A surveying and mapping method and system for dynamic remote sensing monitoring

Abstract

The present invention relates to the field of river mapping technology, and specifically to a mapping method and system for dynamic remote sensing monitoring. The present invention obtains multiple suspected river areas by performing edge detection on remote sensing images; analyzes the grayscale distribution characteristics of pixels in the suspected river areas to obtain a main river area in the remote sensing image; obtains multiple embedded areas of the suspected river areas and the main river areas in the remote sensing image, analyzes the differences between the grayscale values of the pixels in the embedded areas and the grayscale values of the pixels in the main river areas and the suspected river areas, obtains the expression of the blending characteristics of the embedded areas, and further obtains all tributary river areas in the remote sensing image to complete the mapping of the river. This method is based on the feature that when the tributaries of the river to be mapped merge into the mainstream, it will affect the grayscale values of some pixels in the mainstream, and performs post-processing on the area of the river to be mapped to complete the mapping of the river, thereby obtaining a complete and accurate mapping of the river.

Description

Technical Field

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

[0002] Dynamic remote sensing monitoring technology uses sensors aboard platforms such as satellites, aircraft, and drones to conduct long-distance, non-contact detection and measurement of Earth's surface. This technology has become a key tool in surveying and mapping because it can provide surface information over a wide area with high temporal and spatial resolution.

[0003] When mapping a river using dynamic remote sensing monitoring technology, remote sensing satellites are used to photograph a river starting from its source and continuing until the river's estuary is reached, generating multiple remote sensing images of the river to be mapped. Since remote sensing images contain not only river areas 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 mapped from remote sensing images, the tributaries of the river to be mapped may differ in color from the mainstream. Consequently, when a tributary merges into the mainstream, the mainstream in some locations will consist of two regions of different colors. Consequently, existing methods for capturing the river area may not be able to capture the entire 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 a first aspect of an embodiment of the present invention, a surveying and mapping method for dynamic remote sensing monitoring is provided, and the technical solution adopted is as follows:

[0006] Obtain multiple remote sensing images of the river to be mapped;

[0007] Performing edge detection on the remote sensing image to obtain multiple suspected river areas;

[0008] Analyze the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image;

[0009] Acquire multiple embedded regions of the suspected river region and the main river region in the remote sensing image, analyze the differences between the grayscale values of pixels in the embedded regions and the grayscale values of pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions;

[0010] Obtaining all tributary river regions in the remote sensing image according to the blending feature expression corresponding to all embedded regions of the suspected river region;

[0011] The river is drawn based on the main river area and the branch river area.

[0012] In some embodiments of the present invention, edge detection is performed on the remote sensing image to obtain multiple suspected river areas, including:

[0013] Performing edge detection on the remote sensing image to obtain a plurality of edges and edge detection areas in the remote sensing image;

[0014] The edge detection area that shares a common edge with the remote sensing image is recorded as a suspected river area, and a plurality of suspected river areas of the remote sensing image are obtained.

[0015] In some embodiments of the present invention, analyzing the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image includes:

[0016] Analyze the discrete degree of the grayscale values of the pixels in the suspected river area to obtain the possibility that the suspected river area is a main river area;

[0017] Analyzing the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image, and correcting the possibility to obtain a corrected possibility;

[0018] The suspected river area corresponding to the maximum correction possibility is used as a main river area of the remote sensing image.

[0019] In some embodiments of the present invention, analyzing the distribution characteristics of the grayscale values of pixels in the suspected river area in the remote sensing image includes:

[0020] Select any grayscale value b, calculate the ratio of the number of pixels with grayscale value b in the suspected river area to the number of pixels with grayscale value b in the remote sensing image, and combine the number of pixels with grayscale value b in the suspected river area to obtain the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image.

[0021] In some embodiments of the present invention, obtaining a plurality of embedded regions of the suspected river region and the main river region in the remote sensing image includes:

[0022] Obtaining the skeletons of the main river area and the suspected river area;

[0023] A plurality of suspected embedded regions are obtained by drawing a straight line parallel to the skeleton of the suspected river region through the common edge of the main river region and the suspected river region;

[0024] Determining whether the suspected embedded area belongs to the main river area or the suspected river area;

[0025] Get the minimum bounding rectangle of each suspected embedded area;

[0026] Analyzing the ratio of the number of pixels in the minimum bounding rectangle that are included in another region to which the suspected embedded region does not belong to and the total number of pixels in the minimum bounding rectangle to obtain the embedding expressiveness of the suspected embedded region;

[0027] An embedding expression threshold is set, and based on the embedding expression, a plurality of embedding regions of the suspected river region and the main river region in the remote sensing image are obtained.

