CN110838178A - Method and device for determining road scene model - Google Patents

Method and device for determining road scene model Download PDF

Info

Publication number
CN110838178A
CN110838178A CN201911172530.3A CN201911172530A CN110838178A CN 110838178 A CN110838178 A CN 110838178A CN 201911172530 A CN201911172530 A CN 201911172530A CN 110838178 A CN110838178 A CN 110838178A
Authority
CN
China
Prior art keywords
data
vector data
determining
road
target
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN201911172530.3A
Other languages
Chinese (zh)
Other versions
CN110838178B (en
Inventor
孙锐
周明瑞
张金
韩娜
赵龙
石清华
熊继林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Cennavi Technologies Co Ltd
Original Assignee
Beijing Cennavi Technologies Co Ltd
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 Beijing Cennavi Technologies Co Ltd filed Critical Beijing Cennavi Technologies Co Ltd
Priority to CN201911172530.3A priority Critical patent/CN110838178B/en
Publication of CN110838178A publication Critical patent/CN110838178A/en
Application granted granted Critical
Publication of CN110838178B publication Critical patent/CN110838178B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/61—Scene description

Abstract

The application provides a method and a device for determining a road scene model, relates to the technical field of traffic, and can accurately determine the road scene model and reduce labor cost. The method comprises the following steps: acquiring point cloud data of a target road; the target roadway comprises one or more markers; according to the point cloud data, determining vector data corresponding to the marker and the data type of the vector data; the vector data includes position information and attribute information of the marker; determining a geometric model corresponding to the marker according to the vector data and the data type of the vector data; the geometric model is used for characterizing the shape of the marker; determining a three-dimensional model of the marker according to the attribute information and the geometric model; determining a road scene model of the target road according to the three-dimensional model of one or more markers and the position information of the markers.

