Roadway contour line generation method and device, equipment and storage medium
By automatically identifying the center of the house element and potential local contour lines, combined with topological connection optimization technology, the problem of difficult to identify narrow tunnels on remote sensing images is solved, and fast and accurate tunnel generation is achieved.
Patent Information
- Application Number
- CN202510915446.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-03
- Publication Date
- 2025-08-29
AI Technical Summary
In the prior art, narrow tunnels are difficult to identify on remote sensing images, resulting in low manual drawing efficiency and strong subjectivity, and it is impossible to quickly and accurately identify tunnels in the map.
By obtaining the contour feature information of house elements in the map, determining the center of shape information, generating potential local contour lines, and automatically identifying and generating tunnel contour lines based on the contour feature information and center of shape information, center of shape is used to analyze the spatial distribution of center of shape and topological connection optimization technology.
It realizes rapid and accurate identification of tunnels in the map. The generated tunnel contours meet the minimum pass width requirements, maintain spatial consistency, and avoids inefficiency and subjective errors in manual drawing.
Smart Images
Figure CN120562025A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of lane identification technology, and in particular to a lane contour generation method, device, equipment and storage medium. Background Art
[0002] Narrow alleyways are often required for urban and rural planning, land surveys, and map updates. These linear features, often located between houses, are difficult to identify in remote sensing imagery due to their small size and lack of image features. Therefore, manual alleyway mapping is often required. However, manual alleyway identification and mapping is inefficient and subjective, making it difficult to quickly and accurately identify alleyways on maps. Summary of the Invention
[0003] The purpose of this application is to provide a method, device, equipment and storage medium for generating lane contour lines, which can quickly and accurately identify lanes in a map.
[0004] The present invention provides a method for generating a roadway contour line, including: Acquire a map to be processed, and determine outline feature information of house elements in the map to be processed; Determining centroid information of the centroid of the house element based on the outline feature information; the centroid information includes position information of the centroid and distance information between adjacent centroids; Based on the centroid information, generating a potential local contour line corresponding to the house element; determining a local roadway contour line based on the potential local contour line and the contour feature information; According to the local lane contour line, a corresponding lane contour line is generated.
[0005] In some embodiments, determining the centroid information of the centroid of the house element based on the outline feature information includes: When the outline feature information indicates that the top view outline of the house element is a regular shape, the geometric centroid of the house element is selected as the centroid; when the outline feature information indicates that the top view outline of the house element is an irregular shape, the minimum circumscribed rectangle corresponding to the house element is determined, and the geometric centroid of the minimum circumscribed rectangle is selected as the centroid; The centroid information is determined based on the image coordinate information of the centroid.
[0006] In some embodiments, generating a potential local contour line corresponding to the house element based on the centroid information includes: Based on the centroid information, determining the perpendicular bisector of the line connecting adjacent centroids; Based on the perpendicular bisector, generating a Thiessen polygon corresponding to the centroid; Based on the Thiessen polygons, the potential local contour lines are determined.
[0007] In some embodiments, determining a local roadway contour line based on the potential local contour line and the contour feature information includes: Based on the outline feature information, a target local contour line is selected; the target local contour line is a potential local contour line whose distance from the top-view contour of the house element is not less than a preset threshold distance; The local roadway contour line is selected based on the number of end connections of the target local contour line.
[0008] In some embodiments, before selecting the local roadway contour line based on the number of end connections of the target local contour line, the method further includes: Performing a fusion operation on each of the target local contour lines to obtain a fused contour line; The fused contour line is interrupted at the connecting points between the target local contour lines to obtain an optimized target local contour line.
