A road network information extraction method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a method, device, electronic device and storage medium for extracting road network information, the method comprising: determining the starting road triangle of the oblique photography model; based on the splicing relationship between the triangles, traversing the triangles in sequence starting from the starting road triangle, and selecting the triangles that meet the preset conditions to form an initial continuous road surface; performing color contour recognition on the initial continuous road surface, and removing the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface; performing a simulated car traversal exploration on the target continuous road surface to obtain road network information. The embodiment of the present invention achieves the purpose of directly extracting road network information from the oblique photography model, and before extracting the road network information, the triangles that constitute the oblique photography model are first screened based on the preset conditions and color contour recognition to remove a large number of interference factors, so that the accuracy of the extracted road network information is higher.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of map technology, and in particular to a method, device, electronic device and storage medium for extracting road network information. Background Art

[0002] With the widespread use of oblique photography technology, the area covered by oblique photography model buildings is getting larger and larger, and large-scale city-level applications have been achieved. However, a large number of three-dimensional models are only used for display after being loaded into map applications, and more information cannot be extracted from them, such as road network data. The road network data needs to be calculated and imported in the traditional way.

[0003] At present, the traditional way of extracting road network information from oblique photography models is mainly to obtain point cloud data during the process of making oblique photography models, divide the point cloud data into unit grids, calculate the number of point clouds in the unit grid, and distinguish whether it is a road based on the number. However, this way of extracting road network information is completely dependent on the size of the unit grid, and it is difficult to distinguish some isolation belts and roadbeds on the road, resulting in low accuracy of the extracted road network information. Summary of the invention

[0004] The embodiments of the present invention provide a road network information extraction method, device, electronic device and storage medium to achieve the effect of accurately extracting road network information from an oblique photography model.

[0005] In a first aspect, an embodiment of the present invention provides a method for extracting road network information, the method comprising:

[0006] Determine the starting road triangle surface of the oblique photography model;

[0007] Based on the splicing relationship between the triangular faces, traverse the triangular faces in sequence starting from the starting road triangular face, and select the triangular faces that meet the preset conditions to form the initial continuous road surface;

[0008] Performing color contour recognition on the initial continuous road surface, and removing the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface;

[0009] The target continuous road surface is simulated and explored by a small car to obtain the road network information.

[0010] In a second aspect, an embodiment of the present invention provides a device for extracting road network information of an electronic device, the device comprising:

[0011] A starting triangle surface determination module is used to determine the starting road triangle surface of the oblique photography model;

[0012] An initial continuous road surface determination module is used to traverse each triangular surface in sequence starting from the starting road triangular surface based on the splicing relationship between the triangular surfaces, and select the triangular surfaces that meet the preset conditions to form the initial continuous road surface;

[0013] The target continuous road surface determination module is used to perform color contour recognition on the initial continuous road surface, and remove the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface;

[0014] The road network information extraction module is used to simulate the traversal and exploration of the target continuous road surface by a small car to obtain the road network information.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0016] one or more processors;

[0017] a storage device for storing one or more programs,

[0018] When one or more programs are executed by one or more processors, the one or more processors implement the road network information extraction method as in any embodiment of the present invention.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a road network information extraction method as in any embodiment of the present invention.

[0020] In the embodiment of the present invention, by traversing each triangular face of the oblique photography model, triangular faces that meet preset conditions are selected to form an initial continuous road surface, color contour recognition is performed on the initial continuous road surface, and the contour area of ​​the specified color is eliminated to obtain a target continuous road surface, and then a simulated car traversal exploration is performed on the target continuous road surface to obtain road network information. This achieves the purpose of directly extracting road network information based on the oblique photography model, improves the ease of use of oblique photography in urban map applications, and before extracting road network information, the triangular faces that constitute the oblique photography model are first screened based on preset conditions and color contour recognition to remove a large number of interference factors, so that the accuracy of the extracted road network information is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1a This is a flow chart of the road network information extraction method in Embodiment 1 of the present invention;

[0022] Figure 1b Schematic diagram of triangular surfaces constituting a road surface in the first embodiment of the present invention;

[0023] Figure 2 is a flow chart of a method for extracting road network information in Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic diagram of the structure of the road network information extraction device in the third embodiment of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0027] Embodiment 1

[0028] Figure 1a This is a flow chart of a road network information extraction method provided in Embodiment 1 of the present invention. This embodiment can be applied to extracting road network information from an oblique photography model after the oblique photography model is imported into an electronic map application. The method can be executed by a road network information extraction device, which can be implemented in software and / or hardware and can be integrated on an electronic device, such as a mobile terminal or a computer device.