Description

Method and device for determining road scene model
Technical Field
The present application relates to the field of data processing, and in particular, to a method and an apparatus for determining a road scene model.
Background
At present, the method for determining the road scene model is mainly manual modeling. The artificial modeling method comprises the following steps: the staff collects the geographic position information of the road and the description information such as photos, videos and the like. And the staff determines the specific position of the target road according to the geographical position information and determines the three-dimensional model of the target road according to the description information. And the staff constructs a road scene model in the three-dimensional modeling software according to the specific position of the target road and the three-dimensional model.
However, the above-mentioned artificial modeling method is only applicable to a case where a road scene is simple. In the case where the scene of the target road is complicated, the workload of the worker would be very large if it is modeled manually. Therefore, the efficiency of road modeling is greatly reduced by means of manual modeling, and meanwhile, the error rate of the manual modeling is high.
Disclosure of Invention
The application provides a method and a device for determining a road scene model, which are used for accurately determining the road scene model and reducing labor cost.
In order to achieve the purpose, the technical scheme is as follows:
in a first aspect, the present application provides a method for determining a road scene model, which may include:
the server obtains point cloud data of a target road, wherein the target road comprises one or more markers. And the server determines vector data corresponding to the target marker and the data type of the vector data according to the point cloud data. The vector data includes position information and attribute information of the marker, and the target marker is any one of one or more markers. And then, the server determines a geometric model corresponding to the target marker according to the vector data and the data type of the vector data. The geometric model is used to characterize the shape of the target marker. Further, the server determines a three-dimensional model of the target marker based on the attribute information and the geometric model. And finally, the server determines a road scene model of the target road according to the three-dimensional models of the one or more markers and the corresponding position information.
In a second aspect, the present application provides an apparatus for determining a road scene model, the apparatus comprising: the communication unit is used for acquiring point cloud data of a target road, and the target road comprises one or more markers. And the processing unit is used for determining vector data corresponding to the target marker and the data type of the vector data according to the point cloud data, wherein the target marker is any one of one or more markers. The vector data includes position information and attribute information of the target marker. And the processing unit is also used for determining the geometric model corresponding to the target marker according to the vector data and the data type of the vector data. The geometric model is used to characterize the shape of the target marker. And the processing unit is also used for determining a three-dimensional model of the target marker according to the attribute information and the geometric model. And the processing unit is also used for determining a road scene model of the target road according to the three-dimensional model of the one or more markers and the corresponding position information.
In a third aspect, the present application provides an apparatus for determining a road scene model, the apparatus comprising: a processor, a transceiver, and a memory. Wherein the memory is used to store one or more programs. The one or more programs include computer executable instructions which, when executed by the processor, cause the apparatus to perform the method of determining a road scene model as set forth in any of the first aspect and its various alternative implementations.
In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and when the instructions are executed by a computer, the computer executes the method for determining a road scene model according to any one of the first aspect and various optional implementations thereof.
In a fifth aspect, the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method for determining a road scene model according to any one of the above first aspect and its various alternative implementations.
In a sixth aspect, there is provided a chip comprising at least one processor and a communication interface, the communication interface being coupled to the at least one processor, the at least one processor being configured to execute computer programs or instructions to implement the method of the first aspect.
According to the method and the device for determining the road scene model, firstly, a server acquires point cloud data of a target road. Because point cloud data can be collected through automation equipment, compared with the prior art in which pictures or videos of roads are manually shot, the time and cost for manual collection can be reduced. Further, the server determines vector data and the type of the vector data of one or more markers of the target road according to the point cloud data of the target road, and determines a geometric model of the marker according to the type of the vector data and the type of the vector data. Wherein the markers have corresponding attribute information and the geometric model is used for characterizing the shape of the markers. Since the vector data includes the spatial geographical information of the markers and the types of the markers. Therefore, the server can determine the corresponding geometric model of the marker through the vector data and the type of the vector data. Thus, the staff does not need to manually delineate the geometric model of the marker by means of three-dimensional modeling software. The problem of work efficiency low among the prior art is solved. Further, the server may determine a three-dimensional model of the marker based on the attribute information of the marker and the geometric model. Thus, the problem of the three-dimensional model of the marker not conforming to the marker due to human factors (e.g., artificial visual deviation) in some cases can be avoided. And finally, the server can obtain a road scene model of the target road according to the geographical position information and the three-dimensional model of the one or more markers. Therefore, the method for determining the road scene model provided by the embodiment of the application can efficiently and accurately determine the road scene model. Meanwhile, high cost and error risk caused by a large amount of labor are avoided.
Drawings
Fig. 1 is a schematic diagram of point cloud data of a road according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a communication system according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for determining a road scene model according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of point cloud data of another road provided in the embodiment of the present application;
FIG. 5 is a schematic diagram of a road scene model provided in an embodiment of the present application;
fig. 6 is a schematic flowchart of another method for determining a road scene model according to an embodiment of the present disclosure;
