WO2022078499A1 - 一种路网地图实现方法、装置和电子设备 - Google Patents

一种路网地图实现方法、装置和电子设备 Download PDF

Info

Publication number
WO2022078499A1
WO2022078499A1 PCT/CN2021/124119 CN2021124119W WO2022078499A1 WO 2022078499 A1 WO2022078499 A1 WO 2022078499A1 CN 2021124119 W CN2021124119 W CN 2021124119W WO 2022078499 A1 WO2022078499 A1 WO 2022078499A1
Authority
WO
WIPO (PCT)
Prior art keywords
road network
grid
occupied
map
grids
Prior art date
Application number
PCT/CN2021/124119
Other languages
English (en)
French (fr)
Inventor
邹李兵
张一凡
张富强
宁越
Original Assignee
歌尔股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 歌尔股份有限公司 filed Critical 歌尔股份有限公司
Publication of WO2022078499A1 publication Critical patent/WO2022078499A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/206—Drawing of charts or graphs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the present application relates to the field of electronic maps, and in particular, to a method, device and electronic device for implementing a road network map.
  • a road network refers to a road system composed of various roads that are interconnected and interwoven into a network in a certain area, referred to as a road network, and a map with road network information is called a road network map.
  • road network maps have been used in areas such as autonomous driving, but most road network maps in the prior art have problems such as loss of road direction information.
  • a method for implementing a road network map comprising: using a grid coordinate system to perform discretization processing on a road network to be mapped to obtain a basic road network map representing the road network with an occupied grid; According to the direction information of the road network and the connection relationship between the grids, determine the passable direction of each occupied grid in the basic road network map; according to the passable direction of each occupied grid, determine the road network code of the corresponding occupied grid, Thereby realizing the road network map.
  • an apparatus for implementing a road network map includes:
  • the discretization unit is used to discretize the road network to be mapped by using the grid coordinate system to obtain a basic road network map representing the road network with the occupied grid.
  • the direction unit is used to determine the passable direction of each occupied grid in the basic road network map according to the direction information of the road network and the connection relationship between the grids.
  • the coding unit is configured to determine the road network code of the corresponding occupied grid according to the passable direction of each occupied grid, thereby realizing the road network map.
  • an electronic device comprising: a processor; and a memory arranged to store computer-executable instructions, the executable instructions, when executed, cause the processor to execute the above road network map implementation method .
  • a computer-readable storage medium storing one or more programs, and the one or more programs, when executed by an electronic device including a plurality of application programs, cause the electronic device to execute the above path. How to implement a web map.
  • the beneficial effects of the present application are: the road network is discretized by the grid coordinate system, so that the subsequently realized road network map has the basis for inputting the neural network; the direction information based on the road network and the connection between grids The relationship determines the passable direction of each occupied grid, and further determines the road network code of the occupied grid, thereby realizing the road network map with road direction information, which can be extracted by the neural network and improve the training effect.
  • FIG. 1 shows a schematic flowchart of a method for implementing a road network map according to an embodiment of the present application
  • Figure 2 shows a schematic diagram of a grid coordinate system
  • Figure 3 shows a schematic diagram of another grid coordinate system
  • FIG. 4 shows a schematic diagram of a road network discretization process according to an embodiment of the present application
  • FIG. 5 shows a schematic diagram of a grid passable direction according to an embodiment of the present application
  • FIG. 6 shows a schematic diagram of a road network coding template according to an embodiment of the present application
  • FIG. 7 shows a grid with two traversable directions according to an embodiment of the present application.
  • FIG. 8 shows a schematic diagram of road network overlay according to an embodiment of the present application.
  • FIG. 9 shows a schematic diagram of a road network node according to an embodiment of the present application.
  • FIG. 10 shows a schematic structural diagram of an apparatus for implementing a road network map according to an embodiment of the present application
  • FIG. 11 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • FIG. 12 shows a block diagram of a computer-readable storage medium according to an embodiment of the present application.
  • the technical idea of the present application is: by discretizing the road network, the road network map has the basis for being used by the neural network, and the road network map has the direction information of the road through the road network code that can represent the passable direction, so that the road network map contains The amount of information is larger, and it can play a greater role in the model training process of machine learning.
  • FIG. 1 shows a schematic flowchart of a method for implementing a road network map according to an embodiment of the present application. As shown in FIG. 1 , the method for implementing a road network map includes:
  • step S110 the road network to be mapped is discretized by using the grid coordinate system to obtain a basic road network map representing the road network by the occupied grid.
  • Step S120 according to the direction information of the road network and the connection relationship between the grids, determine the passable direction of each occupied grid in the basic road network map.
  • step S130 the road network code of the corresponding occupied grid is determined according to the passable direction of each occupied grid, thereby realizing a road network map.
  • the method shown in Figure 1 uses the grid coordinate system to discretize the road network, so that the subsequent road network map has the basis for inputting the neural network; based on the direction information of the road network and the connection relationship between grids, each The passable directions of the occupied grids further determine the road network codes of the occupied grids, thereby realizing the road network map with road direction information, which can be extracted by the neural network and improve the training effect.
  • the grid coordinate system can be established by determining the origin of the coordinates, the scale, and the size of the map. Generally, a large scale has high precision, and a small scale has low precision.
  • Figure 2 and 3 respectively show schematic diagrams of grid coordinate systems.
  • Figure 2 is a grid coordinate system with the lower left corner as the coordinate origin O
  • Figure 3 is a grid coordinate system with the origin O in the middle of the grid, and the coordinate origin can be at any position on the grid
  • the corresponding grid is shown by x, and the coordinate origin defines the two-dimensional coordinate as [0, 0].
  • the coordinates of other grids can be based on this, and the corresponding coordinates can be determined according to the Cartesian coordinate system.
  • x 0 , y 0 are the offsets
  • x', y' are the coordinates in the grid coordinate system of Figure 3
  • x, y are the coordinates converted to the grid coordinate system of Figure 2.
  • the resulting road network map can be easily transformed according to the change of requirements, and the adaptability is strong.
  • Figure 4 (a) shows a grid coordinate system with the lower left corner as the coordinate origin O and an example of a road network.
  • the road network only shows one road, and the direction of the arrow indicates the actual traffic of the road.
  • the direction of travel indicates that the starting point of the road is the upper right side and the end point is the lower left side.
  • the road network is superimposed into the grid coordinate system. It can be seen that the road passes through (covers) multiple grids. In Figure 4(c), these grids are marked as being covered by the road network. Occupation, the occupancy map of each grid is obtained, thereby realizing the discretization of the road network.
  • the inter-grid connection relationship indicates whether there is an occupied grid adjacent to the current grid, and may also indicate the orientation relationship between the current grid and its adjacent occupied grid.
  • the direction information of the road network refers to the traffic direction of each road in the road network. In the prior art, this information will be lost after the map is constructed, but in the technical solution of the present application, it is the reference network
  • the connection relationship between the grids and the direction information of the road network are used to determine the traversable direction of each occupied grid.
  • the road network code of a grid is generally 0 to indicate that it is not occupied, and 1 to indicate that it is occupied, so that the direction information of the road network cannot be included.
  • the road network code is improved, So that it can represent the direction information of the road network, specifically, the road network code is used to represent the traversable direction of the occupied grid.
  • the grid coordinate system is used to discretize the road network to be mapped, and obtaining a basic road network map representing the road network with the occupied grid includes: The coordinate position of the occupied grid in the grid coordinate system, the subscript of each dimension in the multi-dimensional array represents the offset of the grid in the direction of one coordinate axis;
  • the road network coding of the occupied grid includes: taking the determined road network code as an array element value of a multi-dimensional array corresponding to the occupied grid.
  • the coordinates [x, y] of the two-dimensional grid coordinate system shown above can be represented by a two-dimensional array G, and the number of grids shown in Figure 2, Figure 3, and Figure 4 is 8 ⁇ 8, Then the dimension of G can be (8, 8), the first 8 represents the maximum coordinate value in the horizontal axis direction, and the second 8 represents the maximum coordinate value in the vertical axis direction.
