Radiation correction method and system for remote sensing image

Abstract

The invention discloses a radiation correction method and system for a remote sensing image, and relates to the technical field of remote sensing image processing. The radiation correction method for the remote sensing image comprises the steps that a dark channel image of a target remote sensing image is acquired, the dark channel image is an image formed by minimum channel pixel values of all pixel points in the target remote sensing image, and the minimum channel pixel values are minimum values of channel pixel values of the pixel points in all color channels; according to the dark channel image, atmospheric transmissivity and reflectivity evaluation values of all image areas in the target remote sensing image are determined, and the reflectivity evaluation values are used for representing the intensity of object reflectivity in the image areas; determining a target dark pixel of the target remote sensing image according to the atmospheric transmissivity and reflectivity evaluation value of each image area in the target remote sensing image; and based on the target dark pixel, performing radiation correction on the target remote sensing image to obtain a corrected remote sensing image. According to the invention, effective radiation correction can be carried out on the target remote sensing image, and the radiation correction effect is improved.

Description

Technical Field

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

[0002] With the development of science and technology, the acquisition and application of remote sensing images have become more and more extensive, covering many fields such as environmental monitoring, urban planning and agricultural management. When acquiring remote sensing images, it is usually necessary to perform radiation correction on them, and an important part of radiation correction is atmospheric correction.

[0003] Among various atmospheric correction methods, the dark pixel method is more suitable for atmospheric correction of remote sensing images in scenes with complex atmospheric conditions or lack of meteorological information because it is simple and easy to use and does not require complex meteorological data. In the existing dark pixel method, when performing atmospheric calibration on remote sensing images, the minimum band value in the remote sensing image data or the value entered by the user is generally selected as the dark pixel.

[0004] However, the dark pixels selected in the above method have poor accuracy, which results in the inability to perform effective radiation correction and poor radiation correction effect. Summary of the invention

[0005] The embodiment of the present invention provides a radiation correction method and system for remote sensing images, which can effectively perform radiation correction on target remote sensing images and improve the effect of radiation correction.

[0006] According to a first aspect of an embodiment of the present invention, a radiation correction method for remote sensing images is provided, comprising: Obtain a dark channel image of the target remote sensing image. The dark channel image is an image composed of the minimum channel pixel value of each pixel point in the target remote sensing image. The minimum channel pixel value is the minimum value of the channel pixel value of each color channel. According to the dark channel image, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image are determined. The reflectance evaluation value is used to characterize the strength of the reflectance of the object in the image area. Determine the target dark pixel of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image; Based on the target dark pixels, the target remote sensing image is radiometrically corrected to obtain a corrected remote sensing image.

[0007] A second aspect of an embodiment of the present invention provides a radiation correction system for remote sensing images, comprising: An image acquisition module is used to acquire a dark channel image of a target remote sensing image. The dark channel image is an image composed of the minimum channel pixel value of each pixel point in the target remote sensing image. The minimum channel pixel value is the minimum value of the channel pixel value of each color channel. An image calculation module is used to determine the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image based on the dark channel image. The reflectance evaluation value is used to characterize the intensity of the reflectance of the object in the image area. A dark pixel determination module is used to determine the target dark pixels of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image; The radiation correction module is used to perform radiation correction on the target remote sensing image based on the target dark pixels to obtain a corrected remote sensing image.

[0008] In the radiation correction method for remote sensing images provided by an embodiment of the present invention, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image are determined based on the dark channel image of the target remote sensing image. Then, the target dark pixel of the target remote sensing image is determined based on the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image. Finally, based on the target dark pixel, the target remote sensing image is subjected to radiation correction to obtain a corrected remote sensing image. In this way, the present invention performs a comprehensive evaluation based on the reflectance of the object in the target remote sensing image and the transmittance of the atmosphere, so that the target dark pixel of the target remote sensing image can be accurately determined. In addition, the target remote sensing image can be effectively radiation corrected to improve the effect of radiation correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0010] Figure 1 A schematic flow chart of a first radiation correction method for remote sensing images provided by an embodiment of the present invention; Figure 2 A schematic flow chart of a second method for radiometric correction of remote sensing images provided by an embodiment of the present invention; Figure 3 A schematic flow chart of a third method for radiometric correction of remote sensing images provided by an embodiment of the present invention; Figure 4 A schematic flow chart of a fourth method for radiometric correction of remote sensing images provided by an embodiment of the present invention; Figure 5 A schematic structural diagram of a radiation correction system for remote sensing images provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a radiation correction method and system for remote sensing images proposed according to the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0012] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0013] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0014] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0015] Among the existing atmospheric correction methods, the dark pixel method is more suitable for atmospheric correction of remote sensing images in scenes with complex atmospheric conditions or lack of meteorological information because it is simple and easy to use and does not require complex meteorological data. In the existing dark pixel method, when performing atmospheric calibration on remote sensing images, the minimum value of the band in the remote sensing image data or the value entered by the user is generally selected as the dark pixel. However, the accuracy of the dark pixels selected in this method is poor, resulting in the inability to perform effective radiation correction, and the effect of radiation correction is poor.