fig. 7 is a schematic flowchart of a method for determining a road scene model according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of a device for determining a road scene model according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of another road scene model determining apparatus according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a further apparatus for determining a road scene model according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of a chip according to an embodiment of the present application.
Detailed Description
The following describes in detail a method and an apparatus for determining a road scene model according to an embodiment of the present application with reference to the drawings.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.
In order to facilitate understanding of the technical solutions of the present application, some technical terms are described below.
1. Point cloud data
Point cloud data refers to a collection of vectors in a three-dimensional coordinate system. These vectors are typically expressed in three-dimensional coordinates and are generally used primarily to represent the shape of the external surface of an object. The point cloud data may also represent Red Green Blue (RGB) color, gray value, depth, segmentation result, etc. of a point.
Exemplarily, as shown in fig. 1, point cloud data of a road provided by an embodiment of the present application is provided.
2. Laser point cloud data
The laser point cloud data includes a plurality of laser point data. Each laser point data comprises the coordinates, the acquisition time and the light intensity of the laser point. Wherein the coordinates include longitude and latitude and height.
3. Vector data
The vector data is data indicating the position of a map graphic or a geographic entity in a coordinate system by coordinates. Vector data is generally used to represent the spatial position of a geographic entity as accurately as possible by recording coordinates.
The vector data has a corresponding data type. The data types of the vector data may include point vector data, line vector data, and plane vector data. Vector data of these three data types is explained below.
① dot vector data, which means vector data corresponding to a marker of a three-dimensional structure, for example, a traffic light of a three-dimensional structure is taken as an example, in dot cloud data, a traffic light is composed of a plurality of dots, each dot has a three-dimensional coordinate, a server can determine the longitude and the altitude of the traffic light according to the three-dimensional coordinates of the plurality of dots, in a three-dimensional coordinate system, the server can take the dot corresponding to the longitude and the altitude of the traffic light as the traffic light, for example, the longitude of the traffic light is 116 °, the latitude is 39 °, the altitude is 3 m, in a three-dimensional coordinate system, the three-dimensional coordinate of the point a is (116 °, 39 °, 3), then the server can take the vector data of the point a as the vector data of the traffic light.
② line vector data, which is vector data corresponding to a marker of a stripe-type structure, the line vector data including a plurality of coordinates and a width of a line.
③ surface vector data, the surface vector data refers to vector data corresponding to a planar structure of markers, the surface vector data includes coordinates of a plurality of vertices of a plane, taking the planar structure as a zebra crossing as an example, the zebra crossing is a quadrilateral plane, the plane includes a plurality of continuous lines, the vector data of the zebra crossing includes coordinates of four vertices, coordinates corresponding to the plurality of continuous lines, taking a curved road surface as an example, the vector data of the road surface may include coordinates of vertices of the road surface, and a plurality of coordinates corresponding to each of two boundary lines of the road surface.
4. Road sign
The road signs include street lamps, road markings, zebra crossings, road signs, road boundary lines, road guardrails, road barriers and the like.
5. Geometric model
Geometric models refer to the use of geometric concepts to describe the shape of a physical or mathematical object. The geometric model includes planar models such as lines and planes. Three-dimensional models, such as a stereo model, are also included. The geometric model has no color, no gray scale, etc.
Fig. 2 shows a system structure provided in the embodiment of the present application. The system configuration includes a server 100 and a vehicle radar 200.
The vehicle radar 200 is configured to collect laser point cloud data and image data of a road, and send the laser point cloud data and the image data to the server 100. The server 100 is used to receive laser point data and image data from the vehicle radar. The server 100 is further configured to determine a road scene model of the road from the laser point cloud data and/or the image data.
The following describes a method for determining a road scene model provided in an embodiment of the present application with reference to drawings in the specification.
As shown in fig. 3, the method for determining a road scene model provided in the embodiment of the present application includes:
step 101, a server acquires point cloud data of a target road.
Wherein the server may be the server 100 of fig. 2. The target roadway includes one or more markers. The point cloud data includes position information and attribute information of a plurality of points. Such as color data of the dots, light intensity, etc.
It should be noted that, in the embodiment of the present application, the server may also replace the point cloud data with the laser point cloud data.
And step 102, the server determines the vector data of the target marker and the data type of the vector data according to the point cloud data.
Wherein each vector data has a unique identification (e.g., identification number (ID)). The target marker is any one of one or more markers of the target roadway. The vector data includes position information of the markers and attribute information. The position information of the marker may be longitude and latitude as well as height of the marker. The attribute information of the marker includes the type, texture, and the like of the marker. The types of the markers include linear markers (such as road markings and boundary lines of roads), surface markers (such as road surfaces), and three-dimensional markers (such as traffic lights and street lamps). The texture of the marker is used to represent the color and gray scale of the marker. For example, the texture of the road marking may be yellow, or the like. The texture of the guideboard may include blue (the color of the guideboard), white (the color of the text), and the like.
In one possible implementation, the server may determine vector data corresponding to a plurality of markers of the target road and a data type of the vector data according to three-dimensional coordinates of a plurality of points of the point cloud data and/or attribute information (e.g., color, light intensity) of each of the plurality of points.
Illustratively, the target object is a road surface and a road marking. In the three-dimensional coordinate system of the point cloud data shown in fig. 4, the road surface and the road marking each include a plurality of points, each point of the road surface has the same color (for example, both black) and each point of the road marking has the same color (for example, both white or yellow). The three-dimensional coordinates of the plurality of points of the road surface and the three-dimensional coordinates of the plurality of points of the road marking are both 0 in the Z-axis direction in the three-dimensional coordinate system. Since the colors of the plurality of points on the road surface are different from the colors of the plurality of points on the road sign, the server may determine the vector data corresponding to the road surface and the data type of the vector data (that is, the plane vector data) according to the point in the point cloud data where the data value in the Z-axis direction is 0 and the color data is black. The server may also determine the vector data corresponding to the road identifier and the data type of the vector data (i.e., line vector data) according to a plurality of points in the point cloud data, where the data value in the Z-axis direction is 0 and the color data is yellow or white.