[0028] In some embodiments of the present invention, analyzing the difference distribution between the grayscale values of pixels in the embedded area and the grayscale values of pixels in the main river area and the suspected river area to obtain the blending feature expression of the embedded area includes:

[0029] obtaining a plurality of layer edges of the embedded region;

[0030] Determining whether the embedded area belongs to the main river area or the suspected river area;

[0031] If the embedded area belongs to the suspected river area, analyzing the first difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel points in the main river area, and obtaining the main river area representation degree of each pixel point at the layer edge;

[0032] If the embedded area belongs to the main river area, analyzing the second difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel points in the suspected river area, and obtaining the suspected river area expression degree of each pixel point at the layer edge;

[0033] Analyzing a first difference between the expression degrees of the main river region corresponding to the layer edge and other layer edges, and analyzing a second difference between the expression degrees of the suspected river region corresponding to the layer edge and other layer edges, to obtain a blending feature expression degree of the layer edge;

[0034] All the layer edges of the embedded area are traversed to obtain the blending feature expression of the embedded area.

[0035] In some embodiments of the present invention, if the embedded area belongs to a suspected river area, analyzing a first difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of each pixel point in the main river area includes:

[0036] Calculate the absolute value of the difference between the grayscale value of the pixel point at the edge of the layer and the average grayscale value of all pixels in the main river area, and record it as the grayscale value difference;

[0037] Calculate the ratio of the number of pixels whose absolute value of the difference between the grayscale value of the pixel points on the suspected river area direction side of the pixel points at the edge of the layer and the grayscale value mean is greater than the grayscale value difference, and the total number of pixels on the suspected river area direction side of the pixel points at the edge of the layer, and combine the grayscale value difference to obtain the first difference distribution between the grayscale value of each pixel point at the edge of the layer and the grayscale value of the pixel points in the main river area.

[0038] In some embodiments of the present invention, all tributary river regions in the remote sensing image are obtained based on the blending feature expression corresponding to all embedded regions of the suspected river region, including:

[0039] Calculating the mean and variance of the blending feature expression corresponding to all embedded regions of the suspected river region to obtain the river feature expression of the suspected river region;

[0040] A river feature expression threshold is set, and the suspected river regions whose river feature expression is greater than the river feature expression threshold are taken as tributary river regions, so as to obtain all tributary river regions in the remote sensing image.

[0041] According to a second aspect of an embodiment of the present invention, a surveying and mapping system for dynamic remote sensing monitoring is provided, comprising: a memory and a processor, wherein:

[0042] The memory is used to store program code;

[0043] The processor is configured to read the program code stored in the memory and execute the method described in the first aspect of the embodiment of the present invention.

[0044] In some embodiments of the present invention, the processor includes:

[0045] Remote sensing image acquisition module, used to obtain multiple remote sensing images of the river to be mapped;

[0046] a suspected river region acquisition module, configured to perform edge detection on the remote sensing image to obtain a plurality of suspected river regions;

[0047] A main river region acquisition module is used to analyze the grayscale distribution characteristics of the pixels in the suspected river region to obtain a main river region in the remote sensing image;

[0048] a tributary river region acquisition module, configured to acquire multiple embedded regions of the suspected river region and the main river region in the remote sensing image, analyze the differences between the grayscale values of the pixels in the embedded regions and the grayscale values of the pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions; and obtain all tributary river regions in the remote sensing image based on the blending feature expression corresponding to all embedded regions of the suspected river region;

[0049] The river drawing module is used to complete the river drawing according to the main river area and the branch river area.

[0050] Compared with the existing technology, the surveying and mapping method and system for dynamic remote sensing monitoring provided by the present invention have the following beneficial effects:

[0051] The present invention obtains multiple suspected river areas by performing edge detection on the remote sensing image; further analyzes the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image; then obtains multiple embedded areas of the suspected river area and the main river area in the remote sensing image, analyzes the differences between the grayscale values of the pixels in the embedded area and the grayscale values of the pixels in the main river area and the suspected river area, and obtains the blending feature expression of the embedded area; then obtains all the tributary river areas in the remote sensing image based on the blending feature expression corresponding to all the embedded areas of the suspected river area; completes the mapping of the river based on the main river area and the tributary river area. This method processes the area of the river to be mapped based on the feature that when the tributaries of the river to be mapped merge into the mainstream, it will affect the grayscale values of some pixels in the mainstream, completes the mapping of the river, and obtains a complete and accurate mapping of the river. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A schematic diagram of the basic flow of a surveying and mapping method for dynamic remote sensing monitoring provided by one embodiment of the present invention;