[0009] In some embodiments, selecting the local roadway contour line based on the number of end connections of the target local contour line includes: Determining the regional boundaries of the areas where each of the housing elements is located; For a first local contour line, a first boundary perpendicular line and a second boundary perpendicular line are generated; the first local contour line is a target local contour line having one connection end connected to at least two other target local contour lines and the other connection end not connected to any other target local contour line; the first boundary perpendicular line is a contour line passing through a connecting point of the two connected first local contour lines and perpendicular to a region boundary closest to the connecting point; the second boundary perpendicular line is a contour line passing through a non-connecting end of the isolated first local contour line and perpendicular to a region boundary closest to the non-connecting end; The second local contour line is eliminated, and the third local contour line, the first local contour line, the first boundary perpendicular line and the second boundary perpendicular line are used as the local tunnel contour line; the second local contour line is a target local contour line whose two connection ends are not connected to other target local contour lines, and the third local contour line is a target local contour line whose two connection ends are respectively connected to at least two other target local contour lines.
[0010] In some embodiments, generating a corresponding lane contour line according to the local lane contour line includes: A continuous contour line composed of a plurality of the local lane contour lines is processed into a straight line segment that does not touch the top view contour of the building element to obtain the lane contour line.
[0011] The present application also provides a device for generating a lane contour line, including: The first module is used to obtain a map to be processed and determine the outline feature information of the house elements in the map to be processed; The second module is configured to determine the centroid information of the centroid of the house element based on the outline feature information; the centroid information includes the position information of the centroid and the distance information between adjacent centroids; A third module is configured to generate a potential local contour line corresponding to the house element based on the centroid information; A fourth module is configured to determine a local roadway contour line based on the potential local contour line and the contour feature information; The fifth module is used to generate a corresponding lane contour line according to the local lane contour line.
[0012] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned lane contour line generation method when executing the computer program.
[0013] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for generating a lane contour line is implemented.
[0014] The beneficial effects of this application are as follows: there is no need to rely on manual visual judgment of building gaps and manual drawing. Instead, the centroid information of the centroid of the house element is automatically determined based on the contour feature information of the house element in the map to be processed, the potential local contour line corresponding to the house element is generated based on the centroid information, the local lane contour line is determined based on the potential local contour line and the contour feature information, and finally the corresponding lane contour line is generated according to the local lane contour line. Due to the use of centroid spatial distribution analysis and the topological connection optimization combining the contour feature information of the house element with the potential local contour line, the potential channel network between the house groups can be quickly derived, ensuring that the generated lane contour line meets the minimum passage width requirements and maintains spatial coherence, and can quickly and accurately identify the lanes in the map. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 This is an application environment diagram of the lane contour line generation method provided in an embodiment of the present application.
[0016] Figure 2 This is a flow chart of the lane contour line generation method provided in an embodiment of the present application.
[0017] Figure 3 Schematic diagram of the centroid of the house element provided in the embodiment of the present application.
[0018] Figure 4 This is a schematic diagram of the Thiessen polygon provided in an embodiment of the present application.
[0019] Figure 5 Schematic diagram of the optimized target local contour line provided in an embodiment of the present application.
[0020] Figure 6 It is a schematic diagram of the first local contour line provided in an embodiment of the present application.
[0021] Figure 7 It is a schematic diagram of the second local contour line and the third local contour line provided in an embodiment of the present application.
[0022] Figure 8 This is a schematic diagram of a first boundary perpendicular line and a second boundary perpendicular line provided in an embodiment of the present application.
[0023] Figure 9 It is a schematic diagram of the lane outline provided in an embodiment of the present application.
[0024] Figure 10 It is a structural schematic diagram of the lane contour line generating device provided in an embodiment of the present application.
[0025] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.
[0027] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps illustrated may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. Terms such as "first" and "second" in the specification, claims, and drawings are used to distinguish similar items and are not intended to describe a specific sequence or precedence.
[0028] 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 application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.
[0029] The lane outline generation method provided in the embodiments of the present application can be executed by a computer device, which can be a terminal device or a server. Terminal devices include, but are not limited to, mobile phones, computers, smart home appliances, vehicle-mounted terminals, aircraft, and the like. The server can be a standalone physical server, a server cluster composed of multiple physical servers, a distributed system, or a cloud server.
