A remote sensing image defogging correction method and system

Abstract

The present invention is applicable to the technical field of remote sensing image processing, and provides a remote sensing image defogging and correction method and system. The present invention receives a foggy remote sensing image, performs image defogging processing, and generates a defogging remote sensing image; performs target recognition, determines multiple remote sensing targets, and performs region division in the defogging remote sensing image to obtain multiple target fog-free areas and multiple target defogging areas; performs image correction on the multiple target defogging areas according to the multiple target fog-free areas, and generates a corrected remote sensing image. After performing image defogging processing on the foggy remote sensing image, target recognition and region division are performed, and image correction is performed on the multiple target defogging areas according to the multiple target fog-free areas, so as to achieve correction and restoration of the remote sensing image after defogging, and solves the technical defects of loss of image details, color distortion, blurring, or even complete erasure after defogging, facilitates the subsequent recognition and use of remote sensing images, and enhances the use value of foggy remote sensing images.

Description

Technical Field

[0001] The present invention belongs to the technical field of remote sensing image processing, and in particular relates to a remote sensing image defogging correction method and system. Background Art

[0002] Remote sensing is a long-distance, non-contact detection technology that uses sensors on aviation or aerospace platforms to receive electromagnetic wave information reflected or radiated by ground objects and record it to form remote sensing images.

[0003] Remote sensing image processing is a process of processing, analyzing and processing image data obtained through various remote sensing technologies to improve image quality, enhance target features and extract useful information.

[0004] Dehazing remote sensing images is the most common process. Existing technologies typically employ simple dehazing techniques, often based on basic image enhancement algorithms or filtering techniques. These techniques mechanically adjust basic parameters like image contrast and brightness. This can easily lead to loss of detail, color distortion, blurring, or even complete erasure of dehazed images, severely impacting subsequent recognition and use of remote sensing images. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a remote sensing image defogging correction method and system, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0006] The embodiment of the present invention is implemented as follows:

[0007] A remote sensing image defogging correction method, the method specifically comprising the following steps:

[0008] Receive foggy remote sensing images, perform image defogging processing, and generate defogging remote sensing images;

[0009] Performing target recognition on the defogging remote sensing image to determine a plurality of remote sensing targets, and performing region division on the defogging remote sensing image to obtain a plurality of target fog-free regions and a plurality of target defogging regions;

[0010] According to the multiple target fog-free areas, image correction is performed on the multiple target defogging areas to generate a corrected remote sensing image.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of the foggy remote sensing image, performing image defogging processing, and generating the defogged remote sensing image specifically include the following steps:

[0012] Receive foggy remote sensing images and multiple batches of remote sensing images;

[0013] performing region recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and intercepting a sky region image;

[0014] Identifying the sky area image and calculating the atmospheric light value;

[0015] The defogging calculation process is performed on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula for the defogging calculation process is:

[0017] ;

[0018] in, represents the dehazed remote sensing image, represents a foggy remote sensing image, represents the image pixel position, is the atmospheric light value, Corresponding to RGB channels, is the preset weight coefficient, Atmospheric light in the channel valuation, is the image pixel position of the foggy remote sensing image In the channel The pixel value of is the preset standard atmospheric transmittance.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the performing target recognition on the defogging remote sensing image, determining multiple remote sensing targets, performing region division in the defogging remote sensing image, and obtaining multiple target fog-free areas and multiple target defogging areas specifically include the following steps:

[0020] performing target recognition on the defogging remote sensing image to determine multiple remote sensing targets;

[0021] Acquiring target boundary positions of a plurality of remote sensing targets;

[0022] extracting a plurality of target images of the remote sensing targets from the defogging remote sensing image according to the plurality of target boundary positions;

[0023] Performing defogging recognition on the plurality of target images to determine a plurality of defogging boundary positions;

[0024] According to the multiple defogging boundary positions, the multiple target images are divided into defogging areas to obtain multiple corresponding target fog-free areas and target defogging areas.