  • G[0,0] corresponds to the first grid in the lower left corner of Figure 2.
  • the array element value of each grid can be initialized to 0, and after a grid is determined to be an occupied grid, its array element value can be set to other values, such as -1. After the road network code of the grid is determined, the road network code can be used as the value of the array element, so that the road network code of the grid can be determined only by querying the array element value of the grid.
  • determining the passable direction of each occupied grid in the basic road network map according to the direction information of the road network and the connection relationship between the grids includes: according to the occupied grid and the adjacent grid.
  • the connection relationship between the grids is used to determine the travel direction that matches the direction information of the road network as the travelable direction of the occupied grid.
  • grid G[6, 6] has a connection relationship with G[7, 6], G[5, 5], according to the direction information of the road network, it is determined that G[6, 6] is passable To G[5, 5], that is, the passable direction of G[5, 5] is down to the left. That is, the direction information of the road network is to pass down to the left, and there is a grid with a connection relationship in the lower left of the current grid, then the passable direction of the current grid is down to the left.
  • the road network map is a two-dimensional map
  • the connection relationship between grids includes edge connection and corner connection
  • the traversable direction includes at least one of the following: up, down, left, Right, upper left, upper right, lower left, lower right; or, the road network map is a three-dimensional map
  • the connection relationship between grids includes surface connection, edge connection and vertex connection.
  • the grid usually has eight grids: top, bottom, left, right, top left, top right, bottom left, and bottom right. Adjacent grids are connected by edges and corners, and the traversable directions can be up, down, left, right, upper left, upper right, lower left, and lower right at most. For edge meshes, if one of the adjacent meshes is missing, then a traversable direction is missing.
  • a non-edge mesh has 26 adjacent meshes, connected by faces, edges, and vertices, and can have up to 26 traversable directions.
  • determining the road network code of the corresponding occupied grid according to the passable direction of each occupied grid includes: using a binary code with a preset number of bits as the road network code of the occupied grid Network code, each bit of the road network code corresponds to a passing direction, and marks each passing direction with 1 or 0 whether it is a passable direction.
  • each bit of the 8-bit binary code corresponds to the 8 directions of up, down, left, right, upper left, upper right, and lower left, and the length is 1 byte. Indicates whether a direction is allowed to pass. In one embodiment, if it is allowed, the value of this bit is 1, otherwise it is 0.
  • determining the road network code of the corresponding occupied grid according to the passable direction of each occupied grid further includes: in the case that each occupied grid has the original road network code , first determine the new road network code of each occupied grid according to the passable direction of each occupied grid; perform the first bitwise operation on the original road network code and the new road network code of each occupied grid, Get the road network code of each occupied grid.
  • the final road network coding information is obtained by the first bitwise operation of the road network coding information in all passable directions, for example, the first bitwise operation It is a bitwise OR (
  • ) operation, that is, the final encoding information in FIG. 7 is G[] 00000010
  • 00010000 00010010.
  • the road network map can also be continuously updated, that is, the grid can add new passable directions.
  • the first bitwise operation can be performed on the original road network code and the new road network code of the occupied grid to obtain the occupied grid.
  • the road network code of the grid For example, as shown in Figure 8, multiple occupied grids in the vertical direction correspond to the newly added road network.
  • 00001000 00101000.
  • the road network map obtained in the embodiment of the present application can also conveniently determine the type of road network nodes.
  • the above method further includes: selecting a target grid of the node type to be determined; determining a grid that has an inter-grid connection relationship with the target grid and at least one traversable direction points to the target grid The grid is used as the input grid of the target grid; the second bitwise operation is performed on the road network code of the target grid and the input grid of the target grid, if the binary code obtained after the operation is the same as the preset code, then determine The target mesh is an inflection point mesh that characterizes the road network where there is an inflection point.
  • the gray grid is the occupied grid
  • the grid with the darkest color [3, 6] is the target grid of the road network node type to be determined
  • the road network code is 00001000
  • the adjacent grid [2, 6] is its input grid
  • the road network code is 00000010.
  • the second bitwise operation is performed on the road network codes of [3, 6] and [2, 6].
  • the target mesh is not an inflection point of the road network.
  • the above method further includes: selecting a target grid of the node type to be determined; determining a grid that has an inter-grid connection relationship with the target grid and at least one passable direction points to the target grid As the input grid of the target grid; if the target grid has multiple input grids, and the target grid has at least one passable direction, the target grid is determined to be a routing node-type grid representing routing nodes in the road network .
  • the gray grid is the occupied grid
  • the darkest grid [3, 4] is the road network to be judged
  • the target grid of node type since grid [3, 4] has multiple input grids and there is a passable direction to the lower right, it means that the target grid [3, 4] is a routing node in the road network .
  • the embodiments of the present application also provide an apparatus for implementing a road network map, which can be used to implement the method for implementing a road network map as shown in any of the above embodiments.
  • FIG. 10 shows a schematic structural diagram of an apparatus for implementing a road network map according to an embodiment of the present application.
  • the apparatus 1000 for implementing a road network map includes:
  • the discretization unit 1010 is configured to perform discretization processing on the road network to be mapped by using the grid coordinate system to obtain a basic road network map representing the road network by the occupied grid.
  • the direction unit 1020 is configured to determine the passable direction of each occupied grid in the basic road network map according to the direction information of the road network and the connection relationship between grids.
  • the encoding unit 1030 is configured to determine the road network code of the corresponding occupied grid according to the passable direction of each occupied grid, so as to realize the road network map.
  • the device shown in Fig. 10 discretizes the road network through the grid coordinate system, so that the subsequent road network map can be input into the neural network. Based on the direction information of the road network and the connection relationship between grids, each The passable directions of the occupied grids further determine the road network codes of the occupied grids, thereby realizing the road network map with road direction information, which can be extracted by the neural network and improve the training effect.
  • the grid coordinate system can be established by determining the origin of the coordinates, the scale, and the size of the map. Generally, a large scale has high precision, and a small scale has low precision.
  • Figure 2 and 3 respectively show schematic diagrams of grid coordinate systems.
  • Figure 2 is a grid coordinate system with the lower left corner as the coordinate origin O
  • Figure 3 is a grid coordinate system with the origin O in the middle of the grid, and the coordinate origin can be at any position on the grid
  • the corresponding grid is shown by x, and the coordinate origin defines the two-dimensional coordinate as [0, 0].
  • the coordinates of other grids can be based on this, and the corresponding coordinates can be determined according to the Cartesian coordinate system.
  • x 0 , y 0 are the offsets
  • x', y' are the coordinates in the grid coordinate system of Figure 3
  • x, y are the coordinates converted to the grid coordinate system of Figure 2.
  • the resulting road network map can be easily transformed according to the change of requirements, and the adaptability is strong.
  • Figure 4 (a) shows a grid coordinate system with the lower left corner as the coordinate origin O and an example of a road network.
  • the road network only shows one road, and the direction of the arrow indicates the actual traffic of the road.
  • the direction of travel indicates that the starting point of the road is the upper right side and the end point is the lower left side.
  • the road network is superimposed into the grid coordinate system. It can be seen that the road passes through (covers) multiple grids. In Figure 4(c), these grids are marked as being covered by the road network. Occupation, the occupancy map of each grid is obtained, thereby realizing the discretization of the road network.
  • the inter-grid connection relationship indicates whether there is an occupied grid adjacent to the current grid, and may also indicate the orientation relationship between the current grid and its adjacent occupied grid.
  • the direction information of the road network refers to the traffic direction of each road in the road network. In the prior art, this information will be lost after the map is constructed, but in the technical solution of the present application, it is the reference network
  • the connection relationship between the grids and the direction information of the road network are used to determine the traversable direction of each occupied grid.
