Target segmentation vector boundary simplification method, electronic equipment and storage medium

Abstract

The invention discloses a target segmentation vector boundary simplification method, electronic equipment and a storage medium, and relates to the technical field of remote sensing. The method comprises the following steps: acquiring a remote sensing image, and performing target segmentation on the remote sensing image to obtain raster data; converting the raster data into vector data; combining adjacent surface element vectors with common boundaries to obtain a plurality of combined surface elements; extracting an intersection point of each common boundary and the boundary of the corresponding combined surface element as an anchor point; according to the anchor points, performing segmentation simplification on the boundary and the common boundary of each combined surface element to obtain a plurality of simplified broken lines of which the head ends and the tail ends are connected; and performing line cutting on the multiple simplified broken lines to obtain a boundary simplification result. According to the target segmentation vector boundary simplification method provided by the embodiment of the invention, the condition that a plurality of broken lines in an intersection relationship exist in a vector result of target segmentation is solved, and the problems that topological errors such as overlapping and gaps occur and the topological consistency is changed are avoided.

Description

Technical Field

[0001] The invention relates to the field of remote sensing technology, and in particular to a target segmentation vector boundary simplification method, electronic equipment and storage medium. Background Art

[0002] Remote sensing target segmentation is an important part of remote sensing image processing, which refers to the process of identifying and separating specific targets or objects in remote sensing images covering a large area with rich geographic information and complex scene structures. The application of remote sensing target segmentation covers many fields such as land cover classification, disaster monitoring, urban planning, military reconnaissance, etc.

[0003] At present, the target segmentation methods for high-resolution remote sensing images are mainly divided into two categories. One is to interpret and segment the targets or objects in remote sensing images by industry personnel with professional knowledge. The vector data drawn by this method is relatively accurate, but it takes a long time and requires a lot of manpower and time, and is not suitable for large-scale target segmentation. The second is to use various remote sensing indexes and machine learning, deep learning and other algorithms to capture the spectral and semantic features of the target or object, design a special segmentation process, perform target segmentation to obtain the corresponding raster image, and convert it into vector data for related data analysis and thematic map production. However, in this sampling method, after converting the raster image into vector data, the vector data boundary appears rough and easy to appear jagged due to the influence of the raster image pixel boundary, especially when the boundary does not match the smooth contour of the target object in the remote sensing image, it is difficult to meet the needs of practical applications such as high-precision boundary map production and related analysis. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a target segmentation vector boundary simplification method, electronic device and storage medium, which can optimize the boundary simplification effect of remote sensing images.

[0005] In a first aspect, a target segmentation vector boundary simplification method according to an embodiment of the present invention comprises the following steps:

[0006] Acquire remote sensing images, and perform target segmentation on the remote sensing images to obtain raster data;

[0007] Converting the raster data into vector data, wherein the vector data includes a plurality of surface element vectors;

[0008] Merging adjacent surface element vectors having a common boundary to obtain a plurality of merged surface elements;

[0009] Extracting the intersection of each common boundary and the boundary of the corresponding merged face element as an anchor point;

[0010] According to the anchor point, the boundary of each merged face element and the common boundary are simplified in sections to obtain a plurality of simplified polylines connected at the head and tail ends;

[0011] Line clipping is performed on the plurality of simplified polylines to obtain a boundary simplification result.

[0012] According to some embodiments of the present invention, the step of converting the raster data into vector data comprises:

[0013] Eliminate background pixel values ​​of the raster data;

[0014] The remaining pixel values ​​of the raster data are traversed, and the raster data is polygonized according to the identified continuous pixel groups with the same value, and converted into vector data.

[0015] According to some embodiments of the present invention, the step of merging adjacent surface element vectors having a common boundary to obtain a plurality of merged surface elements includes:

[0016] Performing neighborhood analysis on the plurality of surface element vectors, constructing a spatial index, and determining the neighboring relationship between the surface element vectors;

[0017] For any two adjacent surface element vectors, the boundary coordinates of the two surface element vectors are traversed to extract the common boundary of the two adjacent surface element vectors.