[0054] Figure 2 A schematic diagram of edge detection results of a remote sensing image provided by one embodiment of the present invention;

[0055] Figure 3A schematic diagram of the basic composition of a surveying and mapping system for dynamic remote sensing monitoring provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0056] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a surveying and mapping method and system for dynamic remote sensing monitoring, including its specific implementation, structure, features, and effectiveness. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. Terms such as "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a circuit structure, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such article or device. In the absence of further limitations, the phrase "comprising a ..." to define an element does not preclude the presence of other identical elements in the article or device comprising the element.

[0058] The specific scenario targeted by the present invention is: when river mapping is performed based on remote sensing images of rivers, since the remote sensing images contain not only river areas but also non-river areas, it is necessary to obtain the river areas from the remote sensing images. When obtaining the area of the river to be mapped from the remote sensing image, since the colors of the tributaries of the river to be mapped may be different from the mainstream, when the tributaries of the river to be mapped merge into the mainstream, the river in some locations is composed of color areas that are different from both the mainstream and the tributaries. As a result, when obtaining the river using existing methods, in some cases, the complete area of the river cannot be obtained. Therefore, the purpose of the present invention is to design a method for obtaining a complete area of the river to be mapped when the river to be mapped is composed of two areas of different colors.

[0059] The following describes in detail a specific scheme of a surveying and mapping method for dynamic remote sensing monitoring provided by the present invention in conjunction with the accompanying drawings.

[0060] See also Figure 1 , which shows the basic process of a surveying and mapping method for dynamic remote sensing monitoring provided by an embodiment of the present invention.

[0061] like Figure 1 As shown, an embodiment of the present invention provides a surveying and mapping method for dynamic remote sensing monitoring, which specifically includes:

[0062] S100: Acquire multiple remote sensing images of the river to be mapped.

[0063] Remote sensing satellites are used to photograph the river to be mapped, generating multiple remote sensing images of the river. The images are taken from the river's source to its estuary. A single area of the river will appear in multiple remote sensing images simultaneously.

[0064] At this point, multiple remote sensing images of the river to be mapped have been obtained.

[0065] Since each remote sensing image contains the same river part as other remote sensing images, a main river area and multiple suspected river areas are obtained for each remote sensing image based on the similarity of the edge detection results between each remote sensing image and other remote sensing images.

[0066] When a tributary of the river to be mapped flows into the main stream of the river to be mapped, the tributary and the main stream have different colors, resulting in the river being mapped within a certain area consisting of two regions. This may result in the resulting river region being incomplete. Therefore, further analysis is conducted to determine the likelihood that the suspected river region is actually a river region. When a river region consists of two regions of different colors, the water in the two regions of different colors will influence each other, and this mutual influence is more pronounced at the intersection of the two regions of different colors. Therefore, based on the mutual influence between each river region and the surrounding suspected river regions, the suspected river regions surrounding each river region are obtained as river regions.

[0067] S200: Perform edge detection on the remote sensing image to obtain multiple suspected river areas.

[0068] Perform edge detection on the remote sensing image to obtain multiple suspected river areas. The specific implementation method is: perform edge detection on the remote sensing image to obtain multiple edges in the remote sensing image, and obtain multiple edge detection areas in the remote sensing image based on the areas surrounded by the multiple edges in the remote sensing image, such as Figure 2 shown.

[0069] Since the river to be mapped will not suddenly disappear or appear at a certain location, the river area and the remote sensing image share a section of the edge, such as Figure 2 Middle edge Therefore, the edge detection area that shares an edge with the remote sensing image is recorded as the suspected river area, and multiple suspected river areas of the remote sensing image are obtained.

[0070] S300: Analyze the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image.

[0071] Analyze the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image. Further analysis includes:

[0072] First, since the grayscale values of pixels in the river area in the remote sensing image are relatively close, and the grayscale values of pixels in other areas are relatively chaotic, the possibility that the suspected river area is the main river area is obtained by analyzing the discrete degree of the grayscale values of pixels in the suspected river area.