[0025] As a further limitation of the technical solution of the embodiment of the present invention, the performing of image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate the corrected remote sensing image specifically includes the following steps:

[0026] Extracting a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image;

[0027] Extracting a plurality of defogging area images of the target defogging area from the defogging remote sensing image;

[0028] Performing correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images;

[0029] The rectified remote sensing image is generated by combining multiple fog-free area images and multiple defogging correction images.

[0030] As a further limitation of the technical solution of the embodiment of the present invention, the step of performing correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images specifically includes the following steps:

[0031] In a plurality of fog-free area images and corresponding defogging area images, distance measurement of correction influence is performed, and influence distance data is recorded;

[0032] Get multiple correction ratios;

[0033] According to the impact distance data and the multiple correction ratios, correction calculation processing is performed on the multiple defogging area images to obtain multiple defogging corrected images.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the correction calculation process is:

[0035] ;

[0036] ;

[0037] in, Representative Remote sensing targets, Representative Dehazing and rectified images of remote sensing targets, Represents the first The position of the image pixel, Representative fog-free area images of remote sensing targets, Represents the first The position of the image pixel, There are a total of image pixels, Represents the first image pixels and the defogging area image The correction effect distance between image pixels, is the preset distance decomposition factor, Representative The defogging area image of a remote sensing target, is the first correction ratio, is the second correction ratio.

[0038] A remote sensing image defogging and correction system, comprising an image defogging processing module, an image region division module, and a defogging image correction module, wherein:

[0039] An image defogging processing module is used to receive foggy remote sensing images, perform image defogging processing, and generate defogging remote sensing images;

[0040] An image region division module is used to perform target recognition on the defogging remote sensing image, determine multiple remote sensing targets, and perform region division on the defogging remote sensing image to obtain multiple target fog-free regions and multiple target defogging regions;

[0041] The defogging image correction module is used to perform image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate a corrected remote sensing image.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the image defogging processing module specifically includes:

[0043] An image receiving unit, configured to receive foggy remote sensing images and multiple batches of remote sensing images;

[0044] A sky area image interception unit is used to perform area recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and intercept a sky area image;

[0045] an atmospheric light value calculation unit, configured to identify the sky area image and calculate the atmospheric light value;

[0046] The defogging calculation processing unit is used to perform defogging calculation processing on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

[0047] As a further limitation of the technical solution of the embodiment of the present invention, the defogging image correction module specifically includes:

[0048] a fog-free area image extraction unit, configured to extract a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image;

[0049] a defogging area image extraction unit, configured to extract a plurality of defogging area images of the target defogging area from the defogging remote sensing image;

[0050] a correction calculation processing unit, configured to perform correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images;

[0051] The rectified remote sensing image generation unit is used to integrate multiple fog-free area images and multiple defogging rectified images to generate a rectified remote sensing image.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The embodiment of the present invention receives a foggy remote sensing image, performs image defogging processing, and generates a defogged remote sensing image; performs target recognition to determine multiple remote sensing targets, and performs regional division in the defogged remote sensing image to obtain multiple target fog-free areas and multiple target defogged areas; and performs image correction on the multiple target defogged areas according to the multiple target fog-free areas to generate a corrected remote sensing image. After performing image defogging processing on the foggy remote sensing image, target recognition and regional division are performed, and image correction is performed on the multiple target defogged areas according to the multiple target fog-free areas, thereby achieving correction and restoration of the remote sensing image after defogging. This solves the technical defects of loss of image details, color distortion, blurring, or even complete erasure after defogging, facilitates the subsequent recognition and use of remote sensing images, and enhances the use value of foggy remote sensing images. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A flowchart of a remote sensing image defogging correction method provided by an embodiment of the present invention is shown;

[0055] Figure 2 A flowchart of image defogging processing in the method provided by an embodiment of the present invention is shown;

[0056] Figure 3 The flowchart of the defogging remote sensing image region division method provided by the embodiment of the present invention is shown;

[0057] Figure 4 A flow chart of generating a rectified remote sensing image in a method provided by an embodiment of the present invention is shown;