  • the road network code of a grid is generally 0 to indicate that it is not occupied, and 1 to indicate that it is occupied, so that the direction information of the road network cannot be included.
  • the road network code is improved, So that it can represent the direction information of the road network, specifically, the road network code is used to represent the traversable direction of the occupied grid.
  • the discretization unit 1010 is used to represent the coordinate position of the occupied grid in the grid coordinate system with a multi-dimensional array, and the subscript of each dimension in the multi-dimensional array respectively represents the grid
  • the offset of the grid in one coordinate axis direction; determining the road network code of the corresponding occupied grid according to the passable direction of each occupied grid includes: taking the determined road network code as the multidimensional array of the corresponding occupied grid Array element value.
  • the coordinates [x, y] of the two-dimensional grid coordinate system shown above can be represented by a two-dimensional array G, and the number of grids shown in Figure 2, Figure 3, and Figure 4 is 8 ⁇ 8, Then the dimension of G can be (8, 8), the first 8 represents the maximum coordinate value in the horizontal axis direction, and the second 8 represents the maximum coordinate value in the vertical axis direction.
  • G[0,0] corresponds to the first grid in the lower left corner of Figure 2.
  • the array element value of each grid can be initialized to 0, and after a grid is determined to be an occupied grid, its array element value can be set to other values, such as -1. After the road network code of the grid is determined, the road network code can be used as the value of the array element, so that the road network code of the grid can be determined only by querying the array element value of the grid.
  • the direction unit 1020 is configured to determine the traffic direction that matches the direction information of the road network as the occupied grid according to the connection relationship between the occupied grid and the adjacent grid. The traversable direction of the grid.
  • grid G[6, 6] has a connection relationship with G[7, 6], G[5, 5], according to the direction information of the road network, it is determined that G[6, 6] is passable To G[5, 5], that is, the passable direction of G[5, 5] is down to the left. That is, the direction information of the road network is to pass down to the left, and there is a grid with a connection relationship in the lower left of the current grid, then the passable direction of the current grid is down to the left.
  • the road network map is a two-dimensional map
  • the connection relationship between grids includes edge connection and corner connection
  • the traversable direction includes at least one of the following: up, down, left, Right, upper left, upper right, lower left, lower right; or, the road network map is a three-dimensional map
  • the connection relationship between grids includes surface connection, edge connection and vertex connection.
  • the grid usually has eight grids: top, bottom, left, right, top left, top right, bottom left, and bottom right. Adjacent grids are connected by edges and corners, and the traversable directions can be up, down, left, right, upper left, upper right, lower left, and lower right at most. For edge meshes, if one of the adjacent meshes is missing, then a traversable direction is missing.
  • a non-edge mesh has 26 adjacent meshes, connected by faces, edges, and vertices, and can have up to 26 traversable directions.
  • the encoding unit 1030 is configured to use a binary code with a preset number of bits as the road network code of the occupied grid, where each bit of the road network code corresponds to a traffic direction, and Mark with 1 or 0 whether each travel direction is a passable direction.
  • each bit of the 8-bit binary code corresponds to the 8 directions of up, down, left, right, upper left, upper right, and lower left, and the length is 1 byte. Indicates whether a direction is allowed to pass. In one embodiment, if it is allowed, the value of this bit is 1, otherwise it is 0.
  • the encoding unit 1030 is configured to first determine each occupied grid according to the passable direction of each occupied grid when the original road network code exists in each occupied grid.
  • the new road network code of the grid is performed on the original road network code and the new road network code of each occupied grid to obtain the road network code of each occupied grid.
  • the final road network coding information is obtained by the first bitwise operation of the road network coding information in all passable directions, for example, the first bitwise operation It is a bitwise OR (
  • ) operation, that is, the final encoding information in FIG. 7 is G[] 00000010
  • 00010000 00010010.
  • the road network map can also be continuously updated, that is, the grid can add new passable directions.
  • the first bitwise operation can be performed on the original road network code and the new road network code of the occupied grid to obtain the occupied grid.
  • the road network code of the grid For example, as shown in Figure 8, multiple occupied grids in the vertical direction correspond to the newly added road network.
  • 00001000 00101000.
  • the road network map obtained in the embodiment of the present application can also conveniently determine the type of road network nodes.
  • the above-mentioned apparatus further includes: a node unit for selecting a target grid of the node type to be determined; determining that there is an inter-grid connection relationship with the target grid, and at least one passable direction points to the target grid.
  • the grid of the target grid is used as the input grid of the target grid; the second bitwise operation is performed on the target grid and the road network code of the input grid of the target grid, if the binary code obtained after the operation is the same as the preset If the codes are the same, the target grid is determined to be an inflection point-type grid representing the existence of an inflection point in the road network.
  • the gray grid is the occupied grid
  • the grid with the darkest color [3, 6] is the target grid of the road network node type to be determined
  • the road network code is 00001000
  • the adjacent grid [2, 6] is its input grid
  • the road network code is 00000010.
  • the second bitwise operation is performed on the road network codes of [3, 6] and [2, 6].
  • the target mesh is not an inflection point of the road network.
  • the above-mentioned device further includes: a node unit for selecting a target grid of the node type to be determined; determining that there is an inter-grid connection relationship with the target grid, and at least one passable direction points to the target
  • the grid of the grid is used as the input grid of the target grid; if the target grid has multiple input grids, and the target grid has at least one passable direction, the target grid is determined to be the one representing the routing nodes in the road network. Routing node mesh.
  • the gray grid is the occupied grid
  • the darkest grid [3, 4] is the road network to be judged
  • the target grid of node type since grid [3, 4] has multiple input grids and there is a passable direction to the lower right, it means that the target grid [3, 4] is a routing node in the road network .
  • the technical solution of the present application not only realizes the grid coding of the vector road network, but more importantly preserves the direction information of the road network, and this information can be expressed in the form of a two-dimensional array, which is convenient for Input to the neural network for quick extraction by the neural network.
  • the road network coding can also realize the fusion of multiple road networks and the judgment of node types through simple bit operations, which has high computational efficiency.
  • modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment.
  • the modules or units or components in the embodiments may be combined into one module or unit or component, and further they may be divided into multiple sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method so disclosed may be employed in any combination, unless at least some of such features and/or procedures or elements are mutually exclusive. All processes or units of equipment are combined.
  • Each feature disclosed in this specification may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
  • Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components of the apparatus 1000 for implementing road network maps according to embodiments of the present application.
  • DSP digital signal processor
  • the present application can also be implemented as an apparatus or apparatus program (eg, computer programs and computer program products) for performing part or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.
  • FIG. 11 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the electronic device 1100 includes a processor 1110 and a memory 1120 arranged to store computer executable instructions (computer readable program code).
  • the memory 1120 may be electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the memory 1120 has storage space 1130 for storing computer readable program code 1131 for performing any of the method steps in the above-described methods.
  • the storage space 1130 for storing computer-readable program code may include various computer-readable program codes 1131 for implementing various steps in the above methods, respectively.
  • Computer readable program code 1131 can be read from or written to one or more computer program products.
  • FIG. 12 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.
  • the computer-readable storage medium 1200 stores computer-readable program code 1131 for performing the method steps according to the present application, which can be read by the processor 1110 of the electronic device 1100 when the computer-readable program code 1131 is executed by the electronic device 1100 , causing the electronic device 1100 to execute each step in the above-described method.
  • the computer-readable program code 1131 stored in the computer-readable storage medium can execute the method shown in any of the above-described embodiments.
  • the computer readable program code 1131 may be compressed in a suitable form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Remote Sensing (AREA)
  • Navigation (AREA)