[0073] However, the degree of dispersion of the grayscale values of pixels within each suspected river region in a remote sensing image only considers the overall distribution characteristics of the grayscale values of the pixels within that suspected river region, and does not consider the distribution characteristics of the grayscale values of the pixels within each suspected river region within the entire remote sensing image. Therefore, it is necessary to correct the degree of dispersion of the grayscale values of the pixels within each suspected river region. In a remote sensing image, pixels with the same grayscale values as those in the river region are mostly distributed in the river region, and the grayscale values of most pixels in the river region are different from those of most pixels in non-river regions. In other words, pixels with the same grayscale values as those in the river region are less likely to appear in other regions. Therefore, further analysis is performed on the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image; the specific implementation method is: randomly select a grayscale value b, calculate the ratio of the number of pixels with grayscale value b in the suspected river area to the number of pixels with grayscale value b in the remote sensing image, and combine the number of pixels with grayscale value b in the suspected river area to obtain the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image; then, the possibility is corrected by the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image to obtain the corrected possibility. Construct the first The remote sensing image The formula for calculating the corrected probability that a suspected river area is a river area is:

[0074]

[0075] Where, Indicates the The remote sensing image The probability of the suspected river area being a river area; Indicates the The remote sensing image The mean grayscale value of all pixels in the suspected river area; Represents a grayscale value; Indicates the The remote sensing image The gray value in the suspected river area is The pixel points with gray value in remote sensing image are The ratio of the number of pixels; Indicates the The remote sensing image The gray value in the suspected river area is The total number of pixels; represents the weight normalization function; represents the linear normalization function; Represents 255 grayscale values.

[0076] The smaller the value, the The more the suspected river area conforms to the characteristic that the grayscale values of the pixels in the river area are close; The smaller the value of The probability of the pixel points appearing in the river area is low, and the probability of appearing in the non-river area is high, which does not meet the characteristic that the pixels with the same grayscale value as the pixels in the river area rarely appear in other areas. right Assign a weight.

[0077] Finally, the suspected river area corresponding to the maximum correction possibility in the remote sensing image is taken as a main river area in the remote sensing image.

[0078] Similarly, a main river area in all remote sensing images is obtained.

[0079] S400: Acquire multiple embedded regions of suspected river regions and main river regions in the remote sensing image, analyze the differences between the grayscale values of pixels in the embedded regions and the grayscale values of pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions.

[0080] When the tributaries of the river to be mapped are drawn into the mainstream, the mainstream consists of two areas due to the different colors of the tributaries and the mainstream. As a result, the method of step S300 cannot obtain the entire river area in the remote sensing image, but only part of the river area in the remote sensing image. When the tributaries of the river to be mapped merge into the mainstream, the water in the two different color areas will affect each other, and this mutual influence is more obvious in the intersecting area of the two rivers, that is, if the river area of one color is deeply embedded in the river area of another color, then the characteristics of the mutual influence of the river water in this embedded area are more obvious. Therefore, based on the degree of the characteristic expression of the mutual influence of the river water in the embedded area between the suspected river area and the main river area determined in step S300, the possibility of each suspected river area being a river area is calculated.

[0081] Based on the above analysis, in an embodiment of the present invention, by obtaining multiple embedded regions of suspected river regions and main river regions in a remote sensing image, and analyzing the differences between the grayscale values of pixels in the embedded regions and the grayscale values of pixels in the main river region and the suspected river region, the blending feature expression of the embedded regions is obtained. It should be noted that the suspected river regions here refer to suspected river regions other than the main river region. Unless otherwise specified, the suspected river regions that appear later all refer to suspected river regions other than the main river region.

[0082] A plurality of embedded regions of suspected river regions and main river regions in a remote sensing image are obtained. The specific implementation method is as follows: skeletons of the main river region and the suspected river region are obtained; a plurality of suspected embedded regions are obtained by drawing a straight line parallel to the skeleton of the suspected river region through the common edge of the main river region and the suspected river region; it is determined whether the suspected embedded region belongs to part of the main river region or part of the suspected river region. Specifically, the common edge of the main river region and the suspected river region is used as the dividing line. If the suspected embedded region belongs to one side of the main river region, the suspected embedded region belongs to part of the main river region; if the suspected embedded region belongs to the direction side of the suspected river region, the suspected embedded region belongs to part of the suspected river region; a minimum bounding rectangle is obtained for each suspected embedded region; the ratio of the number of pixels in the minimum bounding rectangle that contains another region to which the corresponding suspected embedded region does not belong to and the total number of pixels in the minimum bounding rectangle are analyzed to obtain the embedding expressiveness of the suspected embedded region; it should be noted that the minimum bounding rectangle that contains another region to which the corresponding suspected embedded region does not belong means that if the suspected embedded region corresponding to the minimum bounding rectangle belongs to part of the suspected river region, the other region represents the main river region; if the suspected embedded region corresponding to the minimum bounding rectangle belongs to part of the main river region, the other region represents the suspected river region.