[0030] In addition, the information, data, and signals involved in the embodiments of this application are authorized by the relevant objects or fully authorized by all parties, and the collection, use, and processing of relevant data comply with the relevant laws, regulations, and standards of relevant countries and regions.
[0031] Figure 1 This is an application environment diagram of the lane contour line generation method provided in the embodiment of the present application. Figure 1 , the lane contour line generation method is applied to the lane contour line generation system. The lane contour line generation system includes a terminal 110 and a server 120. The terminal 110 and the server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented as an independent server or a server cluster composed of multiple servers. The terminal 110 is used to send a map to be processed to the server 120, and the server 120 is used to obtain the map to be processed, determine the contour feature information of the house element in the map to be processed, determine the centroid information of the centroid of the house element based on the contour feature information, generate the potential local contour line corresponding to the house element based on the centroid information, determine the local lane contour line based on the potential local contour line and the contour feature information, and generate the corresponding lane contour line according to the local lane contour line. The centroid information includes the position information of the centroid and the distance information between adjacent centroids.
[0032] It should be understood that Figure 1 The application scenarios shown are only examples. In actual applications, the lane contour line generation method provided by the embodiments of the present application can also be applied to other scenarios. For example, the above-mentioned lane contour line generation method can be directly applied to terminal 110, which is used to obtain a map to be processed, determine the contour feature information of the house element in the map to be processed, determine the centroid information of the centroid of the house element based on the contour feature information, generate the potential local contour line corresponding to the house element based on the centroid information, determine the local lane contour line based on the potential local contour line and the contour feature information, and generate the corresponding lane contour line based on the local lane contour line. The centroid information includes the position information of the centroid and the distance information between adjacent centroids.
[0033] To facilitate understanding of the lane contour line generation method provided in the embodiment of the present application, the application scenario of the lane contour line generation method is exemplarily introduced below, taking the execution subject as the terminal 110 as an example.
[0034] Figure 2 This is a flow chart of a method for generating a lane outline provided in an embodiment of the present application. Figure 2 In some embodiments, the method includes but is not limited to steps 201 to 205.
[0035] Step 201: Obtain a map to be processed and determine the outline feature information of the house elements in the map to be processed.
[0036] Step 202: Determine the centroid information of the centroid of the building element based on the outline feature information.
[0037] Step 203: Generate potential local contour lines corresponding to the building elements based on the centroid information.
[0038] Step 204 : determining a local roadway contour line based on the potential local contour line and contour feature information.
[0039] Step 205: Generate a corresponding lane contour line based on the local lane contour line.
[0040] Optionally, the map to be processed can be a satellite image, referred to as a satellite image, or more accurately, a "satellite remote sensing image, also called a satellite image." Remote sensing refers to remote perception. Satellite remote sensing uses satellites in space to detect the reflection of electromagnetic waves by objects on the Earth's surface and the electromagnetic waves they emit, thereby extracting information about these objects and identifying them from a distance. The image obtained by converting and identifying this radio wave information is a satellite image. The map to be processed can be obtained through user feedback or other channels. The source of the map to be processed is not limited in the embodiments of this application.
[0041] After obtaining the map to be processed, the target detection algorithm can be used to identify the building elements in the map. Then, the outline feature detection of the building elements is performed to obtain the outline feature information of the building elements. Building elements refer to residential buildings, such as self-built houses and residential buildings. Outline feature information refers to the boundary geometric properties of the building elements in a bird's-eye view. Specifically, this can be achieved by extracting polygon vertex coordinates and edge directions through image processing algorithms, which is used to characterize the spatial form of the building's outer contour.
[0042] Centroid information includes centroid position information and distance information between adjacent centroids. It can be understood that the centroid of a building element refers to the core position reflecting the spatial distribution of the building element. The centroid position information of the building element represents the reference position information of the building element, and the distance information between adjacent centroids represents the reference distance information between adjacent building elements. After determining the outline feature information of the building element, the centroid and centroid position information of the building element are determined based on the outline feature information of the building element. Then, the distance information between each centroid and other adjacent centroids is calculated to determine the centroid information of the building element centroid.