[0018] According to some embodiments of the present invention, when there are holes in the merged surface element, the inner and outer ring boundaries of the merged surface element are extracted, and the intersection of the inner and outer ring boundaries of the merged surface element and the common boundary is used as an anchor point.

[0019] According to some embodiments of the present invention, the step of performing segmented simplification on the boundary of each merged surface element and the common boundary according to the anchor point to obtain a plurality of simplified polylines connected at their end and end includes:

[0020] According to the anchor point, the boundary of each of the merged surface elements and the common boundary are segmented, and the boundary of the merged surface elements and the common boundary are segmented into a plurality of polylines connected at their head and tail ends;

[0021] When there is a discontinuous common boundary between two adjacent surface element vectors, the discontinuous common boundary is segmented to obtain a plurality of polylines connected at the head and tail ends;

[0022] The Douglas-Peucker algorithm is used to simplify each segmented polyline to obtain a plurality of simplified boundary polylines and a common boundary polyline.

[0023] According to some embodiments of the present invention, when the inner and outer ring boundaries of the merged surface element with holes are divided into polylines, the correspondence between the inner and outer ring boundaries of the merged surface element with holes is recorded by constructing an index.

[0024] According to some embodiments of the present invention, the step of performing line clipping on the plurality of simplified polylines to obtain a boundary simplification result includes:

[0025] The plurality of simplified polylines are spliced ​​and transformed according to the coordinates of the first and last ends to form a surface element, thereby obtaining a boundary simplification result;

[0026] When the boundary polylines of the merged surface elements with holes are spliced ​​and converted into surface elements according to the first and last end coordinates, the conversion is performed according to the index.

[0027] According to some embodiments of the present invention, the step of performing line clipping on the plurality of simplified polylines to obtain a boundary simplification result further includes:

[0028] Determine whether the coordinate points of the first and last ends of the common boundary polyline intersect with the inner ring boundary of the merged surface element with holes;

[0029] If there are intersections, extract the boundary coordinates between the intersections to construct polylines, and splice the polylines whose starting point of each common boundary polyline is consistent with the coordinates of the tail ends of other polylines until there are no two polylines with the same starting and tail coordinates.

[0030] In a second aspect, an electronic device according to an embodiment of the present invention includes:

[0031] A memory for storing program instructions;

[0032] The processor is used to call the program instructions stored in the memory, and execute the target segmentation vector boundary simplification method described in the embodiment of the first aspect according to the obtained program instructions.

[0033] In a third aspect, a storage medium according to an embodiment of the present invention stores computer executable instructions, and the computer executable instructions are used to enable a computer to execute the target segmentation vector boundary simplification method described in the embodiment of the first aspect.

[0034] According to the target segmentation vector boundary simplification method, electronic device and storage medium of the embodiment of the present invention, there are at least the following beneficial effects: after converting the extraction result of remote sensing target segmentation into vectors, by extracting specific anchor points between vectors, the common boundary of the vectors and the boundary of the merged surface elements are simplified in different ways to obtain optimized vector boundary simplification results, which solves the problem that there are multiple intersecting broken lines in the vector result of target segmentation, avoids topological errors such as overlaps and gaps, and changes in topological consistency. While solving the jagged problem, this method retains the key feature points of the broken line contour, refines the results, improves the visual quality of the segmentation results, reduces the computational complexity, can meet the actual needs of the geographic information industry, and is conducive to practical applications such as high-precision boundary map production and related spatial analysis.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0037] Figure 1 A flowchart of the steps of a method for simplifying the boundary of a target segmentation vector according to an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of a target segmentation vector boundary simplification method according to an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of a remote sensing image according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of an anchor point according to an embodiment of the present invention;

[0041] Figure 5 It is a schematic diagram of the boundary simplification result according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limitations on the present application. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0043] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0044] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0045] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] In the current research on remote sensing target segmentation, various remote sensing indices and machine learning, deep learning and other algorithms have been able to perform relatively accurate segmentation and extraction of targets or objects. However, after the extracted raster data is converted into vector data, the boundaries of the vector data appear to be relatively rough and easily jagged, especially when the boundaries do not match the smooth contours of the targets or objects in the remote sensing images. This makes it difficult to meet the needs of practical applications. Moreover, the existing boundary simplification methods directly simplify each element, which can easily cause topological errors and change the shape of the original elements.

[0047] To this end, an embodiment of the present invention provides a method, electronic device and storage medium for simplifying target segmentation vector boundaries. After converting the extraction results of remote sensing target segmentation into vectors, by extracting specific anchor points between vectors, the common boundaries of the vectors and the merged surface element boundaries are simplified in different ways to obtain optimized vector boundary simplification results, thereby solving the problem that there are multiple intersecting broken lines in the vector results of target segmentation, avoiding topological errors such as overlaps and gaps, and changing the topological consistency. The Douglas-Peucker algorithm is introduced to simplify the boundaries, and the purpose of not changing the main shape, removing jaggedness and simplifying the boundaries is achieved by retaining the key feature points of the contour. While solving the jagged problem, the key feature points of the broken line contour are retained to refine the results, improve the visual quality of the segmentation results, and reduce the computational complexity. It can meet the actual needs of the geographic information industry and is conducive to the practical applications of high-precision boundary map production and related spatial analysis.

[0048] The object segmentation vector boundary simplification method, electronic device and storage medium according to the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] On the one hand, the embodiment of the present invention proposes a method for simplifying the boundary of a target segmentation vector, such as Figure 1 and Figure 2 As shown, the method comprises the following steps:

[0050] Step S100: acquiring a remote sensing image, and performing target segmentation on the remote sensing image to obtain raster data;

[0051] Step S200: converting raster data into vector data, where the vector data includes a plurality of surface element vectors;

[0052] Step S300: merging adjacent surface element vectors having a common boundary to obtain a plurality of merged surface elements;

[0053] Step S400: extracting the intersection of each common boundary and the boundary of the corresponding merged face element as an anchor point;

[0054] Step S500: Segmentally simplifying the boundary and common boundary of each merged face element according to the anchor point to obtain a plurality of simplified polylines connected at the head and tail ends;

[0055] Step S600: performing line clipping on a plurality of simplified polylines to obtain a boundary simplification result.

[0056] Specifically, in step S100, after acquiring the remote sensing image, existing algorithms such as machine learning and deep learning can be used to segment the remote sensing image, thereby extracting raster data corresponding to each target / land object.

[0057] After obtaining the raster data, the raster data extracted by target segmentation needs to be converted into vector data containing surface feature vectors. Compared with point and line features, surface feature vectors can retain the classification information in the raster data, which is convenient for subsequent splicing of polylines and construction of simplified surfaces.

[0058] In some embodiments of the present invention, in the above step S200, converting raster data into vector data includes the following two steps:

[0059] (1) Eliminate the background pixel values ​​of the raster data;

[0060] (2) Traverse the remaining pixel values ​​of the raster data, and polygonize the raster data according to the identified continuous pixel groups with the same value, and convert them into vector data.

[0061] Specifically, in order to remove the background pixel value, the raster data obtained after the target segmentation is firstly subjected to threshold processing, that is, the threshold is set in advance, and then all the pixel values ​​of the raster data are compared with the threshold, and the background pixel value is determined by the comparison result. Then, the background pixel value is removed, and then all the remaining pixel values ​​are traversed to identify the continuous pixel group with the same value, and the polygonization is used to construct the boundary, which is converted into multiple surface element vectors to obtain the vector data of the target segmentation. Figure 3 As shown, the yellow part is the vector data of target segmentation and the red dot is the vector inflection point.

[0062] After converting raster data into vector data, it is necessary to merge adjacent face element vectors in the vector data to avoid inconsistent retained vertex points after simplifying the common boundaries of the face element vectors, resulting in topological errors such as overlaps and gaps. To this end, in this example, the above step S300: merging adjacent face element vectors with common boundaries to obtain a number of merged face elements, includes the following two steps:

[0063] (1) Perform neighborhood analysis on multiple surface element vectors, construct a spatial index, and determine the neighboring relationship between each surface element vector;

[0064] (2) For any two adjacent surface element vectors, traverse the boundary coordinates of the two surface element vectors and extract the common boundary of the two adjacent surface element vectors.

[0065] By performing neighborhood analysis on each face element vector and constructing a spatial index, the adjacent relationship between each face element vector is determined. For any two adjacent face element vectors, the boundary coordinates of the two are traversed and compared, and the completely overlapping boundary coordinates are recorded to extract the common boundary between adjacent faces. At the same time, the adjacent face element vectors are merged to form a merged face element.

[0066] After merging the adjacent face element vectors, the intersection of each common boundary and the boundary of the corresponding merged face element is extracted as the anchor point to ensure the consistency of the topological relationship. Figure 3 As shown in the middle area ① and ②, in order to avoid the problem of overlapping, gaps and other changes in the consistency of topological relationships caused by directly simplifying the adjacent area element vectors of similar areas ① and ②, the area element vectors with common boundaries in the target segmentation vector data are merged, and all area element vectors are traversed to record the boundary coordinates of all merged area elements and the boundary coordinates of the common boundary. If there are holes in the merged area elements, the boundary coordinates of the inner and outer rings of the merged area elements are extracted, and the intersection of the boundaries of each merged area element and the common boundary is used as a specific anchor point, as shown in Figure 4 As shown in the figure, the red dots are the extracted anchor points.

[0067] After extracting the anchor points, the boundaries and common boundaries of each merged face element are segmented and simplified according to the anchor points to obtain a plurality of simplified polylines connected at the head and tail ends. Specifically, the above step S500 includes the following three steps:

[0068] (1) According to the anchor point, the boundary and common boundary of each merged surface element are segmented, and the boundary and common boundary of the merged surface element are segmented into multiple polylines connected at the head and tail ends;

[0069] (2) When there is a discontinuous common boundary between two adjacent face element vectors, the discontinuous common boundary is segmented to obtain multiple polylines connected at the head and tail ends;

[0070] (3) Use the Douglas-Peucker algorithm to simplify each segmented polyline to obtain multiple simplified boundary polylines and common boundary polylines.

[0071] like Figure 2 As shown, the boundaries and common boundaries of the merged surface elements are segmented according to the anchor points to obtain multiple polylines connected at the beginning and the end, and each polyline is simplified using a boundary simplification algorithm to obtain multiple simplified boundary polylines of the merged surface elements and common boundary polylines of the common boundary.

[0072] Using the obtained anchor points to segmentally simplify the merged face feature vectors and common boundaries can help reduce the occurrence of complex polylines and avoid topological errors such as self-commonality that are prone to occur in the current boundary simplification algorithm.

[0073] Furthermore, the boundary simplification algorithm used in the embodiment of the present invention is the Douglas-Peucker algorithm, the recursive process of which is to select an endpoint on the line segment sequence as a convex point, and then find the point farthest from the convex point. If the difference between the error straight-line distance between the farthest point and the convex point and the actual curve distance is less than the preset tolerance value, then except for the convex point and the farthest point, the remaining points are ignored, thereby reducing the number of points in the polyline while maintaining its overall shape, achieving the effect of simplifying the polyline. The algorithm meets the conditions for preserving the overall spatial distribution of the graphics, and the implementation principle based on distance threshold judgment is more in line with the vector result of target segmentation than other boundary simplification algorithms.

[0074] By using anchor points to segment the boundaries of each merged polygon element, the boundaries of each merged polygon element are segmented into multiple polylines connected at the head and tail ends, and the Douglas-Peucker algorithm is used to simplify each segmented boundary polyline to obtain multiple simplified boundary polylines. Traverse all the common boundary polylines to see if there are discontinuous common boundaries, such as Figure 3 As shown in area ②, there are discontinuous common boundaries between adjacent face element vectors. The discontinuous common boundaries are segmented using multiple anchor points to obtain multiple polylines connected at the beginning and end. Then, the Douglas-Peucker algorithm is used to simplify each common boundary polyline to obtain a simplified common boundary polyline.

[0075] It should be noted that when the inner and outer ring boundaries of a merged polygon element with holes are divided into polylines, an index is constructed to record the correspondence between the inner and outer ring boundaries of the merged polygon element with holes, so as to facilitate subsequent line segment to polygon operations.

[0076] Among them, the tolerance value of the Douglas-Peucker algorithm set in this example is 0.00001, that is, the inflection points within the difference of about 1.11 meters between the straight-line distance and the actual curve distance are ignored. The tolerance value can be adjusted according to the remote sensing image resolution and the ground objects extracted by target segmentation. In this example, the selected image is the Gaofen-2 satellite remote sensing image with a resolution of 0.8 meters, and the ground object extracted by target segmentation is cultivated land. The tolerance value of 0.00001 will not change the main shape of the original cultivated land elements.

[0077] For the inner ring coordinates of the previously merged surface elements with holes, retrieve the intersection of the common boundary and the inner ring boundary, connect the common boundary polyline after splicing and simplification with the inner ring boundary, clip the vectors of each merged surface element, and obtain the vector boundary simplification result.

[0078] After obtaining a plurality of simplified boundary polylines and common boundary polylines, the boundary polylines and the common boundary polylines are subjected to line clipping to obtain boundary simplification results. The above step S600 includes the following two steps:

[0079] (1) Multiple simplified polylines are spliced ​​and transformed according to the coordinates of the first and last ends to form a surface element, and the boundary simplification result of the merged surface vector is obtained;

[0080] (2) When the boundary polylines of a merged face element with holes are converted into face elements by splicing them according to the coordinates of the first and last ends, the conversion is performed according to the index.

[0081] Among them, when the polylines of the inner and outer ring boundaries of the simplified merged surface element with holes are spliced ​​and converted into surface elements according to the first and last end coordinates, it is necessary to perform the conversion according to the corresponding relationship of the previously constructed index.

[0082] For each simplified common boundary polyline, determine whether its starting and ending coordinate points have intersections with the inner ring boundary of the merged face vector with holes. If there is an intersection, each inner ring boundary must have more than two intersections. Extract the boundary coordinates between the intersections to construct polylines, and splice the polylines whose starting and ending coordinates are consistent with those of the other polylines to ensure directional consistency. The splicing steps are performed until there are no two polylines with the same starting and ending coordinate points.

[0083] Among them, when extracting common boundaries, such as Figure 3 As shown in areas ① and ②, due to the presence of holes between the two faces, it is easy to extract the common boundary as multiple polylines. Therefore, it is necessary to merge adjacent face elements, obtain the coordinates of their inner ring boundaries, and splice them with the intersecting common boundaries to form a polyline, which is convenient for the subsequent implementation of the line clipping face algorithm.

[0084] Finally, the line clipping surface operation is performed on the boundary simplification result of the merged face vector by the spliced ​​common boundary polyline to obtain the boundary simplification result of the target segmentation vector, as shown in Figure 5 shown.

[0085] According to the target segmentation vector boundary simplification method of the embodiment of the present invention, after converting the extraction result of remote sensing target segmentation into vectors, by extracting specific anchor points between vectors, the common boundary of the vectors and the boundary of the merged face elements are simplified in different ways to obtain the optimized vector boundary simplification result, which solves the problem that there are multiple intersecting broken lines in the vector result of target segmentation, and avoids the problems of topological errors such as overlaps and gaps, and changes in topological consistency. The Douglas-Peucker algorithm is introduced to simplify the boundary, and the purpose of not changing the main shape, removing jaggedness, and simplifying the boundary is achieved by retaining the key feature points of the contour. While solving the jagged problem, the key feature points of the broken line contour are retained to refine the result, improve the visual quality of the segmentation result, and reduce the computational complexity. It can meet the actual needs of the geographic information industry and is conducive to the practical applications of high-precision boundary map production and related spatial analysis.

[0086] On the other hand, an embodiment of the present invention further provides an electronic device, including:

[0087] A memory for storing program instructions;

[0088] The processor is used to call the program instructions stored in the memory and execute the above-mentioned target segmentation vector boundary simplification method according to the obtained program instructions.

[0089] The processor may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0090] The memory can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory, and the processor calls and executes the shift control method of the bicycle electronic transmission in the embodiments of this application; the memory and the processor can be connected through a bus or the like.

[0091] On the other hand, an embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the above-mentioned target segmentation vector boundary simplification method is implemented.

[0092] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0094] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to the exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.

[0095] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.

[0096] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.

[0097] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages ​​include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages ​​or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.

[0098] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0099] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A target segmentation vector boundary simplification method, characterized in that: The following steps are involved: Acquire remote sensing images, and perform target segmentation on the remote sensing images to obtain raster data; Converting the raster data into vector data, wherein the vector data includes a plurality of surface element vectors; Merging adjacent surface element vectors having a common boundary to obtain a plurality of merged surface elements; Extracting the intersection of each common boundary and the boundary of the corresponding merged face element as an anchor point; According to the anchor point, the boundary of each merged face element and the common boundary are simplified in sections to obtain a plurality of simplified polylines connected at the head and tail ends; Line clipping is performed on the plurality of simplified polylines to obtain a boundary simplification result.

2. The target segmentation vector boundary simplification method according to claim 1, characterized in that: The step of converting the raster data into vector data comprises: Eliminate background pixel values ​​of the raster data; The remaining pixel values ​​of the raster data are traversed, and the raster data is polygonized according to the identified continuous pixel groups with the same value, and converted into vector data.

3. The target segmentation vector boundary simplification method according to claim 1, characterized in that: The step of merging adjacent surface element vectors having a common boundary to obtain a plurality of merged surface elements comprises: Performing neighborhood analysis on the plurality of surface element vectors, constructing a spatial index, and determining the neighboring relationship between the surface element vectors; For any two adjacent surface element vectors, the boundary coordinates of the two surface element vectors are traversed to extract the common boundary of the two adjacent surface element vectors.

4. The target segmentation vector boundary simplification method according to claim 1, characterized in that: When there are holes in the merged surface element, the inner and outer ring boundaries of the merged surface element are extracted, and the intersection of the inner and outer ring boundaries of the merged surface element and the common boundary is used as an anchor point.

5. The target segmentation vector boundary simplification method according to claim 1, characterized in that: The step of performing segmented simplification on the boundary of each merged face element and the common boundary according to the anchor point to obtain a plurality of simplified polylines connected at the head and tail ends comprises: According to the anchor point, the boundary of each of the merged surface elements and the common boundary are segmented, and the boundary of the merged surface elements and the common boundary are segmented into a plurality of polylines connected at their head and tail ends; When there is a discontinuous common boundary between two adjacent surface element vectors, the discontinuous common boundary is segmented to obtain a plurality of polylines connected at the head and tail ends; The Douglas-Peucker algorithm is used to simplify each segmented polyline to obtain a plurality of simplified boundary polylines and a common boundary polyline.

6. The target segmentation vector boundary simplification method according to claim 5, characterized in that: When the inner and outer ring boundaries of the merged surface element with holes are divided into polylines, the corresponding relationship between the polylines of the inner and outer ring boundaries of the merged surface element with holes is recorded by constructing an index.

7. The target segmentation vector boundary simplification method according to claim 6, characterized in that: The step of performing line clipping on the plurality of simplified polylines to obtain a boundary simplification result comprises: The plurality of simplified polylines are spliced ​​and transformed according to the coordinates of the first and last ends to form a surface element, thereby obtaining a boundary simplification result; When the boundary polylines of the merged surface elements with holes are spliced ​​and converted into surface elements according to the first and last end coordinates, the conversion is performed according to the index.

8. The target segmentation vector boundary simplification method according to claim 7, characterized in that: The step of performing line clipping on the plurality of simplified polylines to obtain a boundary simplification result also includes: Determine whether the coordinate points of the first and last ends of the common boundary polyline intersect with the inner ring boundary of the merged surface element with holes; If there are intersections, extract the boundary coordinates between the intersections to construct polylines, and splice the polylines whose starting point of each common boundary polyline is consistent with the coordinates of the tail ends of other polylines until there are no two polylines with the same starting and tail coordinates.

9. An electronic device, characterized in that: include: A memory for storing program instructions; The processor is used to call the program instructions stored in the memory, and execute the target segmentation vector boundary simplification method according to any one of claims 1 to 8 according to the obtained program instructions.

10. A storage medium, characterized in that: The storage medium stores computer executable instructions, and the computer executable instructions are used to enable a computer to execute the target segmentation vector boundary simplification method according to any one of claims 1 to 8.

Images