Tracing cloud tracking method and device based on satellite remote sensing data and electronic equipment

Abstract

The invention provides a tracer cloud tracking method and device based on satellite remote sensing data and electronic equipment. Tracer cloud can be efficiently and accurately tracked and detected. The method comprises the following steps: acquiring a first satellite image and a second satellite image; performing similarity analysis on the first satellite image and the second satellite image, and respectively determining an original area and a change area in the first satellite image and the second satellite image; performing image enhancement transformation on the first satellite image and the second satellite image to correspondingly generate a first enhanced image and a second enhanced image; and performing image matching on the first enhanced image and the second enhanced image, and determining a cloud target corresponding to the tracing cloud of the original area in the change area. The device comprises an image acquisition module, a similarity analysis module, an image enhancement module and a target tracking module. The electronic equipment is used for executing the tracing cloud tracking method.

Description

Technical Field

[0001] One or more embodiments of the present application relate to the field of satellite remote sensing technology, and in particular, to a tracer cloud tracking method, device and electronic equipment based on satellite remote sensing data. Background Art

[0002] In the technical fields of satellite remote sensing and weather forecasting, accurate and efficient tracking and monitoring of tracer clouds is an important basic condition for conducting aerosol prediction research. In some related technologies, tracer tracking is carried out by image matching based on satellite remote sensing images. However, due to the rich content and huge amount of data of satellite remote sensing images, image matching directly based on satellite remote sensing images requires high computing power, low computing efficiency, and poor overall matching and tracking effect. In other related technologies, deep learning methods are used to use neural networks to track tracer clouds. In order to build a mature deep neural network model, a large amount of sample image data is often required as the training basis. In the field of satellite remote sensing and weather forecasting technology, the complexity of actual meteorological conditions determines that it is difficult to obtain sufficient amount of sample data that meets the requirements. Therefore, the tracking method using deep learning methods is often unsatisfactory. Summary of the invention

[0003] In view of this, an object of one or more embodiments of the present application is to propose a tracer cloud tracking method, device and electronic equipment based on satellite remote sensing data, which can track and detect tracer clouds efficiently and accurately.

[0004] Based on the above objectives, in a first aspect, one or more embodiments of the present application provide a tracer cloud tracking method based on satellite remote sensing data, comprising:

[0005] Acquire a first satellite image and a second satellite image from high-resolution satellite remote sensing video data;

[0006] By performing similarity analysis on the first satellite image and the second satellite image, a changed area is determined in the second satellite image, and an original area corresponding to the changed area is determined in the first satellite image, wherein the original area contains a tracer cloud;

[0007] Performing image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively;

[0008] By performing image matching on the first enhanced image and the second enhanced image, a cloud target corresponding to the tracer cloud in the original area is determined in the changed area.

[0009] Optionally, the determining the changed area in the second satellite image by performing similarity analysis on the first satellite image and the second satellite image includes:

[0010] Extracting grid feature data of the first satellite image and the second satellite image using a convolutional neural network;

[0011] Calculating Mahalanobis distances of a plurality of image grids of the second satellite image compared to the first satellite image according to the grid feature data;

[0012] The Mahalanobis distances of the plurality of image grids are compared with a region segmentation threshold, and a plurality of image grids whose Mahalanobis distances are smaller than the region segmentation threshold are selected to form the change region.

[0013] Optionally, the method for determining the region segmentation threshold includes:

[0014] Acquire a reference sample image and a marked sample image corresponding to the reference sample image;

[0015] Calculating and determining the Mahalanobis distance between the changed area and the unchanged area of ​​the marked sample image compared with the reference sample image, and generating a Mahalanobis distance histogram;

[0016] The region segmentation threshold is determined according to the Mahalanobis distance histogram.

[0017] Optionally, performing image enhancement transformation on the first satellite image and the second satellite image respectively includes:

[0018] Performing piecewise linear transformation on the image grayscales of the first satellite image and the second satellite image;

[0019] Perform a Gaussian low-pass filter transformation on frequency domain data corresponding to the first satellite image and the second satellite image.

[0020] Optionally, the transformation formula for performing piecewise linear transformation on the image grayscale is:

[0021]

[0022] Among them, h represents the grayscale value of the pixel after transformation, f(x,y) represents the grayscale value of the pixel (x,y) before transformation, L represents the maximum grayscale of the image, and a, b, c, d represent the grayscale segmentation values.

[0023] Optionally, performing Gaussian low-pass filter transformation on frequency domain data corresponding to the first satellite image and the second satellite image includes:

[0024] Using a two-dimensional Gaussian low-pass filter to perform filtering transformation on the frequency domain data corresponding to the first satellite image and the second satellite image;

[0025] The transfer function of the two-dimensional Gaussian low-pass filter is:

[0026]

[0027] Where D(u,v) represents the distance between the point (u,v) in the spectrum image and the origin of the Fourier transform, and D0 represents the cutoff frequency.

[0028] Optionally, determining a cloud target corresponding to the tracer cloud in the original area in the changed area by performing image matching on the first enhanced image and the second enhanced image includes:

[0029] Determine a target window in the first enhanced image according to the original image, determine a search window in the second enhanced image according to the changed area, call the target window to match the search window, and determine a forward matching point set;

[0030] Determine a target window in the second enhanced image according to the changed area, determine a search window in the second enhanced image according to the original area, call the target window to match the search window, and determine a reverse matching point set;

[0031] Taking the intersection of the forward matching point set and the reverse matching point set as the successful matching point set;

[0032] A plurality of target points corresponding to the tracer cloud in the original area are determined in the changed area according to the successful matching point set, and the cloud target corresponding to the tracer cloud is determined according to the plurality of target points.

[0033] Optionally, calling the target window to match the search window includes:

[0034] Calculating correlation coefficients between a plurality of pixels in the target window and a plurality of pixels in the search window, and determining matching points between the target window and the search window according to the correlation coefficients;

[0035] Among them, the correlation coefficient is:

[0036]

[0037] , ρ represents the correlation coefficient, g(c,r) represents the grayscale value of the pixel (c,r), (c1,r1) represents the pixel coordinates of the target window, (c2,r2) represents the pixel coordinates of the search window, i,j are the pixel indexes of the target window and the search window respectively, and the value range of i,j is 1 to n. Based on the above purpose, in a second aspect, one or more embodiments of the present application also provide a tracer cloud tracking device based on satellite remote sensing data, including:

[0038] An image acquisition module, used to acquire a first satellite image and a second satellite image from high-resolution satellite remote sensing video data;

[0039] a similarity analysis module, configured to perform similarity analysis on the first satellite image and the second satellite image, determine a changed area in the second satellite image, and determine an original area corresponding to the changed area in the first satellite image, wherein the original area contains a tracer cloud;

[0040] an image enhancement module, configured to perform image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively; and

[0041] The target tracking module is used to determine a cloud target corresponding to the tracer cloud in the original area in the changed area by performing image matching on the first enhanced image and the second enhanced image.

[0042] Based on the above-mentioned purpose, in a third aspect, one or more embodiments of the present application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the tracer cloud tracking method based on satellite remote sensing data as described in the first aspect is implemented.

[0043] From the above description, it can be seen that a cloud tracking method, device and electronic device based on satellite remote sensing data provided by one or more embodiments of the present application have the following beneficial technical effects:

[0044] (1) By performing similarity analysis on the first satellite image and the second satellite image, the original area and the corresponding changed area are determined in the first satellite image and the second satellite image respectively, thereby greatly narrowing the data range that needs to be paid attention to and greatly reducing the amount of data calculation for subsequent image matching, thereby improving the calculation efficiency; by performing enhancement transformation on the first satellite image and the second satellite image, the information data of the satellite images are optimized and deleted in a targeted manner, thereby improving the targeting and accuracy of subsequent image matching calculations; finally, image matching is performed based on the original area and the changed area, so that the cloud target corresponding to the tracer cloud is determined in the changed area according to the matching result, and tracking and detection of the tracer cloud can be achieved.

[0045] (2) When performing image matching between the first enhanced image and the second enhanced image based on the original area and the changed area, a bidirectional correlation coefficient method is used for matching. Only when both the forward and reverse matching are passed can the matching be considered successful. This method verifies the single matching result and eliminates the influence of noise points, thereby improving the matching accuracy and ensuring the accuracy of the matching calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate one or more embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only one or more embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a tracer cloud tracking method based on satellite remote sensing data provided by one or more embodiments of the present application;

[0048] Figure 2 A schematic diagram of a similarity analysis method in a tracer cloud tracking method based on satellite remote sensing data provided by one or more embodiments of the present application;

[0049] Figure 3 A piecewise linear transformation function diagram in a tracer cloud tracking method based on satellite remote sensing data provided by one or more embodiments of the present application;

[0050] Figure 4 A schematic diagram of a bidirectional correlation coefficient matching method in a tracer cloud tracking method based on satellite remote sensing data provided by one or more embodiments of the present application;

[0051] Figure 5A schematic diagram of the structure of a tracer cloud tracking device based on satellite remote sensing data provided by one or more embodiments of the present application;

[0052] Figure 6 A schematic diagram of the structure of a cloud tracking electronic device based on satellite remote sensing data provided by one or more embodiments of the present application. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present application should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in one or more embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] The technical solution of this application is described below in conjunction with specific embodiments.

[0056] On the one hand, an embodiment of the present application provides a tracer cloud tracking method based on satellite remote sensing data.

[0057] like Figure 1 As shown, one or more optional embodiments of the present application provide a tracer cloud tracking method based on satellite remote sensing data, including:

[0058] S1: Acquire a first satellite image and a second satellite image from high-resolution satellite remote sensing video data.

[0059] A first satellite image and a second satellite image can be captured successively from high-resolution satellite remote sensing video data, wherein the first satellite image contains a tracer cloud, and the second satellite image contains a cloud target corresponding to the tracer cloud in the first satellite image. In some embodiments, the first satellite image and the second satellite image can be two connected frames of images, for example, the second satellite image is the current frame image in the high-resolution satellite remote sensing video, and the first satellite image is the previous frame image. The purpose of the technical solution of the present application is to track the tracer cloud of the previous frame image in the current frame image. In some embodiments, the first satellite image and the second satellite image can also be separated by several frames, and the time interval or the number of frame intervals between the first satellite image and the second satellite image can be flexibly adjusted and set according to actual conditions.

[0060] S2: By performing similarity analysis on the first satellite image and the second satellite image, a changed area is determined in the second satellite image, and an original area corresponding to the changed area is determined in the first satellite image, wherein the original area contains a tracer cloud.

[0061] It is understandable that the movement changes of the tracer cloud are reflected in the satellite remote sensing data as changes in the satellite image content. Therefore, in some optional embodiments, by performing a similarity analysis on the first satellite image and the second satellite image, the area where the second satellite image is different from the first satellite image, namely the changed area, can be determined, thereby narrowing the area that needs attention to the original area and the changed area.

[0062] S3: Performing image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively.

[0063] Image enhancement is to add some information or transform data to the original image by certain means, selectively highlight the features of interest in the image or suppress some unnecessary features in the image to meet the needs of special analysis. The first satellite image and the second satellite image can be enhanced separately, and the information content contained in the satellite images can be optimized and adjusted in a targeted manner to facilitate subsequent image matching analysis. Image enhancement transformation can include two types: spatial domain enhancement and frequency domain enhancement. Spatial domain enhancement methods include linear transformation, nonlinear transformation, histogram equalization, histogram normalization, and spatial domain filtering, while frequency domain enhancement methods include smoothing, sharpening, frequency domain high-pass filtering, and frequency domain low-pass filtering.