[0083] First Take the suspected embedded area belonging to the suspected river area as an example, and construct the The suspected river area and the main river area The calculation formula for the embedding representation of a suspected embedding region is:

[0084]

[0085] Where, Indicates the The suspected river area and the main river area Embedding performance of suspected embedded regions; Indicates the The suspected river area and the main river area The total number of pixels within the minimum bounding rectangle of the suspected embedded area; Indicates the The suspected river area and the main river area The number of pixels in the minimum bounding rectangle of the suspected embedded area that contains the main river area.

[0086] The larger the value, the The suspected river area and the main river area There are many pixels of the main river area around the suspected embedded area, which is consistent with the feature that the embedded area of one area is deeply surrounded by another area.

[0087] Jordi If the suspected embedded area belongs to the main river area, Indicates the The suspected river area and the main river area The number of pixels in the suspected river area contained in the minimum bounding rectangle of the suspected embedded area is the same as the The suspected embedded regions are partly the same as the suspected river regions. The embedding representation of the suspected river regions and all the suspected embedded regions in the main river region.

[0088] Setting the embedding representation threshold , embedding expression threshold The value can be 0.4. , indicating that the suspected embedded area is an embedded area, and multiple embedded areas of the suspected river area and the main river area in the remote sensing image are obtained.

[0089] The difference distribution of the grayscale values of the pixels in the embedded area and the grayscale values of the pixels in the main river area and the suspected river area is analyzed to obtain the blending feature expression of the embedded area. The specific implementation method is as follows:

[0090] First, since an embedded area is composed of multiple pixels, the outermost pixels of the embedded area constitute the edge of the embedded area. If the edge pixels of the embedded area are removed, a new edge of the embedded area will be obtained, which is recorded as the second-layer edge of the embedded area. The pixels of the second-layer edge of the embedded area are removed to obtain the third-layer edge of the embedded area; new edges are obtained in sequence until the innermost edge of the embedded area, and multiple layers of edges of the embedded area are obtained.

[0091] Next, the embedded region is determined to be part of the main river region or part of the suspected river region. Specifically, the shared edge of the main river region and the suspected river region is used as the dividing line. If the embedded region is on the side of the main river region, it is considered to be part of the main river region. If the embedded region is on the side of the suspected river region, it is considered to be part of the suspected river region.

[0092] Then, if the embedded area belongs to the suspected river area, analyze the first difference distribution of the grayscale value of each pixel point at the layer edge of the embedded area and the grayscale value of the pixel point in the main river area, and obtain the main river area expression of each pixel point at the layer edge. Specifically, calculate the absolute value of the difference between the grayscale value of the pixel point at the layer edge of the embedded area and the grayscale value mean of all the pixels in the main river area, and record it as the grayscale value difference; calculate the number of pixels whose absolute value of the difference between the grayscale value and the grayscale value mean of the pixel point on the suspected river area side of the pixel point at the layer edge is greater than the grayscale value difference, and the ratio of the total number of pixels on the suspected river area side of the pixel point at the layer edge, and combine the grayscale value difference to obtain the first difference distribution of the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel point in the main river area. Construct the first The embedded area The edge of the layer The formula for the river area representation of a pixel is:

[0093]

[0094] Where, Indicates the The embedded area The edge of the layer The main river area representation of each pixel; Represents the mean grayscale value of all pixels in the main river area; Indicates the The embedded region is The edge of the layer Gray value of each pixel; Indicates the The embedded area The edge of the layer The total number of pixels on the side of the suspected river area; Indicates the The embedded area The edge of the layer The gray value of the pixel point on the side of the suspected river area is The absolute value of the difference is greater than The number of pixels; Indicates the natural base An exponential function with base .

[0095] Through the The embedded area The edge of the layer The difference between the grayscale value of each pixel point and the main river area is used to represent the difference between each pixel point in each embedded area and the main river area. The smaller the difference, the greater the representation of the main river area of the pixel point. And the larger the area of contact between a pixel point and the main river area, the more similar the pixel point is to the main river area. The embedded area The edge of the layer pixels The value is less than the gray value of the pixel point on the side of the suspected river area. The absolute value of the difference, therefore, The smaller the value, the fewer pixels are on the suspected river area side of the pixel, and the greater the representation of the main river area of the pixel.