[0058] Figure 5 A flowchart of the correction calculation process in the method provided by the embodiment of the present invention is shown;

[0059] Figure 6 The following is an application architecture diagram of a remote sensing image defogging and correction system provided by an embodiment of the present invention;

[0060] Figure 7The following is a structural block diagram of an image defogging processing module in a system provided by an embodiment of the present invention;

[0061] Figure 8 The structural block diagram of the defogging image correction module in the system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] Understandably, dehazing remote sensing images is the most common process. Existing technologies for dehazing remote sensing images are typically simple, relying on basic image enhancement algorithms or filtering techniques that mechanically adjust basic parameters like image contrast and brightness. This can easily lead to loss of image detail, color distortion, blurring, or even complete erasure of dehazed images, severely impacting subsequent recognition and use of remote sensing images.

[0064] To solve the above problems, the embodiments of the present invention disclose a remote sensing image defogging and correction method and system, which receives a foggy remote sensing image, performs image defogging processing, and generates a defogged remote sensing image; performs target recognition on the defogged remote sensing image, determines multiple remote sensing targets, and performs region division in the defogged remote sensing image to obtain multiple target fog-free areas and multiple target defogged areas; performs image correction on the multiple target defogged areas according to the multiple target fog-free areas to generate a corrected remote sensing image. After performing image defogging processing on the foggy remote sensing image, target recognition and region division are performed, and image correction is performed on the multiple target defogged areas according to the multiple target fog-free areas, thereby achieving correction and restoration of the remote sensing image after defogging, solving the technical defects of loss of image details, color distortion, blurring, or even complete erasure after defogging, facilitating the subsequent recognition and use of remote sensing images, and enhancing the use value of foggy remote sensing images.

[0065] Specifically, Figure 1 The flowchart of the remote sensing image defogging correction method provided by an embodiment of the present invention is shown.

[0066] In a preferred embodiment of the present invention, a remote sensing image defogging correction method comprises the following steps:

[0067] Step S101: Receive a foggy remote sensing image, perform image defogging processing, and generate a defogged remote sensing image.

[0068] In an embodiment of the present invention, during a remote sensing detection process, a foggy remote sensing image transmitted by detection is received, and multiple batches of remote sensing images transmitted in the same batch cycle are received. Region recognition is performed on the foggy remote sensing image and the multiple batches of remote sensing images, and an image capturing the sky is selected from the image. An image of the sky region is captured from the image to obtain a sky region image. The sky region image is then recognized, and an atmospheric light value is calculated. Based on the atmospheric light value, defogging calculation processing is performed on the foggy remote sensing image to generate a defogging remote sensing image. Specifically, the calculation formula for the defogging calculation processing is:

[0069] ;

[0070] in, represents the dehazed remote sensing image, represents foggy remote sensing images, represents the image pixel position, is the atmospheric light value, Corresponding to RGB channels, is the preset weight coefficient, Atmospheric light in the channel valuation, is the image pixel position of the foggy remote sensing image In the channel The pixel value of is the preset standard atmospheric transmittance.

[0071] It can be understood that when there is a sky area in the foggy remote sensing image, the sky area image is directly intercepted from the foggy remote sensing image; when there is no sky area in the foggy remote sensing image, an image with a sky area is selected from multiple batches of remote sensing images, and then the sky area image is intercepted from it.

[0072] Specifically, Figure 2 A flowchart of image defogging processing in the method provided by an embodiment of the present invention is shown.

[0073] In another preferred embodiment of the present invention, the receiving of a foggy remote sensing image, performing image defogging processing, and generating a defogged remote sensing image specifically include the following steps:

[0074] Step S1011: receiving a foggy remote sensing image and multiple batches of remote sensing images.

[0075] Step S1012: performing region recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and capturing a sky region image.

[0076] Step S1013: Identify the sky area image and calculate the atmospheric light value.