Abstract

一种路网地图实现方法、装置和电子设备。所述方法包括：利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图（S110）；根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向（S120）；根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图（S130）。通过格网坐标系离散化处理路网，使得后续实现的路网地图具备了可输入神经网络的基础；基于路网的方向信息和网格间连接关系确定各被占据网格的可通行方向，进一步确定被占据网格的路网编码，从而实现了带有道路方向信息的路网地图，能够被神经网络所提取到，提升训练效果。

Description

一种路网地图实现方法、装置和电子设备 技术领域
本申请涉及电子地图领域，特别涉及一种路网地图实现方法、装置和电子设备。
发明背景
道路网(road network)指的是在一定区域内，由各种道路组成的相互联络、交织成网状分布的道路系统，简称路网，具有路网信息的地图则称为路网地图。目前，路网地图已在自动驾驶等领域得到使用，但现有技术中的路网地图大多存在着丢失道路方向信息等问题。
发明内容
鉴于现有技术中路网地图丢失道路方向信息的问题，提出了本申请的一种路网地图实现方法、装置和电子设备，以便克服上述问题。
为了实现上述目的，本申请采用了如下技术方案：
依据本申请的一个方面，提供了一种路网地图实现方法，包括：利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图；根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向；根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
依据本申请的另一方面，提供了一种路网地图实现装置。该装置包括：
离散化单元，用于利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图。
方向单元，用于根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向。
编码单元，用于根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
依据本申请的又一方面，提供了一种电子设备，包括：处理器；以及被安排成存储计算机可执行指令的存储器，可执行指令在被执行时使处理器执行如上的路网地图实现方法。
依据本申请的再一方面，提供了一种计算机可读存储介质，存储一个或多 个程序，一个或多个程序当被包括多个应用程序的电子设备执行时，使得电子设备执行如上的路网地图实现方法。
综上所述，本申请的有益效果是：通过格网坐标系离散化处理路网，使得后续实现的路网地图具备了可输入神经网络的基础；基于路网的方向信息和网格间连接关系确定各被占据网格的可通行方向，进一步确定被占据网格的路网编码，从而实现了带有道路方向信息的路网地图，能够被神经网络所提取到，提升训练效果。
附图简要说明
图1示出了根据本申请一个实施例的一种路网地图实现方法的流程示意图；
图2示出了一个格网坐标系的示意图；
图3示出了另一个格网坐标系的示意图；
图4示出了根据本申请一个实施例的路网离散化处理的示意图；
图5示出了根据本申请一个实施例的网格可通行方向的示意图；
图6示出了根据本申请一个实施例的一种路网编码模板的示意图；
图7示出了根据本申请一个实施例的具有两个可通行方向的网格；
图8示出了根据本申请一个实施例的路网叠加示意图；
图9示出了根据本申请一个实施例的路网节点示意图；
图10示出了根据本申请一个实施例的一种路网地图实现装置的结构示意图；
图11示出了根据本申请一个实施例的一种电子设备的结构示意图；
图12示出了根据本申请一个实施例的一种计算机可读存储介质的框图。
具体实施方式
下面将参照附图更详细地描述本申请的示例性实施例。虽然附图中显示了本申请的示例性实施例，然而应当理解，可以以各种形式实现本申请而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本申请，并且能够将本申请的范围完整的传达给本领域的技术人员。
本申请的技术构思是：通过离散化路网使得路网地图具备了被神经网络使用的基础，通过能够表征可通行方向的路网编码使得路网地图具备道路的方向信息，使得路网地图包含的信息量更大，在机器学习的模型训练过程中能发挥更大的作用。
下面结合具体实施例进行本申请技术方案的示例性说明。
图1示出了根据本申请一个实施例的一种路网地图实现方法的流程示意图，如图1所示，路网地图实现方法包括：
步骤S110，利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图。
步骤S120，根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向。
步骤S130，根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
可见，图1所示的方法，通过格网坐标系离散化处理路网，使得后续实现的路网地图具备了可输入神经网络的基础；基于路网的方向信息和网格间连接关系确定各被占据网格的可通行方向，进一步确定被占据网格的路网编码，从而实现了带有道路方向信息的路网地图，能够被神经网络所提取到，提升训练效果。
格网坐标系可通过确定坐标原点、比例尺、图幅大小建立，一般地，大比例尺精度高，小比例尺精度低。
图2和图3分别示出了格网坐标系的示意图。其中，图2是以左下角为坐标原点O的格网坐标系，图3是原点O在格网中间的格网坐标系，坐标原点可在格网的任意位置，在图2和图3中对应的网格以x示出，坐标原点定义二维坐标为[0，0]，其他网格的坐标可以以此为基础，按照笛卡尔坐标系确定相应的坐标。
可以看出，图3和图2所示出的两个格网坐标系可以通过坐标平移进行转换，变换公式为
Figure PCTCN2021124119-appb-000001
其中，x 0，y 0为偏移量，x′，y′为图3格网坐标系下的坐标，x，y是坐标转换到图2格网坐标系下的坐标。
也就是说，以格网坐标系作为建图基础，可以使得到的路网地图容易根据需求的变更加以变换，适应性强。
在确定格网坐标系后，可以对待建图的路网进行离散化处理，一种示例如图4所示。图4的(a)中示出了以左下角为坐标原点O的格网坐标系以及路网示 例，为便于说明，该路网仅示出了一条道路，箭头的方向标识了道路的实际通行方向，该通行方向指示道路起点为右上方位，终点在左下方位。
图4的(b)中是将路网叠加到格网坐标系中，可以看出道路经过(覆盖)了多个网格，在图4的(c)中将这些网格标记为被路网占据，得到了各个网格的占位图，由此实现了路网的离散化处理。
网格间连接关系指示是否存在与当前网格相邻的被占据网格，还可以指示当前网络和和与其相邻的被占据网格的方位关系。
如图4所述，路网的方向信息就是指路网中各条道路的通行方向，在现有技术中在建图后这些信息会丢失，但是在本申请的技术方案中，则是参考网格间连接关系和路网的方向信息，确定各被占据网格的可通行方向。
例如，图4的(c)中被占据网格[6，6]为例(原点网格为[0，0])，其与被占据网格[7，6]通过网格[6，6]的右侧边(网格[7，6]的左侧边)连接，和被占据网格[5，5]通过网格[6，6]的左下角(网格[5，5]的左下角)连接，则根据图4的(b)中路网从右上至左下的方向信息可知，被占据网格[6，6]的可通行方向为向左下。
现有技术中，网格的路网编码一般以0表示未被占据，以1表示被占据，这样就不能包含路网的方向信息，在本申请的实施例中对路网编码进行了改进，使得其可以表示路网的方向信息，具体地，就是用路网编码表示被占据网格的可通行方向。
在本申请的一个实施例中，上述方法中，利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图包括：以多维数组表示被占据网格在格网坐标系中的坐标位置，多维数组中每个维度的下标分别表示网格在一个坐标轴方向上的偏移量；根据各被占据网格的可通行方向确定相应被占据网格的路网编码包括：将确定的路网编码作为相应被占据网格的多维数组的数组元素值。
例如，前面示出的二维格网坐标系的坐标[x，y]就可以以一个二维数组G来表示，图2、图3、图4示出的网格个数为8×8，则G的维度可为(8，8)，第一个8表示横轴方向上的坐标最大值，第二个8表示纵轴方向上的坐标最大值。举例来说，G[0，0]就对应图2中左下角第一个网格。