[0043] Potential local contour lines are contour lines that may serve as local contour lines that constitute the laneway's contour line. Potential local contour lines can be obtained by calculating the perpendicular bisectors of the centroids of adjacent building elements and constructing a topological network to preliminarily characterize the equidistant boundaries between buildings.
[0044] Local laneway outlines are candidate outlines that have undergone distance screening and topology optimization. Local laneway outlines can be selected by setting a minimum distance threshold from the building outline and factoring in the number of end connections to ensure the generated outlines meet laneway clearance requirements.
[0045] Specifically, the map to be processed is first preprocessed to identify the boundary coordinates of all house elements and the outline feature information of the house elements. For each house element, the corresponding centroid is selected according to its outline shape. The calculation method can be to directly take the diagonal intersection point of the regular rectangular house element, or to generate the minimum enclosing rectangle and then take its center point for the irregular house element. All centroid coordinates are input into the spatial analysis model, the perpendicular bisectors of the adjacent centroids are calculated, and a Thiessen polygon network is constructed. In this network, the edges of the Thiessen polygons are extracted as a set of potential lane centerline candidates, that is, potential local contour lines. Then, based on the contour feature information of the potential local contour lines and the house elements, the potential local contour lines that are too close to the house elements are eliminated, and the local lane contour lines that meet the safety spacing requirements are retained. Finally, the endpoint connection of the local lane contour lines that meet the requirements is optimized to form a continuous lane contour line that does not touch the house elements.
[0046] In some embodiments, based on the contour feature information, the centroid information of the centroid of the house element is determined, including: when the contour feature information represents that the top-view contour of the house element is a regular shape, the geometric centroid of the house element is selected as the centroid; when the contour feature information represents that the top-view contour of the house element is an irregular shape, the minimum circumscribed rectangle corresponding to the house element is determined, and the geometric centroid of the minimum circumscribed rectangle is selected as the centroid; the centroid information is determined based on the image coordinate information of the centroid.
[0047] A regular shape refers to a geometric figure with an axis of symmetry or equal sides, such as a rectangle, square or regular polygon. This can be achieved through an edge straightness detection algorithm. This feature is used to distinguish standardized buildings from irregular buildings. The geometric centroid refers to the coordinates of the geometric center point of a plane figure. It can be calculated using the weighted average method of polygon vertex coordinates. This feature ensures the accuracy of the centroid positioning of regular buildings. The minimum circumscribed rectangle refers to a rectangle that completely encloses an irregular shape and has the smallest area. This can be achieved through a rotating caliper algorithm. This feature can convert complex contours into standard geometric bodies for centroid calculation. Image coordinate information refers to the planar position data of the centroid in a digital map. This can be achieved using a geographic information system coordinate system conversion module. This feature provides a spatial reference for subsequent contour line generation.
[0048] Specifically, when the contour feature information characterizes that the top-view contour of the house element presents a regular shape, such as a quadrilateral or a symmetrical polygon, the geometric centroid of the top-view contour of the house element is directly extracted as the centroid and the image coordinates of the centroid are determined. For irregular contours with uneven or tortuous edges, the minimum enclosing rectangle can be generated by the rotating caliper algorithm, and then the center point of the rectangle is calculated as an alternative centroid. The centroid coordinates are converted into unified geographic space coordinates through the map coordinate system conversion module, and the Euclidean distance values between adjacent centroids are recorded. This process automatically identifies the contour type through the shape classification module, calls the corresponding centroid calculation algorithm, and finally outputs the centroid information containing position information and spacing data. The effect of determining the centroid of the house element is as follows: Figure 3 Therefore, by selecting the optimal calculation strategy through shape classification, the accurate centroid data of regular buildings is retained, and the contour distortion of irregular buildings is eliminated through the minimum circumscribed rectangle, thereby reducing the centroid positioning error.