[0029] like Figure 1a As shown, the road network information extraction method specifically includes the following processes:

[0030] S101: Determine the starting road triangle surface of the oblique photography model.

[0031] Among them, the triangle is the basic unit of the oblique photography model, that is, the buildings, vehicles, road surface, various poles, isolation belts, etc. in the oblique photography model are all composed of triangles. To extract the road information in the oblique photography model, it is first necessary to specify a point on the road as the starting point. For example, the starting point can be determined by detecting the user's click operation, and then the triangle face where the starting point is located is determined based on the coordinates of the starting point, and the triangle face is used as the starting road triangle face.

[0032] S102, based on the splicing relationship between the triangular faces, traverse the triangular faces in sequence starting from the starting road triangular face, and select the triangular faces that meet the preset conditions to form an initial continuous road surface.

[0033] Among them, the splicing relationship between each triangular face represents the adjacent relationship between each triangular face, and the preset condition refers to the condition used to determine the continuous triangular faces that constitute the ground of the oblique photography model, that is, the preset condition is used to eliminate the triangular faces that constitute the objects with vertical heights such as buildings, cars, isolation belts, poles, etc. in the model. Therefore, starting from the starting road triangular face, each triangular face is traversed in turn according to the splicing relationship between the triangular faces, and the triangular faces that constitute the objects with vertical heights such as buildings, cars, isolation belts, poles, etc. are eliminated, and only the continuous horizontal triangular faces are retained to determine the initial continuous road surface. It should be noted that the initial continuous road surface includes not only roads, but also grasslands, lake surfaces, etc.

[0034] In an optional implementation, based on the splicing relationship between the triangular faces, starting from the starting road triangular face, the triangular faces are traversed in sequence, and the triangular faces that meet the preset conditions are selected to form an initial continuous road surface, including:

[0035] S1021, calculating the first type of angle between the normal vector of each triangular face and the vertical axis of the coordinate system where the oblique photography model is located.

[0036] The coordinate system refers to the three-dimensional coordinate system of the engine after the oblique photography model is imported into the map engine, and the vertical axis is the Z axis of the three-dimensional coordinate system. The normal vector of each triangle can be calculated based on the vertex coordinates of each triangle. The angle between the normal vector of the triangle and the Z axis can be calculated according to the vector angle calculation formula. For easy distinction, the angle between the normal vector of the triangle and the Z axis is defined as the first type of angle.

[0037] S1022. In the process of traversing each triangular face according to the splicing relationship, for any two adjacent triangular faces, calculate a second type of angle between the normal vectors of the two adjacent triangular faces.

[0038] Optionally, based on the splicing relationship between the triangular faces, at least one intermediate triangular face adjacent to the starting road triangular face is determined, and the second type of angle between the normal vector of the starting road triangular face and the normal vector of the intermediate triangular face is calculated. Then, other triangular faces adjacent to the intermediate triangular face are determined, and the second type of angle between the normal vector of the intermediate triangular face and the normal vectors of other triangular faces is calculated, and so on, until the traversal is completed.

[0039] For example, see Figure 1b , which shows a schematic diagram of the triangular faces that make up the road surface, where the road surface 1 includes four triangular faces A, B, C, and D, and the normal vectors of the triangular faces A, B, C, and D are respectively According to the operation of S1021, the normal vectors are calculated respectively. The angle with the Z axis; according to S1022 operation, calculate and The angle of and The angle of and Angle.

[0040] S1023, determining each target triangular face whose value of the first type angle is less than the first threshold and whose value of the second type angle is less than the second threshold, and forming each target triangular face into an initial continuous road surface.

[0041] In an embodiment of the present invention, the angle thresholds are pre-set as a first threshold and a second threshold, illustratively, the first threshold is equal to 30 degrees, and the second threshold is 60 degrees. Determine each target triangular face whose value of the first type of angle is less than the first threshold, and whose value of the second type of angle is less than the second threshold, and form each target triangular face into an initial continuous road surface. It should be noted here that if the value of the first type of angle between the normal vector of a triangular face and the Z axis is greater than the first threshold, the triangular face is directly discarded. Similarly, for road bumps caused by shooting shadows, as long as the value of the first type of angle between the normal vector of a single triangular face and the Z axis is less than the first threshold, and the normal vector angle of adjacent triangular faces (i.e., the second type of angle) is less than the second threshold, it is also considered to be a continuous road surface, thereby making the road calculation more continuous.