各网格的数组元素值可以初始化为0，在确定一个网格是被占据网格后，可以将其的数组元素值置为其他值，例如-1。在确定网格的路网编码后，则可以将路网编码作为数组元素值，这样只要查询网格的数组元素值即可确定网格的路 网编码。
在本申请的一个实施例中，上述方法中，根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向包括：根据被占据网格与邻近网格的网格间连接关系，确定与路网的方向信息相匹配的通行方向作为被占据网格的可通行方向。
例如，如图5所示，网格G[6，6]与G[7，6]、G[5，5]具有连接关系，根据路网的方向信息，确定G[6，6]可通行到G[5，5]，即G[5，5]的可通行的方向为向左下。即路网的方向信息是向左下通行，而当前网格左下方存在具有连接关系的网格，那么当前网格的可通行方向就是向左下。
在本申请的一个实施例中，上述方法中，路网地图为二维地图，网格间连接关系包括边连接和角连接，可通行方向包括如下至少一种：向上，向下，向左，向右，向左上，向右上，向左下，向右下；或者，路网地图为三维地图，网格间连接关系包括面连接、棱连接和顶点连接。
二维地图的情况可以参照图2、图3和图4，可以直观地看出，除了边缘的网格外，网格通常具有上、下、左、右、左上、右上、左下、右下八个邻近网格，分别通过边和角连接，可通行方向最多可有向上，向下，向左，向右，向左上，向右上，向左下，向右下这八种。对于边缘的网格，如果缺少某一邻近网格，则就缺少了一个可通行方向。
将其拓展到三维地图的情形，非边缘的网格具有26个邻近网格，分别是通过面、棱和顶点连接，最多可具有26个可通行方向。
在本申请的一个实施例中，上述方法中，根据各被占据网格的可通行方向确定相应被占据网格的路网编码包括：以预设位数的二进制编码作为被占据网格的路网编码，路网编码的每一位对应一个通行方向，并以1或0标记各通行方向是否为可通行方向。
例如，8位二进制编码的每一位分别对应向上，向下，向左，向右，向左上，向右上，向左下这8个方向，长度为1个字节，该字节上每一位表示一个方向是否允许通行，一个实施例中，若允许，则该位上值为1，否则为0。路网编码模板可以参照图6所示，根据路网编码模板，图4中G[6，6]的路网编码为G[6，6]＝00010000。
在本申请的一个实施例中，上述方法中，根据各被占据网格的可通行方向确定相应被占据网格的路网编码还包括：在各被占据网格存在原路网编码的情 况下，先根据各被占据网格的可通行方向，确定各被占据网格的新增路网编码；对各被占据网格的原路网编码和新增路网编码进行第一按位操作，得到各被占据网格的路网编码。
对于网格有多个可通行方向的情况，如图7所示，最终的路网编码信息为所有可通行方向上的路网编码信息的第一按位操作得到，例如该第一按位操作为按位或(|)运算，即图7的最终编码信息为G[]＝00000010|00010000＝00010010。
另外，路网地图还可以不断更新，即网格可以新增可通行方向，此时可以对被占据网格的原路网编码和新增路网编码进行第一按位操作，得到各被占据网格的路网编码。例如，如图8所示，竖直方向的多个被占据网格对应新增路网，对于两个路网的交叉点(颜色最深的网格G[5，5])，其新的可通行方向如图8中最后所示，进行或操作后，新的G[5，5]＝00100000|00001000＝00101000。
本申请实施例得到的路网地图还可以方便地进行路网节点类型的判断。例如在本申请的一个实施例中，上述方法还包括：选取待判断节点类型的目标网格；确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向目标网格的网格作为该目标网格的输入网格；将目标网格以及该目标网格的输入网格的路网编码进行第二按位操作，若操作后得到的二进制编码与预设编码相同，则确定该目标网格为表征路网在此处存在拐点的拐点型网格。
在一个具体的例子中，如图9的(a)所示的以左下角为格网坐标系原点的路网地图中，灰色的网格是被占据网格，颜色最深的网格[3，6]为待判断路网节点类型的目标网格，路网编码为00001000，其邻近网格[2，6]为其输入网格，路网编码为00000010。
对[3，6]和[2，6]的路网编码进行第二按位操作，具体地，第二按位操作可以为按位与操作，即00001000&00000010＝00000000，则表示道路的方向在此改变，即目标网格[3，6]为拐点。在另外的例子中，如果目标网格以及该目标网格的输入网格的路网编码进行与操作后，至少存在不为0的一位，则说明两个网格在此方向均可通行，因此目标网格不是路网拐点。
在本申请的一个实施例中，上述方法还包括：选取待判断节点类型的目标网格；确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向目标网格的网格作为该目标网格的输入网格；若目标网格具有多个输入网格，且目标网格至少存在一个可通行方向，则确定目标网格为表征路网中路由节点的路由节点型网格。
如图9的(b)所示的以左下角为格网坐标系原点的路网地图中，灰色的网格是被占据网格，颜色最深的网格[3，4]为待判断路网节点类型的目标网格，由于网格[3，4]有多个输入网格，且存在向右下的可通行方向，则说明该目标网格[3，4]是路网中的路由节点。
本申请的实施例还提出了一种路网地图实现装置，可用于实现如上任一实施例所示出的路网地图实现方法。
具体地，图10示出了根据本申请一个实施例的一种路网地图实现装置的结构示意图，如图10所示，路网地图实现装置1000包括：
离散化单元1010，用于利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图。
方向单元1020，用于根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向。
编码单元1030，用于根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
可见，图10所示的装置，通过格网坐标系离散化处理路网，使得后续实现的路网地图具备了可输入神经网络的基础；基于路网的方向信息和网格间连接关系确定各被占据网格的可通行方向，进一步确定被占据网格的路网编码，从而实现了带有道路方向信息的路网地图，能够被神经网络所提取到，提升训练效果。
格网坐标系可通过确定坐标原点、比例尺、图幅大小建立，一般地，大比例尺精度高，小比例尺精度低。
图2和图3分别示出了格网坐标系的示意图。其中，图2是以左下角为坐标原点O的格网坐标系，图3是原点O在格网中间的格网坐标系，坐标原点可在格网的任意位置，在图2和图3中对应的网格以x示出，坐标原点定义二维坐标为[0，0]，其他网格的坐标可以以此为基础，按照笛卡尔坐标系确定相应的坐标。
可以看出，图3和图2所示出的两个格网坐标系可以通过坐标平移进行转换，变换公式为
Figure PCTCN2021124119-appb-000002
其中，x 0，y 0为偏移量，x′，y′为图3格网坐标系下的坐标，x，y是坐标转 换到图2格网坐标系下的坐标。
也就是说，以格网坐标系作为建图基础，可以使得到的路网地图容易根据需求的变更加以变换，适应性强。
在确定格网坐标系后，可以对待建图的路网进行离散化处理，一种示例如图4所示。图4的(a)中示出了以左下角为坐标原点O的格网坐标系以及路网示例，为便于说明，该路网仅示出了一条道路，箭头的方向标识了道路的实际通行方向，该通行方向指示道路起点为右上方位，终点在左下方位。
图4的(b)中是将路网叠加到格网坐标系中，可以看出道路经过(覆盖)了多个网格，在图4的(c)中将这些网格标记为被路网占据，得到了各个网格的占位图，由此实现了路网的离散化处理。
网格间连接关系指示是否存在与当前网格相邻的被占据网格，还可以指示当前网络和和与其相邻的被占据网格的方位关系。
如图4所述，路网的方向信息就是指路网中各条道路的通行方向，在现有技术中在建图后这些信息会丢失，但是在本申请的技术方案中，则是参考网格间连接关系和路网的方向信息，确定各被占据网格的可通行方向。
例如，以图4的(c)中被占据网格[6，6]为例(原点网格为[0，0])，其与被占据网格[7，6]通过网格[6，6]的右侧边(网格[7，6]的左侧边)连接，和被占据网格[5，5]通过网格[6，6]的左下角(网格[5，5]的左下角)连接，则根据图4的(b)路网从右上至左下的方向信息可知，被占据网格[6，6]的可通行方向为向左下。