[0049] In some embodiments, based on the centroid information, potential local contour lines corresponding to the house elements are generated, including: determining the perpendicular bisectors of the lines connecting adjacent centroids based on the centroid information; generating Thiessen polygons corresponding to the centroids based on the perpendicular bisectors; and determining potential local contour lines based on the Thiessen polygons.
[0050] Thiessen polygons refer to polygonal areas formed by dividing a set of discrete points through perpendicular medians. Specifically, they can be constructed by calculating the perpendicular bisectors of the lines connecting adjacent points and finding the intersection points. Their function is to convert the gap areas between houses into geometric boundaries.
[0051] Specifically, after obtaining the centroid information, the lines between adjacent centroids are calculated, and the medians are generated as the spatial dividing lines between adjacent houses. By connecting the medians of the adjacent centroids, multiple Thiessen polygons covering the house elements are formed. After the boundary lines of the Thiessen polygons are extracted, the potential local contour lines are obtained, such as Figure 4As shown in the figure, the potential local contour lines are automatically generated by Thiessen polygons, which can adapt to the distribution of house elements with different densities and shapes, avoid subjective errors caused by manual judgment, and improve computational efficiency.
[0052] In some embodiments, determining a local lane contour line based on potential local contour lines and contour feature information includes: selecting a target local contour line based on the contour feature information; and selecting a local lane contour line based on the number of end connections of the target local contour line.
[0053] The target local contour line is a potential local contour line whose distance from the overhead contour of the house element is not less than a preset threshold distance. It can be understood that the target local contour line refers to the potential local contour line that remains after the distance screening eliminates the potential local contour line that is too close to the overhead contour of the house element. Specifically, it can be achieved by using an algorithm that calculates the shortest distance between the potential local contour line and the overhead contour of the house element. This screening process can avoid the overlap of the alley contour and the overhead contour of the house element. The preset threshold distance refers to a pre-set minimum safety distance, which can be specifically a value set according to the traffic requirements of the alley, such as a range of 0.5 meters to 2 meters. This parameter is used to ensure that the alley width meets the actual use requirements.
[0054] Specifically, after selecting potential local contour lines, a distance filter is first used to eliminate potential local contour lines that are too close to the top-view outline of the building elements. Potential local contour lines that meet the spacing requirements are retained as target local contour lines. Next, a topological analysis is performed on the target local contour lines, and the connection status of the two terminals of each group of target local contour lines is counted. Isolated target local contour lines with neither terminal connected to other line segments are eliminated, and target local contour lines with at least one valid connection at the terminal are retained. For target local contour lines located at the edge, boundary contour lines are generated as local lane contour lines. This dual screening process ensures that the generated local lane contour lines maintain a reasonable distance from the building elements and that the lane network is well connected.
[0055] In some embodiments, before selecting the local lane contour line based on the number of end connections of the target local contour line, it also includes: performing a fusion operation on each target local contour line to obtain a fused contour line; and interrupting the fused contour line at the connection points between each target local contour line to obtain an optimized target local contour line.
[0056] The fusion operation combines multiple adjacent local contour lines of a target into a continuous line. This can be achieved using polygon merging techniques from graphics processing algorithms, eliminating overlaps or gaps between adjacent line segments to form a coherent boundary. The break operation splits continuous lines into independent segments where contour lines intersect or connect. This can be achieved using intersection detection algorithms from geometric calculations, inserting breakpoints at the intersection points to decompose the contour line into multiple independent parts.
[0057] Specifically, before generating the local lane contour line, the initially screened target local contour lines are first fused. For example, when multiple target local contour lines are adjacent or partially overlapped in space, they are connected into longer continuous lines through a merging algorithm. Then, all the connecting points are detected in the fused contour line, such as the intersection between adjacent house elements, and the lines are interrupted at these locations. For example, when two fused contour lines intersect at a certain coordinate point, the point is used as a segmentation point through the interruption operation, and the originally continuous line is decomposed into two independent optimized contour lines, namely the optimized target local contour line. The generated optimized target local contour line is as follows: Figure 5 As shown in the figure, the target local contour lines that may have redundant connections or over-extension are segmented into optimized target local contour lines that better conform to the actual lane distribution. This not only preserves the continuity of adjacent target local contour lines but also eliminates redundant connections, making the optimized target local contour lines more accurately fit the actual lane direction.
[0058] In some embodiments, based on the number of end connections of the target local contour line, a local lane contour line is selected, including: determining the regional boundary of the area where each house element is located; generating a first boundary perpendicular line and a second boundary perpendicular line for the first local contour line; eliminating the second local contour line, and using the third local contour line, the first local contour line, the first boundary perpendicular line and the second boundary perpendicular line as the local lane contour line.
[0059] The regional boundary refers to the edge range of the area where the housing elements are located. It can be achieved by extracting the overall range boundary of the housing cluster through the geographic information system. For example, the roads outside the area where the housing elements are located are depicted and determined on the map to be processed to limit the extension range of the lane contour line.
[0060] The first local contour line is a target local contour line whose one connection end is connected to at least two other target local contour lines and whose other connection end is not connected to other target local contour lines. The second local contour line is a target local contour line whose two connection ends are not connected to other target local contour lines. The third local contour line is a target local contour line whose two connection ends are respectively connected to at least two other target local contour lines. Figure 6As shown, the target local contour lines shown in boxes 1, 2 and 3 are all first local contour lines, wherein boxes 1 and 2 are two groups of connected first local contour lines, and box 3 is an isolated first local contour line. Figure 7 As shown, the target local contour line shown in the square box is the second local contour line, and the target local contour line shown in the circle box is the third local contour line.
[0061] The first boundary perpendicular line is a contour line passing through the junction point of two connected first local contour lines and perpendicular to the boundary of the region closest to the junction point. The second boundary perpendicular line is a contour line passing through the non-connection end of an isolated first local contour line and perpendicular to the boundary of the region closest to the non-connection end. Figure 8 As shown, the contour line extending from the connection point of the two connected first local contour lines to the region boundary closest to the connection point is the first boundary vertical line, and the contour line extending from the non-connection end of the isolated first local contour line to the region boundary closest to the non-connection end is the second boundary vertical line.
[0062] Specifically, after determining the regional boundary of the area where each housing element is located, all target local contour lines are traversed and classified according to the number of connection terminals of each target local contour line connected to other target local contour lines. For the first local contour line with only one end connected to other contour lines, if there is a connected first local contour line, a first boundary vertical line perpendicular to the regional boundary is generated at the connection point, and for an isolated first local contour line that is not connected to other first local contour lines, a second boundary vertical line perpendicular to the regional boundary is generated at the non-connection terminal of the isolated first local contour line. For the second local contour line that does not form an effective connection, it is determined to be a redundant line segment through topological analysis and is eliminated. Finally, the third local contour line with effective connections at both ends is retained, and the first local contour line and the generated first boundary vertical line and second boundary vertical line are combined to form the local lane contour line.
[0063] In some embodiments, generating a corresponding lane contour line based on a local lane contour line includes: processing a continuous contour line composed of several local lane contour lines into a straight line segment that does not touch the top view contour of the building element to obtain the lane contour line.
[0064] Specifically, when generating the lane contour line, multiple local lane contour lines are first connected according to the spatial topological relationship to form a continuous broken line contour. Subsequently, the broken line is simplified by a geometric processing algorithm, such as the Douglas Peuker algorithm, to avoid contact with the top-view contour distance of the house element, and the continuous broken line contour is adjusted to a straight line segment. For example, during the broken line simplification process, if the distance between a certain broken line segment and the top-view contour of the house element is less than a preset threshold, the broken line segment is translated away from the house until the spacing requirement is met. Finally, the adjusted broken line is converted into a straight line segment by a straight line fitting algorithm to form the final lane contour line, such as Figure 9 Therefore, by automatically processing continuous local lane contours and combining geometric offset and straight line fitting, the generated lane contours are ensured to maintain a straight shape and a reasonable distance from the house outline, avoiding the inefficiency and lack of accuracy caused by manual intervention.
