the pixel value of the position in the fine transmittance map.
[0029] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.
[0030] The transmittance and atmospheric light intensity value are key parameters for image deblurring and defogging. Although many methods have been proposed to calculate the transmittance and atmospheric light intensity values, either the effect is not good or the calculation is complicated. The present invention first estimates the dark channel image and the rough transmittance map of the frame image and the inverse frame image, and then obtains the atmospheric light intensity value based on the dark channel image and the rough transmittance map of the frame image, and uses the rough transmittance map of the frame image and the inverse frame image to obtain the precise transmittance map of the frame image, thereby realizing the calculation of the atmospheric light intensity value and transmittance, and deblurring and defogging the frame image based on the obtained atmospheric light intensity value and the precise transmittance map, thereby effectively improving the deblurring and defogging effects. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 This is a flow chart of Embodiment 1;
[0032] Figure 2 Schematic diagram of the comparison between the original image and the dehazed image;
[0033] Figure 3 This is a structural diagram of the second embodiment. DETAILED DESCRIPTION
[0034] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.
[0035] It should be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.
[0036] It should be noted that, in the embodiments of the present application, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order. Features limited to "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. If the present application uses the user's personal information or usage records during use, a prompt will be issued to the user to collect the user's personal information or usage records with the user's permission. If there is a conflict with laws and regulations during the production and use of the present application, it shall be produced and used within the scope permitted by laws and regulations.
[0037] Based on the implementations in this application, all other implementations obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0038] In the first embodiment, if Figure 1 As shown, the present invention provides a surveillance video deblurring method, the method comprising the following steps:
[0039] S1, reading a surveillance video and splitting the surveillance video into frame images, performing an inverse color transformation on the frame images to obtain inverse frame images, calculating dark channel images of the frame images and the inverse frame images respectively, and obtaining a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel images;
[0040] Read the surveillance video to be processed, split the video content frame by frame in a frame-by-frame manner, and obtain a continuous frame image sequence, where each frame image represents a still picture in the video. Perform an inverse color transformation on each frame image to generate a corresponding inverse frame image. The inverse color transformation is also called image inversion. It is a pixel-level transformation operation, and its principle is to transform the color value of each pixel from the original value to its complementary color, such as transforming the RGB value (R, G, B) to (255-R, 255-G, 255-B), thereby obtaining an inverse frame image. After obtaining the frame image and the inverse frame image, the dark channel image of the frame image and the inverse frame image is further obtained. Since the calculation of the transmittance map requires the knowledge of the dark channel image and the atmospheric light intensity value, in a specific embodiment, the coarse transmittance map of the frame image and the coarse transmittance map of the inverse frame image are obtained according to the dark channel image, specifically:
[0041] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image;
[0042] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
[0043] Compared with calculating the atmospheric light value of each channel and then calculating the rough transmittance map, using the brightness value as the atmospheric light value of each channel can not only reduce the amount of calculation, but also the three channels may be affected by different degrees of noise. Using the brightness value can average these noises to a certain extent, making the calculation of transmittance more stable and reliable.
[0044] S2, dividing the dark channel image of the frame image into multiple regions, selecting at least one region from the multiple regions based on the dark channel image of the frame image and the coarse transmittance map of the frame image, and estimating the atmospheric light intensity based on the pixel value of the at least one region in the frame image;
[0045] Atmospheric light intensity is also called atmospheric light intensity value and atmospheric light value. In the present invention, unless otherwise specified, these names have the same meaning and can be used interchangeably. In order to distinguish the atmospheric light intensity values of different images in each step, different names are used, but their meanings are the same. Atmospheric light intensity directly affects the contrast of the defogging image, and incorrect estimation will cause color distortion and poor defogging effects. In the past, the atmospheric light intensity was calculated by selecting the brightest point, but due to the influence of white noise and water vapor in foggy or rainy days, these points will affect the correct estimation of the atmospheric light intensity. The present invention divides the dark channel image of the frame image into multiple regions, selects at least one region from the multiple regions based on the dark channel image of the frame image and the coarse transmittance map of the frame image, and calculates the atmospheric light intensity from the at least one region.