[0096] Furthermore, if the embedded area belongs to the main river area, the second difference distribution between the grayscale value of each pixel at the edge of the layer and the grayscale value of the pixel in the suspected river area is analyzed to obtain the suspected river area representation of each pixel at the edge of the layer. Specifically, the difference between the embedded area and the suspected river area is, Represents the mean grayscale value of all pixels in the suspected river area; Indicates the The embedded area The edge of the layer The number of pixels in the main river area direction; Indicates the The embedded area The edge of the layer The gray value of the pixel point in the main river area direction is The absolute value of the difference is greater than The rest are the same.

[0097] Then, the first difference between the main river area expression corresponding to the layer edge and the other layer edges, and the second difference between the suspected river area expression corresponding to the layer edge and the other layer edges are analyzed to obtain the layer edge's blending feature expression. For different layer edges of the embedded area, the pixel points of the layer edge close to the main river area have a larger main river area expression than the pixel points of the layer edge far away from the main river area; similarly, the pixel points of the layer edge close to the suspected river area have a larger suspected river area expression than the pixel points of the layer edge far away from the suspected river area; if these two characteristics are met at the same time, the blending feature of the embedded area to which the pixel point belongs is more significant. Therefore, the first difference between the main river area expression corresponding to the layer edge and the other layer edges, and the second difference between the suspected river area expression corresponding to the layer edge and the other layer edges are analyzed to obtain the layer edge's blending feature expression. Construct the first The embedded area The calculation formula for the blending feature expression of the layer edge is:

[0098]

[0099] Where, Indicates the The embedded area The degree of expression of the blending characteristics of the layer edges; Indicates the The embedded area The mean value of the suspected river area representation of all pixels at the edge of the layer; Indicates the The embedded area The mean value of the suspected river area representation of all pixels at the edge of the layer; Indicates the The embedded area The mean value of the main river area representation of all pixels at the edge of the layer; Indicates the The embedded area The mean value of the main river area representation of all pixels at the edge of the layer; represents the symbolic function; where The embedded area Layer edge relative to the The edge of the layer is close to the main river area, that is, the The difference between the edge of the layer and the edges of other layers close to the main river area.

[0100] like , explain the The suspected river area The expression of suspected river areas at the edge of the layer is greater than that of the The expression of the suspected river area at the edge of the layer is consistent with the fact that the closer the pixel points in the embedded area are to the suspected river area, the more similar the characteristics of the pixel points are to the suspected river area. ; , explain the The suspected river area The main river area at the edge of the layer has a higher expression than the The main river area expression degree of the layer edge is consistent with the fact that the closer the pixel points in the embedded area are to the main river area, the more similar the characteristics of the pixel points are to the main river area. ; The larger the value, the closer the pixel point in the embedded area is to the suspected river area, the more similar its features are to the suspected river area. At the same time, the closer it is to the main river area, the more similar its features are to the main river area, and the greater the expression of the blending feature of the corresponding layer edge.

[0101] Finally, traverse all layer edges of the embedded region to obtain the fusion feature expression of the embedded region. The calculation formula for the fusion feature expression of the embedded region is:

[0102]

[0103] Where, Indicates the The degree of expression of the blended features of the embedded regions; Indicates the The number of layer edges contained in an embedded region; Indicates the The embedded area The degree of expression of the blending characteristics of layer edges.

[0104] Similarly, we get The expression of the blending characteristics of each embedded area of the suspected river area and the main river area.

[0105] S500: Obtain all tributary river regions in the remote sensing image according to the blending feature expression corresponding to all embedded regions of the suspected river region.

[0106] According to the fusion feature expression corresponding to all embedded areas of the suspected river area, all the river areas in the remote sensing image are obtained. The specific implementation method is as follows: When the suspected river area is a river area, The expression of the blending characteristics of the multiple embedded areas of the suspected river area and the main river area is relatively obvious, and the expression of the blending characteristics of each embedded area is relatively similar. Therefore, first, according to the expression of the blending characteristics corresponding to all embedded areas of the suspected river area, the first Specifically, the river feature expression degree of each suspected river region is calculated, and the mean and variance of the blending feature expression degree corresponding to all embedded regions of the suspected river region are calculated to obtain the river feature expression degree of the suspected river region. The formula for calculating the river characteristic expression of a suspected river area is:

[0107]

[0108] Where, Indicates the The degree of river feature expression in suspected river areas; Indicates the The mean value of the expression of the blending characteristics of the suspected river area and all embedded areas of the main river area; Indicates the The variance of the expression of the blending characteristics of the suspected river area and all embedded areas of the main river area; To prevent hyperparameters with a denominator of 0; express Function for normalization.