Yet another example is for the target marker to be a stereo type marker, such as a traffic light of a road. In the three-dimensional system of point cloud data shown in fig. 4, the traffic light includes a plurality of points, and the data values of each point in the three-dimensional coordinate system in the X-axis direction and the Y-axis direction are similar or identical, or the data values in the X-axis direction and the Y-axis direction are concentrated in a preset range. But the data values in the Z-axis direction are not the same and the data values are continuous. Therefore, the server may determine the vector data corresponding to the traffic light and the data type (i.e., the point data type) of the vector data according to that the data values in the X-axis direction and the Y-axis direction in the point cloud data are the same and the data values in the z-axis direction are consecutive points.
And 103, the server determines a geometric model corresponding to the target marker according to the vector data and the data type of the vector data.
Wherein the geometric model is used to characterize the shape of the marker. For example, if the target marker is a road marking, the geometric model of the road marking is a line. Taking the marker as the zebra crossing as an example, the geometric model of the zebra crossing is a plane. Taking the marker as the road signboard as an example, the geometric model of the road signboard is a three-dimensional model.
And step 104, the server determines a three-dimensional model of the target marker according to the attribute information and the geometric model.
The three-dimensional model of the marker may include vertex coordinates, normal vectors, and texture vectors, among others. The vertex coordinates are used to determine the structure of the marker. The normal vector is used to determine the shading of the marker. The texture vector is used to determine the pattern (e.g., the text of the road sign, the arrows of the road direction indicators, etc.) and the color of the marker.
In one possible implementation manner, the server uses the attribute information of the marker as the attribute information of the geometric model corresponding to the marker. And then the server determines the three-dimensional model of the marker according to the attribute information of the geometric model and the geometric model.
For example, after the server determines that the geometric model corresponding to the road marking is a line, the color of the geometric model is determined to be yellow according to the attribute information of the road marking. The server may determine that the three-dimensional model of the road marking is a yellow line.
Step 105, the server determines a road scene model of the target road according to the three-dimensional model of the one or more markers and the corresponding position information.
In one possible implementation, the server is pre-configured with three-dimensional modeling software. The server establishes a three-dimensional blank template through the three-dimensional modeling software. The server then adds the markers to the blank template based on the location information of the one or more markers of the target road. In this way, the server may determine a road scene model of the target road.
Illustratively, the road surface of the target road is taken as an example. After the three-dimensional model of the road surface of the target road is determined, the server converts the position information corresponding to the road surface into coordinate data in the three-dimensional blank template. For example, the origin of the three-dimensional coordinate system in the three-dimensional blank template is (0, 0, 0), and the unit length of the coordinate axis is 1. The vertex coordinates of the road surface are a (116 ° 23 ', 39 ° 54', 0), B (116 ° 23 ', 39 ° 60', 0), C (116 ° 50 ', 39 ° 54', 0), and D (116 ° 50 ', 39 ° 60', 0), respectively. The server may use a as the origin, that is, convert a (116 ° 23 ', 39 ° 54', 0) to (0, 0, 0), and then B corresponds to coordinates (0, 0.6, 0), C corresponds to coordinates (0.27, 0, 0), and D corresponds to coordinates (0.27, 0.6, 0). And the server sets the three-dimensional model of the road surface at a corresponding position in the three-dimensional blank template according to the coordinate data corresponding to the road surface. Further, the server may determine a road scene model that includes a three-dimensional model corresponding to the road surface. And the server determines the positions of the three-dimensional models corresponding to the multiple markers of the target road in the blank scene template according to the same method as the road surface. Then, after determining the position of one or more markers of the target road in the blank scene template, the server may obtain a road scene model of the target road.
Exemplarily, as shown in fig. 5, a road scene model provided in the embodiments of the present application is provided.
It should be noted that the road scene model in the embodiment of the present application has spatial geographic information. The road scene model can be used on a Geographic Information System (GIS) platform, and can also be browsed and secondarily developed in three-dimensional modeling software.
According to the method for determining the road scene model, firstly, a server acquires point cloud data of a target road. Because point cloud data can be collected through automation equipment, compared with the prior art in which pictures or videos of roads are manually shot, the time and cost for manual collection can be reduced. Further, the server determines vector data and the type of the vector data of one or more markers of the target road according to the point cloud data of the target road, and determines a geometric model of the marker according to the type of the vector data and the type of the vector data. Wherein the markers have corresponding attribute information and the geometric model is used for characterizing the shape of the markers. Since the vector data includes the spatial geographical information of the markers and the types of the markers. Therefore, the server can determine the corresponding geometric model of the marker through the vector data and the type of the vector data. Thus, the staff does not need to manually delineate the geometric model of the marker by means of three-dimensional modeling software. The problem of work efficiency low among the prior art is solved. Further, the server may determine a three-dimensional model of the marker based on the attribute information of the marker and the geometric model. Thus, the problem of the three-dimensional model of the marker not conforming to the marker due to human factors (e.g., artificial visual deviation) in some cases can be avoided. And finally, the server can obtain a road scene model of the target road according to the geographical position information and the three-dimensional model of the one or more markers. Therefore, the method for determining the road scene model provided by the embodiment of the application can efficiently and accurately determine the road scene model. Meanwhile, high cost and error risk caused by a large amount of labor are avoided.