[0077] Step S1014: performing defogging calculation processing on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

[0078] Furthermore, the remote sensing image defogging correction method further includes the following steps:

[0079] Step S102: performing target recognition on the defogging remote sensing image to determine a plurality of remote sensing targets, performing region division in the defogging remote sensing image to obtain a plurality of target fog-free regions and a plurality of target defogging regions.

[0080] In an embodiment of the present invention, target recognition is performed on the defogged remote sensing image according to multiple preset target features to determine multiple remote sensing targets, and then the target boundary positions of the multiple remote sensing targets are determined from the defogged remote sensing image. Then, based on the multiple target boundary positions, image capture is performed in the defogged remote sensing image to obtain target images corresponding to the multiple remote sensing targets. Defogging recognition is performed on the multiple target images to determine multiple defogging boundary positions. Then, based on the multiple defogging boundary positions, fog-free and defogging area division processing is performed on the multiple target images to obtain multiple corresponding target fog-free areas and target defogging areas.

[0081] It is understandable that remote sensing targets can be soil, crops, forests, marine oil pollution, infrastructure, buildings, etc., which are related to the specific mission requirements of remote sensing detection.

[0082] It can be understood that if a target image has not been defogged, then after the target image is divided into regions, only the target fog-free region is obtained; if all pixels of a target image have been defogged, then after the target image is divided into regions, only the target defogged region is obtained.

[0083] Specifically, Figure 3 A flowchart of defogging remote sensing image region division in the method provided by an embodiment of the present invention is shown.

[0084] Among them, in another preferred embodiment provided by the present invention, the performing target recognition on the defogging remote sensing image, determining multiple remote sensing targets, performing region division in the defogging remote sensing image, and obtaining multiple target fog-free areas and multiple target defogging areas specifically include the following steps:

[0085] Step S1021: performing target recognition on the defogging remote sensing image to determine multiple remote sensing targets.

[0086] Step S1022: Acquire target boundary positions of a plurality of remote sensing targets.

[0087] Step S1023 : extracting a plurality of target images of the remote sensing targets from the defogging remote sensing image according to the plurality of target boundary positions.

[0088] Step S1024: performing defogging recognition on the plurality of target images to determine a plurality of defogging boundary positions.

[0089] Step S1025 : dividing the plurality of target images into defogging regions according to the plurality of defogging boundary positions to obtain a plurality of corresponding target non-fog regions and target defogging regions.

[0090] Furthermore, the remote sensing image defogging correction method further includes the following steps:

[0091] Step S103 : performing image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate a corrected remote sensing image.

[0092] In an embodiment of the present invention, multiple fog-free area images of target fog-free areas are extracted from the defogging remote sensing image, and multiple defogging area images of target defogging areas are extracted. In the fog-free area image and the defogging area image corresponding to each remote sensing target, the distance measurement of the correction influence is performed to obtain the correction influence distance, and the multiple correction influence distances are statistically recorded to generate influence distance data, and the preset first correction ratio and second correction ratio are imported. Then, according to the influence distance data, the first correction ratio and the second correction ratio, the multiple defogging area images are corrected. According to the corresponding fog-free area image, the defogging area image is corrected and calculated to obtain multiple corresponding defogging corrected images. Then, the multiple fog-free area images and the multiple defogging corrected images are inserted at corresponding positions to generate a corrected remote sensing image. Specifically, the calculation formula for the correction calculation is:

[0093] ;

[0094] ;

[0095] in, Representative Remote sensing targets, Representative Dehazing and rectified images of remote sensing targets, Represents the first The position of the image pixel, Representative fog-free area images of remote sensing targets, Represents the first The position of the image pixel, There are a total of image pixels, Represents the first image pixels and the defogging area image The correction effect distance between image pixels, is the preset distance decomposition factor, Representative The defogging area image of a remote sensing target, is the first correction ratio, is the second correction ratio.

[0096] It is understandable that if a remote sensing target only has an image of a fog-free area or an image of a defogged area, no correction calculation processing is required.

