Remote sensing image haze removal processing method and system

Abstract

The invention discloses a remote sensing image haze removal processing method and system, and relates to the technical field of image processing. The method comprises the steps of obtaining a to-be-processed remote sensing image; extracting wave band data of a plurality of wave bands in the remote sensing image to be processed, and determining a reference wave band and a plurality of target wave bands based on the wave band data; based on the reference wave band, determining an atmosphere illumination parameter, and calculating a transmittance distribution diagram of each target wave band; for each target wave band, carrying out haze removal processing on the target wave band according to the atmosphere illumination parameters and the transmittance distribution diagram to obtain an initial haze removal image of the target wave band; and performing fusion processing on the initial haze-removed images of the target wavebands to obtain a haze-removed image corresponding to the to-be-processed remote sensing image. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of haze removal processing of the remote sensing image is achieved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a remote sensing image dehazing method, system, electronic device and storage medium. Background Art

[0002] With the continuous advancement of remote sensing technology, it has become possible to obtain high-resolution and multispectral remote sensing images. These images provide valuable data support in many fields such as environmental monitoring, urban planning, and agricultural management. Remote sensing technology is a technology that uses sensors carried by spacecraft or aircraft to observe the earth's surface and atmosphere from a distance. These sensors are able to capture electromagnetic spectrum from different wavelengths, including visible light and infrared light. Remote sensing images play an important role in many fields such as agriculture, forestry, geological exploration, and environmental monitoring. However, the quality and accuracy of these images are often affected by atmospheric conditions, especially haze.

[0003] At present, the existing remote sensing image dehazing processing methods mainly achieve the dehazing effect by performing dehazing on the remote sensing image as a whole. However, in practical applications, since the remote sensing images are affected differently by haze under different band conditions, the error of haze processing under different bands is often easily ignored by only processing the remote sensing images as a whole, resulting in low accuracy of remote sensing image dehazing processing. Summary of the invention

[0004] The present application provides a remote sensing image dehazing processing method and system, which has the effect of improving the accuracy of remote sensing image dehazing processing.

[0005] In a first aspect, the present application provides a remote sensing image dehazing method, comprising: Acquire remote sensing images to be processed; Extracting band data of multiple bands in the remote sensing image to be processed, and determining a reference band and multiple target bands based on each of the band data; Based on the reference band, determine the atmospheric illumination parameters, and calculate the transmittance distribution map of each target band; For each of the target wavebands, dehazing the target waveband according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial dehazing image of the target waveband; The initial dehazed images of the target bands are fused to obtain dehazed images corresponding to the remote sensing images to be processed.

[0006] In a second aspect of the present application, a remote sensing image dehazing processing system is provided, the system comprising: An image acquisition module, used for acquiring remote sensing images to be processed; A band determination module, used for extracting band data of multiple bands in the remote sensing image to be processed, and determining a reference band and multiple target bands based on each of the band data; A parameter determination module, used to determine the atmospheric illumination parameters based on the reference band, and calculate the transmittance distribution map of each target band; The image processing module is used to perform dehazing processing on each target band according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial dehazing image of the target band; and perform fusion processing on the initial dehazing image of each target band to obtain a dehazing image corresponding to the remote sensing image to be processed.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a remote sensing image dehazing method when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a remote sensing image dehazing processing method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical scheme, the remote sensing image to be processed is obtained and the band data of multiple bands thereof are extracted, the reference band and multiple target bands are accurately determined, and the sensitivity differences of different bands to haze are fully considered. Based on the reference band, the atmospheric illumination parameters are accurately determined, and the transmittance distribution map of each target band is calculated, ensuring the accuracy of atmospheric parameter estimation and the meticulousness of transmittance calculation. Subsequently, the atmospheric illumination parameters and transmittance distribution map are used to perform haze removal processing on each target band to obtain the corresponding initial haze removal image, which effectively reduces the influence of atmospheric scattering and absorption while restoring the image clarity. Finally, the initial haze removal images of each target band are fused to generate the final haze removal remote sensing image, which integrates the defogging effects of each band and improves the overall clarity and contrast of the image. This technical scheme avoids the errors caused by the traditional overall defogging processing through multi-band processing and fusion, and achieves the effect of improving the accuracy of remote sensing image defogging processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of a remote sensing image dehazing method provided in an embodiment of the present application; Figure 2It is a structural schematic diagram of a remote sensing image dehazing processing system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides a remote sensing image dehazing method. In one embodiment, please refer to Figure 1 , Figure 1 This is a flow chart of a remote sensing image dehazing processing method provided in an embodiment of the present application. The method can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run in a remote sensing image dehazing processing system based on a von Neumann system. Specifically, the method can include the following steps: Step 101: obtaining a remote sensing image to be processed; extracting band data of multiple bands in the remote sensing image to be processed, and determining a reference band and multiple target bands based on the data of each band.

[0016] Among them, the remote sensing image to be processed refers to the multispectral image data obtained by remote sensing equipment carried by spacecraft or aircraft. Specifically, the remote sensing image contains image information collected in the same geographical area under different wavelengths of the electromagnetic spectrum, and this information is usually stored as digital image data containing multiple bands. Each band corresponds to the electromagnetic wave reflection or radiation information of a specific wavelength range, such as the visible light band (including red, green, and blue light bands), near infrared band, etc.

[0017] Band data refers to a two-dimensional digital matrix formed by the electromagnetic wave reflection or radiation information collected by the remote sensing image to be processed within a specific wavelength range. Each band data corresponds to a specific interval in the electromagnetic spectrum, such as the blue light band (0.45-0.52μm), green light band (0.52-0.60μm), red light band (0.63-0.69μm), near infrared band (0.76-0.90μm), etc. The value of each pixel represents the reflectivity or radiation intensity of the object at that location within a specific wavelength range.