Alternatively, as shown in fig. 6, in the embodiment of the present application, step 103 may be implemented in the following manner.
1. In the case that the data type of the vector data is a line vector data type and/or a plane vector data type, the server may determine the geometric model corresponding to the target marker by:
step 1031, the server determines a plurality of coordinate data corresponding to the target marker according to the vector data.
Wherein the coordinate data comprises a plurality of latitudes and longitudes of the target marker.
For example, the coordinate data of the road marking includes a plurality of continuous coordinate data from the start point to the end point of the road marking and a width. The coordinate data of the zebra stripes include a plurality of vertex coordinate data of the zebra stripes, widths of a plurality of lines constituting the zebra stripes, distances between the plurality of lines, and the like.
And 1032, the server determines a geometric model corresponding to the target marker according to the coordinate data.
For example, for line vector data, the server may determine start point coordinates, end point coordinates, and line width data of a line from the line vector data. The server then determines the length of the line from the start and end coordinates in the line vector data. Finally, the server determines the width of the line from the line width data. The server can then determine the geometric model corresponding to the line based on the length and width of the line.
For the face vector data, the server may determine a plurality of vertex coordinates of the face from the face vector data. The server determines the shape of the surface from the plurality of vertex coordinates. If the face includes a plurality of lines (such as zebra stripes), the server may also determine the latitude and longitude and the width of the plurality of lines of the face. And then the server obtains a geometric model corresponding to the surface according to the longitude and latitude, the width and the shape of the surface of the plurality of lines of the surface.
2. In the case that the data type of the vector data is a point vector data type, the server may determine the geometric model corresponding to the target marker by:
and step 1033, the server determines the type of the target marker according to the vector data.
In one possible implementation, the server may determine the type of the marker according to the attribute information of the vector data.
Step 1034, the server determines a geometric model corresponding to the target marker from a plurality of preset geometric models according to the type of the target marker.
In one possible implementation, the server may have a plurality of preset geometric models. The server may match a plurality of preset geometric models according to the type of the marker. And the server takes the geometric model with the highest similarity with the marker in the plurality of preset geometric models as the geometric model corresponding to the marker.
It should be noted that in some cases (for example, a plurality of preset geometric models in the server do not have geometric models corresponding to the markers), the server may determine vertex coordinates, normal vectors, and texture coordinates of the markers according to the vector data. And then the server constructs a geometric model corresponding to the marker in three-dimensional modeling software according to the vertex coordinates of the marker. And finally, the server determines the attribute information of the geometric model according to the normal vector and the texture coordinate of the marker.
For example, the server first determines a geometric model of the marker from its vertex coordinates. The server then determines the pattern or text of the geometric model from the texture coordinates of the markers. And finally, the server determines the gray level and the brightness of the geometric model according to the normal vector of the marker.
Optionally, as shown in fig. 7, the method for determining a road scene model provided in the embodiment of the present application may further include:
step 201, the server acquires picture data of a target road.
It should be noted that, when the server acquires the point cloud data of the target road, the server may also acquire the picture data of the target road.
Optionally, the server may also obtain the image data of the target road after determining the road scene model of the target road.
Step 202, under the condition that the point cloud data is not consistent with the picture data or the point cloud data is not complete, the server determines a geometric model corresponding to the target marker according to the picture data.
The point cloud data is inconsistent with the picture data, and the point cloud data and the picture data mean that a road scene model determined by the server is inconsistent with an actual scene of the target road. For example, roads may have different models of street lamps, e.g., road a includes both a and b types of street lamps. But the type of the street lamp in the road scene model of the road a determined in the server is a.
The incomplete point cloud data refers to point cloud data which is obtained by the server and corresponds to part of markers in the point cloud data. For example, due to the limited shooting range of the vehicle radar, part of the markers of the target road are not acquired, so that part of the point cloud data of the target road is short of data. For another example, in the process of acquiring the point cloud data of the target road, the point cloud data of the marker cannot be acquired by the vehicle radar because the marker of the target road is shielded by other vehicles.
In a possible implementation manner, under the condition that the point cloud data is inconsistent with the picture data, the server may correct the road scene model through the picture data to obtain a road scene model consistent with the picture data. For example, after the server determines the three-dimensional model and the position information of the street lamp of type b according to the picture data, the street lamp of type a of the position information in the road scene model is replaced by the street lamp of type b. Thus, the server may determine a road scene model consistent with the picture data.
In another possible implementation manner, under the condition that the point cloud data is incomplete, the server analyzes the picture data and determines the complete point cloud data of the target road by combining the point cloud data of the target road. And then, the server determines a road scene model of the target road according to the complete point cloud data. For another example, after determining the incomplete road scene model, the server determines, according to the picture data, a three-dimensional model corresponding to a marker missing from the incomplete road scene model. And then, the server modifies the incomplete road scene model according to the three-dimensional model of the marker, so as to obtain a complete road scene model.
Optionally, the embodiment of the application may also improve the incomplete road scene model by other methods, for example, artificially improve the road scene model.
In the embodiment of the present application, the determining apparatus of the road scene model may be divided into the functional modules or the functional units according to the above method examples, for example, each functional module or functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
Fig. 8 shows a schematic diagram of a possible structure of the determining apparatus of the road scene model according to the above embodiment. The determination device includes a communication unit 801 and a processing unit 802.