[0097] It can be understood that through correction calculation processing, the grayscale and / or RGB channels of the defogging area image can be corrected and optimized according to the grayscale and / or RGB channels of the fog-free area image and the defogging area image itself, and the corresponding defogging corrected image can be generated, which can avoid problems such as loss of image details, color distortion, blurring or even complete erasure after defogging.

[0098] Specifically, Figure 4 A flow chart of generating a rectified remote sensing image in a method provided by an embodiment of the present invention is shown.

[0099] In another preferred embodiment of the present invention, performing image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate the corrected remote sensing image specifically includes the following steps:

[0100] Step S1031 : extracting a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image.

[0101] Step S1032: extracting a plurality of defogging area images of the target defogging area from the defogging remote sensing image.

[0102] Step S1033: performing correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images.

[0103] Specifically, Figure 5 A flowchart of the correction calculation process in the method provided by the embodiment of the present invention is shown.

[0104] In another preferred embodiment of the present invention, the correction calculation processing of the plurality of corresponding defogging area images using the plurality of fog-free area images to obtain the plurality of defogging corrected images specifically includes the following steps:

[0105] Step S10331: perform distance measurement for correction effects on multiple fog-free area images and corresponding defogging area images, and record the affected distance data.

[0106] Step S10332: Obtain multiple correction ratios.

[0107] Step S10333: performing correction calculation processing on the multiple defogging area images according to the impact distance data and the multiple correction ratios to obtain multiple defogging corrected images.

[0108] Furthermore, performing image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate a corrected remote sensing image further includes the following steps:

[0109] Step S1034: Combine the multiple fog-free area images and the multiple defogging correction images to generate a corrected remote sensing image.

[0110] Further, Figure 6 The application architecture diagram of the remote sensing image defogging and correction system provided by an embodiment of the present invention is shown.

[0111] Specifically, in another preferred embodiment provided by the present invention, a remote sensing image defogging correction system includes:

[0112] The image defogging processing module 101 is used to receive a foggy remote sensing image, perform image defogging processing on the image, and generate a defogging remote sensing image.

[0113] In an embodiment of the present invention, during the remote sensing detection process, the image defogging processing module 101 receives the foggy remote sensing image transmitted by the detection, and receives multiple batches of remote sensing images transmitted under the same batch cycle. By performing region recognition on the foggy remote sensing image and the multiple batches of remote sensing images, an image with the sky is selected from them, and an image of the sky area is captured from the image to obtain a sky area image. The sky area image is then recognized, and the atmospheric light value is calculated. Then, based on the atmospheric light value, the foggy remote sensing image is defogged and processed to generate a defogged remote sensing image. Specifically, the calculation formula for the defogging calculation process is:

[0114] ;

[0115] in, represents the dehazed remote sensing image, represents a foggy remote sensing image, represents the image pixel position, is the atmospheric light value, Corresponding to RGB channels, is the preset weight coefficient, Atmospheric light in the channel valuation, is the image pixel position of the foggy remote sensing image In the channel The pixel value of Preset standard atmospheric transmittance.

[0116] Specifically, Figure 7 FIG. 1 shows a structural block diagram of the image defogging processing module 101 in the system provided by an embodiment of the present invention.

[0117] In another preferred embodiment of the present invention, the image defogging processing module 101 specifically includes:

[0118] The image receiving unit 1011 is configured to receive foggy remote sensing images and multiple batches of remote sensing images.

[0119] The sky area image interception unit 1012 is configured to perform area recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and intercept a sky area image.

[0120] The atmospheric light value calculation unit 1013 is used to identify the sky area image and calculate the atmospheric light value.

[0121] The defogging calculation processing unit 1014 is configured to perform defogging calculation processing on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

[0122] Furthermore, the remote sensing image defogging correction system further includes:

[0123] The image region division module 102 is configured to perform target recognition on the defogging remote sensing image, determine multiple remote sensing targets, and perform region division in the defogging remote sensing image to obtain multiple target fog-free regions and multiple target defogging regions.