[0042] It should also be noted that compared with the method of determining roads based on point cloud computing, the embodiment of the present application only needs to compare vector angles to eliminate a large amount of interference and determine the road surface, which makes the calculation speed higher and thus ensures the efficiency of subsequent road network extraction.

[0043] S103, performing color contour recognition on the initial continuous road surface, and removing contour areas of a specified color from the initial continuous road surface according to the recognition result to obtain a target continuous road surface.

[0044] In the initial continuous road surface obtained by S102, although the model objects with a certain height are eliminated, the grass, lake surface, etc. connected to the road cannot be eliminated, so the initial continuous road surface needs to be screened again. Optionally, the three-dimensional perspective is switched to the top view, and the color contour of the initial continuous road surface is recognized. According to the recognition result, the contour area of ​​the specified color is eliminated from the initial continuous road surface to obtain the target continuous road surface, wherein the specified color can be a pre-specified color range segment, and the pre-specified color range segment can be determined according to the color of the non-road ground area such as grass, lake surface, etc. on the ground. For example, the color range segment may include light green or dark green corresponding to the grass, or sky blue corresponding to the lake surface. Exemplarily, the color contour recognition function in the OpenCV function library can be used to perform color contour recognition on the initial continuous road surface to obtain a light green area, a dark green area, or a sky blue area, and the recognized light green area, dark green area, or sky blue area is eliminated from the initial continuous road surface, thereby obtaining the target continuous road surface with only the road left.

[0045] S104, simulating a car traversal exploration on the target continuous road surface to obtain road network information.

[0046] Through S101-S103, the road triangular surface information (i.e., the target continuous road surface) is obtained, but the number of triangular surfaces is very large, and the road network data cannot be directly obtained by using the triangular surface information. Therefore, the embodiment of the present application extracts the road network data by simulating the traversal of a small car. Optionally, since the real road network data is generally collected by simulating a small car according to the real road, the road network information can also be collected on the target continuous road surface by simulating a small car in the oblique photography environment.

[0047] It should be noted that if the road network is collected directly in the original data, a large number of interfering vertical surfaces will interfere with the advancement of the simulated car, resulting in errors in the road network data collection. Therefore, the present application creatively eliminates a large number of interfering factors after screening and cleaning the road triangular surfaces through S102-S103, so that only roads are included in the target continuous road surface, thereby ensuring that the process of extracting road network information through simulated car traversal exploration is feasible and reliable, and the accuracy of the extracted road network information is higher.

[0048] In the embodiment of the present invention, by traversing each triangular face of the oblique photography model, the triangular faces that meet the preset conditions are selected to form an initial continuous road surface, the initial continuous road surface is subjected to color contour recognition, and the contour area of ​​the specified color is eliminated to obtain the target continuous road surface, and then the target continuous road surface is simulated to be traversed and explored by a small car to obtain road network information. In this way, the purpose of directly extracting road network information based on the oblique photography model is achieved, the usability of oblique photography in urban map applications is improved, and the oblique photography data provision capability is enriched. Moreover, before extracting the road network information, the triangular faces that constitute the oblique photography model are first screened based on the preset conditions and color contour recognition to remove a large number of interference factors, so that the accuracy of the extracted road network information is higher.

[0049] Embodiment 2

[0050] Figure 2 This is a flowchart of a method for extracting road network information provided by Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiment. Figure 2 , the method comprising:

[0051] S201: Determine the starting road triangle surface of the oblique photography model.

[0052] Among them, the triangle surface is the basic unit of the oblique photography model.

[0053] S202: based on the splicing relationship between the triangular faces, traverse the triangular faces in sequence starting from the starting road triangular face, and select the triangular faces that meet the preset conditions to form an initial continuous road surface.

[0054] S203, performing color contour recognition on the initial continuous road surface, and removing contour areas of a specified color from the initial continuous road surface according to the recognition result to obtain a target continuous road surface.

[0055] S204: Determine the starting point and the moving direction of the simulated vehicle on the target continuous road surface.

[0056] The simulated car can be optionally replaced by a movable point, the starting point of the simulated car can be selected as any point on the center line of the target continuous road surface, and the direction of travel can be determined according to the position of the starting point.