[0065] See also Figure 10 The embodiment of the present application further provides a lane contour line generation device, which can implement the above lane contour line generation method, and the device includes: The first module 101 is used to obtain a map to be processed and determine the outline feature information of the house elements in the map to be processed; The second module 102 is configured to determine centroid information of the centroid of the building element based on the contour feature information; the centroid information includes position information of the centroid and distance information between adjacent centroids; The third module 103 is used to generate potential local contour lines corresponding to the house elements based on the centroid information; The fourth module 104 is used to determine the local roadway contour line based on the potential local contour line and contour feature information; The fifth module 105 is used to generate a corresponding lane contour line according to the local lane contour line.
[0066] The specific implementation of the lane contour line generating device is basically the same as the specific embodiment of the lane contour line generating method described above, and will not be repeated here.
[0067] Figure 11 It is a block diagram of an electronic device according to an exemplary embodiment.
[0068] Refer to the following Figure 11 1100 according to this embodiment of the present disclosure will be described. Figure 11 The electronic device 1100 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.
[0069] like Figure 11As shown, electronic device 1100 is implemented as a general-purpose computing device. Components of electronic device 1100 may include, but are not limited to, at least one processing unit 1110, at least one storage unit 1120, a bus 1130 connecting various system components (including storage unit 1120 and processing unit 1110), and a display unit 1140.
[0070] The storage unit stores program codes, which can be executed by the processing unit 1110, so that the processing unit 1110 executes the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned lane contour line generation method section of this specification.
[0071] The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 11201 and / or a cache memory unit 11202 , and may further include a read-only memory unit (ROM) 11203 .
[0072] The storage unit 1120 may also include a program / utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0073] The bus 1130 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0074] The electronic device 1100 can also communicate with one or more external devices 1100' (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1100, and / or any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 1150. Furthermore, the electronic device 1100 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 1160. The network adapter 1160 can communicate with other modules of the electronic device 1100 via the bus 1130. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device 1100, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0075] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned lane contour line generation method is implemented.
[0076] The lane outline generation method, apparatus, device, and storage medium provided in the embodiments of the present application do not rely on manual visual judgment of building gaps and manual drawing. Instead, they automatically determine the centroid information of the centroid of the house element based on the contour feature information of the house element in the map to be processed, generate the potential local contour line corresponding to the house element based on the centroid information, determine the local lane outline based on the potential local contour line and the contour feature information, and finally generate the corresponding lane outline based on the local lane outline. Due to the use of centroid spatial distribution analysis and the topological connection optimization combining the contour feature information of the house element with the potential local contour line, the potential channel network between the house groups can be quickly derived, ensuring that the generated lane outline meets the minimum passage width requirements while maintaining spatial coherence, and can quickly and accurately identify lanes in the map.
[0077] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above-mentioned method according to the embodiments of the present disclosure.
[0078] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
[0079] Computer-readable storage media may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.
[0080] Those skilled in the art will appreciate that the modules described above can be distributed in the device according to the description of the embodiment, or can be modified accordingly to be used in one or more devices that are different from the embodiment. The modules of the above embodiment can be combined into one module or further divided into multiple submodules.
[0081] While the exemplary embodiments of the present disclosure have been specifically illustrated and described above, it should be understood that the present disclosure is not limited to the detailed structures, configurations, or implementations described herein; rather, the present disclosure is intended to encompass various modifications and equivalent configurations within the spirit and scope of the appended claims.
Claims
1. A method for generating a roadway contour line, characterized in that: include: Acquire a map to be processed, and determine outline feature information of house elements in the map to be processed; Determining centroid information of the centroid of the house element based on the outline feature information; the centroid information includes position information of the centroid and distance information between adjacent centroids; Based on the centroid information, generating a potential local contour line corresponding to the house element; determining a local roadway contour line based on the potential local contour line and the contour feature information; According to the local lane contour line, a corresponding lane contour line is generated.
2. The method for generating a lane outline according to claim 1, wherein: The determining, based on the outline feature information, the centroid information of the centroid of the house element includes: When the outline feature information indicates that the top view outline of the house element is a regular shape, the geometric centroid of the house element is selected as the centroid; when the outline feature information indicates that the top view outline of the house element is an irregular shape, the minimum circumscribed rectangle corresponding to the house element is determined, and the geometric centroid of the minimum circumscribed rectangle is selected as the centroid; The centroid information is determined based on the image coordinate information of the centroid.
3. The method for generating a lane outline according to claim 1, wherein: Generating a potential local contour line corresponding to the house element based on the centroid information includes: Based on the centroid information, determining the perpendicular bisector of the line connecting adjacent centroids; Based on the perpendicular bisector, generating a Thiessen polygon corresponding to the centroid; Based on the Thiessen polygons, the potential local contour lines are determined.
4. The method for generating a lane outline according to claim 1, wherein: The determining of a local roadway contour line based on the potential local contour line and the contour feature information includes: Based on the outline feature information, a target local contour line is selected; the target local contour line is a potential local contour line whose distance from the top-view contour of the house element is not less than a preset threshold distance; The local roadway contour line is selected based on the number of end connections of the target local contour line.
5. The method for generating a lane outline according to claim 4, wherein: Before selecting the local roadway contour line based on the number of end connections of the target local contour line, the method further includes: Performing a fusion operation on each of the target local contour lines to obtain a fused contour line; The fused contour line is interrupted at the connecting points between the target local contour lines to obtain an optimized target local contour line.
6. The method for generating a lane outline according to claim 4 or 5, characterized in that: The selecting of the local roadway contour line based on the number of end connections of the target local contour line includes: Determining the regional boundaries of the areas where each of the housing elements is located; For a first local contour line, a first boundary perpendicular line and a second boundary perpendicular line are generated; the first local contour line is a target local contour line having one connection end connected to at least two other target local contour lines and the other connection end not connected to any other target local contour line; the first boundary perpendicular line is a contour line passing through a connecting point of the two connected first local contour lines and perpendicular to a region boundary closest to the connecting point; the second boundary perpendicular line is a contour line passing through a non-connecting end of the isolated first local contour line and perpendicular to a region boundary closest to the non-connecting end; The second local contour line is eliminated, and the third local contour line, the first local contour line, the first boundary perpendicular line and the second boundary perpendicular line are used as the local tunnel contour line; the second local contour line is a target local contour line whose two connection ends are not connected to other target local contour lines, and the third local contour line is a target local contour line whose two connection ends are respectively connected to at least two other target local contour lines.
7. The method for generating a lane outline according to claim 1, wherein: Generating a corresponding lane contour line according to the local lane contour line includes: A continuous contour line composed of a plurality of the local lane contour lines is processed into a straight line segment that does not touch the top view contour of the building element to obtain the lane contour line.
8. A device for generating a roadway contour line, characterized in that: include: The first module is used to obtain a map to be processed and determine the outline feature information of the house elements in the map to be processed; The second module is configured to determine the centroid information of the centroid of the house element based on the outline feature information; the centroid information includes the position information of the centroid and the distance information between adjacent centroids; A third module is configured to generate a potential local contour line corresponding to the house element based on the centroid information; A fourth module is configured to determine a local roadway contour line based on the potential local contour line and the contour feature information; The fifth module is used to generate a corresponding lane contour line according to the local lane contour line.
9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the lane contour line generation method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for generating a lane contour line according to any one of claims 1 to 7 is implemented.