现有技术中，网格的路网编码一般以0表示未被占据，以1表示被占据，这样就不能包含路网的方向信息，在本申请的实施例中对路网编码进行了改进，使得其可以表示路网的方向信息，具体地，就是用路网编码表示被占据网格的可通行方向。
在本申请的一个实施例中，上述装置中，离散化单元1010，用于以多维数组表示被占据网格在格网坐标系中的坐标位置，多维数组中每个维度的下标分别表示网格在一个坐标轴方向上的偏移量；根据各被占据网格的可通行方向确定相应被占据网格的路网编码包括：将确定的路网编码作为相应被占据网格的多维数组的数组元素值。
例如，前面示出的二维格网坐标系的坐标[x，y]就可以以一个二维数组G来表示，图2、图3、图4示出的网格个数为8×8，则G的维度可为(8，8)，第一个8表示横轴方向上的坐标最大值，第二个8表示纵轴方向上的坐标最大值。举例 来说，G[0，0]就对应图2中左下角第一个网格。
各网格的数组元素值可以初始化为0，在确定一个网格是被占据网格后，可以将其的数组元素值置为其他值，例如-1。在确定网格的路网编码后，则可以将路网编码作为数组元素值，这样只要查询网格的数组元素值即可确定网格的路网编码。
在本申请的一个实施例中，上述装置中，方向单元1020，用于根据被占据网格与邻近网格的网格间连接关系，确定与路网的方向信息相匹配的通行方向作为被占据网格的可通行方向。
例如，如图5所示，网格G[6，6]与G[7，6]、G[5，5]具有连接关系，根据路网的方向信息，确定G[6，6]可通行到G[5，5]，即G[5，5]的可通行的方向为向左下。即路网的方向信息是向左下通行，而当前网格左下方存在具有连接关系的网格，那么当前网格的可通行方向就是向左下。
在本申请的一个实施例中，上述装置中，路网地图为二维地图，网格间连接关系包括边连接和角连接，可通行方向包括如下至少一种：向上，向下，向左，向右，向左上，向右上，向左下，向右下；或者，路网地图为三维地图，网格间连接关系包括面连接、棱连接和顶点连接。
二维地图的情况可以参照图2、图3和图4，可以直观地看出，除了边缘的网格外，网格通常具有上、下、左、右、左上、右上、左下、右下八个邻近网格，分别通过边和角连接，可通行方向最多可有向上，向下，向左，向右，向左上，向右上，向左下，向右下这八种。对于边缘的网格，如果缺少某一邻近网格，则就缺少了一个可通行方向。
将其拓展到三维地图的情形，非边缘的网格具有26个邻近网格，分别是通过面、棱和顶点连接，最多可具有26个可通行方向。
在本申请的一个实施例中，上述装置中，编码单元1030，用于以预设位数的二进制编码作为被占据网格的路网编码，路网编码的每一位对应一个通行方向，并以1或0标记各通行方向是否为可通行方向。
例如，8位二进制编码的每一位分别对应向上，向下，向左，向右，向左上，向右上，向左下这8个方向，长度为1个字节，该字节上每一位表示一个方向是否允许通行，一个实施例中，若允许，则该位上值为1，否则为0。路网编码模板可以参照图6所示，根据路网编码模板，图4中G[6，6]的路网编码为G[6，6]＝00010000。
在本申请的一个实施例中，上述装置中，编码单元1030，用于在各被占据网格存在原路网编码的情况下，先根据各被占据网格的可通行方向，确定各被占据网格的新增路网编码；对各被占据网格的原路网编码和新增路网编码进行第一按位操作，得到各被占据网格的路网编码。
对于网格有多个可通行方向的情况，如图7所示，最终的路网编码信息为所有可通行方向上的路网编码信息的第一按位操作得到，例如该第一按位操作为按位或(|)运算，即图7的最终编码信息为G[]＝00000010|00010000＝00010010。
另外，路网地图还可以不断更新，即网格可以新增可通行方向，此时可以对被占据网格的原路网编码和新增路网编码进行第一按位操作，得到各被占据网格的路网编码。例如，如图8所示，竖直方向的多个被占据网格对应新增路网，对于两个路网的交叉点(颜色最深的网格G[5，5])，其新的可通行方向如图8中最后所示，进行或操作后，新的G[5，5]＝00100000|00001000＝00101000。
本申请实施例得到的路网地图还可以方便地进行路网节点类型的判断。例如在本申请的一个实施例中，上述装置还包括：节点单元，用于选取待判断节点类型的目标网格；确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向目标网格的网格作为该目标网格的输入网格；将目标网格以及该目标网格的输入网格的路网编码进行第二按位操作，若操作后得到的二进制编码与预设编码相同，则确定该目标网格为表征路网在此处存在拐点的拐点型网格。
在一个具体的例子中，如图9的(a)所示的以左下角为格网坐标系原点的路网地图中，灰色的网格是被占据网格，颜色最深的网格[3，6]为待判断路网节点类型的目标网格，路网编码为00001000，其邻近网格[2，6]为其输入网格，路网编码为00000010。
对[3，6]和[2，6]的路网编码进行第二按位操作，具体地，第二按位操作可以为按位与操作，即00001000&00000010＝00000000，则表示道路的方向在此改变，即目标网格[3，6]为拐点。在另外的例子中，如果目标网格以及该目标网格的输入网格的路网编码进行与操作后，至少存在不为0的一位，则说明两个网格在此方向均可通行，因此目标网格不是路网拐点。
在本申请的一个实施例中，上述装置还包括：节点单元，用于选取待判断节点类型的目标网格；确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向目标网格的网格作为该目标网格的输入网格；若目标网格具有多个输入网格，且目标网格至少存在一个可通行方向，则确定目标网格为表征路 网中路由节点的路由节点型网格。
如图9的(b)所示的以左下角为格网坐标系原点的路网地图中，灰色的网格是被占据网格，颜色最深的网格[3，4]为待判断路网节点类型的目标网格，由于网格[3，4]有多个输入网格，且存在向右下的可通行方向，则说明该目标网格[3，4]是路网中的路由节点。
综上所述，本申请的技术方案，不仅实现了对矢量路网的栅格化编码，更重要的是保留了路网的方向信息，而且这种信息能以二维数组的方式表示，方便输入到神经网络，方便神经网络快速提取。此外，路网编码还能通过简单的位操作，实现多个路网融合、节点类型判断，具有很高的计算效率。
需要说明的是：
在此提供的算法和显示不与任何特定计算机、虚拟装置或者其它设备固有相关。各种通用装置也可以与基于在此的示教一起使用。根据上面的描述，构造这类装置所要求的结构是显而易见的。此外，本申请也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本申请的内容，并且上面对特定语言所做的描述是为了披露本申请的最佳实施方式。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施 例的路网地图实现装置1000中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
例如，图11示出了根据本申请一个实施例的电子设备的结构示意图。该电子设备1100包括处理器1110和被安排成存储计算机可执行指令(计算机可读程序代码)的存储器1120。存储器1120可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器1120具有存储用于执行上述方法中的任何方法步骤的计算机可读程序代码1131的存储空间1130。例如，用于存储计算机可读程序代码的存储空间1130可以包括分别用于实现上面的方法中的各种步骤的各个计算机可读程序代码1131。计算机可读程序代码1131可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘，紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为例如图12所述的计算机可读存储介质。图12示出了根据本申请一个实施例的一种计算机可读存储介质的结构示意图。该计算机可读存储介质1200存储有用于执行根据本申请的方法步骤的计算机可读程序代码1131，可以被电子设备1100的处理器1110读取，当计算机可读程序代码1131由电子设备1100运行时，导致该电子设备1100执行上面所描述的方法中的各个步骤，具体来说，该计算机可读存储介质存储的计算机可读程序代码1131可以执行上述任一实施例中示出的方法。计算机可读程序代码1131可以以适当形式进行压缩。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (11)

  1. 一种路网地图实现方法，其中，所述路网地图实现方法包括：
    利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征所述路网的基础路网地图；
    根据所述路网的方向信息和网格间连接关系，确定所述基础路网地图中各被占据网格的可通行方向；
    根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
  2. 根据权利要求1所述的路网地图实现方法，其中，所述利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征所述路网的基础路网地图包括：
    以多维数组表示被占据网格在所述格网坐标系中的坐标位置，多维数组中每个维度的下标分别表示网格在一个坐标轴方向上的偏移量；
    所述根据各被占据网格的可通行方向确定相应被占据网格的路网编码包括：将确定的路网编码作为相应被占据网格的多维数组的数组元素值。
  3. 根据权利要求1所述的路网地图实现方法，其中，所述根据所述路网的方向信息和网格间连接关系，确定所述基础路网地图中各被占据网格的可通行方向包括：
    根据被占据网格与邻近网格的网格间连接关系，确定与所述路网的方向信息相匹配的通行方向作为被占据网格的可通行方向。
  4. 根据权利要求1所述的路网地图实现方法，其中，
    所述路网地图为二维地图，所述网格间连接关系包括边连接和角连接，所述可通行方向包括如下至少一种：向上，向下，向左，向右，向左上，向右上，向左下，向右下；
    或者，
    所述路网地图为三维地图，所述网格间连接关系包括面连接、棱连接和顶点连接。
  5. 根据权利要求1所述的路网地图实现方法，其中，所述根据各被占据网格的可通行方向确定相应被占据网格的路网编码包括：
    以预设位数的二进制编码作为被占据网格的路网编码，所述路网编码的每一位对应一个通行方向，并以1或0标记各通行方向是否为可通行方向。
  6. 根据权利要求5所述的方法，其中，所述根据各被占据网格的可通行方向确定相应被占据网格的路网编码还包括：
    在所述各被占据网格存在原路网编码的情况下，先根据各被占据网格的可通行方向，确定各被占据网格的新增路网编码；
    对各被占据网格的原路网编码和新增路网编码进行第一按位操作，得到各被占据网格的路网编码。
  7. 根据权利要求5所述的方法，其中，所述方法还包括：
    选取待判断节点类型的目标网格；
    确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向所述目标网格的网格作为该目标网格的输入网格；
    将所述目标网格以及该目标网格的输入网格的路网编码进行第二按位操作，若操作后得到的二进制编码与预设编码相同，则确定该目标网格为表征路网在此处存在拐点的拐点型网格。
  8. 根据权利要求5所述的方法，其中，所述方法还包括：
    选取待判断节点类型的目标网格；
    确定与该目标网格存在网格间连接关系、且至少一个可通行方向指向所述目标网格的网格作为该目标网格的输入网格；
    若所述目标网格具有多个输入网格，且所述目标网格至少存在一个可通行方向，则确定所述目标网格为表征路网中路由节点的路由节点型网格。
  9. 一种路网地图实现装置，其中，所述装置包括：
    离散化单元，用于利用格网坐标系对待建图的路网进行离散化处理，得到以被占据网格表征路网的基础路网地图；
    方向单元，用于根据路网的方向信息和网格间连接关系，确定基础路网地图中各被占据网格的可通行方向；
    编码单元，用于根据各被占据网格的可通行方向确定相应被占据网格的路网编码，从而实现路网地图。
  10. 根据权利要求9所述的装置，其中，编码单元，用于以预设位数的二进制编码作为被占据网格的路网编码，路网编码的每一位对应一个通行方向，并以1或0标记各通行方向是否为可通行方向。
  11. 一种电子设备，其中，所述电子设备包括：
    处理器；以及
    被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器执行根据权利要求1-8中任一项所述的路网地图实现方法。
PCT/CN2021/124119 2020-10-16 2021-10-15 一种路网地图实现方法、装置和电子设备 WO2022078499A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011108504.7A CN112348917B (zh) 2020-10-16 2020-10-16 一种路网地图实现方法、装置和电子设备
CN202011108504.7 2020-10-16

Publications (1)

Publication Number Publication Date
WO2022078499A1 true WO2022078499A1 (zh) 2022-04-21

Family

ID=74360832

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124119 WO2022078499A1 (zh) 2020-10-16 2021-10-15 一种路网地图实现方法、装置和电子设备

Country Status (2)

Country Link
CN (1) CN112348917B (zh)
WO (1) WO2022078499A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116127672A (zh) * 2023-04-17 2023-05-16 北京路凯智行科技有限公司 露天矿路网生成方法和露天矿路网生成装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112348917B (zh) * 2020-10-16 2022-12-09 歌尔股份有限公司 一种路网地图实现方法、装置和电子设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107144288A (zh) * 2017-05-19 2017-09-08 北京旋极伏羲大数据技术有限公司 一种无路网地形条件下的路径规划的方法及其装置
CN109993064A (zh) * 2019-03-06 2019-07-09 东南大学 一种提取图片中道路网络节点间的连接路径的方法
CN110556049A (zh) * 2018-06-04 2019-12-10 百度在线网络技术（北京）有限公司 一种地图数据处理方法、装置、服务器和存储介质
CN111475597A (zh) * 2020-03-31 2020-07-31 中国人民解放军战略支援部队信息工程大学 非刚性网格编码、空间对象唯一标识、查询方法及装置
US20200265248A1 (en) * 2019-02-14 2020-08-20 Hanwha Defense Co., Ltd. Obstacle map generating method and apparatus
CN112348917A (zh) * 2020-10-16 2021-02-09 歌尔股份有限公司 一种路网地图实现方法、装置和电子设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2905503C (en) * 2013-03-14 2021-08-24 Sirius Xm Radio Inc. High resolution encoding and transmission of traffic information
CN107084729B (zh) * 2017-05-03 2020-02-07 北京都在哪网讯科技有限公司 导航方法和装置
CN109541634B (zh) * 2018-12-28 2023-01-17 歌尔股份有限公司 一种路径规划方法、装置和移动设备
CN109948477B (zh) * 2019-03-06 2022-05-13 东南大学 一种提取图片中道路网络拓扑点的方法
CN111583652B (zh) * 2020-05-21 2021-10-08 北京易华录信息技术股份有限公司 一种交通路网的拓扑建模方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107144288A (zh) * 2017-05-19 2017-09-08 北京旋极伏羲大数据技术有限公司 一种无路网地形条件下的路径规划的方法及其装置
CN110556049A (zh) * 2018-06-04 2019-12-10 百度在线网络技术（北京）有限公司 一种地图数据处理方法、装置、服务器和存储介质
US20200265248A1 (en) * 2019-02-14 2020-08-20 Hanwha Defense Co., Ltd. Obstacle map generating method and apparatus
CN109993064A (zh) * 2019-03-06 2019-07-09 东南大学 一种提取图片中道路网络节点间的连接路径的方法
CN111475597A (zh) * 2020-03-31 2020-07-31 中国人民解放军战略支援部队信息工程大学 非刚性网格编码、空间对象唯一标识、查询方法及装置
CN112348917A (zh) * 2020-10-16 2021-02-09 歌尔股份有限公司 一种路网地图实现方法、装置和电子设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116127672A (zh) * 2023-04-17 2023-05-16 北京路凯智行科技有限公司 露天矿路网生成方法和露天矿路网生成装置

Also Published As

Publication number Publication date
CN112348917A (zh) 2021-02-09
CN112348917B (zh) 2022-12-09

Similar Documents

Publication Publication Date Title
WO2022078499A1 (zh) 一种路网地图实现方法、装置和电子设备
WO2020134082A1 (zh) 一种路径规划方法、装置和移动设备
KR20200115173A (ko) 교차로를 드로잉하는 방법, 장치, 서버 및 저장 매체
CN109584302B (zh) 相机位姿优化方法、装置、电子设备和计算机可读介质
CN105787977B (zh) 建筑物矢量边界简化的方法
CN107330438A (zh) 一种图像轮廓线描述符的获取方法、装置
CN107193923B (zh) 一种二维地理空间快速矢量叠加的方法及系统
CN107564077B (zh) 一种绘制道路网的方法及装置
CN113704381B (zh) 路网数据处理方法、装置、计算机设备和存储介质
CN110909961A (zh) 基于bim的室内路径查询方法及装置
KR101182683B1 (ko) 시각적 형상 디스크립터 생성 방법 및 그 기록매체
JP4928993B2 (ja) 農地区画データ作成システム
CN110992481B (zh) 基于最邻近连线的建筑物白模一致性合并方法
CN103970901A (zh) 一种地理信息图形数据整合方法
Haunert et al. Using the straight skeleton for generalisation in a multiple representation environment
CN111538735A (zh) 基于任意数据库的空间数据编码、查询方法和电子设备
CN114283343A (zh) 基于遥感卫星图像的地图更新方法、训练方法和设备
JP2007256402A (ja) 地図データ生成装置
CN115796111A (zh) 一种适用于agf文件处理方法、计算机设备、可读存储介质
CN111009036B (zh) 同步定位与地图构建中栅格地图的修正方法、装置
CN111008668B (zh) 一种数据奇异点的识别方法、装置、设备和介质
CN109859118B (zh) 一种基于四叉树的有效镶嵌多边形优化去除云覆盖区域的方法和系统
Jiao et al. Research on an environmental adaptive feature extraction algorithm
Johnston et al. Problems arising from a simple GIS generalisation algorithm
Yin et al. Incremental construction of generalized Voronoi diagrams on pointerless quadtrees

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21879540

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21879540

Country of ref document: EP

Kind code of ref document: A1