[0109] The larger the value, the more consistent it is with the characteristics of the greater degree of expression of the integration characteristics of the embedded areas of the two river regions; The smaller the value, the more consistent it is with the fact that the integration characteristics of the embedded areas of the two river regions are relatively similar.

[0110] Then, set the river feature expression threshold , , the suspected river areas whose river feature expression is greater than the river feature expression threshold are regarded as tributary river areas, and all tributary river areas in the remote sensing image are obtained.

[0111] S600: Complete the river drawing based on the main river area and the tributary river area.

[0112] Based on the distance between the remote sensing satellite and the ground when the remote sensing image was captured, the distance represented by the width of each pixel in the remote sensing image is obtained. The product of the width of the river area (main river area and tributary river area) at each location in the remote sensing image and the width of each pixel in the remote sensing image is used as the actual width of the river area (main river area and tributary river area) at that location. This completes the acquisition of river width during the surveying and mapping process and completes the river mapping.

[0113] Based on the same inventive concept as the above method, this embodiment also provides a surveying and mapping system for dynamic remote sensing monitoring.

[0114] See also Figure 3, which shows the basic composition of a surveying and mapping system for dynamic remote sensing monitoring provided by an embodiment of the present invention.

[0115] like Figure 3 As shown, a surveying and mapping system for dynamic remote sensing monitoring includes: a memory 10 and a processor 20, wherein:

[0116] Memory 10, for storing program code;

[0117] The processor 20 is used to read the program code stored in the memory 10 and execute it to obtain multiple remote sensing images of the river to be mapped; perform edge detection on the remote sensing image to obtain multiple suspected river areas; analyze the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image; obtain multiple embedded areas of the suspected river area and the main river area in the remote sensing image, analyze the differences between the grayscale values of the pixels in the embedded area and the grayscale values of the pixels in the main river area and the suspected river area, and obtain the blending feature expression of the embedded area; obtain all the tributary river areas in the remote sensing image based on the blending feature expression corresponding to all the embedded areas of the suspected river area; and complete the mapping of the river based on the main river area and the tributary river area.

[0118] Furthermore, 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 branch river region acquisition module 24 and a river drawing module 25.

[0119] A remote sensing image acquisition module 21 is used to obtain multiple remote sensing images of the river to be mapped;

[0120] The suspected river region acquisition module 22 is used to perform edge detection on the remote sensing image to obtain multiple suspected river regions;

[0121] The main river region acquisition module 23 is used to analyze the grayscale distribution characteristics of the pixels in the suspected river region to obtain a main river region in the remote sensing image;

[0122] The tributary river region acquisition module 24 is configured to acquire multiple embedded regions of suspected river regions and main river regions in the remote sensing image, analyze the differences between the grayscale values of pixels in the embedded regions and the grayscale values of pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions; and obtain all tributary river regions in the remote sensing image based on the blending feature expression corresponding to all embedded regions of the suspected river region.

[0123] The river drawing module 25 is used to complete the river drawing based on the main river area and the branch river area.

[0124] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A surveying and mapping method for dynamic remote sensing monitoring, characterized in that: The method comprises: Obtain multiple remote sensing images of the river to be mapped; Performing edge detection on the remote sensing image to obtain multiple suspected river areas; Analyze the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area in the remote sensing image; Acquire multiple embedded regions of the suspected river region and the main river region in the remote sensing image, analyze the differences between the grayscale values of pixels in the embedded regions and the grayscale values of pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions; Obtaining all tributary river regions in the remote sensing image according to the blending feature expression corresponding to all embedded regions of the suspected river region; Complete river mapping based on the main river area and the tributary river area; Analyzing the grayscale distribution characteristics of the pixels in the suspected river area to obtain a main river area of the remote sensing image includes: Analyze the discrete degree of the grayscale values of the pixels in the suspected river area to obtain the possibility that the suspected river area is a main river area; Analyzing the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image, and correcting the possibility to obtain a corrected possibility; taking the suspected river area corresponding to the maximum correction possibility as a main river area of the remote sensing image; Analyzing the difference distribution between the grayscale values of the pixels in the embedded area and the grayscale values of the pixels in the main river area and the suspected river area, and obtaining the blending feature expression of the embedded area, including: obtaining a plurality of layer edges of the embedded region; Determining whether the embedded area belongs to the main river area or the suspected river area; If the embedded area belongs to the suspected river area, analyzing the first difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel points in the main river area, and obtaining the main river area representation degree of each pixel point at the layer edge; If the embedded area belongs to the main river area, analyzing the second difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel points in the suspected river area, and obtaining the suspected river area expression degree of each pixel point at the layer edge; Analyzing a first difference between the expression degrees of the main river region corresponding to the layer edge and other layer edges, and analyzing a second difference between the expression degrees of the suspected river region corresponding to the layer edge and other layer edges, to obtain a blending feature expression degree of the layer edge; All the layer edges of the embedded area are traversed to obtain the blending feature expression of the embedded area.

2. The surveying and mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that: Edge detection is performed on the remote sensing image to obtain multiple suspected river areas, including: Performing edge detection on the remote sensing image to obtain a plurality of edges and edge detection areas in the remote sensing image; The edge detection area that shares a common edge with the remote sensing image is recorded as a suspected river area, and a plurality of suspected river areas of the remote sensing image are obtained.

3. The surveying and mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that: Analyzing the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image includes: Choose a gray value b and calculate the gray value in the suspected river area as The ratio of the number of pixels in the suspected river area to the number of pixels with a grayscale value of b in the remote sensing image is combined with the number of pixels with a grayscale value of b in the suspected river area to obtain the distribution characteristics of the grayscale values of the pixels in the suspected river area in the remote sensing image.

4. The surveying and mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that: Acquiring a plurality of embedded regions of the suspected river region and the main river region in the remote sensing image, comprising: Obtaining the skeletons of the main river area and the suspected river area; A plurality of suspected embedded regions are obtained by drawing a straight line parallel to the skeleton of the suspected river region through the common edge of the main river region and the suspected river region; Determining whether the suspected embedded area belongs to the main river area or the suspected river area; Get the minimum bounding rectangle of each suspected embedded area; Analyzing the ratio of the number of pixels in the minimum bounding rectangle that are included in another region to which the suspected embedded region does not belong to and the total number of pixels in the minimum bounding rectangle to obtain the embedding expressiveness of the suspected embedded region; An embedding expression threshold is set, and based on the embedding expression, a plurality of embedding regions of the suspected river region and the main river region in the remote sensing image are obtained.

5. The surveying and mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that: If the embedded area belongs to a suspected river area, analyzing a first difference distribution between the grayscale value of each pixel point at the layer edge and the grayscale value of the pixel points in the main river area includes: Calculate the absolute value of the difference between the grayscale value of the pixel point at the edge of the layer and the average grayscale value of all pixels in the main river area, and record it as the grayscale value difference; Calculate the ratio of the number of pixels whose absolute value of the difference between the grayscale value of the pixel points on the suspected river area direction side of the pixel points at the edge of the layer and the grayscale value mean is greater than the grayscale value difference, and the total number of pixels on the suspected river area direction side of the pixel points at the edge of the layer, and combine the grayscale value difference to obtain the first difference distribution between the grayscale value of each pixel point at the edge of the layer and the grayscale value of the pixel points in the main river area.

6. The surveying and mapping method for dynamic remote sensing monitoring according to claim 1, characterized in that: According to the blending feature expression corresponding to all embedded regions of the suspected river region, all tributary river regions in the remote sensing image are obtained, including: Calculating the mean and variance of the blending feature expression corresponding to all embedded regions of the suspected river region to obtain the river feature expression of the suspected river region; A river feature expression threshold is set, and the suspected river regions whose river feature expression is greater than the river feature expression threshold are taken as tributary river regions, so as to obtain all tributary river regions in the remote sensing image.

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

8. The surveying and mapping system for dynamic remote sensing monitoring according to claim 7, characterized in that: The processor includes: Remote sensing image acquisition module, used to obtain multiple remote sensing images of the river to be mapped; a suspected river region acquisition module, configured to perform edge detection on the remote sensing image to obtain a plurality of suspected river regions; A main river region acquisition module is used to analyze the grayscale distribution characteristics of the pixels in the suspected river region to obtain a main river region in the remote sensing image; a tributary river region acquisition module, configured to acquire multiple embedded regions of the suspected river region and the main river region in the remote sensing image, analyze the differences between the grayscale values of the pixels in the embedded regions and the grayscale values of the pixels in the main river region and the suspected river region, and obtain the blending feature expression of the embedded regions; and obtain all tributary river regions in the remote sensing image based on the blending feature expression corresponding to all embedded regions of the suspected river region; The river drawing module is used to complete the river drawing according to the main river area and the branch river area.

Images