Surveying and mapping method and system for dynamic remote sensing monitoring

Abstract

The invention relates to the technical field of river surveying and mapping, in particular to a surveying and mapping method and system for dynamic remote sensing monitoring, and the method comprises the steps: carrying out the edge detection of a remote sensing image, and obtaining a plurality of suspected river regions; analyzing gray level distribution characteristics of pixel points in the suspected river area to obtain a main river area of the remote sensing image; the method comprises the following steps: acquiring a plurality of embedded regions of a suspected river region and a main river region in a remote sensing image, analyzing the difference between the gray values of pixel points in the embedded regions and the gray values of pixel points in the main river region and the suspected river region, obtaining the fusion feature representation degree of the embedded regions, and further obtaining all branch river regions in the remote sensing image. And finishing river drawing. According to the method, post-processing is performed on the area of the to-be-mapped river according to the characteristic that when the branches of the to-be-mapped river merge into the main stream, the gray values of part of pixel points in the main stream can be influenced, river drawing is completed, and the complete and accurate mapped river is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of river surveying and mapping, and particularly relates to a surveying and mapping method and system for dynamic remote sensing monitoring. Background Art

[0002] Dynamic remote sensing monitoring technology is a technology that uses sensors carried on platforms such as satellites, airplanes, and drones to remotely and non-contactedly detect and measure the information on the earth's surface. Because this technology can provide surface information with a large range and high spatio-temporal resolution, it has become an important means in the field of surveying and mapping.

[0003] When surveying and mapping a river through dynamic remote sensing monitoring technology, a remote sensing satellite is used to take pictures of the river from the source of the river until the image of the river's estuary is captured, obtaining multiple remote sensing images of the river to be surveyed. Since the remote sensing images contain not only the river area but also non-river areas, it is necessary to obtain the river area from the remote sensing images. When obtaining the river area to be surveyed from the remote sensing images, because the colors of the tributaries and the main stream of the river to be surveyed may be different, when the tributaries of the river to be surveyed flow into the main stream, the main stream at some positions is composed of two regions with different colors, resulting in the existing methods being unable to obtain the complete area of the river in some cases. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a surveying and mapping method and system for dynamic remote sensing monitoring.

[0005] According to the first aspect of the embodiments of the present invention, a surveying and mapping method for dynamic remote sensing monitoring is provided, and the technical solutions adopted are as follows: Obtain multiple remote sensing images of the river to be surveyed; Perform edge detection on the remote sensing images to obtain multiple suspected river areas; Analyze the gray-scale distribution characteristics of the pixel points in the suspected river areas to obtain a main river area of the remote sensing images; Obtain multiple embedded areas of the suspected river areas and the main river area in the remote sensing images, and analyze the differences between the gray-scale values of the pixel points in the embedded areas and the gray-scale values of the pixel points in the main river area and the suspected river areas respectively, to obtain the blending feature expression degrees of the embedded areas; According to the blending feature expression degrees corresponding to all the embedded areas of the suspected river areas, obtain all the tributary river areas in the remote sensing images; Complete the drawing of the river according to the main river area and the tributary river areas.

[0006] In some embodiments of the present invention, edge detection is performed on the remote sensing image to obtain a plurality of suspected river regions, including: Perform edge detection on the remote sensing image to obtain a plurality of edges and edge detection regions in the remote sensing image; Record the edge detection regions that share an edge with the remote sensing image as suspected river regions to obtain a plurality of suspected river regions of the remote sensing image.

[0007] In some embodiments of the present invention, analyze the gray-scale distribution characteristics of the pixel points in the suspected river region to obtain a main river region of the remote sensing image, including: Analyze the dispersion degree of the gray-scale values of the pixel points in the suspected river region to obtain the possibility that the suspected river region is the main river region; Analyze the distribution characteristics of the gray-scale values of the pixel points in the suspected river region in the remote sensing image, and correct the possibility to obtain a corrected possibility; Take the suspected river region corresponding to the maximum corrected possibility as a main river region of the remote sensing image.

[0008] In some embodiments of the present invention, analyzing the distribution characteristics of the gray-scale values of the pixel points in the suspected river region in the remote sensing image includes: Optionally select a gray-scale value b, calculate the ratio of the number of pixel points with the gray-scale value b in the suspected river region to the number of pixel points with the gray-scale value b in the remote sensing image, and combine the number of pixel points with the gray-scale value b in the suspected river region to obtain the distribution characteristics of the gray-scale values of the pixel points in the suspected river region in the remote sensing image.

[0009] In some embodiments of the present invention, obtain a plurality of embedded regions of the suspected river region and the main river region in the remote sensing image, including: Obtain the skeletons of the main river region and the suspected river region; Draw a straight line parallel to the skeleton of the suspected river region across the common edge of the main river region and the suspected river region to obtain a number of suspected embedded regions; Determine whether the suspected embedded region belongs to the part of the main river region or the part of the suspected river region; Obtain the minimum circumscribed rectangle of each suspected embedded region; Analyze the ratio of the number of pixel points of another region that the minimum circumscribed rectangle contains but its corresponding suspected embedded region does not belong to to the total number of pixel points in the minimum circumscribed rectangle to obtain the embedding performance of the suspected embedded region. Set the embedding performance threshold, and obtain multiple embedding regions of the suspected river region and the main river region in the remote sensing image according to the embedding performance.

[0010] In some embodiments of the present invention, analyzing the difference distribution of the gray values of the pixel points in the embedding region with the gray values of the pixel points in the main river region and the suspected river region respectively to obtain the blending feature performance of the embedding region includes: Obtain multiple layer edges of the embedding region; Determine whether the embedding region belongs to the part of the main river region or the part of the suspected river region; If the embedding region belongs to the part of the suspected river region, analyze the first difference distribution of the gray value of each pixel point on the layer edge with the gray value of the pixel points in the main river region to obtain the main river region performance of each pixel point on the layer edge; If the embedding region belongs to the part of the main river region, analyze the second difference distribution of the gray value of each pixel point on the layer edge with the gray value of the pixel points in the suspected river region to obtain the suspected river region performance of each pixel point on the layer edge; Analyze the first difference degree between the main river region performance corresponding to the layer edge and other layer edges, and analyze the second difference degree between the suspected river region performance corresponding to the layer edge and other layer edges to obtain the blending feature performance of the layer edge; Traverse all the layer edges of the embedding region to obtain the blending feature performance of the embedding region.

[0011] In some embodiments of the present invention, if the embedding region belongs to the part of the suspected river region, analyzing the first difference distribution of the gray value of each pixel point on the layer edge with the gray value of the pixel points in the main river region includes: Calculate the absolute value of the difference between the gray value of the pixel point on the layer edge and the average value of the gray values of all pixel points in the main river region, denoted as the gray value difference; Calculate the ratio of the number of pixel points on the suspected river region direction side of the pixel points on the layer edge whose absolute value of the difference between the gray value and the average value is greater than the gray value difference to the total number of pixel points on the suspected river region direction side of the pixel points on the layer edge, and combine the gray value difference to obtain the first difference distribution of the gray value of each pixel point on the layer edge with the gray value of the pixel points in the main river region.

[0012] In some embodiments of the present invention, obtaining all the tributary river regions in the remote sensing image according to the blending feature performance corresponding to all the embedding regions of the suspected river region includes: Calculate the mean and variance of the blending feature representation degrees corresponding to all the embedded regions in the suspected river region to obtain the river feature representation degree of the suspected river region; Set a river feature representation degree threshold, and use the suspected river regions with the river feature representation degree greater than the river feature representation degree threshold as branch river regions to obtain all the branch river regions in the remote sensing image.

[0013] According to a second aspect of an embodiment of the present invention, there is provided a mapping system for dynamic remote sensing monitoring, including: a memory and a processor, wherein: The memory is used to store program codes; The processor is used to read the program codes stored in the memory and execute the method described in the first aspect of the embodiment of the present invention.

[0014] In some embodiments of the present invention, the processor includes: A remote sensing image acquisition module for acquiring multiple remote sensing images of the river to be mapped; A suspected river region acquisition module for performing edge detection on the remote sensing image to obtain multiple suspected river regions; A main river region acquisition module for analyzing the gray-scale distribution characteristics of pixel points in the suspected river region to obtain a main river region of the remote sensing image; A branch river region acquisition module for obtaining multiple embedded regions of the suspected river region and the main river region in the remote sensing image, analyzing the differences between the gray-scale values of pixel points in the embedded regions and the gray-scale values of pixel points in the main river region and the suspected river region respectively to obtain the blending feature representation degree of the embedded regions; and for obtaining all the branch river regions in the remote sensing image according to the blending feature representation degrees corresponding to all the embedded regions of the suspected river region; A river drawing module for completing the drawing of the river according to the main river region and the branch river regions.

[0015] Compared with the prior art, a mapping method and system for dynamic remote sensing monitoring provided by the present invention have the following beneficial effects: The present invention performs edge detection on a remote sensing image to obtain multiple suspected river regions; further analyzes the gray-scale distribution characteristics of pixel points within the suspected river regions to obtain a main river region of the remote sensing image; then acquires multiple embedded regions of the suspected river regions and the main river region within the remote sensing image, analyzes the differences between the gray-scale values of pixel points within the embedded regions and the gray-scale values of pixel points within the main river region and the suspected river regions respectively, to obtain the blending feature manifestation degree of the embedded regions; then, based on the blending feature manifestation degrees corresponding to all the embedded regions of the suspected river regions, obtains all the tributary river regions in the remote sensing image; and completes the drawing of the river according to the main river region and the tributary river regions. This method processes the region of the river to be surveyed based on the feature that when the tributaries of the river to be surveyed flow into the main stream, it will affect the gray-scale values of some pixel points in the main stream, completes the drawing of the river, and obtains a complete and accurate surveyed river. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of a mapping method for dynamic remote sensing monitoring provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the edge detection result of a remote sensing image provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the basic composition of a mapping system for dynamic remote sensing monitoring provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a mapping method and system for dynamic remote sensing monitoring proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention pertains. Terms such as "comprise," "include," or any other variant thereof are intended to cover non-exclusive inclusion, such that a circuit structure, article, or device that includes a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the article or device that includes the element.

[0020] The specific scenario targeted by this invention is as follows: When conducting river mapping based on remote sensing images of a river, since the remote sensing images contain not only the river area but also non-river areas, it is necessary to obtain the river area from the remote sensing images. When obtaining the area of the river to be mapped from the remote sensing images, due to the fact that the tributaries and the main stream of the river to be mapped may have different colors, when the tributaries of the river to be mapped flow into the main stream, some parts of the river are composed of color areas that are different from both the main stream and the tributaries. As a result, in some cases, the existing methods for obtaining the river cannot obtain the complete area of the river. Therefore, the objective of this invention is to design a method for obtaining the complete area of the river to be mapped when the river to be mapped is composed of two areas with different colors.

[0021] The following specifically describes the specific solution of a mapping method for dynamic remote sensing monitoring provided by this invention in conjunction with the accompanying drawings.

[0022] Please refer to Figure 1 , which shows the basic process of a mapping method for dynamic remote sensing monitoring provided by an embodiment of this invention.

[0023] As Figure 1 shown, a mapping method for dynamic remote sensing monitoring provided by an embodiment of this invention specifically includes: S100: Obtain multiple remote sensing images of the river to be mapped.

[0024] Take pictures of the river to be mapped through a remote sensing satellite to obtain multiple remote sensing images of the river to be mapped. When taking pictures of the river to be mapped, it starts from the source of the river to be mapped until the estuary of the river to be mapped is photographed. One area of the river to be mapped will appear in multiple remote sensing images simultaneously.

[0025] Thus, multiple remote sensing images of the river to be mapped are obtained.

[0026] Since each remote sensing image contains the same river section as other remote sensing images, a main river region and multiple suspected river regions of each remote sensing image are obtained according to the similarity of the edge detection results of each remote sensing image and other remote sensing images.

[0027] When the tributary of the river to be surveyed flows into the main stream of the river to be surveyed, since the color of the tributary and the main stream of the river to be surveyed is different, the river to be surveyed in a certain area is composed of 2 areas, resulting in the obtained river region may not be a complete river region. Therefore, the possibility that the suspected river region is a river region is further analyzed. When the river region is composed of two regions with different colors, the water in the two regions with different colors will affect each other, and this mutual influence is more obvious at the intersection of the two regions with different colors. Therefore, according to the mutual influence between each river region and the suspected river regions around it, the suspected river regions around each river region that are river regions are obtained.

[0028] S200: Perform edge detection on the remote sensing image to obtain multiple suspected river regions.

[0029] Perform edge detection on the remote sensing image to obtain multiple suspected river regions. The specific implementation method is: perform edge detection on the remote sensing image to obtain multiple edges in the remote sensing image, and according to the regions surrounded by the multiple edges in the remote sensing image, obtain multiple edge detection regions in the remote sensing image, as Figure 2 shown.

[0030] Since the river to be surveyed will not suddenly disappear or appear at a certain location, resulting in the river region sharing an edge with the remote sensing image, as Figure 2 the edge shown. Therefore, the edge detection region sharing an edge with the remote sensing image is denoted as a suspected river region, and multiple suspected river regions of the remote sensing image are obtained.

[0031] S300: Analyze the gray-scale distribution characteristics of the pixel points in the suspected river region to obtain a main river region of the remote sensing image.

[0032] Analyze the gray-scale distribution characteristics of the pixel points in the suspected river region to obtain a main river region of the remote sensing image. Further including: First, since the gray-scale values of the pixel points in the river region of the remote sensing image are relatively close, and the gray-scale values of the pixel points in other regions are relatively chaotic, therefore, by analyzing the dispersion degree of the gray-scale values of the pixel points in the suspected river region, the possibility that the suspected river region is the main river region is obtained.

[0033] However, the degree of dispersion of the gray values of the pixel points in each suspected river area in the remote sensing image only considers the overall characteristics of the distribution of the gray values of the pixel points in the suspected river area, and does not consider the distribution characteristics of the gray values of the pixel points in each suspected river area in the entire remote sensing image. Therefore, it is necessary to correct the degree of dispersion of the gray values of the pixel points in each suspected river area. In the remote sensing image, the pixel points with the same gray values as those in the river area are mostly distributed in the river area, and there are differences between the gray values of most pixel points in the river area and those of most pixel points in the non-river area, that is, the pixel points with the same gray values as those in the river area rarely appear in other areas. Therefore, further analyze the distribution characteristics of the gray values of the pixel points in the suspected river area in the remote sensing image; the specific implementation method is: randomly select a gray value b, calculate the ratio of the number of pixel points with the gray value b in the suspected river area to the number of pixel points with the gray value b in the remote sensing image, and combine the number of pixel points with the gray value b in the suspected river area to obtain the distribution characteristics of the gray values of the pixel points in the suspected river area in the remote sensing image; then correct the possibility through the distribution characteristics of the gray values of the pixel points in the suspected river area in the remote sensing image to obtain the corrected possibility. The formula for constructing the corrected possibility that the th suspected river area in the th remote sensing image is a river area is: In the formula, represents the corrected possibility that the th suspected river area in the th remote sensing image is a river area; represents the mean value of all the gray values of the pixel points in the th suspected river area in the th remote sensing image; represents a gray value; represents the th th suspected river area in the th remote sensing image, and the ratio of the number of pixel points with the gray value in the suspected river area to the number of pixel points with the gray value in the remote sensing image; represents the th th suspected river area in the th remote sensing image, and the total number of pixel points with the gray value in the suspected river area; represents the weight normalization function; represents the linear normalization function; represents 255 gray values.

[0034] The smaller the value of The more a suspected river area conforms to the feature that the gray values of pixel points within the river area are relatively close; The smaller the value of indicates that the probability of pixel points with gray value appearing within the river area is relatively low, and the probability of appearing in non-river areas is relatively high, which does not conform to the feature that pixel points with the same gray value as those within the river area rarely appear in other areas. Therefore, according to a weight is assigned to

[0035] Finally, the suspected river area corresponding to the time when the correction possibility in the remote sensing image is the greatest is used as a main river area of the remote sensing image.

[0036] Similarly, a main river area in all remote sensing images is obtained.

[0037] S400: Obtain multiple embedded areas of the suspected river areas and the main river area within the remote sensing image, analyze the differences between the gray values of pixel points within the embedded areas and the gray values of pixel points within the main river area and the suspected river area respectively, and obtain the blending feature expression degree of the embedded areas.

[0038] When the tributary of the river to be surveyed is drawn into the mainstream, due to the different colors of the tributary and the mainstream, the mainstream is composed of 2 areas, resulting in that not all river areas in the remote sensing image can be obtained by the method in step S300, but only some river areas in the remote sensing image can be obtained. When the tributary of the river to be surveyed flows into the mainstream, the water in the two different color areas will affect each other, and this mutual influence is more obvious in the intersection area of the two rivers, that is, if a river area of one color deeply embeds into a river area of another color, then the feature of the mutual influence of the river water in this embedded area is more obvious. Therefore, according to the degree of the feature expression of the mutual influence of the river water in the embedded areas of the suspected river areas and the main river area determined in step S300, calculate the possibility of each suspected river area being a river area.

[0039] Based on the above analysis, in the embodiment of the present invention, by obtaining multiple embedded areas of the suspected river areas and the main river area within the remote sensing image, and analyzing the differences between the gray values of pixel points within the embedded areas and the gray values of pixel points within the main river area and the suspected river area respectively, the blending feature expression degree of the embedded areas is obtained. It should be noted that the suspected river areas here refer to other suspected river areas except the main river area. Without special explanation, the suspected river areas that appear later all refer to other suspected river areas except the main river area.

[0040] Obtain multiple embedded regions of the suspected river area and the main river area in the remote sensing image. The specific implementation method is as follows: Obtain the skeletons of the main river area and the suspected river area; draw a straight line parallel to the skeleton of the suspected river area across the common edge of the main river area and the suspected river area to obtain several suspected embedded regions; determine whether the suspected embedded region belongs to the main river area part or the suspected river area part. Specifically, taking the common edge of the main river area and the suspected river area as the demarcation line, if the suspected embedded region belongs to one side of the main river area, then the suspected embedded region belongs to the main river area part; if the suspected embedded region belongs to the suspected river area side, then the suspected embedded region belongs to the suspected river area part; obtain the minimum bounding rectangle of each suspected embedded region; analyze the ratio of the number of pixel points of another region that is not included in its corresponding suspected embedded region in the minimum bounding rectangle to the total number of pixel points in the minimum bounding rectangle to obtain the embedding performance degree of the suspected embedded region. It should be noted that the other region included in the minimum bounding rectangle that is not included in its corresponding suspected embedded region means that if the suspected embedded region corresponding to the minimum bounding rectangle belongs to the suspected river area part, then the other region represents the main river area; if the suspected embedded region corresponding to the minimum bounding rectangle belongs to the main river area part, then the other region represents the suspected river area.

[0041] Taking the th suspected embedded region belonging to the suspected river area part as an example, the calculation formula for the embedding performance degree of the th suspected river area and the th suspected embedded region of the main river area is as follows: In the formula, represents the embedding performance degree of the th suspected river area and the th suspected embedded region of the main river area; represents the total number of pixel points in the minimum bounding rectangle of the th suspected river area and the th suspected embedded region of the main river area; represents the number of pixel points of the main river area included in the minimum bounding rectangle of the th suspected river area and the th suspected embedded region of the main river area.

[0042] The larger the value of , it indicates that there are many pixel points of the main river area around the th suspected river area and the

[0043] If the If a suspected embedded area belongs to a part of the main river area, then it represents the number of pixel points of the suspected river area contained within the minimum bounding rectangle of the th suspected embedded area of the suspected river area and the main river area. The rest is the same as that of the th suspected embedded area belonging to the suspected river area part. Thus, the embedding performance degrees of all suspected embedded areas of the th suspected river area and the main river area are obtained.

[0044] Set an embedding performance degree threshold , and the value of the embedding performance degree threshold can be 0.4. If , it indicates that the suspected embedded area is an embedded area, and multiple embedded areas of the suspected river area and the main river area within the remote sensing image are obtained.

[0045] Analyze the difference distribution of the gray values of the pixel points within the embedded area and the gray values of the pixel points within the main river area and the suspected river area respectively to obtain the blending feature performance degree of the embedded area. The specific implementation method is as follows: First, since an embedded area is composed of multiple pixel points, the outermost pixel points of this embedded area form the edge of this embedded area. If the edge pixel points of this embedded area are removed, a new edge of this embedded area will be obtained, denoted as the second-layer edge of this embedded area. Remove the pixel points of the second-layer edge of this embedded area to obtain the third-layer edge of this embedded area; sequentially obtain new edges until the innermost edge of the embedded area to obtain multiple layer edges of the embedded area.

[0046] Then, determine whether the embedded area belongs to the main river area part or the suspected river area part. Specifically, taking the common edge between the main river area and the suspected river area as the dividing line, if the embedded area belongs to the main river area side, then the embedded area belongs to the main river area part; if the embedded area belongs to the suspected river area side, then the embedded area belongs to the suspected river area part.

[0047] Then, if the embedding region belongs to a suspected river region, analyze the first difference distribution of the gray values of each pixel point on the layer edge of the embedding region and the gray values of the pixel points in the main river region, and obtain the main river region representation degree of each pixel point on the layer edge. Specifically, calculate the absolute value of the difference between the gray value of the pixel point on the layer edge of the embedding region and the average value of the gray values of all pixel points in the main river region, which is denoted as the gray value difference; calculate the ratio of the number of pixel points whose absolute value of the difference between the gray value and the average value of the gray values on the suspected river region side pixel points of the pixel points on the layer edge is greater than the gray value difference to the total number of pixel points on the suspected river region side pixel points of the pixel points on the layer edge, and combine the gray value difference to obtain the first difference distribution of the gray values of each pixel point on the layer edge and the gray values of the pixel points in the main river region. Construct the th embedding region's th layer edge's th pixel point's river region representation degree formula as: In the formula, represents the main river region representation degree of the th pixel point on the th layer edge in the th embedding region; represents the average value of the gray values of all pixel points in the main river region; represents the th embedding region at the th layer edge's th pixel point's gray value; represents the th embedding region's th layer edge's th pixel point's total number of suspected river region side pixel points; represents the th embedding region's th layer edge's th pixel point's number of pixel points on the suspected river region side pixel points whose absolute value of the difference between the gray value and is greater than ; represents the exponential function with the natural base ;

[0048] Through the th embedding region's th layer edge's The difference between the gray value of each pixel and all pixel gray values in the main river area is used to represent the difference between each pixel in each embedding area and the main river area. The smaller the difference, the greater the representation degree of the main river area of the pixel; and if the area of a pixel in contact with the main river area is larger, the more similar the pixel is to the main river area. For the th embedding area, for the th edge of the th pixel, if its value is less than the absolute value of the difference between the gray value of the pixel on the suspected river area direction side and , then, the smaller the value, the fewer the number of pixels on the suspected river area direction side of the pixel, and the greater the representation degree of the main river area of the pixel.

[0049] In addition, if the embedding area belongs to the part of the main river area, analyze the second difference distribution of the gray value of each pixel on the layer edge and the gray value of the pixel in the suspected river area to obtain the suspected river area representation degree of each pixel on the layer edge. Specifically, the difference from the part where the embedding area belongs to the suspected river area is that represents the average gray value of all pixels in the suspected river area; represents the th embedding area, for the th edge of the th pixel, the number of pixels on the main river area direction side; represents the th embedding area, for the th edge of the th pixel, among the pixels on the main river area direction side, the number of pixels whose absolute value of the difference from is greater than . The rest is the same.

[0050] Then, analyze the first difference degree between the expression degrees of the main river regions corresponding to the edges of the analysis layer and the edges of other layers, and the second difference degree between the expression degrees of the suspected river regions corresponding to the edges of the analysis layer and the edges of other layers, to obtain the expression degree of the blending feature of the layer edge. For the different layer edges of the embedded region, the pixel points of the layer edge close to the main river region have a larger expression degree of the main river region than the pixel points of the layer edge far from the main river region; similarly, the pixel points of the layer edge close to the suspected river region have a larger expression degree of the suspected river region than the pixel points of the layer edge far from the suspected river region; if both of these characteristics are satisfied, the blending feature of the embedded region to which the pixel point belongs is more significant. Therefore, analyze the first difference degree between the expression degrees of the main river regions corresponding to the edges of the analysis layer and the edges of other layers, and the second difference degree between the expression degrees of the suspected river regions corresponding to the edges of the analysis layer and the edges of other layers, to obtain the expression degree of the blending feature of the layer edge. Construct the expression degree calculation formula of the blending feature of the layer edge in the th embedded region as: In the formula, represents the expression degree of the blending feature of the layer edge in the th embedded region; represents the mean value of the expression degrees of the suspected river regions of all pixel points of the layer edge in the th embedded region; represents the mean value of the expression degrees of the suspected river regions of all pixel points of the layer edge in the th embedded region; represents the mean value of the expression degrees of the main river regions of all pixel points of the layer edge in the th embedded region; represents the mean value of the expression degrees of the main river regions of all pixel points of the layer edge in the represents the sign function; among them, the layer edge of the th embedded region is close to the main river region relative to the layer edge, that is, here analyze the difference between the layer edge and the edges of other layers close to the main river region.

[0051] If , it means that the expression degree of the suspected river region of the th suspected river region of the layer edge is greater than that of the The expression degree of the suspected river area at the layer edge conforms to the fact that the closer the pixel points in the embedded area are to the suspected river area, the more similar their characteristics are to those of the suspected river area. At this time ; , indicating that the expression degree of the main river area at the th layer edge of the th suspected river area is greater than that of the main river area at the th layer edge, which conforms to the fact that the closer the pixel points in the embedded area are to the main river area, the more similar their characteristics are to those of the main river area. At this time ; The larger the

[0052] value is, the closer the pixel points in the embedded area are to the suspected river area, the more similar their characteristics are to those of the suspected river area, and at the same time, the closer they are to the main river area, the more similar their characteristics are to those of the main river area, and the greater the expression degree of the blending characteristics of the corresponding layer edge. Finally, traverse all the layer edges of the embedded area to obtain the expression degree of the blending characteristics of the embedded area. The calculation formula for the expression degree of the blending characteristics of the th embedded area is as follows: In the formula, represents the expression degree of the blending characteristics of the th embedded area; represents the number of layer edges contained in the th embedded area; represents the expression degree of the blending characteristics of the th layer edge in the

[0053] th embedded area. Similarly, obtain the expression degree of the blending characteristics of each embedded area between the

[0054] th suspected river area and the main river area.

[0055] S500: Obtain all the branch river areas in the remote sensing image according to the expression degrees of the blending characteristics corresponding to all the embedded areas of the suspected river area. When the th suspected river area is a river area, the expression degrees of the blending characteristics of multiple embedded areas between the The river feature expression degree of a suspected river area. Specifically, calculate the mean and variance of the blending feature expression degrees corresponding to all embedded areas in the suspected river area to obtain the river feature expression degree of the suspected river area. Construct the formula for calculating the river feature expression degree of the suspected river area as follows: In the formula, represents the river feature expression degree of the th suspected river area; represents the mean of the blending feature expression degrees of all embedded areas between the th suspected river area and the main river area; represents the variance of the blending feature expression degrees of all embedded areas between the th suspected river area and the main river area; is a hyperparameter to prevent the denominator from being zero; represents function for normalization processing.

[0056] The larger the value, the more it conforms to the characteristic that the blending feature expression degrees of the embedded areas of the two river areas are larger; the smaller the

[0057] value, the more it conforms to the characteristic that the blending feature expression degrees of the embedded areas of the two river areas are more similar. , Then, set the river feature expression degree threshold

[0058] S600: Complete the drawing of the river according to the main river area and the branch river areas.

[0059] According to the distance between the remote sensing satellite and the ground when the remote sensing image is taken, obtain the distance represented by the width of each pixel point in the remote sensing image. Multiply the width of the river area (main river area and branch river areas) at each position in the remote sensing image by the width of each pixel point in the remote sensing image to obtain the actual width of the river area (main river area and branch river areas) at that position, complete the acquisition of the river width in the mapping process, and complete the drawing of the river.

[0060] Based on the same inventive concept as the above method, this embodiment also provides a mapping system for dynamic remote sensing monitoring.

[0061] Please refer to Figure 3 , which shows the basic composition of a mapping system for dynamic remote sensing monitoring provided by an embodiment of the present invention.

[0062] As Figure 3 shown, a mapping system for dynamic remote sensing monitoring includes: a memory 10 and a processor 20, where: The memory 10 is used to store program codes; The processor 20 is configured to read the program codes stored in the memory 10 and perform the following operations: obtain multiple remote sensing images of the river to be mapped; perform edge detection on the remote sensing images to obtain multiple suspected river regions; analyze the gray distribution characteristics of pixel points in the suspected river regions to obtain a main river region of the remote sensing image; obtain multiple embedded regions between the suspected river regions and the main river region in the remote sensing image, analyze the differences between the gray values of pixel points in the embedded regions and the gray values of pixel points in the main river region and the suspected river regions respectively, to obtain the blending feature representation degree of the embedded regions; obtain all the tributary river regions in the remote sensing image according to the blending feature representation degrees corresponding to all the embedded regions of the suspected river regions; and complete the mapping of the river according to the main river region and the tributary river regions.

[0063] Further, the processor 20 includes: a remote sensing image acquisition module 21, a suspected river region acquisition module 22, a main river region acquisition module 23, a tributary river region acquisition module 24, and a river mapping module 25. Where: The remote sensing image acquisition module 21 is used to obtain multiple remote sensing images of the river to be mapped; The suspected river region acquisition module 22 is used to perform edge detection on the remote sensing images to obtain multiple suspected river regions; The main river region acquisition module 23 is used to analyze the gray distribution characteristics of pixel points in the suspected river regions to obtain a main river region of the remote sensing image; The tributary river region acquisition module 24 is used to obtain multiple embedded regions between the suspected river regions and the main river region in the remote sensing image, analyze the differences between the gray values of pixel points in the embedded regions and the gray values of pixel points in the main river region and the suspected river regions respectively, to obtain the blending feature representation degree of the embedded regions; and is used to obtain all the tributary river regions in the remote sensing image according to the blending feature representation degrees corresponding to all the embedded regions of the suspected river regions; The river mapping module 25 is used to complete the mapping of the river according to the main river region and the tributary river regions.

[0064] It should be noted that: the above-mentioned sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific sequence or continuous sequence shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0065] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the difference between each embodiment and other embodiments is emphasized.

Claims

1. A mapping method for dynamic remote sensing monitoring, characterized in that, The method includes: Obtaining multiple remote sensing images of the river to be surveyed; Performing edge detection on the remote sensing images to obtain multiple suspected river regions; Analyzing the gray-scale distribution characteristics of the pixel points in the suspected river regions to obtain a main river region of the remote sensing images; Obtaining multiple embedded regions of the suspected river regions and the main river region in the remote sensing images, and analyzing the differences between the gray-scale values of the pixel points in the embedded regions and the gray-scale values of the pixel points in the main river region and the suspected river regions respectively to obtain the blending feature expression degree of the embedded regions; Obtaining all the tributary river regions in the remote sensing images according to the blending feature expression degrees corresponding to all the embedded regions of the suspected river regions; Completing the drawing of the river according to the main river region and the tributary river regions; Analyzing the gray-scale distribution characteristics of the pixel points in the suspected river regions to obtain a main river region of the remote sensing images, including: Analyzing the dispersion degree of the gray-scale values of the pixel points in the suspected river regions to obtain the possibility that the suspected river region is the main river region; Analyzing the distribution characteristics of the gray-scale values of the pixel points in the suspected river regions in the remote sensing images to correct the possibility and obtain the corrected possibility; Taking the suspected river region corresponding to the maximum corrected possibility as a main river region of the remote sensing images; Analyzing the difference distribution between the gray-scale values of the pixel points in the embedded regions and the gray-scale values of the pixel points in the main river region and the suspected river regions respectively to obtain the blending feature expression degree of the embedded regions, including: Obtaining multiple layer edges of the embedded regions; Judging whether the embedded region belongs to the part of the main river region or the part of the suspected river region; If the embedded region belongs to the part of the suspected river region, analyzing the first difference distribution between the gray-scale value of each pixel point of the layer edge and the gray-scale value of the pixel points in the main river region to obtain the main river region expression degree of each pixel point of the layer edge; If the embedded region belongs to the part of the main river region, analyzing the second difference distribution between the gray-scale value of each pixel point of the layer edge and the gray-scale value of the pixel points in the suspected river region to obtain the suspected river region expression degree of each pixel point of the layer edge; Analyzing the first difference degree between the main river region expression degrees corresponding to the layer edge and other layer edges, and analyzing the second difference degree between the suspected river region expression degrees corresponding to the layer edge and other layer edges to obtain the blending feature expression degree of the layer edge; Traversing all the layer edges of the embedded regions to obtain the blending feature expression degree of the embedded regions.