[0124] In an embodiment of the present invention, the image area division module 102 performs target recognition on the defogged remote sensing image according to multiple preset target features to determine multiple remote sensing targets, and then determines the target boundary positions of the multiple remote sensing targets from the defogged remote sensing image. Then, based on the multiple target boundary positions, image capture is performed in the defogged remote sensing image to obtain target images corresponding to the multiple remote sensing targets. By performing defogging recognition on the multiple target images, multiple defogging boundary positions are determined, and then, based on the multiple defogging boundary positions, the multiple target images are divided into fog-free and defogging areas to obtain multiple corresponding target fog-free areas and target defogging areas.

[0125] The defogging image correction module 103 is configured to perform image correction on the multiple target defogging areas according to the multiple target non-fog areas to generate a corrected remote sensing image.

[0126] In an embodiment of the present invention, the defogging image correction module 103 extracts fog-free area images of multiple target fog-free areas from the defogging remote sensing image, and extracts defogging area images of multiple target defogging areas, performs correction influence distance measurement in the fog-free area image and the defogging area image corresponding to each remote sensing target, obtains the correction influence distance, and statistically records the multiple correction influence distances to generate influence distance data, and imports the preset first correction ratio and second correction ratio, and then corrects the multiple defogging area images according to the influence distance data, the first correction ratio and the second correction ratio, and performs correction calculation processing on the defogging area images according to the corresponding fog-free area images to obtain multiple corresponding defogging corrected images, and then inserts the multiple fog-free area images and the multiple defogging corrected images at corresponding positions to generate a corrected remote sensing image. Specifically, the calculation formula for the correction calculation processing is:

[0127] ;

[0128] ;

[0129] in, Representative Remote sensing targets, Representative Dehazing and rectified images of remote sensing targets, Represents the first The position of the image pixel, Representative fog-free area images of remote sensing targets, Represents the first The position of the image pixel, There are a total of image pixels, Represents the first image pixels and the defogging area image The correction effect distance between image pixels, is the preset distance decomposition factor, Representative The defogging area image of a remote sensing target, is the first correction ratio, is the second correction ratio.

[0130] Specifically, Figure 8 The structure block diagram of the defogging image correction module 103 in the system provided by an embodiment of the present invention is shown.

[0131] In another preferred embodiment of the present invention, the defogging image correction module 103 specifically includes:

[0132] The fog-free area image extraction unit 1031 is configured to extract a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image.

[0133] The defogging area image extraction unit 1032 is configured to extract a plurality of defogging area images of the target defogging area from the defogging remote sensing image.

[0134] The correction calculation processing unit 1033 is configured to perform correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images.

[0135] The rectified remote sensing image generation unit 1034 is used to combine multiple fog-free area images and multiple defogging rectified images to generate a rectified remote sensing image.

[0136] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0137] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile 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 link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0138] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A remote sensing image defogging correction method, characterized in that: The method specifically comprises the following steps: Receive foggy remote sensing images, perform image defogging processing, and generate defogging remote sensing images; Performing target recognition on the defogging remote sensing image to determine a plurality of remote sensing targets, and performing region division on the defogging remote sensing image to obtain a plurality of target fog-free regions and a plurality of target defogging regions; According to the multiple target fog-free areas, image correction is performed on the multiple target defogging areas to generate a corrected remote sensing image.

2. The remote sensing image defogging correction method according to claim 1, characterized in that: The receiving of the foggy remote sensing image, performing image defogging processing, and generating the defogging remote sensing image specifically comprises the following steps: Receive foggy remote sensing images and multiple batches of remote sensing images; performing region recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and intercepting a sky region image; Identifying the sky area image and calculating the atmospheric light value; The defogging calculation process is performed on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

3. The remote sensing image defogging correction method according to claim 2, characterized in that: The calculation formula for the defogging calculation process is: ； in, represents the dehazed remote sensing image, represents foggy remote sensing images, represents the image pixel position, is the atmospheric light value, Corresponding to RGB channels, is the preset weight coefficient, Atmospheric light in the channel valuation, is the image pixel position of the foggy remote sensing image In the channel The pixel value of is the preset standard atmospheric transmittance.

4. The remote sensing image defogging correction method according to claim 1, characterized in that: The performing target recognition on the defogging remote sensing image, determining multiple remote sensing targets, and performing region division on the defogging remote sensing image to obtain multiple target fog-free areas and multiple target defogging areas specifically comprises the following steps: performing target recognition on the defogging remote sensing image to determine multiple remote sensing targets; Acquiring target boundary positions of a plurality of remote sensing targets; extracting a plurality of target images of the remote sensing targets from the defogging remote sensing image according to the plurality of target boundary positions; Performing defogging recognition on the plurality of target images to determine a plurality of defogging boundary positions; According to the multiple defogging boundary positions, the multiple target images are divided into defogging areas to obtain multiple corresponding target fog-free areas and target defogging areas.

5. The remote sensing image defogging correction method according to claim 1, characterized in that: The step of performing image correction on the plurality of target defogging areas according to the plurality of target fog-free areas to generate a corrected remote sensing image specifically comprises the following steps: Extracting a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image; Extracting a plurality of defogging area images of the target defogging area from the defogging remote sensing image; Performing correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images; The rectified remote sensing image is generated by combining multiple fog-free area images and multiple defogging correction images.

6. The remote sensing image defogging correction method according to claim 5, characterized in that: The step of performing correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images specifically comprises the following steps: In a plurality of fog-free area images and corresponding defogging area images, distance measurement of correction influence is performed, and influence distance data is recorded; Get multiple correction ratios; According to the impact distance data and the multiple correction ratios, correction calculation processing is performed on the multiple defogging area images to obtain multiple defogging corrected images.

7. The remote sensing image defogging correction method according to claim 6, characterized in that: The calculation formula for the correction calculation process is: ； ； in, Representative Remote sensing targets, Representative Dehazing and rectified images of remote sensing targets, Represents the first The position of the image pixel, Representative fog-free area images of remote sensing targets, Represents the first The position of the image pixel, There are a total of image pixels, Represents the first image pixels and the defogging area image The correction effect distance between image pixels, is the preset distance decomposition factor, Representative The defogging area image of a remote sensing target, is the first correction ratio, is the second correction ratio.

8. A remote sensing image defogging correction system, characterized in that: The system includes an image defogging processing module, an image region division module, and a defogging image correction module, wherein: An image defogging processing module is used to receive foggy remote sensing images, perform image defogging processing, and generate defogging remote sensing images; An image region division module is used to perform target recognition on the defogging remote sensing image, determine multiple remote sensing targets, and perform region division on the defogging remote sensing image to obtain multiple target fog-free regions and multiple target defogging regions; The defogging image correction module is used to perform image correction on the multiple target defogging areas according to the multiple target fog-free areas to generate a corrected remote sensing image.

9. The remote sensing image defogging correction system according to claim 8, characterized in that: The image defogging processing module specifically includes: An image receiving unit, configured to receive foggy remote sensing images and multiple batches of remote sensing images; A sky area image interception unit is used to perform area recognition on the foggy remote sensing image and the plurality of batches of remote sensing images, and intercept a sky area image; an atmospheric light value calculation unit, configured to identify the sky area image and calculate the atmospheric light value; The defogging calculation processing unit is used to perform defogging calculation processing on the foggy remote sensing image according to the atmospheric light value to generate a defogging remote sensing image.

10. The remote sensing image defogging correction system according to claim 8, characterized in that: The defogging image correction module specifically includes: a fog-free area image extraction unit, configured to extract a plurality of fog-free area images of the target fog-free area from the defogging remote sensing image; a defogging area image extraction unit, configured to extract a plurality of defogging area images of the target defogging area from the defogging remote sensing image; a correction calculation processing unit, configured to perform correction calculation processing on a plurality of corresponding defogging area images using the plurality of fog-free area images to obtain a plurality of defogging corrected images; The rectified remote sensing image generation unit is used to integrate multiple fog-free area images and multiple defogging rectified images to generate a rectified remote sensing image.

Images