[0057] S205, simulating that the car moves at the starting point in the direction of travel and emits a fixed-length line segment in a preset direction in real time.

[0058] The simulated car is equipped with a scanning radar to collect road network information during the travel. Optionally, when the simulated car moves in the travel direction from the starting point, the scanning radar emits a fixed-length line segment in a preset direction in real time, wherein the fixed-length line segment can be a 50-meter line segment, and the preset directions include the front, left, and right of the simulated car.

[0059] S206. Determine the width of the target continuous road surface and the distance directly in front of the simulated vehicle according to the intersection of the fixed-length line segment and the target continuous road surface.

[0060] Optionally, to determine the width of the road, it is only necessary to determine the length of the intersection of the fixed-length line segments emitted to the left and right and the target continuous road. Specifically, the left road width can be determined according to the intersection of the fixed-length line segments emitted to the left side of the simulated car and the target continuous road; the right road width can be determined according to the intersection of the fixed-length line segments emitted to the right side of the simulated car and the target continuous road; and the sum of the left road width and the right road width is used as the width of the target continuous road.

[0061] The fixed-length line segment emitted directly in front of the simulated car is used to calculate the distance directly in front of the simulated car. Its function is to detect whether the simulated car has reached the end of the road. For example, when the distance directly in front is zero, it means that it has reached the end of the road.

[0062] Furthermore, in order to ensure the accuracy of calculating the road width, the fixed-length line segment is divided into fine equal parts, for example, into 200 equal segments, that is, there are 200 subdivision points, and these 200 points are checked to see if they fall vertically on the triangular surface, and these 200 points that intersect with the target continuous road surface are connected, that is, a broken line along the undulations of the surface, and the width of the detection direction is determined by the number of these points.

[0063] Furthermore, in order to ensure that the simulated car always moves along the center line of the target continuous road surface, the method further includes: determining whether the left road width is equal to the right road width, and if not, adjusting the direction of travel of the simulated car so that the left road width measured after the direction adjustment is equal to the right road width. Exemplarily, if the left road width is greater than the right road width, the simulated car is controlled to rotate to the left, and the angle of each rotation can be preset until the left road width is equal to the right road width.

[0064] S207, the simulated car stops moving when the distance directly in front is equal to zero, and the travel route and road width of the simulated car are used as road network information.

[0065] When the distance in front of the simulated car is equal to zero, that is, the simulated car has reached the end of the road and needs to stop moving forward, at this time the route traversed by the simulated car and the measured road width can be used as road network information and saved.

[0066] In the embodiment of the present application, in the process of simulating the movement of a small car, the road width can be measured quickly and accurately according to the intersection of the emitted fixed-length line segment and the target continuous road surface, thereby improving the efficiency of extracting road network information.

[0067] Furthermore, when the simulated car moves to a certain position, if the measured left road width and / or right road width is greater than a preset threshold, the position is determined to be a road fork; when the distance directly in front of the simulated car is zero, the car stops moving forward and restarts the exploration at the road fork. This achieves a complete and comprehensive traversal exploration of the target continuous road surface and avoids missing road network information.

[0068] Furthermore, in order to enrich the road network information, the roads may be classified according to the measured width of the target continuous road surface, for example, urban main roads may be distinguished, so that the classification results of the roads may be added to the road network information.

[0069] Embodiment 3

[0070] Figure 3 Schematic diagram of the structure of the road network information extraction device in the third embodiment of the present invention. This embodiment is applicable to the case where the road network information is extracted from the oblique photography model after the oblique photography model is imported into the electronic map application. Figure 3 , the device comprises:

[0071] A starting triangle face determination module 301 is used to determine a starting road triangle face of an oblique photography model, wherein the triangle face is a basic unit constituting the oblique photography model;

[0072] An initial continuous road surface determination module 302 is used to traverse each triangular surface in sequence starting from the starting road triangular surface based on the splicing relationship between the triangular surfaces, and select the triangular surfaces that meet the preset conditions to form the initial continuous road surface;

[0073] The target continuous road surface determination module 303 is used to perform color contour recognition on the initial continuous road surface, and remove the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface;

[0074] The road network information extraction module 304 is used to simulate the traversal and exploration of the target continuous road surface by a small car to obtain the road network information.