2. The mapping method for dynamic remote sensing monitoring according to claim 1, wherein Performing edge detection on the remote sensing images to obtain multiple suspected river regions, including: Performing edge detection on the remote sensing images to obtain multiple edges and edge detection regions in the remote sensing images; Denoting the edge detection regions sharing a section of edge with the remote sensing images as suspected river regions to obtain multiple suspected river regions of the remote sensing images.

3. The mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that, Analyzing the distribution characteristics of the gray-scale values of the pixel points in the suspected river regions in the remote sensing images, including: Optionally select a gray value b, and calculate the ratio of the number of pixel points with gray value in the suspected river area to the number of pixel points with gray value b in the remote sensing image. Combine the number of pixel points with gray value b in the suspected river area to obtain the distribution characteristics of the gray values of the pixel points in the suspected river area within the remote sensing image.

4. The mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that, Obtain multiple embedded regions of the suspected river region and the main river region in the remote sensing image, including: Obtain the skeletons of the main river region and the suspected river region; Draw a straight line parallel to the skeleton of the suspected river region across the common edge of the main river region and the suspected river region to obtain several suspected embedded regions; Determine whether the suspected embedded region belongs to the part of the main river region or the part of the suspected river region; Obtain the minimum bounding rectangle of each suspected embedded region; Analyze the ratio of the number of pixel points of another region that the minimum bounding rectangle contains but its corresponding suspected embedded region does not belong to, to the total number of pixel points in the minimum bounding rectangle, to obtain the embedding performance of the suspected embedded region; Set an embedding performance threshold, and obtain multiple embedded regions of the suspected river region and the main river region in the remote sensing image according to the embedding performance.

5. The mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that If the embedded region belongs to the part of the suspected river region, analyze the first difference distribution of the gray value of each pixel point on the layer edge and the gray value of the pixel points in the main river region, including: Calculate the absolute value of the difference between the gray value of the pixel point on the layer edge and the average value of the gray values of all pixel points in the main river region, and denote it as the gray value difference; Calculate the ratio of the number of pixel points on the suspected river region side of the pixel points on the layer edge whose absolute value of the difference between the gray value and the average value is greater than the gray value difference, to the total number of pixel points on the suspected river region side of the pixel points on the layer edge, and combine the gray value difference to obtain the first difference distribution of the gray value of each pixel point on the layer edge and the gray value of the pixel points in the main river region.

6. The mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that Obtain all the tributary river regions in the remote sensing image according to the blending feature performance corresponding to all the embedded regions of the suspected river region, including: Calculate the mean and variance of the blending feature performance corresponding to all the embedded regions of the suspected river region to obtain the river feature performance of the suspected river region; Set a river feature performance threshold, and take the suspected river regions whose river feature performance is greater than the river feature performance threshold as tributary river regions to obtain all the tributary river regions in the remote sensing image.

7. A surveying and mapping system for dynamic remote sensing monitoring, characterized in that, The system includes: a memory and a processor, where: The memory is used to store program codes; The processor is used to read the program codes stored in the memory and execute the method according to any one of claims 1 to 6.

8. The mapping system for dynamic remote sensing monitoring according to claim 7, characterized in that, The processor includes: A remote sensing image acquisition module, used to acquire multiple remote sensing images of the river to be surveyed; A suspected river region acquisition module, used to perform edge detection on the remote sensing image to obtain multiple suspected river regions; A main river region acquisition module, used to analyze the gray distribution characteristics of the pixel points in the suspected river region to obtain a main river region of the remote sensing image; A tributary river area acquisition module, configured to acquire a plurality of embedded areas of the suspected river area and the main river area in the remote sensing image, analyze the differences between the gray values of the pixel points in the embedded areas and the gray values of the pixel points in the main river area and the suspected river area respectively, and obtain the blending feature representation degree of the embedded areas; and configured to obtain all tributary river areas in the remote sensing image according to the blending feature representation degrees corresponding to all the embedded areas of the suspected river area; A river drawing module, configured to complete the drawing of the river according to the main river area and the tributary river areas.

Images