[0016] The object of the present invention is to provide a radiation correction method and system for remote sensing images. In the radiation correction method for remote sensing images provided by the embodiment of the present invention, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image are determined according to the dark channel image of the target remote sensing image. Then, the target dark pixel of the target remote sensing image is determined according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image. Finally, based on the target dark pixel, the target remote sensing image is subjected to radiation correction to obtain a corrected remote sensing image. In this way, the present invention performs a comprehensive evaluation based on the reflectance of the object in the target remote sensing image and the transmittance of the atmosphere, so as to accurately determine the target dark pixel of the target remote sensing image. In addition, the target remote sensing image can be effectively radiation corrected to improve the effect of radiation correction.

[0017] The following describes a specific embodiment of a radiation correction method and system for remote sensing images provided by an embodiment of the present invention.

[0018] Figure 1 A flow chart of a radiation correction method for remote sensing images is provided. The radiation correction method for remote sensing images can be applied to a server. The radiation correction method for remote sensing images can include the following steps S101 to S104.

[0019] S101, obtaining a dark channel image of a target remote sensing image, wherein the dark channel image is an image formed by the minimum channel pixel value of each pixel point in the target remote sensing image, and the minimum channel pixel value is the minimum value of the channel pixel values ​​of each color channel.

[0020] In this embodiment, the target remote sensing image is usually a multi-band image, such as an image constructed using satellite data such as Landsat or Sentinel-2.

[0021] A dark channel image (DCI) is an image constructed based on the target assumption that in most areas, at least one color channel at each pixel position has a very low value (close to 0), which is usually caused by atmospheric scattering.

[0022] The channel pixel value is used to represent the pixel value corresponding to each color channel of the pixel point of the target remote sensing image. For example, the channel pixel value of the pixel point may include the red channel pixel value , green channel pixel value And the blue channel pixel value .

[0023] As an example, the server first reads the target remote sensing image from the database. Then, for each pixel point in the target remote sensing image, the minimum value is found in the channel pixel values ​​of all corresponding color channels, and the minimum pixel value is used as the pixel value of the dark channel image at the corresponding pixel point position, thereby obtaining the dark channel image corresponding to the target remote sensing image.

[0024] S102, determining the atmospheric transmittance and reflectance evaluation values ​​of each image region in the target remote sensing image according to the dark channel image, wherein the reflectance evaluation value is used to characterize the reflectance strength of the object in the image region.

[0025] In this embodiment, the target remote sensing image includes multiple image regions. For example, after obtaining the target remote sensing image, the server can traverse the target remote sensing image based on a sliding window of a preset size, thereby dividing the target remote sensing image into multiple image regions.

[0026] When an object's radiation penetrates the atmosphere, it will be affected by three factors, including atmospheric transmittance, atmospheric absorptivity, and object reflectivity. The higher the atmospheric transmittance, the lower the atmospheric absorptivity, and the higher the object reflectivity, the more accurate the radiation collected from the object will be.

[0027] Atmospheric transmittance and atmospheric absorptivity are two related parameters, so only one of them needs to be determined. Among them, atmospheric transmittance is a parameter that describes the attenuation of radiation intensity after passing through the atmosphere, which is defined as the ratio of the radiation intensity after passing through the atmosphere to the radiation intensity before incident; atmospheric absorptivity is a parameter that describes the attenuation of radiation intensity caused by the absorption of atmospheric components when radiation passes through the atmosphere, which is defined as the ratio of the absorption attenuation of radiation after passing through a certain air layer with only atmospheric absorption to the radiation before incident.

[0028] Object reflectivity is a parameter that describes the reflectivity of an object to radiation. It is defined as the ratio of the radiation flux reflected by the object surface to the incident radiation flux. The reflectivity rating value is used to characterize the strength of the object reflectivity in the image area. Specifically, the larger the reflectivity rating value, the greater the object reflectivity; the smaller the reflectivity rating value, the smaller the object reflectivity.

[0029] As an example, the server inputs the dark channel image into a pre-trained atmospheric transmittance recognition model to obtain the atmospheric transmittance of each image area in the target remote sensing image; then, the average pixel value or pixel value standard deviation of each image area in the dark channel image is calculated, and the average pixel value or pixel value standard deviation between each image area in the dark channel image is compared to determine the reflectivity evaluation value of each image area in the target remote sensing image.