[0018] Reference bands and multiple target bands refer to two types of bands obtained by classifying the band data of the remote sensing image to be processed according to the clarity assessment results. Among them, the reference band refers to the single band with the largest clarity value among all bands, indicating that this band is least affected by haze and the ground features are clearest; the target band refers to all bands except the reference band. These bands are relatively more affected by haze and need to be dehazed based on the information of the reference band.

[0019] Specifically, firstly, a remote sensing image to be processed is obtained through a remote sensing device. Since the remote sensing image contains electromagnetic spectrum information of multiple different wavelengths, it is necessary to extract band data of multiple bands from the remote sensing image to be processed. These band data may include but are not limited to visible light bands, near infrared bands, etc., and each band carries different spectral information of ground object characteristics. Considering that different bands are affected by haze to different degrees, in order to improve the accuracy of haze removal processing, it is necessary to perform differential processing on the data of each band. After extracting the band data, edge detection is used to determine the reference band and the target band. Edge detection is performed on the band data of each band to obtain a corresponding edge detection image. Commonly used edge detection algorithms such as Sobel operator and Canny operator can be used for edge detection. Through edge detection, the edge contour information in the image can be highlighted. After obtaining the edge detection image, the number of edge pixels in each edge detection image is counted, and the number is used as the clarity value of the corresponding band. This is because in the bands that are less affected by haze, the edge features of the ground objects are clearer and the number of edge pixels is relatively large. Based on the calculation results of the above clarity values, the band with the largest clarity value is selected as the reference band among all the bands, and the remaining bands are determined as target bands. The reason for selecting the band with the highest clarity as the reference band is that this band is least affected by haze, and the ground feature information contained in it is the most reliable, which can be used as a benchmark for subsequent processing. The other bands are used as target bands, and the corresponding dehaze processing will be performed based on the processing results of the reference band. By determining the reference band and the target band in this way, the characteristics of different bands can be fully utilized, a processing mechanism based on the reference benchmark can be established, and the effective extraction and classification of band data can be realized, laying the foundation for subsequent differentiated processing.

[0020] Based on the above embodiment, as an optional embodiment, in step 101: determining a reference band and a plurality of target bands based on the data of each band, this step may also include the following steps: Step 201: Perform edge detection on the band data of each band to obtain an edge detection image of the band data.

[0021] The edge detection image refers to a binary image obtained by applying the Sobel operator to the band data for edge detection. The image identifies and marks the locations where there are significant grayscale changes in the image by calculating the grayscale value changes in the horizontal and vertical directions of the image. These locations usually correspond to the boundary contours of the ground objects. In the edge detection image, a pixel value of 1 indicates that the location is an edge point, and a pixel value of 0 indicates that the location is a non-edge point.

[0022] Specifically, edge detection processing is performed on the extracted data of each band to obtain the edge detection image of each band data. The main purpose of edge detection is to judge the clarity of each band by evaluating the edge features in the image. This is because in the remote sensing image affected by haze, haze will cause the image to be blurred, which will weaken the edge features of the ground objects. On the contrary, in the bands less affected by haze, the edge features of the ground objects are clearer and more prominent. Therefore, edge detection can effectively evaluate the degree of haze influence on each band. The specific edge detection process is processed by Sobel operator. Sobel operator contains two convolution kernels in the horizontal direction and the vertical direction, which are used to detect the grayscale changes of the image in the horizontal and vertical directions respectively. For each band data, the Sobel operator in the horizontal direction is first used for convolution operation to obtain the gradient image in the horizontal direction; then the Sobel operator in the vertical direction is used for convolution operation to obtain the gradient image in the vertical direction. The gradient images in these two directions are combined to calculate the gradient amplitude of each pixel point, so as to obtain the edge detection image of the band. In the edge detection process, for pixels whose gradient amplitude is less than the preset threshold, their values ​​are set to 0 to eliminate the influence of noise; for pixels whose gradient amplitude is greater than or equal to the preset threshold, their values ​​are set to 1, indicating that the point is an edge pixel. The edge detection image obtained in this way is a binary image, in which the pixel value of 1 represents the detected edge position, and the pixel value of 0 represents the non-edge position. In the bands less affected by haze, the number of edge pixels in the edge detection image will be relatively large because the edge features of the ground objects are better preserved; while in the bands more affected by haze, the number of edge pixels in the edge detection image will be relatively small because the edge features of the ground objects are weakened by haze. The obtained edge detection image intuitively reflects the degree of haze influence on each band, and provides an objective basis for the subsequent determination of reference bands and target bands.

[0023] Step 202: Determine the number of edge pixels in each edge detection image, and use the number of edge pixels in each edge detection image as the clarity value of the corresponding band.

[0024] The clarity value refers to the numerical index obtained by counting the number of edge pixels in the edge detection image corresponding to each band and normalizing it. This index reflects the degree of retention of the edge features of the ground objects in the band data. Its value range is between 0 and 1. The larger the value, the clearer the image of the band is and the less affected by haze.

[0025] Specifically, each edge detection image is scanned pixel by pixel. Since the edge detection image is a binary image, a pixel value of 1 represents an edge point, and a pixel value of 0 represents a non-edge point, it is only necessary to count the total number of points with a pixel value of 1 to obtain the number of edge pixels. In order to eliminate the influence of image size on the statistical results, the number of edge pixels can be divided by the total number of pixels in the image to obtain a normalized clarity value. This not only ensures the comparability of clarity values ​​between images of different sizes, but also limits the clarity value to between 0 and 1, which is convenient for subsequent processing. In order to improve the accuracy of statistics, special processing of the image boundary area needs to be considered in the calculation process. Since there may be incomplete edge features in the image boundary area, it is possible to choose to ignore several pixels at the outermost edge of the image during statistics, and only count the internal area, which can reduce the influence of the boundary effect on the calculation of the clarity value. At the same time, in order to reduce the interference of noise on the statistical results, a minimum connected area threshold can be set to only count edge features with a certain scale, while ignoring isolated edge points that are too small. The clarity value obtained in this way provides a reliable basis for the subsequent band selection and can objectively identify the band least affected by haze as the reference band, thus laying a good foundation for the entire dehaze processing process.