The communication unit 801 is configured to acquire point cloud data of a target road.
The target roadway includes one or more markers.
The processing unit 802 is configured to determine, according to the point cloud data, vector data corresponding to the target marker and a data type of the vector data.
The vector data includes position information of the markers and attribute information. The target marker is any of one or more markers.
The processing unit 802 is further configured to determine a geometric model corresponding to the target marker according to the vector data and the data type of the vector data.
The geometric model is used to characterize the shape of the target marker.
The processing unit 802 is further configured to determine a three-dimensional model of the target marker according to the attribute information and the geometric model.
The processing unit 802 is further configured to determine a road scene model of the target road according to the three-dimensional model of the one or more markers and the corresponding position information.
Optionally, the data type of the vector data includes a line vector data type, a plane vector data type, and a point vector data type.
Optionally, in a case that the data type of the vector data is a line vector data type and/or a plane vector data type, the processing unit 802 is specifically configured to: determining a plurality of coordinate data of the target marker according to the vector data; and determining a geometric model corresponding to the target marker according to the plurality of coordinate data.
Optionally, in a case that the data type of the vector data is a point vector data type, the processing unit 802 is specifically configured to: determining the type of the target marker according to the vector data; and determining a geometric model corresponding to the target marker from a plurality of preset geometric models according to the type of the target marker.
Optionally, the communication unit 801 is further configured to acquire picture data of the target road.
The processing unit 802 is configured to determine the road scene model according to the picture data when the road scene model is inconsistent with the picture data or the point cloud data is incomplete.
The determining means may further comprise a storage unit. The memory unit is to store computer program code, the computer program code comprising instructions. If the determining device is a chip applied in a server, the storage unit may be a storage unit (e.g., a register, a cache, etc.) in the chip, or a storage unit (e.g., a read-only memory, a random access memory, etc.) of the server located outside the chip.
Fig. 9 shows a schematic diagram of a possible logical structure of the determination device according to the above-described embodiment, in the case of an integrated unit. The determination device includes: a processing module 902 and a communication module 901. The processing module 902 is used for controlling and managing the actions of the determination device, for example, the processing module 902 is used for executing the steps of information/data processing in the determination device. The communication module 901 is used to support the step of information/data transmission or reception in the determination device.
In a possible embodiment, the determining means may further comprise a storage module 903 for storing program code and data of the determining means.
The processing module 902 may perform the steps performed by the processing unit 802. The communication module 901 may perform the steps performed by the communication unit 801 described above.
Fig. 10 shows a schematic diagram of another possible structure of the determination device according to the above embodiment. The device includes: one or more processors 101 and a communication interface 102. The processor 101 is used to control and manage the actions of the device, e.g., to perform the steps performed by the processing unit 802 described above, and/or other processes for performing the techniques described herein.
In particular implementations, processor 101 may include one or more CPUs such as CPU0 and CPU1 in fig. 10 for one embodiment.
In particular implementations, a communication device may include multiple processors, such as processor 101 in fig. 10, for one embodiment. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
Optionally, the apparatus may further comprise a memory 103 and a communication line 104, the memory 103 being for storing program codes and data of the apparatus.
Fig. 11 is a schematic structural diagram of a chip 110 according to an embodiment of the present disclosure. Chip 110 includes one or more (including two) processors 1110 and a communication interface 1130.
Optionally, the chip 110 further includes a memory 1140, and the memory 1140 may include a read-only memory and a random access memory, and provides operating instructions and data to the processor 1110. A portion of memory 1140 may also include non-volatile random access memory (NVRAM).
In some embodiments, memory 1140 stores elements, execution modules or data structures, or subsets thereof, or expanded sets thereof.
In the embodiment of the present application, the corresponding operation is performed by calling an operation instruction stored in the memory 1140 (the operation instruction may be stored in an operating system).
The processor 1110 may implement or execute various illustrative logical blocks, units, and circuits described in connection with the disclosure herein. The processor may be a central processing unit, general purpose processor, digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, units, and circuits described in connection with the disclosure. The processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, among others.
Memory 1140 may comprise volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
The bus 1120 may be an Extended Industry Standard Architecture (EISA) bus or the like. The bus 1120 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one line is shown in FIG. 11, but this does not represent only one bus or one type of bus.
It is clear to those skilled in the art from the foregoing description of the embodiments that, for convenience and simplicity of description, the foregoing division of the functional units is merely used as an example, and in practical applications, the above function distribution may be performed by different functional units according to needs, that is, the internal structure of the device may be divided into different functional units to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
The embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed by a computer, the computer executes each step in the method flow shown in the above method embodiment.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, and a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), registers, a hard disk, an optical fiber, a portable Compact disk Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any other form of computer-readable storage medium, in any suitable combination, or as appropriate in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Embodiments of the present application provide a computer program product having instructions stored thereon, which when executed on a computer, cause the computer to perform a method for determining a road scene model as described in fig. 3, fig. 6 or fig. 7.
Since the determining apparatus, the computer-readable storage medium, and the computer program product of the road scene model in the embodiments of the present application may be applied to the method described above, reference may also be made to the method embodiments for obtaining technical effects, and details of the embodiments of the present application are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (12)