[0075] By traversing the triangular faces of the oblique photography model, the triangular faces that meet the preset conditions are selected to form the initial continuous road surface, the color contour recognition is performed on the initial continuous road surface, and the contour area of ​​the specified color is eliminated to obtain the target continuous road surface, and then the target continuous road surface is simulated to traverse and explore the road network information. In this way, the purpose of directly extracting road network information based on the oblique photography model is achieved, and the usability of oblique photography in urban map applications is improved. Moreover, before extracting the road network information, the triangular faces that constitute the oblique photography model are first screened based on the preset conditions and color contour recognition to remove a large number of interference factors, so that the accuracy of the extracted road network information is higher.

[0076] Based on the above embodiment, optionally, the initial continuous road surface determination module includes:

[0077] A first calculation unit, used for calculating a first type of angle between the normal vector of each triangular face and the vertical axis of the coordinate system where the oblique photography model is located;

[0078] A second calculation unit is used to calculate a second type of angle between normal vectors of any two adjacent triangular faces in a process of traversing each triangular face according to the splicing relationship;

[0079] The initial continuous road surface determination unit is used to determine each target triangular surface whose value of the first type angle is less than the first threshold and whose value of the second type angle is less than the second threshold, and to form each target triangular surface into an initial continuous road surface.

[0080] Based on the above embodiment, optionally, the road network information extraction module includes:

[0081] A starting point and direction determination unit, used to determine the starting point and travel direction of the simulated vehicle on the target continuous road surface;

[0082] The launch unit is used to simulate the process of the car moving in the direction of travel from the starting point, and launch a fixed-length line segment in a preset direction in real time; wherein the preset direction includes the front, left and right sides of the simulated car;

[0083] A third calculation unit is used to determine the width of the target continuous road surface and the distance directly in front of the simulated vehicle according to the intersection of the fixed-length line segment and the target continuous road surface;

[0084] The road network information acquisition unit is used to simulate that the car stops moving when the distance directly in front is equal to zero, and uses the travel route and road width of the simulated car as the road network information.

[0085] Based on the above embodiment, optionally, the third calculation unit is specifically used for:

[0086] The left side road width is determined according to the intersection of the fixed-length line segment emitted to the left side of the simulated car and the target continuous road surface;

[0087] The right road width is determined according to the intersection of the fixed-length line segment emitted to the right side of the simulated car and the target continuous road surface;

[0088] The sum of the left road width and the right road width is used as the width of the target continuous road surface.

[0089] Based on the above embodiment, optionally, the device further includes:

[0090] The direction adjustment module is used to determine whether the left road width is equal to the right road width. If not, the moving direction of the simulated car is adjusted so that the left road width measured after the direction adjustment is equal to the right road width.

[0091] Based on the above embodiment, optionally, the device further includes:

[0092] A fork position determination module is used to determine that when the simulated car moves to a certain position, if the measured left road width and / or right road width is greater than a preset threshold, the position is determined to be a road fork;

[0093] The secondary exploration module is used to restart the exploration at the road fork after the simulated car stops moving forward according to the distance directly ahead.

[0094] Based on the above embodiment, optionally, the device further includes:

[0095] The road classification module is used to classify the road according to the measured width of the target continuous road surface.

[0096] The road network information extraction device provided in the embodiment of the present invention can execute the road network information extraction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0097] Embodiment 4

[0098] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 4 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0099] like Figure 4 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0100] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0101] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0102] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0103] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 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. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0104] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0105] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the road network information extraction method provided in the embodiment of the present invention, the method comprising:

[0106] Determine the starting road triangle of the oblique photography model, wherein the triangle is the basic unit constituting the oblique photography model;

[0107] Based on the splicing relationship between the triangular faces, traverse the triangular faces in sequence starting from the starting road triangular face, and select the triangular faces that meet the preset conditions to form the initial continuous road surface;

[0108] Performing color contour recognition on the initial continuous road surface, and removing the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface;

[0109] The target continuous road surface is simulated and explored by a small car to obtain the road network information.

[0110] Embodiment 5

[0111] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the road network information extraction method provided in the embodiment of the present invention is implemented. The method includes:

[0112] Determine the starting road triangle of the oblique photography model, wherein the triangle is the basic unit constituting the oblique photography model;

[0113] Based on the splicing relationship between the triangular faces, traverse the triangular faces in sequence starting from the starting road triangular face, and select the triangular faces that meet the preset conditions to form the initial continuous road surface;

[0114] Performing color contour recognition on the initial continuous road surface, and removing the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface;

[0115] The target continuous road surface is simulated and explored by a small car to obtain the road network information.