[0030] S103, determining target dark pixels of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image.

[0031] In this embodiment, the target dark pixel is used to characterize the pixel with very low atmospheric transmittance and object reflectance in the visible light band in the target remote sensing image. Among them, the target dark pixel can reflect the influence of the atmosphere on radiation, and is therefore often used as a reference point for atmospheric correction.

[0032] As an example, the server may screen and determine target dark pixels in the target remote sensing image based on the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image.

[0033] Specifically, the server determines the image area with the lowest atmospheric transmittance and the lowest reflectance evaluation value as the image area corresponding to the target dark pixel. Then, the pixel values ​​of each pixel in the image area are averaged and the average is used as the target dark pixel.

[0034] S104, performing radiation correction on the target remote sensing image based on the target dark pixels to obtain a corrected remote sensing image.

[0035] In this embodiment, the server establishes a radiation correction model based on the target dark pixels. Specifically, the radiation correction model aims to eliminate the influence of the atmosphere on the target remote sensing image.

[0036] Then, the established radiation correction model is applied to the entire target remote sensing image. For each pixel point in the target remote sensing image, the radiation correction model is used to adjust the pixel value to obtain a corrected remote sensing image.

[0037] In the radiation correction method for remote sensing images provided in this embodiment, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image are determined based on the dark channel image of the target remote sensing image. Then, the target dark pixel of the target remote sensing image is determined based on the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image. Finally, based on the target dark pixel, the target remote sensing image is subjected to radiation correction to obtain a corrected remote sensing image. In this way, the present invention performs a comprehensive evaluation based on the reflectance of the object in the target remote sensing image and the transmittance of the atmosphere, so that the target dark pixel of the target remote sensing image can be accurately determined. In addition, the target remote sensing image can be effectively radiation corrected to improve the effect of radiation correction.

[0038] As an optional embodiment, Figure 2 As shown, S101 may specifically include the following S201 to S203.

[0039] S201, acquiring remote sensing image data; S202, converting the remote sensing image data to obtain a target remote sensing image; S203, determining a dark channel image of the target remote sensing image according to the pixel value of each pixel point in the target remote sensing image.

[0040] In this embodiment, the remote sensing image data is not presented as an image in the form of pixels, but is presented as data brightness values ​​(Digital Number, DN) that are not clearly quantified and have no unified dimension. Therefore, the remote sensing image data needs to be converted into a target remote sensing image first.

[0041] As an example, the server first imports remote sensing image data, and then performs radiometric calibration on the remote sensing image data, that is, converting the data brightness value of the remote sensing image data into a physically meaningful radiometric value (i.e., radiometric brightness). Then, the format is converted based on the converted result to a target remote sensing image in GeoTIFF format containing three channels.

[0042] Then, for each pixel in the target remote sensing image, find the minimum pixel value in all corresponding color channels, and use the minimum pixel value as the pixel value of the dark channel image at the corresponding pixel position, thereby obtaining the dark channel image corresponding to the target remote sensing image. Furthermore, a local minimum filter can be used to smooth the dark channel image and reduce noise and artifacts.

[0043] Through this embodiment, the acquired remote sensing image data is converted to obtain a target remote sensing image. Then, the dark channel image of the target remote sensing image is determined according to the pixel value of each pixel point in the target remote sensing image. In this way, the dark channel image of the target remote sensing image can be accurately obtained, which is helpful for subsequent accurate analysis of the dark channel image, so that the target remote sensing image can be effectively corrected for radiation, and the effect of radiation correction can be improved.

[0044] As an optional embodiment, S203 may specifically include: Obtain the channel pixel value of each pixel in each color channel in the target remote sensing image; For each pixel point in the target remote sensing image, the minimum value of each channel pixel value is determined as the dark channel pixel value of the pixel point; Based on the dark channel pixel value of each pixel point, a dark channel image of the target remote sensing image is constructed.

[0045] In this embodiment, the dark channel pixel value is used to represent the pixel value of the dark channel image at the corresponding pixel point position.

[0046] As an example, the server obtains the channel pixel values ​​of each pixel in the target remote sensing image in the red channel, green channel, and blue channel respectively. Then at each pixel Find the minimum value as the dark channel pixel value of the corresponding pixel.

[0047] Finally, the dark channel pixel values ​​of each pixel point obtained above are projected and distributed according to the positions of each pixel point in the original target remote sensing image, thereby forming a dark channel image corresponding to the target remote sensing image.

[0048] Through this embodiment, for each pixel point in the target remote sensing image, the minimum value of each channel pixel value is determined as the dark channel pixel value of the pixel point; finally, based on the dark channel pixel value of each pixel point, the dark channel image of the target remote sensing image is constructed. In this way, the dark channel image of the target remote sensing image can be accurately obtained, which is helpful for subsequent accurate analysis of the dark channel image, so that the target remote sensing image can be effectively corrected for radiation and the effect of radiation correction can be improved.

[0049] As an optional embodiment, Figure 3As shown, S102 may specifically include the following S301 to S304.

[0050] S301, performing mean processing on the dark channel pixel values ​​of each target pixel point that meets the target screening condition in the dark channel image to obtain an atmospheric illumination value, wherein the target screening condition is that the dark channel pixel value is greater than a preset pixel value threshold; S302, dividing the target remote sensing image into a plurality of image regions; S303, determining the atmospheric transmittance of each image region based on the atmospheric illumination value; S304, determining a reflectivity evaluation value of each image region according to the atmospheric transmittance of each image region and the dark channel pixel value of each pixel point in each image region.

[0051] In this embodiment, the preset pixel value threshold may be a pixel value threshold input by a user, or may be a pixel value threshold determined according to the distribution of pixel values ​​of each pixel point in the dark channel image. For example, the pixel values ​​of each pixel point in the dark channel image may be sorted from large to small, and the pixel value at the 0.1% position may be determined as the preset pixel value threshold, that is, the brightest first 0.1% of the pixel points in the dark channel image may be screened out.

[0052] The atmospheric illumination value is used to characterize the light intensity reaching the bottom surface after sunlight passes through the atmosphere.

[0053] As an example, the server sorts the pixel values ​​of each pixel in the dark channel image from large to small, and determines the pixel value at the 0.1% position as the preset pixel value threshold. Then traverse each pixel in the dark channel image and compare its dark channel pixel value with the preset pixel value threshold; if it is greater than the preset pixel value threshold, it is considered that the pixel meets the target screening condition and is included in the subsequent calculation. Then the dark channel pixel values ​​of all pixels that meet the target screening condition are averaged to obtain the atmospheric illumination value.

[0054] At the same time, the server determines the appropriate division method based on the image size and resolution. For example, the image can be divided into grid areas of fixed size, or irregular division can be performed based on specific features in the image. Then, the target remote sensing image is divided according to the determined division method to obtain multiple image areas.

[0055] Then, the server uses an atmospheric scattering model (such as the Koschmieder model) to describe the transmission process of light in the target remote sensing image. The atmospheric scattering model includes two key parameters: atmospheric transmittance and atmospheric illumination value. Therefore, the server can obtain the atmospheric transmittance of each image area based on the atmospheric scattering model and the known atmospheric illumination value.

[0056] Finally, for each image area, the server extracts the dark channel pixel values ​​of all pixels in the image area and calculates the average value or standard deviation. Then, based on the atmospheric transmittance of each image area and the average pixel value or pixel value standard deviation of each image area, the reflectivity evaluation value of each image area in the target remote sensing image is evaluated.

[0057] Through this embodiment, the dark channel pixel values ​​of each target pixel point that meets the target screening condition in the dark channel image are averaged to obtain the atmospheric illumination value; then based on the atmospheric illumination value, the atmospheric transmittance of each image area is determined; finally, the reflectance evaluation value of each image area is determined according to the atmospheric transmittance of each image area and the dark channel pixel value of each pixel point in each image area. In this way, this embodiment can accurately determine the atmospheric transmittance and reflectance evaluation value of each image area in the target remote sensing image, which is helpful for comprehensive evaluation based on the reflectivity of the object in the target remote sensing image and the transmittance of the atmosphere, so that the target dark pixel of the target remote sensing image can be accurately determined, and the effect of radiation correction can be improved.

[0058] As an optional embodiment, S302 may specifically include: by The target remote sensing image is divided by a sliding window to obtain the first information complexity mean, which is The average information complexity of each first candidate region after the sliding window is divided, and the initial value of N is 3; by The target remote sensing image is divided by a sliding window to obtain the second information complexity mean, which is The mean value of the information complexity of each first candidate region after the sliding window is divided; When the absolute value of the difference between the first information complexity mean and the second information complexity mean is greater than the preset difference threshold, N is updated to N+2 and the first information complexity mean is updated to the second information complexity mean, and the loop execution is returned to The target remote sensing image is divided by a sliding window to obtain the second information complexity mean; When the absolute value of the difference between the first information complexity mean and the second information complexity mean is not greater than the preset difference threshold, The first candidate regions obtained by dividing the sliding window are determined as image regions of the target remote sensing image.

[0059] In this embodiment, information complexity is used to characterize the intricacies of information contained in the target remote sensing image, reflecting the visual complexity of the target remote sensing image.

[0060] This embodiment divides the image region based on the information complexity of the image region. Generally, the same scene has the same information complexity; at the same time, the air quality of the same scene is relatively close, so its atmospheric transmittance is basically the same.

[0061] As an example, the server first The target remote sensing image is divided into multiple corresponding first candidate regions by a sliding window. The information complexity of each first candidate region is calculated by the following formula 1: , Formula 1, In formula 1, Used to characterize the information complexity of the mth first candidate region, It is used to represent the probability of a pixel point with a pixel value of g appearing in the mth first candidate area, and log is used to represent the logarithmic operation.

[0062] Then, the information complexity of each first candidate region is averaged and the result is The mean information complexity under the sliding window partitioning condition.

[0063] Then The target remote sensing image is divided into multiple corresponding first candidate regions by a sliding window. The information complexity of each first candidate region is calculated by the above formula 1. Then, the information complexity of each first candidate region is averaged and obtained. The mean information complexity under the sliding window partitioning condition.

[0064] Then, calculate The mean information complexity of the sliding window partition is The absolute value of the difference between the information complexity means under the sliding window partitioning. When the absolute value of the difference is greater than the preset difference threshold, it means that the partitioning at this time is not reasonable.

[0065] Then, continue with The target remote sensing image is divided into multiple corresponding first candidate regions by a sliding window. The information complexity of each first candidate region is calculated by the above formula 1. Then, the information complexity of each first candidate region is averaged and obtained. The mean information complexity under the sliding window partitioning condition.

[0066] At the same time, calculation The mean information complexity of the sliding window partition is The absolute value of the difference between the information complexity means under the sliding window division. If the absolute value of the difference is not greater than the preset difference threshold, it means that the division is reasonable. The first candidate regions obtained by dividing the sliding window are determined as image regions of the target remote sensing image.

[0067] Through this embodiment, the image area division of the target remote sensing image is performed based on the information complexity of the image area. In this way, by reasonably dividing the image area of ​​the target remote sensing image, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image obtained later can be made more accurate. Therefore, the target dark pixel of the target remote sensing image can be accurately determined, and the effect of radiation correction can be improved.

[0068] As an optional embodiment, S304 may specifically include: The mean value of the dark channel pixel value of each pixel point in each image area is calculated respectively to obtain the mean value of the dark channel pixel of each image area; Calculate the cosine similarity between each image region to obtain the highest structural similarity region corresponding to each image region; Based on each highest structural similarity region, respectively determine a similarity compensation value of each corresponding image region; For each image area, the following operations are performed: based on the atmospheric transmittance of the image area, the mean value of dark channel pixels of the image area, the mean value of dark channel pixels of the area with the highest structural similarity, and the similarity compensation value, the reflectivity evaluation value of the image area is determined.

[0069] In this embodiment, the highest structural similarity region is used to characterize other image regions that are most similar in structure to the image region; the similarity compensation value is used to adjust the reflectivity evaluation value to improve the accuracy of the reflectivity evaluation value.

[0070] As an example, the server first calculates the mean of the dark channel pixel value of each pixel point in each image area, so as to obtain the mean of the dark channel pixel of each image area.

[0071] Then, for each image region, the following operations are performed: calculating the cosine similarity between the image region and other image regions, and selecting the image region corresponding to the largest cosine similarity as the region with the highest structural similarity of the image region.

[0072] Then, for each image region, according to its corresponding highest structural similarity region, the similarity compensation value of the image region is calculated by the following formula 2: , Formula 2, In formula 2, The similarity compensation value used to characterize the i-th image region, It is used to characterize the cosine similarity between the i-th image region and its corresponding region with the highest structural similarity. It is used to characterize the minimum value of the cosine similarity between the region with the highest structural similarity and each image region except the i-th image region. It is used to characterize the maximum value of the cosine similarity between the region with the highest structural similarity and each image region except the i-th image region.

[0073] Since different image regions have different similarities with the region with the highest structural similarity, the similarities between all image regions and the region with the highest structural similarity are dimensionally unified, and the dimensionally unified value is used as a compensation value to adjust the reflectivity evaluation value.

[0074] Finally, based on the atmospheric transmittance of the image area, the mean value of the dark channel pixels of the image area, the mean value of the dark channel pixels of the area with the highest structural similarity, and the similarity compensation value, the reflectance evaluation value of each image area is determined by the following formula 3: , Formula 3, In formula 3, The reflectivity evaluation value used to characterize the i-th image area, The mean value of dark channel pixels used to represent the i-th image area, The mean value of dark channel pixels in the region with the highest structural similarity used to characterize the i-th image region, The similarity compensation value used to characterize the i-th image region, Used to characterize the atmospheric transmittance of the ith image region.