[0046] In a specific embodiment, the selecting at least one region from the multiple regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically:
[0047] Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
[0048] In one embodiment, filtering the selected area based on the average value to obtain at least one area is specifically:
[0049] The selected areas are ranked in order of the average values from small to large, and the first several selected areas are used as at least one area. After obtaining at least one area, the average value of the pixel values of all at least one area is calculated, and the average value is used as the atmospheric light intensity value.
[0050] S3, obtaining a refined transmittance map based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, obtaining an enhanced frame image using the atmospheric light intensity and the refined transmittance map, and synthesizing the enhanced frame images into a surveillance video in the order of the frame images.
[0051] Guided filtering can enable the resulting image to retain more details. The refined transmittance map is obtained based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image. Specifically, the coarse transmittance map of the frame image and the coarse transmittance map of the inverse frame image are compared pixel by pixel, and the pixel with the largest pixel value at each position is selected as the pixel value of the position in the refined transmittance map. Figure 2 The diagram shows the effect of deblurring the surveillance video according to the present invention.
[0052] In a second embodiment, the present invention also provides a surveillance video deblurring system, such as Figure 3 As shown, the system includes the following modules:
[0053] A transmittance calculation module, used to read the surveillance video and split the surveillance video into frame images, perform inverse color transformation on the frame image to obtain an inverse frame image, calculate dark channel images of the frame image and the inverse frame image respectively, and obtain a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel image;
[0054] an atmospheric light intensity calculation module, configured to divide the dark channel image of the frame image into a plurality of regions, select at least one region from the plurality of regions based on the dark channel image of the frame image and a coarse transmittance map of the frame image, and estimate the atmospheric light intensity based on a pixel value of the at least one region in the frame image;
[0055] The video enhancement module is used to obtain a fine transmittance map based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, obtain an enhanced frame image using the atmospheric light intensity and the fine transmittance map, and synthesize the enhanced frame images into a surveillance video in the order of the frame images.
[0056] Preferably, the obtaining of the coarse transmittance map of the frame image and the coarse transmittance map of the inverse frame image according to the dark channel image is specifically as follows:
[0057] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image;
[0058] Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
[0059] Preferably, the selecting at least one region from the plurality of regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically:
[0060] Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
[0061] Preferably, filtering the selected area based on the average value to obtain at least one area is specifically:
[0062] The selected areas are ranked in ascending order according to the average values, and the first several selected areas are taken as at least one area.
[0063] Preferably, the rough transmittance map of the frame image after the guided filtering and the rough transmittance map of the inverse frame image are used to obtain the refined transmittance map, specifically:
[0064] The rough transmittance map of the frame image and the rough transmittance map of the inverse frame image are compared pixel by pixel, and the one with the largest pixel value at each position is selected as the pixel value of the position in the fine transmittance map.
[0065] In a third embodiment, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first embodiment is implemented.
[0066] It should be noted that a part of the electronic device of the above embodiment can also be implemented by a computer. In this case, a program for implementing the control function can be recorded in a computer-readable recording medium, and the program recorded in the recording medium can be read into a computer system and executed to implement it.
[0067] It should be noted that the "computer system" mentioned here refers to a computer system built into an electronic device, and uses a computer system including hardware such as an OS and peripheral devices. In addition, "computer-readable recording medium" refers to removable media such as floppy disks, magneto-optical disks, ROMs, CD-ROMs, and storage devices such as hard disks built into computer systems.
[0068] Furthermore, "computer-readable recording media" may include: media that dynamically store programs for a short period of time, such as communication lines when sending programs via networks such as the Internet or communication lines such as telephone lines; and media that store programs for a fixed period of time, such as volatile memories inside computer systems that serve as servers or clients in this case. In addition, the above-mentioned program may be a program for realizing a part of the above-mentioned functions, or a program that can realize the above-mentioned functions by combining with a program already recorded in a computer system.
[0069] In addition, the electronic device in the above-mentioned embodiment can also be implemented as a collection (device group) composed of multiple devices. Each device constituting the device group can have a part or all of the functions or functional blocks of the electronic device in the above-mentioned embodiment. As a device group, it is sufficient to have all the functions or functional blocks of the electronic device.
[0070] Those skilled in the art should recognize that the above embodiments are only used to illustrate the present application and are not intended to be limiting of the present application. As long as they are within the spirit and scope of the present application, appropriate changes and modifications to the above embodiments are within the scope of protection claimed in the present application.
Claims
1. A surveillance video deblurring method, characterized in that: The method comprises the following steps: Reading a surveillance video and splitting the surveillance video into frame images, performing an inverse color transformation on the frame image to obtain an inverse frame image, respectively calculating dark channel images of the frame image and the inverse frame image, and obtaining a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel image; Dividing the dark channel image of the frame image into a plurality of regions, selecting at least one region from the plurality of regions based on the dark channel image of the frame image and a coarse transmittance map of the frame image, and estimating the atmospheric light intensity based on a pixel value of the at least one region in the frame image; A refined transmittance map is obtained based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, an enhanced frame image is obtained using the atmospheric light intensity and the refined transmittance map, and the enhanced frame images are synthesized into a surveillance video in the order of the frame images.
2. The method according to claim 1, characterized in that The step of obtaining the rough transmittance map of the frame image and the rough transmittance map of the inverse frame image according to the dark channel image is specifically as follows: Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image; Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
3. The method according to claim 1, characterized in that The selecting at least one region from the plurality of regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically: Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
4. The method according to claim 3, characterized in that The filtering of the selected area based on the average value to obtain at least one area is specifically: The selected areas are ranked in ascending order according to the average values, and the first several selected areas are taken as at least one area.
5. The method according to claim 1, characterized in that The rough transmittance map of the frame image after the guided filtering and the rough transmittance map of the inverse frame image are used to obtain the refined transmittance map, specifically: The rough transmittance map of the frame image and the rough transmittance map of the inverse frame image are compared pixel by pixel, and the one with the largest pixel value at each position is selected as the pixel value of the position in the fine transmittance map.
6. A surveillance video deblurring system, characterized in that: The system includes the following modules: A transmittance calculation module, used to read the surveillance video and split the surveillance video into frame images, perform inverse color transformation on the frame image to obtain an inverse frame image, calculate dark channel images of the frame image and the inverse frame image respectively, and obtain a coarse transmittance map of the frame image and a coarse transmittance map of the inverse frame image according to the dark channel image; an atmospheric light intensity calculation module, configured to divide the dark channel image of the frame image into a plurality of regions, select at least one region from the plurality of regions based on the dark channel image of the frame image and a coarse transmittance map of the frame image, and estimate the atmospheric light intensity based on a pixel value of the at least one region in the frame image; The video enhancement module is used to obtain a fine transmittance map based on the coarse transmittance map of the frame image after guided filtering and the coarse transmittance map of the inverse frame image, obtain an enhanced frame image using the atmospheric light intensity and the fine transmittance map, and synthesize the enhanced frame images into a surveillance video in the order of the frame images.
7. The system according to claim 6, characterized in that The step of obtaining the rough transmittance map of the frame image and the rough transmittance map of the inverse frame image according to the dark channel image is specifically as follows: Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the frame image in the frame image, calculate the brightness value of the position in the frame image, take the average value of the brightness value as the atmospheric light value of the frame image, and calculate and obtain a rough transmittance map of the frame image according to the atmospheric light value of the frame image and the dark channel image; Determine the position of the pixel with the highest brightness in the first one thousandth of the dark channel image of the inverse frame image in the inverse frame image, calculate the brightness value of the position in the inverse frame image, take the average value of the brightness value as the atmospheric light value of the inverse frame image, and obtain a rough transmittance map of the inverse frame image based on the atmospheric light value of the inverse frame image and the dark channel image.
8. The system according to claim 6, characterized in that The selecting at least one region from the plurality of regions based on the dark channel image of the frame image and the rough transmittance map of the frame image is specifically: Calculate the average value of the pixel value of each area of the dark channel image of the frame image, sort the areas in descending order according to the average value, select multiple areas starting from the first one in the sorting, determine the position of the selected area in the rough transmittance map of the frame image according to the position of the selected area in the dark channel image of the frame image, calculate the average value of the pixel value of the selected area in the rough transmittance map of the frame image, and filter the selected area based on the average value to obtain at least one area.
9. The method according to claim 8, characterized in that The filtering of the selected area based on the average value to obtain at least one area is specifically: The selected areas are ranked in ascending order according to the average values, and the first several selected areas are taken as at least one area.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 5.