[0116] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer 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 of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0117] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-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 of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-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.

[0118] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0119] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0120] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A road network information extraction method, It is characterized in that The method comprises: Determine the starting road triangle surface of the oblique photography model; Based on the splicing relationship between the triangular faces, starting from the starting road triangular face, traverse the triangular faces in sequence, and select the triangular faces that meet the preset conditions to form an initial continuous road surface; Performing color contour recognition on the initial continuous road surface, and removing contour areas of a specified color from the initial continuous road surface according to the recognition result to obtain a target continuous road surface; Conducting a simulated car traversal exploration on the target continuous road surface to obtain road network information; The method of traversing each triangular face in sequence starting from the starting road triangular face based on the splicing relationship between the triangular faces and selecting the triangular faces that meet the preset conditions to form an initial continuous road surface includes: Calculate the first type of angle between the normal vector of each triangular face and the vertical axis of the coordinate system where the oblique photography model is located; In the process of traversing each triangular face according to the splicing relationship, for any two adjacent triangular faces, a second type of angle between the normal vectors of the two adjacent triangular faces is calculated; Determine each target triangular face whose value of the first type angle is less than the first threshold and whose value of the second type angle is less than the second threshold, and form each of the target triangular faces into an initial continuous road surface.

2. The method according to claim 1, It is characterized in that The target continuous road surface is simulated and explored by a small car to obtain road network information, including: Determining a starting point and a moving direction of the simulated vehicle on the target continuous road surface; When the simulated car moves from the starting point in the direction of travel, it emits a fixed-length line segment in real time in a preset direction; wherein the preset direction includes the front, left and right sides of the simulated car; Determining the width of the target continuous road surface and the distance directly in front of the simulated vehicle according to the intersection of the fixed-length line segment and the target continuous road surface; The simulated car stops moving forward when the distance directly in front is equal to zero, and the travel route and road width of the simulated car are used as road network information.

3. The method according to claim 2, It is characterized in that Determining the width of the target continuous road surface according to the intersection of the fixed-length line segment and the target continuous road surface includes: Determine the left side road width according to the intersection of the fixed-length line segment emitted to the left side of the simulated car and the target continuous road surface; Determine the right road width according to the intersection of the fixed-length line segment emitted to the right side of the simulated car and the target continuous road surface; The sum of the left road width and the right road width is used as the width of the target continuous road surface.

4. The method according to claim 3, It is characterized in that The method further comprises: It is determined whether the left road width is equal to the right road width. If not, the traveling direction of the simulated car is adjusted so that the left road width measured after the direction adjustment is equal to the right road width.

5. The method according to any one of claims 2 to 4, It is characterized in that The method further comprises: When the simulated car moves to a certain position, if the measured left road width and / or right road width is greater than a preset threshold, the position is determined to be a road fork; After the simulated car stops moving forward according to the distance directly ahead, it restarts exploring at the road fork.

6. The method according to any one of claims 2 to 4, It is characterized in that The method further comprises: The roads are classified according to the measured width of the target continuous road surface.

7. A road network information extraction device, It is characterized in that The device comprises: A starting triangle surface determination module is used to determine the starting road triangle surface of the oblique photography model; An initial continuous road surface determination module is used to traverse each triangular surface in sequence starting from the starting road triangular surface based on the splicing relationship between the triangular surfaces, and select the triangular surfaces that meet the preset conditions to form the initial continuous road surface; A target continuous road surface determination module is used to perform color contour recognition on the initial continuous road surface, and remove the contour area of ​​the specified color from the initial continuous road surface according to the recognition result to obtain the target continuous road surface; A road network information extraction module is used to simulate a small car traversal exploration of the target continuous road surface to obtain road network information; Wherein, the initial continuous road surface determination module includes: A first calculation unit, used for calculating a first type of angle between the normal vector of each triangular face and the vertical axis of the coordinate system where the oblique photography model is located; A second calculation unit is used to calculate a second type of angle between normal vectors of any two adjacent triangular faces in a process of traversing the triangular faces according to the splicing relationship; The initial continuous road surface determination unit is used to determine each target triangular surface whose value of the first type angle is less than the first threshold and whose value of the second type angle is less than the second threshold, and to form each target triangular surface into an initial continuous road surface.

8. An electronic device, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the road network information extraction method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the road network information extraction method as described in any one of claims 1-6 is implemented.

Images