[0026] Step 203: Among the bands, the band with the largest clarity value is determined as the reference band, and the remaining bands are determined as the target bands.

[0027] Specifically, firstly, the clarity values ​​of each band are compared and sorted to find the band with the maximum clarity value. In actual processing, the clarity values ​​of all bands can be traversed, and the maximum clarity value and its corresponding band index can be continuously updated using comparison operators, so as to finally obtain the band with the largest clarity value. After the band is determined as the reference band, all the remaining bands are automatically determined as the target band. This band classification method based on clarity values ​​ensures that the selection of reference bands is objective and repeatable. In order to improve the reliability of the selection, some special cases need to be considered when determining the reference band. For example, when there are multiple bands with very close clarity values, additional evaluation criteria can be introduced, such as considering the spectral characteristics of the band or the correlation with the adjacent bands, and selecting the one that is most suitable as the reference band. At the same time, it is also necessary to ensure that the selected reference band is representative in terms of spatial distribution, so as to avoid selecting bands that are particularly clear in local areas but not representative enough overall. This step divides all bands into two categories: reference bands and target bands, establishing a clear processing framework for subsequent dehazing processing; by selecting the bands with the highest clarity as reference bands, the reliability of subsequent parameter estimation is ensured; the remaining bands are identified as target bands, clarifying the processing objects that need to be optimized for dehazing.

[0028] Step 102: Based on the reference band, determine the atmospheric illumination parameters and calculate the transmittance distribution map of each target band.

[0029] Among them, the atmospheric illumination parameter refers to the global illumination intensity value caused by atmospheric scattering and absorption in the process of remote sensing image formation. It reflects the intensity of the scattering effect of the atmosphere on solar radiation under haze weather conditions and is one of the key physical parameters in the dehazing process of remote sensing images. In the embodiment of the present application, the atmospheric illumination parameter can be understood as a scalar value describing the optical properties of the atmosphere, which characterizes the scattering contribution of the atmosphere to the incident light under haze weather conditions.

[0030] The transmittance distribution map refers to a two-dimensional matrix that describes the degree of attenuation of the atmospheric radiation information of the ground object at each pixel position in the remote sensing image. The value range of each element in the matrix is ​​between 0 and 1. The closer the value is to 1, the higher the atmospheric transmittance at that position, that is, the smaller the attenuation of the ground object information; the closer the value is to 0, the lower the atmospheric transmittance at that position, that is, the more serious the attenuation of the ground object information. In the embodiment of the present application, the transmittance distribution map can be understood as a characteristic image that characterizes the uneven spatial distribution of haze. Since the spatial distribution of haze is usually non-uniform and is affected by factors such as terrain and airflow, the transmittance in different areas will be different.

[0031] Specifically, the atmospheric illumination parameters are estimated based on the reference band. The dark channel image is calculated for the image data of the reference band, that is, the minimum pixel value is found in the local window. Since the reference band is least affected by haze, its dark channel image can more accurately reflect the radiation characteristics of the ground object itself. The top 0.1% of the pixels with the highest brightness value are selected in the dark channel image, and then the value of the point with the highest brightness is selected in the original reference band image corresponding to these positions as the atmospheric illumination parameter. This estimation method based on the reference band can reduce the interference of haze on parameter estimation and improve the accuracy of the estimation result. After obtaining the atmospheric illumination parameters, it is necessary to calculate the transmittance distribution map of each target band. First, the dark channel image is calculated for each target band. Then, based on the atmospheric illumination parameters and the dark channel image, the transmittance distribution map is calculated using the improved transmittance estimation model. In the estimation process, considering the different sensitivity of different bands to haze, it is necessary to adjust the parameters of the transmittance estimation model according to the spectral correlation between the target band and the reference band. For target bands with high spectral correlation with the reference band, the transmittance estimation results of the reference band can be directly applied; for bands with low correlation, appropriate parameter adjustments need to be made according to their spectral characteristics. In order to improve the accuracy of transmittance estimation, a soft cutout algorithm is also used to optimize the transmittance distribution map during the calculation process. By considering the local smoothness constraints of the image, the algorithm can effectively avoid the block effect in the transmittance estimation, making the transmittance distribution more in line with the actual situation. At the same time, in order to prevent under- or over-estimation of the transmittance, upper and lower limits of the transmittance are set, and the transmittance is usually limited to between 0.1 and 1. This step successfully estimates the accurate atmospheric illumination parameters through the reference band, providing a reliable parameter basis for subsequent dehazing processing; accurate transmittance distribution maps of each target band are obtained, which truly reflect the attenuation degree of haze on different bands.

[0032] Based on the above embodiment, as an optional embodiment, in step 102: determining the atmospheric illumination parameter based on the reference band, this step may also include the following steps: Step 301: Acquire a dark channel image of a reference band; divide the dark channel image into a plurality of image blocks according to a preset size, and determine an average brightness value of each image block.

[0033] Among them, the dark channel image refers to a characteristic image obtained by performing a minimum operation in a local area of ​​the original image, which reflects the minimum radiation intensity value at each position of the image and its neighborhood. In an embodiment of the present application, the dark channel image can be understood as a characteristic map used to characterize the degree of influence of haze. Since haze increases the overall brightness of the image, making the originally darker areas brighter, the value of the dark channel image increases with the increase of haze concentration.

[0034] An image block refers to a local sub-image area obtained by dividing the dark channel image according to a preset size. Each image block contains a fixed number of pixels that are spatially adjacent and form a rectangular area. The size of the image block is usually set according to the resolution and processing requirements of the image, ensuring that it contains enough local information while avoiding excessive loss of spatial resolution.

[0035] The average brightness value refers to the arithmetic average of all pixel values ​​in the image block, which represents the overall radiation intensity level of the dark channel image in the area. This statistic is obtained by summing the values ​​of each pixel in the image block and then dividing it by the total number of pixels, reflecting the average degree to which the local area is affected by haze.

[0036] Specifically, a sliding window is used on the reference band image for local minimum filtering. The window size is usually set to 15×15 pixels, which can ensure that sufficient local information is captured without causing excessive smoothing. For each pixel position, the minimum value is found in the window area around it, and the minimum value is used as the dark channel value of the current position. In order to improve the computational efficiency, optimization methods such as integral images can be used to accelerate the minimum value search process. After obtaining the dark channel image, it needs to be divided into multiple image blocks for analysis. The size of the image block is set to a preset value, such as 32×32 pixels. This size can ensure that the block contains sufficient statistical information without reducing the spatial resolution too much. The division process adopts a grid division method to ensure that there is no overlap between image blocks. For areas where the edge of the image is less than a complete block, zero padding or mirror extension can be used. When calculating the average brightness value for each image block, the arithmetic average of all pixel values ​​in the block is directly calculated. This regional statistical method can reduce the impact of local noise and obtain more stable brightness features. During the calculation process, the position information of each image block can be recorded at the same time, which is convenient for establishing spatial correspondence in subsequent processing. This step successfully extracts the haze characteristic information in the reference band through dark channel processing; through image block division and average brightness calculation, the regional characterization of haze distribution is achieved; the obtained average brightness value of the image block provides a reliable statistical feature for the subsequent estimation of atmospheric illumination parameters.

[0037] Step 302: Select a preset number of image blocks in descending order of average brightness value; calculate the average pixel value of each selected image block in the reference band to obtain atmospheric illumination parameters.

[0038] Specifically, all the obtained image blocks are sorted in descending order according to their average brightness values. The basis for this sorting is that the image blocks with larger average brightness values ​​usually indicate that the area is more seriously affected by haze and are more likely to contain information reflecting the characteristics of atmospheric illumination. By sorting in descending order, the image blocks that are most likely to contain atmospheric illumination information can be preferentially selected. After the sorting is completed, the first N image blocks are selected from the sorting results, where N is a preset number, for example, the first 0.1% of image blocks can be selected. The setting of the number of selections needs to weigh two factors: selecting too few may make the estimation result unstable, and selecting too many may introduce interference from non-atmospheric illumination areas. Through experimental verification, selecting the first 0.1% of image blocks can not only ensure sufficient statistical sample size, but also effectively avoid interference from non-target areas. For each selected image block, it is necessary to return to the reference band image to determine its corresponding position and calculate the average pixel value of the image block at that position. Here, the value of the dark channel image is no longer used, but the original pixel value of the reference band is directly used, because the original pixel value more directly reflects the intensity of atmospheric illumination. When calculating the average pixel value, the arithmetic mean method is used to sum all the pixel values ​​in the image block and divide it by the number of pixels. Finally, the average pixel values ​​of all selected image blocks are arithmetic averaged again to obtain the final atmospheric illumination parameters. This multi-level averaging processing method can further improve the stability of the estimation results. Since the areas with high dark channel values ​​are selected, the average pixel values ​​of these areas in the reference band can better reflect the intensity of atmospheric illumination.

[0039] Based on the above embodiment, as an optional embodiment, in step 102: calculating the transmittance distribution diagram of each target band, this step may also include the following steps: Step 303: Obtain a dark channel image of each target band; calculate the transmittance of each target band according to the pixel value of the dark channel image of each target band and the atmospheric illumination parameter.

[0040] Among them, transmittance refers to the proportion of energy remaining after light passes through the atmospheric medium. It describes the attenuation of electromagnetic wave signals in the atmosphere during the transmission path from the ground object to the imaging device. Transmittance is a physical quantity between 0 and 1, where 0 means that the light is completely blocked or scattered, and 1 means that the light is not attenuated at all. This physical quantity directly reflects the attenuation effect of haze on the radiation signals of ground objects at different locations.

[0041] Specifically, it is first necessary to perform the same dark channel processing as the reference band on each target band to obtain its dark channel image. This processing is necessary because different bands are affected by haze to different degrees, and the haze characteristics of each band need to be extracted separately. The dark channel processing adopts the same method as step 301, that is, the minimum value filtering operation is performed in the local window. This can ensure the consistency of the processing method and make the dark channel characteristics of different bands comparable. After obtaining the dark channel image of the target band, it is necessary to establish a transmittance estimation model based on the dark channel prior theory. In this model, the pixel value of the dark channel image is first divided by the atmospheric illumination parameter obtained in step 302. This step realizes the normalization of the dark channel value. The normalized value range is more suitable for transmittance estimation because the transmittance itself is a physical quantity between 0 and 1. When estimating the transmittance, a calculation formula based on the dark channel prior is used. The physical meaning of this formula is: the larger the ratio of the dark channel value to the atmospheric illumination parameter, the more serious the haze is affected at this place, and the lower the corresponding transmittance. In order to avoid the estimated transmittance being too small and causing the dehazed image to be too dark locally, a lower limit threshold, such as 0.1, needs to be set. When the estimated transmittance is lower than the threshold, it is set as the threshold. This lower limit constraint can ensure the visual effect of the dehazed image and prevent the appearance of unnatural dark areas. This step successfully obtains the transmittance distribution map reflecting the spatial distribution characteristics of haze in different bands by performing dark channel processing and transmittance estimation on each target band.

[0042] Step 313: Substitute the pixel values ​​of the dark channel image of each target band and the atmospheric illumination parameters into a preset transmittance formula to obtain the transmittance of each target band; wherein the preset transmittance formula is: Where, t i represents the transmittance of the i-th target band, ω represents the reference scattering coefficient, I i represents the pixel value of the dark channel image of the i-th target band, and A represents the atmospheric illumination parameter.

[0043] Specifically, it is necessary to convert the dark channel image pixel values ​​and atmospheric illumination parameters of each target band into transmittance through a preset transmittance formula. This conversion is based on the theoretical basis of the atmospheric scattering model. By introducing the reference scattering coefficient, it more accurately describes the differences in the scattering characteristics of haze in different bands. The preset transmittance formula adopts an exponential form, which can better reflect the impact of haze on electromagnetic wave transmission. First, the reference scattering coefficient ω needs to be determined. This coefficient is a reference parameter that reflects the intensity of atmospheric scattering, and its value needs to be calibrated according to the actual haze weather conditions. In practice, the reasonable value range of the reference scattering coefficient can be determined by analyzing the image features under typical haze weather conditions and combining the measured atmospheric parameters. A larger reference scattering coefficient indicates that the atmospheric scattering effect is stronger, which will cause the estimated transmittance to be smaller overall; conversely, a smaller reference scattering coefficient indicates that the atmospheric scattering effect is weaker, which will cause the estimated transmittance to be larger overall. For each target band i, the pixel value I of its dark channel image is i Substitute the obtained atmospheric illumination parameter A into the preset transmittance formula. The exponential term in the formula It reflects the attenuation effect of haze on electromagnetic wave transmission, among which molecule I i represents the dark channel characteristics of the local area, and the denominator A plays a normalization role. Through exponential operation, the dark channel characteristics can be converted into transmittance values ​​that conform to physical laws. Due to the introduction of the reference scattering coefficient ω, the estimated transmittance can better adapt to different degrees of haze weather conditions.

[0044] The implementation of this step successfully converts image features into transmittance parameters with clear physical meaning through a transmittance estimation method driven by a physical model. The preset transmittance formula not only takes into account the physical mechanism of haze scattering, but also maintains the simplicity of calculation, and can effectively handle the effects of haze in different bands and degrees. By adjusting the reference scattering coefficient, it can flexibly adapt to different haze weather conditions and improve the accuracy and applicability of transmittance estimation. The estimated transmittance not only maintains the spatial distribution information of the dark channel characteristics, but also has a reasonable numerical range, providing reliable parameter support for subsequent image restoration.

[0045] Step 304: Generate a transmittance distribution graph of each target waveband based on the transmittance of each target waveband.

[0046] Specifically, the transmittance data of each target band is first normalized. The transmittance value is mapped to the grayscale value range [0, 255] of the standard 8-bit image using a linear mapping method. This mapping maintains the relative size relationship of the transmittance while providing sufficient grayscale levels to show subtle changes. In the generated distribution map, high transmittance areas (lightly affected by haze) are presented as brighter grayscale values, and low transmittance areas (heavily affected by haze) are presented as darker grayscale values. To further enhance the visualization of the transmittance distribution, pseudo-color enhancement technology can be used. The grayscale value is converted into a more distinguishable color display through a preset color mapping table. For example, a gradient color band from blue to red can be used, where blue corresponds to high transmittance areas, red corresponds to low transmittance areas, and the intermediate transition areas are represented by corresponding gradient tones. This color coding method can more clearly show the spatial variation trend of transmittance. This step converts the transmittance data into an intuitive distribution map through standardized image processing, which not only retains the spatial distribution information of the transmittance, but also enhances the readability of the data. The transmittance distribution maps of multiple target bands can be compared and analyzed to reveal the impact of haze on different bands and provide a reference for accurate haze removal.

[0047] Step 103: For each target band, dehaze the target band according to the atmospheric illumination parameters and the transmittance distribution map to obtain an initial dehazed image of the target band.

[0048] The initial dehazed image refers to the restored image obtained by processing the original image affected by haze through the atmospheric scattering model. It reflects the radiation characteristics of the ground object after removing the atmospheric scattering effect. This image is the preliminary result obtained by inversion of the physical model, which retains the basic spectral information of the ground object, but may require further optimization processing.

[0049] Specifically, the obtained atmospheric illumination parameters and transmittance distribution map are used to perform dehazing processing on each target band. This processing is based on the atmospheric scattering model, and the original radiation characteristics of the ground object are restored by eliminating the influence of atmospheric scattering. Dehazing processing is the core step of the entire algorithm, and its purpose is to restore the image affected by haze to a clear ground object image by inverting the physical model. In specific implementation, for example, the image restoration formula based on the atmospheric scattering model can be used: J(x, y) = (I(x, y)-A) / t(x, y)+A, where J(x, y) is the initial dehazing image after restoration, I(x, y) is the original image, A is the atmospheric illumination parameter, and t(x, y) is the transmittance. This formula reflects the physical process of image degradation and restoration, where the term (I(x, y)-A) represents the removal of the atmospheric illumination influence, divided by t(x, y) represents the compensation of atmospheric transmission attenuation, and finally the addition of the atmospheric illumination parameter A represents the retention of a moderate atmospheric effect. This processing method not only takes into account the physical mechanism of atmospheric scattering, but also avoids the image distortion that may be caused by excessive dehazing. In actual processing, it is necessary to pay attention to the problem that too small a transmittance value may lead to excessive dehazing. When the transmittance is close to zero, the division operation will cause the pixel value to be abnormally amplified, resulting in unnaturally bright areas. To avoid this situation, it is necessary to set a lower limit threshold for the transmittance (for example, 0.1), and when the transmittance somewhere is lower than the threshold, it is set to the threshold value. This constraint can ensure the stability of the dehazing process and avoid the phenomenon of local over-enhancement.

[0050] Based on the above embodiment, as an optional embodiment, in step 103: performing haze removal processing on the target band according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial haze removal image of the target band, this step may also include the following steps: Step 401: Obtain the original pixel value of each pixel in the target band and the transmittance corresponding to each pixel in the transmittance distribution map; calculate the target pixel value of each pixel after dehazing based on the atmospheric illumination parameters and the original pixel value and transmittance of each pixel.

[0051] Specifically, it is necessary to perform dehazing processing on each pixel point of the target band to restore the real radiation characteristics of the ground object. This pixel-level processing method is based on the atmospheric scattering model. By combining the original pixel value, transmittance and atmospheric illumination parameters, it can effectively remove the influence of haze on the radiation information of the ground object. Since the influence of haze on the image is spatially non-uniform, it is necessary to process each pixel point separately to ensure the accuracy of the dehazing effect. First, the original pixel value I(x, y) of each pixel point (x, y) position is obtained from the target band image, and the transmittance value t(x, y) corresponding to the position is obtained from the transmittance distribution map. For each pixel point, its original pixel value I(x, y), transmittance t(x, y) and the obtained atmospheric illumination parameter A are substituted into the image restoration formula: J(x, y) = (I(x, y)-A) / t(x, y)+A, and the target pixel value J(x, y) after dehazing of the pixel point is calculated. Among them, (I(x, y)-A) represents the removal of the diffuse component of atmospheric illumination, divided by t(x, y) represents the compensation for the attenuation during atmospheric transmission, and finally A is added to retain a moderate atmospheric effect. In order to avoid numerical instability when the transmittance is small, it is necessary to set a lower limit threshold t0 (usually 0.1) for the transmittance. When the transmittance t(x, y) of a pixel point is less than t0, it is limited to t0, that is: t(x, y) = max(t(x, y), t0). This constraint can prevent image distortion caused by excessive dehazing and ensure the rationality of the processing results. At the same time, the calculated target pixel value also needs to be limited in value range to ensure that it falls within the valid numerical range.

[0052] Step 402: combining the target pixel values ​​of each pixel after dehazing to obtain an initial dehazing image of the target band.

[0053] Specifically, first create an image matrix with the same spatial resolution and data format as the original image to store the target pixel value after dehazing. According to the spatial position relationship of the pixel points, fill the target pixel value J(x, y) corresponding to each position (x, y) into the corresponding matrix position. During the filling process, the spatial topological relationship of the pixels needs to be kept unchanged to ensure that the geometric features of the image are accurately preserved. For pixels in the edge area of ​​the image, special attention should be paid to maintaining the smoothness of the transition between them and adjacent pixels to avoid obvious boundary effects. In order to ensure the quality of the combined image, the target pixel value needs to be normalized. According to the storage format of the image data (such as 8 bits, 16 bits, etc.), the target pixel value is linearly mapped to the corresponding value range. At the same time, it is necessary to check and process possible outliers to ensure that the final initial dehazing image has a reasonable pixel value distribution. If obvious discontinuity or anomalies are found in the local area, appropriate smoothing is required to improve the transition effect. This step successfully constructs an initial dehazing image reflecting the true characteristics of the ground object through reasonable pixel combination. The combined image not only maintains the dehazing effect of each pixel, but also ensures the visual continuity and data integrity of the overall image.

[0054] Step 104: performing fusion processing on the initial dehazed images of each target band to obtain a dehazed image corresponding to the remote sensing image to be processed.

[0055] Among them, the dehazed image refers to the final image obtained by fusing the initial dehazed images of each target band. It is a high-quality remote sensing image obtained by removing the influence of atmospheric scattering and optimizing fusion based on the physical model and combining multi-band information, which effectively eliminates the haze effect in the original image and accurately restores the characteristics of the ground objects.

[0056] Specifically, the initial dehazed images of each target band need to be fused to form a complete multispectral dehazed image. The necessity of this fusion process lies in that the initial dehazed images of different bands may have different dehazed degrees, and these differences need to be balanced and coordinated through fusion processing; at the same time, the fusion of multi-band images can make full use of the spectral information of different bands to provide a more comprehensive expression of ground object features. Specifically, a weight-based multi-band fusion method is adopted. First, the quality of the initial dehazed image of each target band is evaluated, including calculating indicators such as image clarity, signal-to-noise ratio, and spectral fidelity. According to the evaluation results, a corresponding weight coefficient wi is assigned to each band. The weight assignment needs to consider the importance of the band in ground object recognition and the reliability of the dehazed effect. For bands with clearer feature expression and better dehazed effect, a larger weight is assigned; for bands that may be over-processed or have information loss, their weights are reduced. The fusion process adopts a weighted average strategy. For each pixel position (x, y) in the image, the calculation formula of the fused pixel value F(x, y) is: F(x, y) = ∑(wi×Ji(x, y)) / ∑wi, where Ji(x, y) represents the pixel value of the initial dehazed image of the i-th band at the position (x, y). In order to maintain the spectral characteristics of the image, the fusion process needs to avoid excessive changes in the spectral relationship between bands while ensuring the enhancement of spatial details. A local adaptive weight adjustment mechanism can be introduced to dynamically adjust the fusion weight according to the image characteristics of different regions. The spatial details of the objects in the fused image are better maintained and enhanced, and the boundaries of different types of objects are clearer; secondly, the spectral characteristics of the image are reasonably maintained, avoiding the spectral distortion that may be caused by single-band processing; thirdly, the differences in the dehazed effects of different bands are effectively coordinated, forming a more balanced overall effect.

[0057] Based on the above embodiment, as an optional embodiment, in step 104: performing fusion processing on the initial dehazed images of each target band to obtain the dehazed images corresponding to the remote sensing image to be processed, this step may also include the following steps: Step 501: determining the spectral similarity between the initial dehazed images of the target bands based on the band spectral characteristics in the initial dehazed images of the target bands.

[0058] Among them, the band spectral feature refers to the characteristic information set that reflects the radiation characteristics of the ground objects in the initial dehazed image of the target band. It contains information on the statistical distribution characteristics of pixel values ​​in the image, spectral response patterns, spatial distribution characteristics, and other aspects, reflecting the radiation response characteristics and imaging characteristics of different ground objects in specific bands.

[0059] Spectral similarity refers to a numerical indicator that quantitatively describes the degree of correlation between the spectral characteristics of the initial dehazed images in different target bands. It reflects the closeness of the images in different bands in terms of the spectral response patterns of the ground objects, and quantitatively expresses the similarity between bands through mathematical methods such as the normalized mutual correlation coefficient.

[0060] Specifically, it is necessary to first extract the spectral features of the initial dehazed images of each target band. For the initial dehazed images of any two bands, the spectral similarity between them is calculated. The normalized cross-correlation coefficient is used as the similarity metric, which is obtained by calculating the ratio of the covariance of the pixel values ​​of the two band images to their respective standard deviations. Specifically, it is necessary to first calculate the mean of the two band images, then calculate the deviation of each pixel from the mean, and divide the sum of the deviation products of the pixels at the corresponding positions of the two bands by the product of the standard deviations of the two bands to obtain the final similarity value. In order to improve the reliability of the similarity calculation, the spectral feature differences in the local area need to be considered. The sliding window method is used to calculate the local similarity in different areas of the image to form a similarity distribution map. The selection of the window size needs to balance the computational efficiency and the integrity of the feature expression. For each local area, in addition to calculating the normalized cross-correlation coefficient, the spectral gradient consistency between the bands needs to be considered to more comprehensively describe the similarity relationship between the bands. This step successfully quantifies the correlation between the initial dehazed images of different bands through the calculation of spectral similarity. The calculation results form a similarity matrix, in which each element represents the degree of similarity between the corresponding band pairs. A high similarity value indicates that the two bands have similar ground feature response characteristics and are suitable for a larger fusion weight; a low similarity value indicates that there are significant spectral differences between the bands.

[0061] Step 502: Determine the fusion weight of the initial dehazed image of each target band according to the similarity of each spectrum.

[0062] Among them, the fusion weight refers to the numerical coefficient used to adjust the contribution of each target band in the fusion process of the multi-band initial dehazing image. It is a set of normalized parameters that reflect the importance of different bands in the fusion process, taking into account factors such as the spectral similarity between bands, the importance of the bands themselves, and local spatial characteristics.

[0063] Specifically, first, it is necessary to comprehensively evaluate the spectral similarity between each band and all other bands. For each target band, the average similarity between it and other bands is calculated. This average similarity reflects the representativeness of the band in the entire band group. At the same time, considering the different importance of different bands in the expression of ground feature characteristics, it is necessary to introduce a band importance weight factor. This factor can be determined based on indicators such as the contribution of the band in target recognition and the signal-to-noise ratio level. For example, for vegetation monitoring, the near-infrared band has a higher importance weight; for water body monitoring, the weight of the visible light band needs to be emphasized. When determining the specific fusion weight, an adaptive weighting strategy based on similarity is adopted. When the average similarity of a band with other bands is high, it means that the band contains more common information and should be given a larger weight; when the similarity of a band with other bands is low, it means that the band may contain unique ground feature information and its characteristics need to be maintained through appropriate weights. In addition, the spatial local characteristics of the bands also need to be considered. For the boundaries of objects or areas with complex textures, the weights can be dynamically adjusted according to the local similarity to better maintain the detail features. This step achieves the optimal integration of multi-band information by reasonably allocating fusion weights.

[0064] Step 503: weighted fusion is performed on the initial dehazed images of each target band according to each fusion weight, so as to obtain a dehazed image corresponding to the remote sensing image to be processed.

[0065] Specifically, it is necessary to ensure that all the initial dehazed images to be fused have the same spatial resolution and registration accuracy. For each pixel position, the pixel values ​​of the initial dehazed images of each target band are multiplied by their corresponding fusion weights, and then all weighted pixel values ​​are added to obtain the pixel value of the fused image at that position. This process needs to be performed pixel by pixel throughout the entire image to ensure the integrity and continuity of the fusion result. In order to improve the fusion effect, the changes in local spatial features need to be considered in the weighting process. For areas with obvious boundaries or texture features of objects, the weights can be adjusted in a local adaptive manner to better maintain spatial details. At the same time, in order to avoid numerical overflow or truncation during the fusion process, the fusion results need to be properly normalized so that the final pixel values ​​are distributed within a reasonable range. This weighted fusion method not only improves the dehazed effect, but also maintains the spectral and spatial integrity of the image, providing a high-quality data basis for subsequent remote sensing applications. The dehazed image finally obtained through this process not only eliminates the influence of atmospheric pollution, but also maintains the intrinsic characteristics of the objects, achieving an overall improvement in image quality.

[0066] Reference Figure 2 , a remote sensing image dehazing and haze processing system provided in an embodiment of the present application, the system comprises: an image acquisition module, a band determination module, a parameter determination module, and an image processing module, wherein: An image acquisition module, used for acquiring remote sensing images to be processed; The band determination module is used to extract the band data of multiple bands in the remote sensing image to be processed, and determine the reference band and multiple target bands based on the data of each band; The parameter determination module is used to determine the atmospheric illumination parameters based on the reference band and calculate the transmittance distribution map of each target band; the image processing module is used to perform haze removal processing on each target band according to the atmospheric illumination parameters and the transmittance distribution map to obtain the initial haze removal image of the target band; the initial haze removal images of each target band are fused to obtain the haze removal image corresponding to the remote sensing image to be processed.

[0067] On the basis of the above embodiment, the band determination module is also used to perform edge detection on the band data of each band to obtain an edge detection image of each band data; determine the number of edge pixels in each edge detection image, and use the number of each edge pixel as the clarity value of the corresponding band; in each band, determine the band with the largest clarity value as the reference band, and determine the remaining bands as target bands.

[0068] Based on the above embodiment, the parameter determination module is also used to obtain a dark channel image of a reference band; divide the dark channel image into multiple image blocks according to a preset size, and determine the average brightness value of each image block; select a preset number of image blocks in order from large to small in average brightness value; calculate the average pixel value of each selected image block in the reference band to obtain atmospheric illumination parameters.