[0075] Among them, the lower the mean value of the dark channel pixels in the i-th image area, the lower the object reflectivity of the i-th image area, that is, the smaller the reflectivity evaluation value; the closer the mean value of the dark channel pixels in the i-th image area is to the mean value of the dark channel pixels in the corresponding highest structural similarity area, the i-th image area has a higher object reflectivity, that is, the larger the reflectivity evaluation value; the greater the atmospheric transmittance of the i-th image area, the higher the object reflectivity, that is, the larger the reflectivity evaluation value.

[0076] Through this embodiment, for each image region, the reflectivity evaluation value of the image region is determined based on the atmospheric transmittance of the image region, the dark channel pixel mean of the image region, the dark channel pixel mean of the highest structural similarity region, and the similarity compensation value. In this way, the reflectivity evaluation value of each image region in the target remote sensing image can be accurately determined, which can help to accurately determine the target dark pixel of the target remote sensing image and improve the effect of radiation correction.

[0077] As an optional embodiment, Figure 4 As shown, S103 may specifically include the following S401 to S403.

[0078] S401, determining a plurality of candidate dark pixels according to the reflectivity evaluation value of each image region; S402, determining a screening parameter corresponding to each candidate dark pixel based on the atmospheric transmittance of the image region corresponding to each candidate dark pixel; S403, screening each candidate dark pixel according to the screening parameters corresponding to each candidate dark pixel, to obtain the target dark pixel of the target remote sensing image.

[0079] In this embodiment, the screening parameters are used to screen candidate dark pixels to obtain target dark pixels of the target remote sensing image.

[0080] As an example, the server compares the reflectivity evaluation value of each image area with the corresponding evaluation value threshold, and determines the minimum value of the dark channel pixel value in each image area that is smaller than the evaluation value threshold as the candidate dark pixel.

[0081] Then, for each candidate dark pixel, the corresponding screening parameter is determined by the following formula 4 according to the atmospheric transmittance of the corresponding image area: , formula 4, In formula 4, It is used to characterize the screening parameters corresponding to the b-th candidate dark pixel. Used to represent the dark channel pixel value corresponding to the bth candidate dark pixel. It is used to characterize the atmospheric transmittance of the i-th image area, and I is used to characterize the number of image areas of the target remote sensing image. It is used to represent the bth candidate dark pixel corresponding to the The atmospheric transmittance of each image area, e, is used to characterize the calculation of the natural exponential function.

[0082] The closer the atmospheric transmittance of the image area corresponding to the candidate dark pixel is to the atmospheric transmittance of the target remote sensing image, the better the atmospheric correction effect of the candidate dark pixel on the target remote sensing image, that is, the smaller the screening parameter corresponding to the candidate dark pixel is.

[0083] Finally, the screening parameters corresponding to each candidate dark pixel are compared with a preset screening threshold, and each candidate dark pixel smaller than the preset screening threshold is determined as the target dark pixel of the target remote sensing image.

[0084] Through this embodiment, based on the atmospheric transmittance of the image area corresponding to each candidate dark pixel, the screening parameter corresponding to each candidate dark pixel is determined; thus, each candidate dark pixel is screened according to the screening parameter corresponding to each candidate dark pixel to obtain the target dark pixel of the target remote sensing image. In this way, by accurately determining the target dark pixel of the target remote sensing image, it is helpful to effectively perform radiation correction on the target remote sensing image and improve the effect of radiation correction.

[0085] As an optional embodiment, S401 may specifically include: Sort the reflectivity evaluation values ​​of each image area in order of size to obtain a reflectivity evaluation value sequence; The image area corresponding to the first Z smallest reflectivity evaluation values ​​in the reflectivity evaluation value sequence is determined as the second candidate area, where Z is a positive integer; The mean value of the dark channel pixels in each second candidate area is determined as the candidate dark pixel.

[0086] In this embodiment, the second candidate region is used to represent the image region where the candidate dark pixel is located.

[0087] As an example, the server sorts the reflectivity evaluation values ​​of all image regions in order from small to large or from large to small to obtain a reflectivity evaluation value sequence.

[0088] Then, the image areas with the smallest reflectivity evaluation value sequence in the first 10% are determined as the second candidate areas. Finally, for each second candidate area, the dark channel pixel values ​​of each pixel in the second candidate area are averaged to obtain the dark channel pixel mean. The dark channel pixel mean of each second candidate area is determined as the candidate dark pixel.

[0089] Through this embodiment, the image area corresponding to the first Z reflectivity evaluation values ​​with the smallest reflectivity evaluation value is determined as the second candidate area. Then the mean value of the dark channel pixels of each second candidate area is determined as the candidate dark pixel. In this way, this embodiment predetermines multiple candidate dark pixels according to the magnitude relationship of the reflectivity evaluation value. In this way, it is only necessary to determine the target dark pixel of the target remote sensing image from the candidate dark pixels later, thereby improving the determination efficiency of the target dark pixel.

[0090] As an optional embodiment, S403 may specifically include: The image area corresponding to the candidate dark pixel with the smallest screening parameter is determined as the dark pixel area; The minimum value of the dark channel pixel value of each pixel point in the dark pixel area is determined as the target dark pixel of the target remote sensing image.

[0091] In this embodiment, the dark pixel region is used to represent the image region where the target dark pixel is located.

[0092] As an example, the server selects the image region corresponding to the candidate dark pixel with the smallest screening parameter as the dark pixel region. Then, the minimum value of the dark channel pixel values ​​of each pixel point in the dark pixel region is determined as the target dark pixel of the target remote sensing image.

[0093] Through this embodiment, each candidate dark pixel is screened according to the screening parameters corresponding to each candidate dark pixel to obtain the target dark pixel of the target remote sensing image. In this way, the target dark pixel of the target remote sensing image can be accurately determined, thereby helping to improve the effect of radiation correction.

[0094] Based on the radiation correction method for remote sensing images, the present invention also provides a specific embodiment of a radiation correction system for remote sensing images.

[0095] Figure 5 A schematic structural diagram of a radiation correction system for remote sensing images provided in an embodiment of the present invention is shown. The radiation correction system 500 for remote sensing images may include an image acquisition module 510, an image calculation module 520, a dark pixel determination module 530 and a radiation correction module 540.

[0096] An image acquisition module 510 is used to acquire a dark channel image of a target remote sensing image. The dark channel image is an image formed by the minimum channel pixel value of each pixel in the target remote sensing image. The minimum channel pixel value is the minimum value of the channel pixel values ​​of each color channel. An image calculation module 520 is used to determine the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image according to the dark channel image, and the reflectance evaluation value is used to characterize the intensity of the reflectance of the object in the image area; A dark pixel determination module 530 is used to determine the target dark pixels of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image; The radiation correction module 540 is used to perform radiation correction on the target remote sensing image based on the target dark pixels to obtain a corrected remote sensing image.

[0097] In the radiation correction system for remote sensing images provided by the embodiment of the present invention, the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image are determined according to the dark channel image of the target remote sensing image. Then, the target dark pixel of the target remote sensing image is determined according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image. Finally, based on the target dark pixel, the target remote sensing image is subjected to radiation correction to obtain a corrected remote sensing image. In this way, the present invention performs a comprehensive evaluation based on the reflectance of the object in the target remote sensing image and the transmittance of the atmosphere, so that the target dark pixel of the target remote sensing image can be accurately determined. In addition, the target remote sensing image can be effectively radiation corrected to improve the effect of radiation correction.

[0098] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0099] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0100] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A radiation correction method for remote sensing images, characterized in that: The method comprises: Acquire a dark channel image of the target remote sensing image, wherein the dark channel image is an image composed of the minimum channel pixel value of each pixel point in the target remote sensing image, and the minimum channel pixel value is the minimum value of the channel pixel values ​​of the pixel point in each color channel; Determine, according to the dark channel image, an atmospheric transmittance and reflectance evaluation value of each image area in the target remote sensing image, wherein the reflectance evaluation value is used to characterize the intensity of the reflectance of the object in the image area; Determining target dark pixels of the target remote sensing image according to evaluation values ​​of atmospheric transmittance and reflectance of each image area in the target remote sensing image; Based on the target dark pixels, radiation correction is performed on the target remote sensing image to obtain a corrected remote sensing image.

2. The radiation correction method for remote sensing images according to claim 1, characterized in that: The step of acquiring a dark channel image of a target remote sensing image comprises: Acquisition of remote sensing image data; Converting the remote sensing image data to obtain the target remote sensing image; A dark channel image of the target remote sensing image is determined according to the pixel value of each pixel point in the target remote sensing image.

3. The radiation correction method for remote sensing images according to claim 2, characterized in that: Determining the dark channel image of the target remote sensing image according to the pixel value of each pixel point in the target remote sensing image includes: Obtaining the channel pixel value of each pixel point in each color channel in the target remote sensing image; For each pixel point in the target remote sensing image, the minimum value among the pixel values ​​of each channel is determined as the dark channel pixel value of the pixel point; Based on the dark channel pixel value of each of the pixel points, a dark channel image of the target remote sensing image is constructed.

4. The radiation correction method for remote sensing images according to claim 1, characterized in that: Determining the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image according to the dark channel image includes: Performing mean processing on the dark channel pixel values ​​of each target pixel point in the dark channel image that meets the target screening condition to obtain an atmospheric illumination value, wherein the target screening condition is that the dark channel pixel value is greater than a preset pixel value threshold; Dividing the target remote sensing image into a plurality of image regions; Determining the atmospheric transmittance of each of the image regions based on the atmospheric illumination value; The reflectivity evaluation value of each image area is determined according to the atmospheric transmittance of each image area and the dark channel pixel value of each pixel point in each image area.

5. The radiation correction method for remote sensing images according to claim 4, characterized in that: The step of dividing the target remote sensing image into a plurality of image regions comprises: by The target remote sensing image is divided by a sliding window to obtain a first information complexity mean, wherein the first information complexity mean is The average value of the information complexity of each first candidate region after the sliding window is divided, and the initial value of N is 3; by The target remote sensing image is divided by a sliding window to obtain a second information complexity mean, wherein the second information complexity mean is The mean value of the information complexity of each first candidate region after the sliding window is divided; When the absolute value of the difference between the first information complexity mean and the second information complexity mean is greater than a preset difference threshold, N is updated to N+2 and the first information complexity mean is updated to the second information complexity mean, and the loop is returned to execute. The target remote sensing image is divided by a sliding window to obtain a second information complexity mean; If the absolute value of the difference between the first information complexity mean and the second information complexity mean is not greater than the preset difference threshold, The first candidate regions obtained by the sliding window division are determined as the image regions of the target remote sensing image.

6. The radiation correction method for remote sensing images according to claim 4, characterized in that: Determining the reflectivity evaluation value of each image area according to the atmospheric transmittance of each image area and the dark channel pixel value of each pixel point in each image area includes: Calculating the mean of the dark channel pixel values ​​of each pixel point in each image area to obtain the mean of the dark channel pixel values ​​of each image area; Calculating the cosine similarity between the image regions to obtain the highest structural similarity region corresponding to each image region; Based on each of the highest structural similarity regions, respectively determine a similarity compensation value of each corresponding image region; For each of the image regions, respectively, the following steps are performed: determining a reflectivity evaluation value of the image region based on the atmospheric transmittance of the image region, the dark channel pixel mean of the image region, the dark channel pixel mean of the highest structural similarity region, and the similarity compensation value.

7. The radiation correction method for remote sensing images according to claim 1, characterized in that: Determining the target dark pixel of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image comprises: Determining a plurality of candidate dark pixels according to the reflectivity evaluation values ​​of the image regions; Determining the screening parameters corresponding to each of the candidate dark pixels based on the atmospheric transmittance of the image area corresponding to each of the candidate dark pixels; The candidate dark pixels are screened according to the screening parameters corresponding to the candidate dark pixels to obtain the target dark pixels of the target remote sensing image.

8. The radiation correction method for remote sensing images according to claim 7, characterized in that: Determining a plurality of candidate dark pixels according to the reflectivity evaluation values ​​of the image regions comprises: Sorting the reflectivity evaluation values ​​of the image regions in order of magnitude to obtain a reflectivity evaluation value sequence; Determine the image area corresponding to the first Z smallest reflectivity evaluation values ​​in the reflectivity evaluation value sequence as the second candidate area, where Z is a positive integer; The mean value of the dark channel pixels of each of the second candidate areas is determined as the candidate dark pixel.

9. The radiation correction method for remote sensing images according to claim 7, characterized in that: The step of screening each of the candidate dark pixels according to the screening parameters corresponding to each of the candidate dark pixels to obtain the target dark pixel of the target remote sensing image comprises: Determine the image region corresponding to the candidate dark pixel with the smallest screening parameter as the dark pixel region; The minimum value of the dark channel pixel values ​​of the pixels in the dark pixel area is determined as the target dark pixel of the target remote sensing image.

10. A radiation correction system for remote sensing images, characterized in that: The system comprises: An image acquisition module is used to acquire a dark channel image of a target remote sensing image, wherein the dark channel image is an image composed of the minimum channel pixel value of each pixel point in the target remote sensing image, and the minimum channel pixel value is the minimum value of the channel pixel values ​​of the pixel point in each color channel; An image calculation module, used to determine the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image according to the dark channel image, wherein the reflectance evaluation value is used to characterize the intensity of the reflectance of the object in the image area; A dark pixel determination module, used for determining the target dark pixel of the target remote sensing image according to the atmospheric transmittance and reflectance evaluation values ​​of each image area in the target remote sensing image; The radiation correction module is used to perform radiation correction on the target remote sensing image based on the target dark pixel to obtain a corrected remote sensing image.

Images