[0064] S4: Determine, in the changed area, a cloud target corresponding to the tracer cloud in the original area by performing image matching on the first enhanced image and the second enhanced image.

[0065] The focus range is positioned at the original area in the first enhanced image and the changed area in the second enhanced image. The two images can be matched, and a plurality of points corresponding to the original area of ​​the first enhanced image can be determined in the changed area of ​​the second enhanced image, thereby further determining a plurality of points corresponding to the tracer cloud in the original area. Thus, the cloud target corresponding to the tracer cloud can be determined in the changed area, thereby realizing tracking and identification of the tracer cloud in the second satellite image.

[0066] The tracer cloud tracking method based on satellite remote sensing data performs similarity analysis on the first satellite image and the second satellite image, and determines the original area and the corresponding changed area in the first satellite image and the second satellite image respectively, thereby greatly narrowing the data range that needs to be paid attention to, and greatly reducing the amount of data calculation for subsequent image matching, thereby improving the calculation efficiency; by performing enhancement transformation on the first satellite image and the second satellite image, the information data of the satellite images is optimized and deleted in a targeted manner, which can improve the pertinence and accuracy of subsequent image matching calculations; finally, image matching is performed based on the original area and the changed area, so as to determine the cloud target corresponding to the tracer cloud in the changed area according to the matching result, and the tracking detection of the tracer cloud can be realized.

[0067] like Figure 2 As shown, in a tracer cloud tracking method based on satellite remote sensing data provided in one or more optional embodiments of the present application, the similarity analysis of the first satellite image and the second satellite image is performed to determine the changed area in the second satellite image, including:

[0068] S201: Extracting grid feature data of the first satellite image and the second satellite image using a convolutional neural network.

[0069] The convolutional neural network model can be used to extract features from high spatial resolution satellite remote sensing images to obtain downsampled grid feature data. The grid feature data has a high degree of abstraction and can adapt to complex deformation, light and other changes, while also being able to well describe the overall characteristics of the target.

[0070] S202: Calculate Mahalanobis distances between a plurality of image grids of the second satellite image and the first satellite image according to the grid feature data.

[0071] The Mahalanobis distance can be used to characterize the phase velocity of the first satellite image and the second satellite image. The Mahalanobis distance between the corresponding grids is calculated based on the grid feature data of the grids of the first satellite image and the grid feature data of the grids of the second satellite image.

[0072] S203: Compare the Mahalanobis distances of the plurality of image grids with a region segmentation threshold, and select a plurality of image grids whose Mahalanobis distances are smaller than the region segmentation threshold to form the change region.

[0073] The Mahalanobis distance is used to characterize the similarity of image content. For image grids whose Mahalanobis distance is less than the region segmentation threshold, it means that the image content has changed significantly and belongs to the changed region. The region segmentation threshold is used as a standard to measure whether the image content has changed significantly and can be obtained based on historical image data.

[0074] In some optional embodiments of the present application, the method for determining the region segmentation threshold includes:

[0075] A reference sample image and a marked sample image corresponding to the reference sample image are obtained. The reference sample image is compared with the marked sample image, where unchanged areas and changed areas are marked.

[0076] The Mahalanobis distances between the changed area and the unchanged area of ​​the marked sample image compared with the reference sample image are calculated and determined, and a Mahalanobis distance histogram is generated. For the unchanged area and the changed area, there is a large difference in the corresponding Mahalanobis distances. The difference in the Mahalanobis distances of different areas can be intuitively determined based on the corresponding Mahalanobis distance histogram, so that the region segmentation threshold for dividing the unchanged area and the changed area can be determined based on the Mahalanobis distance histogram.

[0077] In a tracer cloud tracking method based on satellite remote sensing data provided in one or more optional embodiments of the present application, the performing image enhancement transformation on the first satellite image and the second satellite image respectively includes:

[0078] A piecewise linear transformation is performed on the image grayscales of the first satellite image and the second satellite image.

[0079] Perform a Gaussian low-pass filter transformation on frequency domain data corresponding to the first satellite image and the second satellite image.

[0080] Among them, the piecewise linear transformation is a spatial domain enhancement. As shown in the figure, the piecewise linear transformation can expand the grayscale range of useful information on the graphic and increase the contrast, while the grayscale range of the corresponding noise is compressed into a smaller area at the end.

[0081] The transformation formula for performing piecewise linear transformation on the grayscale of the image is:

[0082]

[0083] Wherein, h represents the gray value of the pixel after transformation, f(x,y) represents the gray value of the pixel (x,y) before transformation, L represents the maximum gray value of the image, and a, b, c, d represent the gray segmentation values. The gray segmentation values ​​a, b, c, d can be flexibly adjusted and set according to actual conditions.

[0084] (0,0)

[0085] Among them, the Gaussian low-pass filter transformation belongs to the frequency domain transformation. In some optional embodiments of the present application, the Gaussian low-pass filter transformation is performed on the frequency domain data corresponding to the first satellite image and the second satellite image, including:

[0086] Using a two-dimensional Gaussian low-pass filter to perform filtering transformation on the frequency domain data corresponding to the first satellite image and the second satellite image;

[0087] The transfer function of the two-dimensional Gaussian low-pass filter is:

[0088]

[0089] Where D(u,v) represents the distance between the point (u,v) in the spectrum image and the origin of the Fourier transform, and D0 represents the cutoff frequency.

[0090] The Gaussian low-pass filter variation retains low-frequency data information in the frequency domain, can suppress high frequencies reflecting edge features of sudden grayscale changes, and filters out isolated point noise contained in high frequencies, thus achieving a denoising and smoothing effect.

[0091] like Figure 4 As shown, in a tracer cloud tracking method based on satellite remote sensing data provided by one or more optional embodiments of the present application, the cloud target corresponding to the tracer cloud in the original area is determined in the changed area by performing image matching on the first enhanced image and the second enhanced image, including:

[0092] S401: determining a target window in the first enhanced image according to the original image, determining a search window in the second enhanced image according to the changed region, calling the target window to match the search window, and determining a forward matching point set.

[0093] The first enhanced image is used as the left image and the second enhanced image is used as the right image for forward matching. Matching points corresponding to multiple pixels in the target window are determined in the search window. The matching result is to determine multiple groups of matching points, which constitute the forward matching point set. For example, m1 in the search window is determined by image matching. ′ Point matches point m1 in the target window, and point m1 matches point m1 ′The points form a set of matching points (m1,m1 ′ ). P groups of matching points are determined by matching to form the forward matching point group [(m1,m1 ′ ),(m2,m2 ′ ),…,(m p ,m p ′ )].

[0094] S402: determining a target window in the second enhanced image according to the changed area, determining a search window in the second enhanced image according to the original area, calling the target window to match the search window, and determining a reverse matching point set.

[0095] In reverse matching, the left and right images are swapped, the second enhanced image is used as the left image, and the first enhanced image is used as the right image, and the target window and the search window are called for image matching. Reverse matching also determines multiple groups of matching points to form a reverse matching point set. For example, through image matching, m2 in the search window is determined ′ Point matches point m2 in the target window, and point m2 matches point m2 ′ The points form a set of matching points (m2,m2 ′ ). By matching, q groups of matching point groups are determined to form the reverse matching point group [(m2, m2 ′ ),(m3,m3 ′ ),…,(m p ,m p ′ ),…,(m q-2 ,m q-2 ′ )(m q-1 ,m q-1 ′ )]

[0096] S403: Take the intersection of the forward matching point set and the reverse matching point set as the successful matching point set. Taking the above two matching point sets as an example, the forward matching point set [(m1,m1 ′ ),(m2,m2 ′ ),…,(m p ,m p ′ )] and the reverse matching point group [(m2,m2 ′ ),(m3,m3 ′ ),…,(m p ,m p ′ ),…,(m q-2 ,m q-2 ′ )(m q-1 ,mq-1 ′ )] The intersection is [(m2,m2 ′ ),(m3,m3 ′ ),…,(m p ,m p ′ )].

[0097] S404: Determine a plurality of target points corresponding to the tracer cloud in the original area in the changed area according to the successful matching point set, and determine the cloud target corresponding to the tracer cloud according to the plurality of target points.

[0098] The tracer cloud tracking method based on satellite remote sensing data adopts the two-way correlation coefficient method for matching. Only when both the forward and reverse matching are passed can the matching be considered successful. This method verifies the single matching result and eliminates the influence of noise points. For example, in the forward matching point group (m1, m1 ′ ) is eliminated and fails to pass the verification, indicating that this matching point group is likely to be a noise point. Using such a two-way matching method can improve the matching accuracy and ensure the accuracy of the matching calculation results.

[0099] In a tracer cloud tracking method based on satellite remote sensing data provided by one or more optional embodiments of the present application, the calling of the target window to match the search window includes:

[0100] Calculating correlation coefficients between a plurality of pixels in the target window and a plurality of pixels in the search window, and determining matching points between the target window and the search window according to the correlation coefficients;

[0101] Among them, the correlation coefficient is:

[0102]

[0103] ρ represents the correlation coefficient, g(c,r) represents the grayscale value of the pixel (c,r), (c1,r1) represents the pixel coordinates of the target window, (c2,r2) represents the pixel coordinates of the search window, i and j are the pixel indexes of the target window and the search window respectively, and the value range of i and j are both 1 to n.

[0104] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0105] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0106] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a tracer cloud tracking device based on satellite remote sensing data.

[0107] refer to Figure 5 The cloud tracking device based on satellite remote sensing data comprises:

[0108] The image acquisition module 501 is used to acquire the first satellite image and the second satellite image from the high-resolution satellite remote sensing video data;

[0109] A similarity analysis module 502 is used to perform similarity analysis on the first satellite image and the second satellite image, determine a changed area in the second satellite image, and determine an original area corresponding to the changed area in the first satellite image, wherein the original area contains a tracer cloud;

[0110] An image enhancement module 503 is used to perform image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively; and

[0111] The target tracking module 504 is configured to determine, in the changed area, a cloud target corresponding to the tracer cloud in the original area by performing image matching on the first enhanced image and the second enhanced image.

[0112] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0113] The device of the above embodiment is used to implement the corresponding tracer cloud tracking method based on satellite remote sensing data in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0114] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the tracer cloud tracking method based on satellite remote sensing data described in any of the above embodiments is implemented.

[0115] Figure 6 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0116] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0117] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0118] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0119] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0120] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0121] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0122] The electronic device of the above-mentioned embodiment is used to implement the corresponding tracer cloud tracking method based on satellite remote sensing data in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0123] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the tracer cloud tracking method based on satellite remote sensing data as described in any of the above embodiments.

[0124] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0125] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the tracer cloud tracking method based on satellite remote sensing data as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0126] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0127] In addition, to simplify the description and discussion, and in order not to make one or more embodiments of the present application difficult to understand, the known power / ground connections to the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making one or more embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which one or more embodiments of the present application will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present disclosure, it is obvious to those skilled in the art that one or more embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0128] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0129] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the scope of protection of this disclosure.

Claims

1. A cloud tracking method based on satellite remote sensing data, characterized in that: include: Acquire a first satellite image and a second satellite image from high-resolution satellite remote sensing video data; By performing similarity analysis on the first satellite image and the second satellite image, a changed area is determined in the second satellite image, and an original area corresponding to the changed area is determined in the first satellite image, wherein the original area contains a tracer cloud; Performing image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively; By performing image matching on the first enhanced image and the second enhanced image, a cloud target corresponding to the tracer cloud in the original area is determined in the changed area.

2. The method according to claim 1, characterized in that The determining a changed area in the second satellite image by performing similarity analysis on the first satellite image and the second satellite image includes: Extracting grid feature data of the first satellite image and the second satellite image using a convolutional neural network; Calculating Mahalanobis distances of a plurality of image grids of the second satellite image compared to the first satellite image according to the grid feature data; The Mahalanobis distances of the plurality of image grids are compared with a region segmentation threshold, and a plurality of image grids whose Mahalanobis distances are smaller than the region segmentation threshold are selected to form the change region.

3. The method according to claim 2, characterized in that The method for determining the region segmentation threshold comprises: Acquire a reference sample image and a marked sample image corresponding to the reference sample image; Calculating and determining the Mahalanobis distance between the changed area and the unchanged area of ​​the marked sample image compared with the reference sample image, and generating a Mahalanobis distance histogram; The region segmentation threshold is determined according to the Mahalanobis distance histogram.

4. The method according to claim 1, characterized in that The performing image enhancement transformation on the first satellite image and the second satellite image respectively includes: Performing piecewise linear transformation on the image grayscales of the first satellite image and the second satellite image; Perform a Gaussian low-pass filter transformation on frequency domain data corresponding to the first satellite image and the second satellite image.

5. The method according to claim 4, characterized in that The transformation formula for performing piecewise linear transformation on the grayscale of the image is: Among them, h represents the grayscale value of the pixel after transformation, f(x,y) represents the grayscale value of the pixel (x,y) before transformation, L represents the maximum grayscale of the image, and a, b, c, d represent the grayscale segmentation values.

6. The method according to claim 4, characterized in that The performing Gaussian low-pass filter transformation on the frequency domain data corresponding to the first satellite image and the second satellite image includes: Using a two-dimensional Gaussian low-pass filter to perform filtering transformation on the frequency domain data corresponding to the first satellite image and the second satellite image; The transfer function of the two-dimensional Gaussian low-pass filter is: Where D(u,v) represents the distance between the point (u,v) in the spectrum image and the origin of the Fourier transform, and D0 represents the cutoff frequency.

7. The method according to claim 1, characterized in that The determining, in the changed area, a cloud target corresponding to the tracer cloud in the original area by performing image matching on the first enhanced image and the second enhanced image comprises: Determine a target window in the first enhanced image according to the original image, determine a search window in the second enhanced image according to the changed area, call the target window to match the search window, and determine a forward matching point set; Determine a target window in the second enhanced image according to the changed area, determine a search window in the second enhanced image according to the original area, call the target window to match the search window, and determine a reverse matching point set; Taking the intersection of the forward matching point set and the reverse matching point set as the successful matching point set; A plurality of target points corresponding to the tracer cloud in the original area are determined in the changed area according to the successful matching point set, and the cloud target corresponding to the tracer cloud is determined according to the plurality of target points.

8. The method according to claim 7, characterized in that The calling the target window to match the search window includes: Calculating correlation coefficients between a plurality of pixels in the target window and a plurality of pixels in the search window, and determining matching points between the target window and the search window according to the correlation coefficients; Among them, the correlation coefficient is: Wherein, ρ represents the correlation coefficient, g(c,r) represents the grayscale value of the pixel (c,r), (c1,r1) represents the pixel coordinates of the target window, (c2,r2) represents the pixel coordinates of the search window, i and j are the pixel indexes of the target window and the search window respectively, and the value range of i and j are both 1 to n.

9. A cloud tracking device based on satellite remote sensing data, characterized in that: include: An image acquisition module, used to acquire a first satellite image and a second satellite image from high-resolution satellite remote sensing video data; a similarity analysis module, configured to perform similarity analysis on the first satellite image and the second satellite image, determine a changed area in the second satellite image, and determine an original area corresponding to the changed area in the first satellite image, wherein the original area contains a tracer cloud; An image enhancement module, used to perform image enhancement transformation on the first satellite image and the second satellite image to generate a first enhanced image and a second enhanced image respectively; as well as The target tracking module is used to determine a cloud target corresponding to the tracer cloud in the original area in the changed area by performing image matching on the first enhanced image and the second enhanced image.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

Images