[0069] On the basis of the above embodiment, the parameter determination module is also used to obtain the dark channel image of each target band; calculate the transmittance of each target band according to the pixel value of the dark channel image of each target band and the atmospheric illumination parameters; and generate the transmittance distribution map of each target band based on the transmittance of each target band.

[0070] On the basis of the above embodiment, the parameter determination module is further used to substitute the pixel value of the dark channel image of each target band and the atmospheric illumination parameter into the preset transmittance formula to obtain the transmittance of each target band; wherein the preset transmittance formula is: Where, t i represents the transmittance of the i-th target band, ω represents the reference scattering coefficient, I i represents the pixel value of the dark channel image of the i-th target band, and A represents the atmospheric illumination parameter.

[0071] On the basis of the above embodiment, the image processing module is also used to obtain the original pixel value of each pixel point in the target band and the transmittance corresponding to each pixel point in the transmittance distribution map; calculate the target pixel value of each pixel point after dehazing according to the atmospheric illumination parameters and the original pixel value and transmittance of each pixel point; combine the target pixel values ​​of each pixel point after dehazing to obtain the initial dehazed image of the target band.

[0072] On the basis of the above embodiments, the image processing module is also used to determine the spectral similarity between the initial dehazed images of each target band based on the band spectral characteristics in the initial dehazed images of each target band; determine the fusion weights of the initial dehazed images of each target band according to the spectral similarities; perform weighted fusion on the initial dehazed images of each target band according to the fusion weights to obtain the dehazed image corresponding to the remote sensing image to be processed.

[0073] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0074] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0075] The communication bus 302 is used to realize the connection and communication between these components.

[0076] The user interface 303 may include a display interface and a camera interface. The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0077] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0078] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0079] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a remote sensing image dehazing processing method.

[0080] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing a remote sensing image dehaze processing method in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0081] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0086] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0087] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A remote sensing image dehazing method, characterized in that: include: Acquire remote sensing images to be processed; Extracting band data of multiple bands in the remote sensing image to be processed, and determining a reference band and multiple target bands based on each of the band data; Based on the reference band, determine the atmospheric illumination parameters, and calculate the transmittance distribution map of each target band; For each of the target wavebands, performing dehazing processing on the target waveband according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial dehazing image of the target waveband; The initial dehazed images of the target bands are fused to obtain dehazed images corresponding to the remote sensing images to be processed.

2. The remote sensing image dehazing processing method according to claim 1, characterized in that: The step of determining a reference band and a plurality of target bands based on the band data comprises: Performing edge detection on the band data of each of the bands to obtain an edge detection image of the band data; Determine the number of edge pixels in each edge detection image, and use the number of edge pixels in each edge detection image as the clarity value of the corresponding band; Among the bands, the band with the largest clarity value is determined as a reference band, and the remaining bands are determined as target bands.

3. The remote sensing image dehazing processing method according to claim 1, characterized in that: The step of determining the atmospheric illumination parameter based on the reference band includes: Acquire a dark channel image of the reference band; Dividing the dark channel image into a plurality of image blocks according to a preset size, and determining an average brightness value of each of the image blocks; Selecting a preset number of image blocks in descending order of the average brightness values; The average pixel value of each of the selected image blocks in the reference band is calculated to obtain the atmospheric illumination parameter.

4. The remote sensing image dehazing processing method according to claim 1, characterized in that: The calculating of the transmittance distribution diagram of each target waveband comprises: Acquire dark channel images of each target band; Calculating the transmittance of each target band according to the pixel value of the dark channel image of each target band and the atmospheric illumination parameter; Based on the transmittance of each target wavelength band, a transmittance distribution graph of each target wavelength band is generated.

5. The remote sensing image dehazing processing method according to claim 4, characterized in that: The calculating the transmittance of each target band according to the pixel value of the dark channel image of each target band and the atmospheric illumination parameter comprises: substituting the pixel value of the dark channel image of each target band and the atmospheric illumination parameter into a preset transmittance formula to obtain the transmittance of each target band; Wherein, the preset transmittance formula is: Where, t i represents the transmittance of the i-th target band, ω represents the reference scattering coefficient, I i represents the pixel value of the dark channel image of the i-th target band, and A represents the atmospheric illumination parameter.

6. The remote sensing image dehazing processing method according to claim 1, characterized in that: The dehazing process is performed on the target band according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial dehazing image of the target band, including: Obtaining the original pixel value of each pixel in the target band and the transmittance corresponding to each pixel in the transmittance distribution map; Calculating the target pixel value of each pixel after removing haze according to the atmospheric illumination parameter and the original pixel value and transmittance of each pixel; The target pixel values ​​after dehazing of each pixel point are combined to obtain an initial dehazed image of the target band.

7. The remote sensing image dehazing processing method according to claim 1, characterized in that: The fusing process of the initial dehazed images of the target bands to obtain the dehazed images corresponding to the remote sensing images to be processed includes: Determining the spectral similarity between the initial dehazed images of the target bands based on the band spectral characteristics in the initial dehazed images of the target bands; Determining the fusion weight of the initial dehazed image of each target band according to the spectral similarities; The initial dehazed images of the target bands are weightedly fused according to the fusion weights to obtain a dehazed image corresponding to the remote sensing image to be processed.

8. A remote sensing image dehazing and haze processing system, characterized in that: The system comprises: An image acquisition module, used for acquiring remote sensing images to be processed; A band determination module, used for extracting band data of multiple bands in the remote sensing image to be processed, and determining a reference band and multiple target bands based on each of the band data; A parameter determination module, used to determine the atmospheric illumination parameters based on the reference band, and calculate the transmittance distribution map of each target band; The image processing module is used to perform dehazing processing on each target band according to the atmospheric illumination parameter and the transmittance distribution map to obtain an initial dehazing image of the target band; and perform fusion processing on the initial dehazing image of each target band to obtain a dehazing image corresponding to the remote sensing image to be processed.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the remote sensing image dehaze processing method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the remote sensing image dehaze processing method according to any one of claims 1 to 7 is executed.

Images