1. A method for determining a road scene model, comprising:
acquiring point cloud data of a target road, wherein the target road comprises one or more markers;
according to the point cloud data, determining vector data corresponding to a target marker and the data type of the vector data, wherein the vector data comprises position information and attribute information of the marker; the target marker is any one of the one or more markers;
determining a geometric model corresponding to the target marker according to the vector data and the data type of the vector data, wherein the geometric model is used for representing the shape of the target marker;
determining a three-dimensional model of the target marker according to the attribute information and the geometric model;
and determining a road scene model of the target road according to the three-dimensional model of the one or more markers and the corresponding position information.
2. The determination method according to claim 1, wherein the data type of the vector data includes a line vector data type, a plane vector data type, and a point vector data type.
3. The method according to claim 2, wherein in a case where the data type of the vector data is a line vector data type and/or a plane vector data type, the determining the geometric model corresponding to the target marker according to the vector data and the data type of the vector data includes:
determining a plurality of coordinate data of the target marker according to the vector data;
and determining a geometric model corresponding to the target marker according to the coordinate data.
4. The method according to claim 2, wherein, in a case where the data type of the vector data is the point vector data type, the determining the geometric model corresponding to the target marker according to the vector data and the data type of the vector data includes:
determining the type of the target marker according to the vector data;
and determining a geometric model corresponding to the marker from a plurality of preset geometric models according to the type of the target marker.
5. The method according to any one of claims 1-4, further comprising:
acquiring picture data of the target road;
determining the road scene model from the picture data if the road scene model is inconsistent with the picture data or the point cloud data is incomplete.
6. An apparatus for determining a road scene model, comprising:
a communication unit for acquiring point cloud data of a target road, the target road including one or more markers;
the processing unit is used for determining vector data corresponding to a target marker and the data type of the vector data according to the point cloud data, wherein the vector data comprises position information and attribute information of the target marker; the target marker is any one of the one or more markers;
the processing unit is further configured to determine a geometric model corresponding to the target marker according to vector data and a data type of the vector data, where the geometric model is used to characterize a shape of the target marker;
the processing unit is further used for determining a three-dimensional model of the target marker according to the attribute information and the geometric model;
the processing unit is further configured to determine a road scene model of the target road according to the three-dimensional model of the one or more markers and the corresponding position information.
7. The determination apparatus according to claim 6, wherein the data type of the vector data includes a line vector data type, a plane vector data type, and a point vector data type.
8. The apparatus according to claim 7, wherein, in a case that the data type of the vector data is a line vector data type and/or a plane vector data type, the processing unit is specifically configured to:
determining a plurality of coordinate data of the target marker according to the vector data;
and determining a geometric model corresponding to the target marker according to the coordinate data.
9. The apparatus according to claim 7, wherein, in a case that the data type of the vector data is the point vector data type, the processing unit is specifically configured to:
determining the type of the target marker according to the vector data;
and determining a geometric model corresponding to the target marker from a plurality of preset geometric models according to the type of the target marker.
10. The determination apparatus according to any one of claims 6 to 9,
the communication unit is further used for acquiring picture data of the target road;
the processing unit is further configured to determine a three-dimensional model corresponding to the target marker according to the picture data when the point cloud data is inconsistent with the picture data or the point cloud data is incomplete.
11. An apparatus for determining a road scene model, the apparatus comprising: a processor, a transceiver, and a memory; wherein the memory is configured to store one or more programs, the one or more programs including computer executable instructions, which when the determining means is running, are executed by the processor to cause the determining means to perform the determining method of the road scene model according to any one of claims 1 to 5.
12. A computer-readable storage medium having stored therein instructions which, when executed by a computer, cause the computer to perform the method of determining a road scene model according to any one of claims 1 to 5.
CN201911172530.3A 2019-11-26 2019-11-26 Road scene model determining method and device Active CN110838178B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911172530.3A CN110838178B (en) 2019-11-26 2019-11-26 Road scene model determining method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911172530.3A CN110838178B (en) 2019-11-26 2019-11-26 Road scene model determining method and device

Publications (2)

Publication Number Publication Date
CN110838178A true CN110838178A (en) 2020-02-25
CN110838178B CN110838178B (en) 2024-01-26

Family

ID=69577480

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911172530.3A Active CN110838178B (en) 2019-11-26 2019-11-26 Road scene model determining method and device

Country Status (1)

Country Link
CN (1) CN110838178B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111949173A (en) * 2020-07-31 2020-11-17 广州启量信息科技有限公司 Panoramic VR (virtual reality) picture switching method and device, terminal equipment and storage medium
CN112633722A (en) * 2020-12-29 2021-04-09 交通运输部公路科学研究所 Vehicle-mounted road safety risk assessment system and method
CN112927370A (en) * 2021-02-25 2021-06-08 苍穹数码技术股份有限公司 Three-dimensional building model construction method and device, electronic equipment and storage medium
CN113744544A (en) * 2020-05-29 2021-12-03 杭州海康威视数字技术股份有限公司 Parameter configuration method, device and equipment
CN114427876A (en) * 2021-12-15 2022-05-03 武汉中海庭数据技术有限公司 Automatic checking method and system for traffic sign incidence relation

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140267279A1 (en) * 2013-03-15 2014-09-18 Janne Kontkanen System and method for overlaying two-dimensional map data on a three-dimensional scene
CN105913485A (en) * 2016-04-06 2016-08-31 北京小小牛创意科技有限公司 Three-dimensional virtual scene generation method and device
CN108334523A (en) * 2017-01-20 2018-07-27 腾讯科技（深圳）有限公司 The construction method and device of road scene map
CN109461211A (en) * 2018-11-12 2019-03-12 南京人工智能高等研究院有限公司 Semantic vector map constructing method, device and the electronic equipment of view-based access control model point cloud

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140267279A1 (en) * 2013-03-15 2014-09-18 Janne Kontkanen System and method for overlaying two-dimensional map data on a three-dimensional scene
CN105913485A (en) * 2016-04-06 2016-08-31 北京小小牛创意科技有限公司 Three-dimensional virtual scene generation method and device
CN108334523A (en) * 2017-01-20 2018-07-27 腾讯科技（深圳）有限公司 The construction method and device of road scene map
CN109461211A (en) * 2018-11-12 2019-03-12 南京人工智能高等研究院有限公司 Semantic vector map constructing method, device and the electronic equipment of view-based access control model point cloud

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113744544A (en) * 2020-05-29 2021-12-03 杭州海康威视数字技术股份有限公司 Parameter configuration method, device and equipment
CN111949173A (en) * 2020-07-31 2020-11-17 广州启量信息科技有限公司 Panoramic VR (virtual reality) picture switching method and device, terminal equipment and storage medium
CN111949173B (en) * 2020-07-31 2022-02-15 广州启量信息科技有限公司 Panoramic VR (virtual reality) picture switching method and device, terminal equipment and storage medium
CN112633722A (en) * 2020-12-29 2021-04-09 交通运输部公路科学研究所 Vehicle-mounted road safety risk assessment system and method
CN112633722B (en) * 2020-12-29 2024-01-12 交通运输部公路科学研究所 Vehicle-mounted road safety risk assessment system and method
CN112927370A (en) * 2021-02-25 2021-06-08 苍穹数码技术股份有限公司 Three-dimensional building model construction method and device, electronic equipment and storage medium
CN114427876A (en) * 2021-12-15 2022-05-03 武汉中海庭数据技术有限公司 Automatic checking method and system for traffic sign incidence relation
CN114427876B (en) * 2021-12-15 2023-11-28 武汉中海庭数据技术有限公司 Automatic checking method and system for association relation of traffic sign

Also Published As

Publication number Publication date
CN110838178B (en) 2024-01-26

Similar Documents

Publication Publication Date Title
CN110838178B (en) Road scene model determining method and device
EP3505869B1 (en) Method, apparatus, and computer readable storage medium for updating electronic map
CN109285188B (en) Method and apparatus for generating position information of target object
CN109461211A (en) Semantic vector map constructing method, device and the electronic equipment of view-based access control model point cloud
CN110568451B (en) Method and device for generating road traffic marking in high-precision map
CN111238498B (en) Road map generation method, device and related system for lane-level display
CN111238504A (en) Road segment modeling data generation method and device of road map and related system
CN115937439B (en) Method and device for constructing three-dimensional model of urban building and electronic equipment
CN112541049A (en) High-precision map processing method, device, equipment, storage medium and program product
CN112579715B (en) Data processing method, device, electronic equipment and storage medium
CN111316324A (en) Automatic driving simulation system, method, equipment and storage medium
CN112017262B (en) Pavement marker generation method and device, storage medium and electronic equipment
CN111238500B (en) Map generation method, device and system for road segments of road map area
CN109520513B (en) Three-dimensional map drawing method and device
CN111433779A (en) System and method for identifying road characteristics
CN113763522A (en) Map rendering method, device, equipment and medium
CN114743395A (en) Signal lamp detection method, device, equipment and medium
US11112264B2 (en) System and method for rendering an overpass object using map and link data
CN114964210A (en) Map drawing method, map drawing device, computer equipment and storage medium
CN111427981A (en) Method and system for simulating point location data by using road network data
US20190156455A1 (en) Converting Spatial Features to Map Projection
CN112484739B (en) Map updating method, device, equipment and storage medium
CN116645483B (en) Method and device for constructing lane line level road three-dimensional model and electronic equipment
CN112528892B (en) Unmanned aerial vehicle point cloud lane line extraction method and system
CN111238505A (en) Road segment drawing method, device and related system of road map

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant