WO2018227980A1 - Camera sensor based lane line map construction method and construction system - Google Patents

Camera sensor based lane line map construction method and construction system Download PDF

Info

Publication number
WO2018227980A1
WO2018227980A1 PCT/CN2018/074403 CN2018074403W WO2018227980A1 WO 2018227980 A1 WO2018227980 A1 WO 2018227980A1 CN 2018074403 W CN2018074403 W CN 2018074403W WO 2018227980 A1 WO2018227980 A1 WO 2018227980A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane line
vehicle
coordinate system
camera sensor
lane
Prior art date
Application number
PCT/CN2018/074403
Other languages
French (fr)
Chinese (zh)
Inventor
孙鹏
Original Assignee
蔚来汽车有限公司
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 蔚来汽车有限公司 filed Critical 蔚来汽车有限公司
Publication of WO2018227980A1 publication Critical patent/WO2018227980A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3848—Data obtained from both position sensors and additional sensors
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram

Definitions

  • the invention relates to the field of geographic information data collection and the field of map surveying, in particular to a method and a system for constructing a high-definition lane line map.
  • the lane line map construction step splices the trajectories of the lane lines obtained in the lane trajectory acquisition step to form a lane line map.
  • the camera sensor identifies the lane line, and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
  • v means: o means that in the geodetic coordinate system, v represents the vehicle.
  • the position coordinates on the lane line at the i-th time are obtained as follows:
  • the position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
  • ⁇ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the ith time.
  • a GPS sensor disposed on the vehicle for acquiring location information of the vehicle
  • a camera sensor for identifying a lane line and outputting lane line information
  • y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
  • C 2 represents the curvature of the lane line
  • C 3 represents the curvature transformation of the lane line.
  • v means: o means that in the geodetic coordinate system, v represents the vehicle.
  • the vehicle position coordinates on the lane line obtained at the ith are expressed as:
  • the position of the camera sensor in the vehicle coordinate system is expressed as:
  • the position coordinates on the lane line at the i-th time are obtained as follows:
  • the position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
  • ⁇ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the ith time.
  • the processor performs the following processing:
  • the storage device of the present invention wherein a plurality of instructions are stored, the instructions being adapted to be loaded by a processor and to execute the construction method of the lane line map described above.
  • the method and construction system for constructing a lane line map of the present invention uses a camera sensor and a GPS sensor as acquisition tools, so the collection cost is low and the time spent is relatively small;
  • the method and the construction system for constructing the lane line map of the present invention can also import the collected lane line map data into the simulation scene, and quickly restore the actual traffic scene, which can make the simulation test closer to the actual lane line road environment, for example,
  • the lane line map can be poured into the simulation scene to generate a simulation scene, and the automatic driving algorithm is developed in the simulated road traffic scene.
  • FIG. 1 is a flowchart showing a method of constructing a lane line map according to an embodiment of the present invention.
  • Figure 2 is a diagram showing the coordinate position of a point on the lane line (i.e., the vehicle) in the camera sensor coordinate system.
  • Fig. 3 is a schematic diagram showing a construction system of a lane line map of the present invention.
  • the technical idea of the method for constructing a lane line map of the present invention is that the advantage of the image sensor information can be recognized by the camera sensor, the lane line on the road is recognized in real time by the image processing algorithm, and the position signal obtained by the high-precision GPS sensor is combined to calculate The parameters of the current lane segment.
  • the detected lane segments are connected to obtain a lane line map.
  • FIG. 1 is a flowchart showing a method of constructing a lane line map according to an embodiment of the present invention.
  • a method for constructing a lane line map according to an embodiment of the present invention includes the following steps:
  • Vehicle position information obtaining step S100 acquiring position information of the vehicle using a GPS sensor provided on the vehicle;
  • a lane line trajectory obtaining step S300 calculating a trajectory of the lane line according to the position information of the vehicle acquired in the vehicle position information obtaining step S100 and the lane line curve information acquired in the lane line curve information obtaining step S200;
  • Figure 2 is a diagram showing the coordinate position of a point on the lane line (i.e., the vehicle) in the camera sensor coordinate system.
  • y c and x c refer to coordinate positions of points on the lane line in the camera sensor coordinate system.
  • C 0 represents the distance from the camera sensor to the lane line in the direction perpendicular to the longitudinal axis of the vehicle
  • C 1 represents the angle between the longitudinal axis direction of the vehicle and the tangential direction of the lane line
  • C 2 represents the curvature of the lane line
  • C 3 represents the lane line. Curvature transformation.
  • ⁇ is ⁇ in Fig. 2 .
  • the position information of the vehicle at the ith time is acquired by the GPS sensor provided on the vehicle:
  • v means: o means that in the geodetic coordinate system, v represents the vehicle.
  • the vehicle position coordinates on the lane line obtained at the ith time are expressed as:
  • the position of the camera sensor in the vehicle coordinate system is expressed as:
  • the position of the nearest point on the lane line under the camera sensor coordinate system is converted to the position in the vehicle coordinate system as:
  • the position coordinates on the lane line at the i-th time are obtained as follows:
  • the position of the point on the lane line in the geodetic coordinate system at the ith time is expressed as:
  • the position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
  • Fig. 3 is a schematic diagram showing a construction system of a lane line map of the present invention.
  • the lane line map construction system of the present invention has:
  • a GPS sensor 100 disposed on the vehicle, for acquiring location information of the vehicle;
  • a camera sensor 200 disposed on the vehicle for identifying a lane line and outputting lane line information
  • the processor 300 acquires position information of the vehicle from the GPS sensor 100 and acquires lane line information from the camera sensor 200, calculates a trajectory of the lane line according to the position information and the lane line curve information, and calculates a trajectory of the calculated lane line Splicing to form a lane line map.
  • the camera sensor 200 can be placed at the front windshield of the vehicle.
  • the camera sensor 200 is used to identify the lane line and obtain a lane curve in the camera sensor coordinate system represented by the following formula:
  • y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
  • C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
  • C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
  • C 2 represents the curvature of the lane line
  • C 3 represents the curvature transformation of the lane line.
  • the GPS sensor 100 acquires the position information of the vehicle at the ith time:
  • v means: o means that in the geodetic coordinate system, v represents the vehicle.
  • the processor 300 performs the following processing:
  • the vehicle position coordinates on the lane line obtained at the ith are expressed as:
  • the position of the camera sensor in the vehicle coordinate system is expressed as:
  • the position coordinates on the lane line at the i-th time are obtained as follows:
  • the position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
  • ⁇ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the i-th time, see Figure 2 for details.
  • the processor 300 performs the following processing:
  • the method and construction system for constructing a lane line map of the present invention uses a camera sensor and a GPS sensor as acquisition tools, so the collection cost is low and the time spent is relatively small;
  • the method and the construction system for constructing the lane line map of the present invention can also import the collected lane line map data into the simulation scene, and quickly restore the actual traffic scene, which can make the simulation test closer to the actual lane line road environment, for example,
  • the lane line map can be poured into the simulation scene to generate a simulation scene, and the automatic driving algorithm is developed in the simulated road traffic scene.

Abstract

Provided are a method for constructing a lane line map and a construction system. The method comprises: acquiring location information of a vehicle by using a GPS sensor disposed on the vehicle (S100); identifying a lane line with a camera sensor provided on the vehicle and outputting lane line curve information (S200); calculating a lane line track according to the acquired location information of the vehicle and the acquired lane line curve information (S300); and splicing the obtained lane line track to form a lane line map (S400). The method can obtain a high-accuracy lane line map with lower cost.

Description

基于摄像头传感器的车道线地图构建方法以及构建系统Lane line map construction method based on camera sensor and construction system 技术领域Technical field
本发明涉及地理信息数据采集领域、地图测绘领域，具体地涉及一种高精细的车道线地图的构建方法以及构建系统。The invention relates to the field of geographic information data collection and the field of map surveying, in particular to a method and a system for constructing a high-definition lane line map.
背景技术Background technique
现有导航地图精度一般不高，并且以整条道路作为对象提供道路信息数据或者进行导航指令发布，这种导航地图称之为道路级别地图，是对实际交通环境的大幅度简化，能提供的信息量数量少，精确度低，对驾驶员的辅助能力较低。The accuracy of the existing navigation map is generally not high, and the road information data is provided as an object or the navigation instruction is issued. The navigation map is called a road level map, which is a substantial simplification of the actual traffic environment and can be provided. The amount of information is small, the accuracy is low, and the assistance ability to the driver is low.
随着车辆的辅助驾驶技术以及无人驾驶技术的发展，对地图精度以及信息量的要求也逐渐提高，原有道路级地图已经无法满足，需要一种能够提供高精度、详细道路信息的新型高精细地图。With the development of assisted driving technology and unmanned driving technology, the requirements for map accuracy and information volume are gradually improved. The original road-level maps are no longer satisfactory, and a new type of high-precision and detailed road information is required. Fine map.
作为这样的新型高精细地图已经提出了车道线级别的高精度地图。车道线级别的高精度地图是自动驾驶系统的重要输入。在自动驾驶汽车行驶过程中，车上的传感器检测周围环境信息，完成环境感知，但传感器不具有驾驶员联想的作用，车道线地图能够弥补传感器系统的不足，能够增强自动驾驶系统的环境感知能力。As such a new high-definition map, a high-precision map at the lane line level has been proposed. High-precision maps at the lane line level are an important input to the autopilot system. During the driving process of the autonomous vehicle, the sensors on the vehicle detect the surrounding environment information and complete the environment perception, but the sensor does not have the role of the driver association. The lane line map can make up for the deficiency of the sensor system and enhance the environmental awareness of the automatic driving system. .
目前现有技术中主要通过激光雷达扫描周围环境，结合GPS完成地图的构建，而由于车道线采集的难度和工作量，现有的高精度地图一般不包含车道线信息。At present, in the prior art, the surrounding environment is mainly scanned by laser radar, and the construction of the map is completed by using GPS. However, due to the difficulty and workload of the lane line collection, the existing high-precision map generally does not include lane line information.
由于这样的车道线级别的高精度地图的构建，需要花费极大的时间和成本，因此，急需提供一种能够自动化构成车道线地图的方法。Since such a lane-line-level high-precision map is constructed, it takes a lot of time and cost, and therefore, it is urgent to provide a method capable of automatically compiling a lane line map.
发明内容Summary of the invention
鉴于上述问题，本发明旨在提供一种能够构建高精度车道线地图的车道线地图的构建方法以及构建系统。In view of the above problems, the present invention is directed to a method and a construction system for constructing a lane line map capable of constructing a high-accuracy lane line map.
本发明的车道线地图的构建方法，其特征在于，包括下述步骤：The method for constructing a lane line map of the present invention is characterized in that it comprises the following steps:
车辆位置信息获取步骤，利用设置在车辆上的GPS传感器获取车辆的位置信息；a vehicle position information obtaining step of acquiring position information of the vehicle by using a GPS sensor provided on the vehicle;
车道线曲线信息获取步骤，利用设置在车辆上的摄像头传感器识别车道线并输出车道线曲线信息；a lane line curve information obtaining step of identifying a lane line by using a camera sensor provided on the vehicle and outputting lane line curve information;
车道线轨迹获取步骤，根据上述车辆位置信息获取步骤获取的车辆的位置信息和上述车道线曲线信息获取步骤获取的车道线曲线信息计算得到车道线的轨迹；以及a lane line trajectory obtaining step of calculating a trajectory of the lane line according to the position information of the vehicle acquired by the vehicle position information acquiring step and the lane line curve information acquired by the lane line curve information obtaining step;
车道线地图构建步骤，将在上述车道线轨迹获取步骤中得到的车道线的轨迹拼接而构成车道线地图。The lane line map construction step splices the trajectories of the lane lines obtained in the lane trajectory acquisition step to form a lane line map.
可选地，在所述车道线曲线信息获取步骤中，所述摄像头传感器识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：Optionally, in the lane line curve information obtaining step, the camera sensor identifies the lane line, and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
Figure PCTCN2018074403-appb-000001
Figure PCTCN2018074403-appb-000001
其中，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置， Where y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离， C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
C 1表示车辆纵轴方向上与车道线切线方向的夹角， C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
C 2表示车道线的曲率， C 2 represents the curvature of the lane line,
C 3表示车道线的曲率变换。 C 3 represents the curvature transformation of the lane line.
可选地，在所述车辆位置信息获取步骤中，利用设置在车辆上的GPS传感器获取车辆在第i时刻的位置信息记作：Optionally, in the vehicle location information acquiring step, acquiring, by using a GPS sensor disposed on the vehicle, location information of the vehicle at the ith time is recorded as:
Figure PCTCN2018074403-appb-000002
Figure PCTCN2018074403-appb-000002
其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
可选地，在所述车道线曲线信息获取步骤中，将第i时刻获得的车道线上的车辆位置坐标表示为：Optionally, in the lane line curve information obtaining step, the vehicle position coordinates on the lane line obtained at the ith time are expressed as:
Figure PCTCN2018074403-appb-000003
Figure PCTCN2018074403-appb-000003
在车辆坐标系下的摄像头传感器的位置表示为：The position of the camera sensor in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000004
Figure PCTCN2018074403-appb-000004
Figure PCTCN2018074403-appb-000005
Figure PCTCN2018074403-appb-000005
将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：Converting the position of the nearest point on the lane line under the camera sensor coordinate system to the position in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000006
Figure PCTCN2018074403-appb-000006
由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
Figure PCTCN2018074403-appb-000007
Figure PCTCN2018074403-appb-000007
可选地，在所述车道线轨迹获取步骤中，第i时刻在大地坐标系下的车道线上的点的位置表示为：Optionally, in the lane line trajectory obtaining step, the position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
Figure PCTCN2018074403-appb-000008
Figure PCTCN2018074403-appb-000008
将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
Figure PCTCN2018074403-appb-000009
Figure PCTCN2018074403-appb-000009
利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
Figure PCTCN2018074403-appb-000010
Figure PCTCN2018074403-appb-000010
其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换 为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
Figure PCTCN2018074403-appb-000011
Figure PCTCN2018074403-appb-000011
由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
Figure PCTCN2018074403-appb-000012
Figure PCTCN2018074403-appb-000012
其中，θ为第i时刻在大地坐标系下,车辆纵轴与大地坐标系横坐标的夹角。Where θ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the ith time.
可选地，在所述车道线地图构建步骤中，将在上述车道线轨迹获取步骤中得到的车道线的轨迹、即第i时刻在大地坐标系下的车道线上的点连接起来得到构成车道线地图，其中i＝1，2，3，....N，N为正数。Optionally, in the lane line map construction step, the trajectory of the lane line obtained in the lane trajectory acquisition step, that is, the point on the lane line in the geodetic coordinate system at the ith time is connected to form a lane. Line map, where i=1, 2, 3, ....N, N is a positive number.
本发明的车道线地图的构建系统，其特征在于，具备：A system for constructing a lane line map according to the present invention is characterized by comprising:
GPS传感器，设置在车辆上，用于获取车辆的位置信息；a GPS sensor disposed on the vehicle for acquiring location information of the vehicle;
摄像头传感器，用于识别车道线并输出车道线信息；a camera sensor for identifying a lane line and outputting lane line information;
处理器，从所述GPS传感器获取车辆的位置信息并且从所述摄像头传感器获取车道线信息，根据所述位置信息和所述车道线曲线信息计算得到车道线的轨迹，将计算得到的车道线的轨迹拼接而构成车道线地图。a processor, acquiring position information of the vehicle from the GPS sensor, and acquiring lane line information from the camera sensor, calculating a trajectory of the lane line according to the position information and the lane line curve information, and calculating the calculated lane line The track is spliced to form a lane line map.
可选地，所述摄像头传感器识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：Optionally, the camera sensor identifies the lane line and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
Figure PCTCN2018074403-appb-000013
Figure PCTCN2018074403-appb-000013
其中，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置， Where y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离， C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
C 1表示车辆纵轴方向上与车道线切线方向的夹角， C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
C 2表示车道线的曲率， C 2 represents the curvature of the lane line,
C 3表示车道线的曲率变换。 C 3 represents the curvature transformation of the lane line.
可选地，所述GPS传感器获取车辆在第i时刻的位置信息记作：Optionally, the location information of the GPS sensor acquired by the GPS sensor at the ith time is recorded as:
Figure PCTCN2018074403-appb-000014
Figure PCTCN2018074403-appb-000014
其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
可选地，所述处理器进行如下处理：Optionally, the processor performs the following processing:
将第i时获得的车道线上的车辆位置坐标表示为：The vehicle position coordinates on the lane line obtained at the ith are expressed as:
Figure PCTCN2018074403-appb-000015
Figure PCTCN2018074403-appb-000015
在车辆坐标系下的摄像头传感器的位置表示为：The position of the camera sensor in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000016
Figure PCTCN2018074403-appb-000016
将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：Converting the position of the nearest point on the lane line under the camera sensor coordinate system to the position in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000017
Figure PCTCN2018074403-appb-000017
由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
Figure PCTCN2018074403-appb-000018
Figure PCTCN2018074403-appb-000018
可选地，所述处理器进行如下处理：Optionally, the processor performs the following processing:
第i时刻在大地坐标系下的车道线上的点的位置表示为：The position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
Figure PCTCN2018074403-appb-000019
Figure PCTCN2018074403-appb-000019
将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
Figure PCTCN2018074403-appb-000020
Figure PCTCN2018074403-appb-000020
利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
Figure PCTCN2018074403-appb-000021
Figure PCTCN2018074403-appb-000021
其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
Figure PCTCN2018074403-appb-000022
Figure PCTCN2018074403-appb-000022
由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
Figure PCTCN2018074403-appb-000023
Figure PCTCN2018074403-appb-000023
其中，θ为第i时刻在大地坐标系下,车辆纵轴与大地坐标系横坐标的夹角。Where θ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the ith time.
可选地，所述处理器进行如下处理：Optionally, the processor performs the following processing:
将所述车道线的轨迹、即第i时刻在大地坐标系下的车道线上的点连接起来得到构成车道线地图，其中i＝1，2，3，....N，N为正数。The trajectory of the lane line, that is, the point at the i-th moment on the lane line in the geodetic coordinate system is connected to obtain a lane line map, where i=1, 2, 3, . . . N, N is a positive number .
本发明的储存设备，其中，储存有多条指令，所述指令适于由处理器加载并执行上述车道线地图的构建方法。The storage device of the present invention, wherein a plurality of instructions are stored, the instructions being adapted to be loaded by a processor and to execute the construction method of the lane line map described above.
根据本发明的车道线地图的构建方法以及构建系统能够获得以下的有益技术效果：The construction method and construction system of the lane line map according to the present invention can obtain the following beneficial technical effects:
(1)本发明的车道线地图的构建方法以及构建系统以摄像头传感器、GPS传感器为采集工具，因此采集成本低、花费时间相对少；(1) The method and construction system for constructing a lane line map of the present invention uses a camera sensor and a GPS sensor as acquisition tools, so the collection cost is low and the time spent is relatively small;
(2)本发明的车道线地图的构建方法以及构建系统以摄像头传感器、GPS传感器为采集工具，因此，采集精度高，能够获得高精度的车道线地图；(2) The method for constructing a lane line map of the present invention and the construction system using the camera sensor and the GPS sensor as acquisition tools, therefore, the acquisition accuracy is high, and a highly accurate lane line map can be obtained;
(3)本发明的车道线地图的构建方法以及构建系统可以应用在实际道路的自动驾驶中；(3) The method and construction system for constructing a lane line map of the present invention can be applied to automatic driving of an actual road;
(4)本发明的车道线地图的构建方法以及构建系统也可以把采集到的车道线地图数据导入仿真场景中，快速还原实际交通场景，能够使得仿真测试更加接近实际的车道线道路环境，例如，能够将车道线地图倒入仿真场景中生成模拟场景，在模拟道路交通场景中开发自动驾驶算法。(4) The method and the construction system for constructing the lane line map of the present invention can also import the collected lane line map data into the simulation scene, and quickly restore the actual traffic scene, which can make the simulation test closer to the actual lane line road environment, for example, The lane line map can be poured into the simulation scene to generate a simulation scene, and the automatic driving algorithm is developed in the simulated road traffic scene.
附图说明DRAWINGS
图1是表示本发明的一实施方式的车道线地图的构建方法的流程图。FIG. 1 is a flowchart showing a method of constructing a lane line map according to an embodiment of the present invention.
图2是表示车道线上的点(即车辆)在摄像头传感器坐标系下的坐标位置。Figure 2 is a diagram showing the coordinate position of a point on the lane line (i.e., the vehicle) in the camera sensor coordinate system.
图3是表示本发明的车道线地图的构建系统的示意图。Fig. 3 is a schematic diagram showing a construction system of a lane line map of the present invention.
具体实施方式detailed description
下面介绍的是本发明的多个实施例中的一些，旨在提供对本发明的基本了解。并不旨在确认本发明的关键或决定性的要素或限定所要保护的范围。The following are some of the various embodiments of the invention, which are intended to provide a basic understanding of the invention. It is not intended to identify key or critical elements of the invention or the scope of the invention.
本发明的车道线地图的构建方法的技术构思在于，利用摄像头传感器能够识别图像纹理信息的优势，通过图像处理算法实时识别出道路上的车道线，结合高精度GPS传感器获得的位置信号，计算出当前车道线段的参数。将检测到的车道线段连接起来，从而得到车道线地图。The technical idea of the method for constructing a lane line map of the present invention is that the advantage of the image sensor information can be recognized by the camera sensor, the lane line on the road is recognized in real time by the image processing algorithm, and the position signal obtained by the high-precision GPS sensor is combined to calculate The parameters of the current lane segment. The detected lane segments are connected to obtain a lane line map.
接着对于本发明的一实施方式的车道线地图的构建方法进行说明。Next, a method of constructing a lane line map according to an embodiment of the present invention will be described.
图1是表示本发明的一实施方式的车道线地图的构建方法的流程图。FIG. 1 is a flowchart showing a method of constructing a lane line map according to an embodiment of the present invention.
如图1所示，本发明的一实施方式的车道线地图的构建方法包括下述步骤：As shown in FIG. 1, a method for constructing a lane line map according to an embodiment of the present invention includes the following steps:
车辆位置信息获取步骤S100：利用设置在车辆上的GPS传感器获取车辆的位置信息；Vehicle position information obtaining step S100: acquiring position information of the vehicle using a GPS sensor provided on the vehicle;
车道线曲线信息获取步骤S200：利用设置在车辆上的摄像头传感器识别车道线并输出车道线曲线信息；Lane line curve information obtaining step S200: recognizing a lane line using a camera sensor provided on the vehicle and outputting lane line curve information;
车道线轨迹获取步骤S300：根据上述车辆位置信息获取步骤S100获取的车辆的位置信息和上述车道线曲线信息获取步骤S200获取的车道线曲线信息计算得到车道线的轨迹；以及a lane line trajectory obtaining step S300: calculating a trajectory of the lane line according to the position information of the vehicle acquired in the vehicle position information obtaining step S100 and the lane line curve information acquired in the lane line curve information obtaining step S200;
车道线地图构建步骤S400:将在上述车道线轨迹获取步骤S300中得到的车道线的轨迹拼接而构成车道线地图。The lane line map construction step S400: splicing the trajectories of the lane lines obtained in the above-described lane line trajectory acquisition step S300 to form a lane line map.
接着对于上述各步骤进行具体说明。Next, each step described above will be specifically described.
图2是表示车道线上的点(即车辆)在摄像头传感器坐标系下的坐标位置。Figure 2 is a diagram showing the coordinate position of a point on the lane line (i.e., the vehicle) in the camera sensor coordinate system.
在车道线曲线信息获取步骤S100中，摄像头传感器识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：In the lane line curve information obtaining step S100, the camera sensor recognizes the lane line, and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
Figure PCTCN2018074403-appb-000024
Figure PCTCN2018074403-appb-000024
其中，如图2所示，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置。并且，C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离，C 1表示车辆纵轴方向上与车道线切线方向的夹角，C 2表示车道线的曲率，C 3表示车道线的曲率变换。其中，θ为图2中的θ。 Wherein, as shown in FIG. 2, y c and x c refer to coordinate positions of points on the lane line in the camera sensor coordinate system. Moreover, C 0 represents the distance from the camera sensor to the lane line in the direction perpendicular to the longitudinal axis of the vehicle, C 1 represents the angle between the longitudinal axis direction of the vehicle and the tangential direction of the lane line, C 2 represents the curvature of the lane line, and C 3 represents the lane line. Curvature transformation. Where θ is θ in Fig. 2 .
这样，在车辆位置信息获取步骤S200中，利用设置在车辆上的GPS传感器获取车辆在第i时刻的位置信息记作：Thus, in the vehicle position information acquisition step S200, the position information of the vehicle at the ith time is acquired by the GPS sensor provided on the vehicle:
Figure PCTCN2018074403-appb-000025
Figure PCTCN2018074403-appb-000025
其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
在车道线曲线信息获取步骤S300中，将第i时刻获得的车道线上的车辆位置坐标表示为：In the lane line curve information obtaining step S300, the vehicle position coordinates on the lane line obtained at the ith time are expressed as:
Figure PCTCN2018074403-appb-000026
Figure PCTCN2018074403-appb-000026
并且，在车辆坐标系下的摄像头传感器的位置表示为：Also, the position of the camera sensor in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000027
Figure PCTCN2018074403-appb-000027
同时，将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：At the same time, the position of the nearest point on the lane line under the camera sensor coordinate system is converted to the position in the vehicle coordinate system as:
Figure PCTCN2018074403-appb-000028
Figure PCTCN2018074403-appb-000028
由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
Figure PCTCN2018074403-appb-000029
Figure PCTCN2018074403-appb-000029
接着，在车道线轨迹获取步骤S300中，第i时刻在大地坐标系下的车道线上的点的位置表示为：Next, in the lane line trajectory acquisition step S300, the position of the point on the lane line in the geodetic coordinate system at the ith time is expressed as:
Figure PCTCN2018074403-appb-000030
Figure PCTCN2018074403-appb-000030
将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
Figure PCTCN2018074403-appb-000031
Figure PCTCN2018074403-appb-000031
利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
Figure PCTCN2018074403-appb-000032
Figure PCTCN2018074403-appb-000032
其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换 为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
Figure PCTCN2018074403-appb-000033
Figure PCTCN2018074403-appb-000033
由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
Figure PCTCN2018074403-appb-000034
Figure PCTCN2018074403-appb-000034
在车道线地图构建步骤S400中，将在上述车道线轨迹获取步骤S300中得到的车道线的轨迹、即第i时刻在大地坐标系下的车道线上的点连接起来得到构成车道线地图，其中i＝1，2，3，....N，N为正数。In the lane line map construction step S400, the trajectory of the lane line obtained in the lane trajectory acquisition step S300, that is, the point on the lane line in the geodetic coordinate system at the ith time is connected to obtain a lane line map, wherein i=1, 2, 3, ....N, N is a positive number.
以上对于本发明一实施方式的车道线地图的构建系统进行了说明。接着，对于本发明的车道线地图的构建系统进行说明。The system for constructing a lane line map according to an embodiment of the present invention has been described above. Next, a construction system of the lane line map of the present invention will be described.
图3是表示本发明的车道线地图的构建系统的示意图。Fig. 3 is a schematic diagram showing a construction system of a lane line map of the present invention.
如图3所示，本发明的车道线地图的构建系统具备：As shown in FIG. 3, the lane line map construction system of the present invention has:
GPS传感器100，设置在车辆上，用于获取车辆的位置信息；a GPS sensor 100, disposed on the vehicle, for acquiring location information of the vehicle;
摄像头传感器200，设置于车辆上，用于识别车道线并输出车道线信息；以及a camera sensor 200 disposed on the vehicle for identifying a lane line and outputting lane line information;
处理器300，从GPS传感器100获取车辆的位置信息并且从摄像头传感器200获取车道线信息，根据所述位置信息和所述车道线曲线信息计算得到车道线的轨迹，将计算得到的车道线的轨迹拼接而构成车道线地图。The processor 300 acquires position information of the vehicle from the GPS sensor 100 and acquires lane line information from the camera sensor 200, calculates a trajectory of the lane line according to the position information and the lane line curve information, and calculates a trajectory of the calculated lane line Splicing to form a lane line map.
可选地，摄像头传感器200可设置在车辆前挡风玻璃处。摄像头传感器200用于识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：Alternatively, the camera sensor 200 can be placed at the front windshield of the vehicle. The camera sensor 200 is used to identify the lane line and obtain a lane curve in the camera sensor coordinate system represented by the following formula:
Figure PCTCN2018074403-appb-000035
Figure PCTCN2018074403-appb-000035
其中，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置， Where y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离， C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
C 1表示车辆纵轴方向上与车道线切线方向的夹角， C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
C 2表示车道线的曲率， C 2 represents the curvature of the lane line,
C 3表示车道线的曲率变换。 C 3 represents the curvature transformation of the lane line.
进一步，GPS传感器100获取车辆在第i时刻的位置信息记作：Further, the GPS sensor 100 acquires the position information of the vehicle at the ith time:
Figure PCTCN2018074403-appb-000036
Figure PCTCN2018074403-appb-000036
其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
如此，处理器300进行如下处理：As such, the processor 300 performs the following processing:
将第i时获得的车道线上的车辆位置坐标表示为：The vehicle position coordinates on the lane line obtained at the ith are expressed as:
Figure PCTCN2018074403-appb-000037
Figure PCTCN2018074403-appb-000037
在车辆坐标系下的摄像头传感器的位置表示为：The position of the camera sensor in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000038
Figure PCTCN2018074403-appb-000038
将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：Converting the position of the nearest point on the lane line under the camera sensor coordinate system to the position in the vehicle coordinate system is expressed as:
Figure PCTCN2018074403-appb-000039
Figure PCTCN2018074403-appb-000039
由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
Figure PCTCN2018074403-appb-000040
Figure PCTCN2018074403-appb-000040
Figure PCTCN2018074403-appb-000041
Figure PCTCN2018074403-appb-000041
而且，处理器300进行如下处理：Moreover, the processor 300 performs the following processing:
第i时刻在大地坐标系下的车道线上的点的位置表示为：The position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
Figure PCTCN2018074403-appb-000042
Figure PCTCN2018074403-appb-000042
将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
Figure PCTCN2018074403-appb-000043
Figure PCTCN2018074403-appb-000043
利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
Figure PCTCN2018074403-appb-000044
Figure PCTCN2018074403-appb-000044
其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
Figure PCTCN2018074403-appb-000045
Figure PCTCN2018074403-appb-000045
由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
Figure PCTCN2018074403-appb-000046
Figure PCTCN2018074403-appb-000046
Figure PCTCN2018074403-appb-000047
Figure PCTCN2018074403-appb-000047
其中，θ为第i时刻在大地坐标系下,车辆纵轴与大地坐标系横坐标的夹角，具体请参见图2。Where θ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the i-th time, see Figure 2 for details.
接着，处理器300进行如下处理：Next, the processor 300 performs the following processing:
将所述车道线的轨迹、即第i时刻在大地坐标系下的车道线上的点连接起来得到构成车道线地图，其中i＝1，2，3，....N，N为正数。The trajectory of the lane line, that is, the point at the i-th moment on the lane line in the geodetic coordinate system is connected to obtain a lane line map, where i=1, 2, 3, . . . N, N is a positive number .
如上所述，利用本发明的车道线地图的构建方法以及构建系统能够获得以下的有益技术效果：As described above, the following advantageous technical effects can be obtained by the construction method and construction system of the lane line map of the present invention:
(1)本发明的车道线地图的构建方法以及构建系统以摄像头传感器、GPS传感器为采集工具，因此采集成本低、花费时间相对少；(1) The method and construction system for constructing a lane line map of the present invention uses a camera sensor and a GPS sensor as acquisition tools, so the collection cost is low and the time spent is relatively small;
(2)本发明的车道线地图的构建方法以及构建系统以摄像头传感器、GPS传感器为采集工具，因此，采集精度高，能够获得高精度的车道线地图；(2) The method for constructing a lane line map of the present invention and the construction system using the camera sensor and the GPS sensor as acquisition tools, therefore, the acquisition accuracy is high, and a highly accurate lane line map can be obtained;
(3)本发明的车道线地图的构建方法以及构建系统可以应用在实际道路的自动驾驶中；(3) The method and construction system for constructing a lane line map of the present invention can be applied to automatic driving of an actual road;
(4)本发明的车道线地图的构建方法以及构建系统也可以把采集到的车道线地图数据导入仿真场景中，快速还原实际交通场景，能够使得仿真测试更加接近实际的车道线道路环境，例如，能够将车道线地图倒入仿真场景中生成模拟场景，在模拟道路交通场景中开发自动驾驶算法。(4) The method and the construction system for constructing the lane line map of the present invention can also import the collected lane line map data into the simulation scene, and quickly restore the actual traffic scene, which can make the simulation test closer to the actual lane line road environment, for example, The lane line map can be poured into the simulation scene to generate a simulation scene, and the automatic driving algorithm is developed in the simulated road traffic scene.
以上例子主要说明了本发明的基于摄像头传感器的车道线地图构建方法以及构建系统。尽管只对其中一些本发明的具体实施方式进行了描述，但是本领域普通技术人员应当了解，本发明可以在不偏离其主旨与范围内以许多其他的形式实施。因此，所展示的例子与实施方式被视为示意性的而非限制性的，在不脱离如所附各权利要求所定义的本发明精神及范围的情况下，本发明可能涵盖各种的修改与替换。The above examples mainly illustrate the camera sensor-based lane line map construction method and construction system of the present invention. Although only a few of the specific embodiments of the present invention have been described, it is understood that the invention may be embodied in many other forms without departing from the spirit and scope of the invention. Accordingly, the present invention is to be construed as illustrative and not restrictive, and the invention may cover various modifications without departing from the spirit and scope of the invention as defined by the appended claims With replacement.

Claims (13)

  1. 一种车道线地图的构建方法，其特征在于，包括下述步骤：A method for constructing a lane line map, comprising the steps of:
    车辆位置信息获取步骤，利用设置在车辆上的GPS传感器获取车辆的位置信息；a vehicle position information obtaining step of acquiring position information of the vehicle by using a GPS sensor provided on the vehicle;
    车道线曲线信息获取步骤，利用设置在车辆上的摄像头传感器识别车道线并输出车道线曲线信息；a lane line curve information obtaining step of identifying a lane line by using a camera sensor provided on the vehicle and outputting lane line curve information;
    车道线轨迹获取步骤，根据上述车辆位置信息获取步骤获取的车辆的位置信息和上述车道线曲线信息获取步骤获取的车道线曲线信息计算得到车道线的轨迹；以及a lane line trajectory obtaining step of calculating a trajectory of the lane line according to the position information of the vehicle acquired by the vehicle position information acquiring step and the lane line curve information acquired by the lane line curve information obtaining step;
    车道线地图构建步骤，将在上述车道线轨迹获取步骤中得到的车道线的轨迹拼接而构成车道线地图。The lane line map construction step splices the trajectories of the lane lines obtained in the lane trajectory acquisition step to form a lane line map.
  2. 如权利要求1所述的车道线地图的构建方法，其特征在于，A method of constructing a lane line map according to claim 1, wherein
    在所述车道线曲线信息获取步骤中，所述摄像头传感器识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：In the lane line curve information obtaining step, the camera sensor recognizes the lane line, and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
    Figure PCTCN2018074403-appb-100001
    Figure PCTCN2018074403-appb-100001
    其中，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置， Where y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
    C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离， C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
    C 1表示车辆纵轴方向上与车道线切线方向的夹角， C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
    C 2表示车道线的曲率， C 2 represents the curvature of the lane line,
    C 3表示车道线的曲率变换。 C 3 represents the curvature transformation of the lane line.
  3. 如权利要求2所述的车道线地图的构建方法，其特征在于，A method of constructing a lane line map according to claim 2, wherein
    在所述车辆位置信息获取步骤中，利用设置在车辆上的GPS传感器获取车辆在第i时刻的位置信息记作：In the vehicle position information acquisition step, the position information of the vehicle at the ith time is acquired by using a GPS sensor provided on the vehicle:
    Figure PCTCN2018074403-appb-100002
    Figure PCTCN2018074403-appb-100002
    Figure PCTCN2018074403-appb-100003
    Figure PCTCN2018074403-appb-100003
    其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
  4. 如权利要求3所述的车道线地图的构建方法，其特征在于，A method of constructing a lane line map according to claim 3, characterized in that
    在所述车道线曲线信息获取步骤中，将第i时刻获得的车道线上的车辆位置坐标表示为：In the lane line curve information obtaining step, the vehicle position coordinates on the lane line obtained at the ith time are expressed as:
    Figure PCTCN2018074403-appb-100004
    Figure PCTCN2018074403-appb-100004
    在车辆坐标系下的摄像头传感器的位置表示为：The position of the camera sensor in the vehicle coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100005
    Figure PCTCN2018074403-appb-100005
    将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：Converting the position of the nearest point on the lane line under the camera sensor coordinate system to the position in the vehicle coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100006
    Figure PCTCN2018074403-appb-100006
    由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
    Figure PCTCN2018074403-appb-100007
    Figure PCTCN2018074403-appb-100007
  5. 如权利要求4所述的车道线地图的构建方法，其特征在于，A method of constructing a lane line map according to claim 4, wherein
    在所述车道线轨迹获取步骤中，第i时刻在大地坐标系下的车道线上的点的位置表示为：In the lane line trajectory obtaining step, the position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
    Figure PCTCN2018074403-appb-100008
    Figure PCTCN2018074403-appb-100008
    将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100009
    Figure PCTCN2018074403-appb-100009
    利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
    Figure PCTCN2018074403-appb-100010
    Figure PCTCN2018074403-appb-100010
    其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
    Figure PCTCN2018074403-appb-100011
    Figure PCTCN2018074403-appb-100011
    由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
    Figure PCTCN2018074403-appb-100012
    车辆纵轴与大地坐标系横坐标的夹角。
    Figure PCTCN2018074403-appb-100012
    The angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system.
  6. 如权利要求4所述的车道线地图的构建方法，其特征在于，A method of constructing a lane line map according to claim 4, wherein
    在所述车道线地图构建步骤中，将在上述车道线轨迹获取步骤中得到的车道线的轨迹、即第i时刻在大地坐标系下的车道线上的点连接起来得到构成车道线地图，其中i＝1，2，3，….N，N为正数。In the lane line map construction step, the trajectory of the lane line obtained in the lane trajectory acquisition step, that is, the point on the lane line in the geodetic coordinate system at the ith time is connected to obtain a lane line map, wherein i=1, 2, 3, ....N, N is a positive number.
  7. 一种车道线地图的构建系统，其特征在于，具备：A system for constructing a lane line map, comprising:
    GPS传感器，设置在车辆上，用于获取车辆的位置信息；a GPS sensor disposed on the vehicle for acquiring location information of the vehicle;
    摄像头传感器，用于识别车道线并输出车道线信息；a camera sensor for identifying a lane line and outputting lane line information;
    处理器，从所述GPS传感器获取车辆的位置信息并且从所述摄像头传感器获取车道线信息，根据所述位置信息和所述车道线曲线信息计算得到车道线的轨迹，将计算得到的车道线的轨迹拼接而构成车道线地图。a processor, acquiring position information of the vehicle from the GPS sensor, and acquiring lane line information from the camera sensor, calculating a trajectory of the lane line according to the position information and the lane line curve information, and calculating the calculated lane line The track is spliced to form a lane line map.
  8. 如权利要求7所述的车道线地图的构建系统，其特征在于，A lane line map construction system according to claim 7, wherein
    所述摄像头传感器识别车道线，得到由以下公式表示的在摄像头传感器坐标系下的车道曲线：The camera sensor identifies the lane line and obtains a lane curve in the camera sensor coordinate system represented by the following formula:
    Figure PCTCN2018074403-appb-100013
    Figure PCTCN2018074403-appb-100013
    其中，y c、x c是指车道线上的点在摄像头传感器坐标系下的坐标位置， Where y c and x c refer to the coordinate positions of the points on the lane line in the camera sensor coordinate system.
    C 0表示垂直于车辆纵轴方向上摄像头传感器到车道线的距离， C 0 represents the distance from the camera sensor to the lane line perpendicular to the longitudinal axis of the vehicle.
    C 1表示车辆纵轴方向上与车道线切线方向的夹角， C 1 represents the angle between the longitudinal axis of the vehicle and the tangential direction of the lane line.
    C 2表示车道线的曲率， C 2 represents the curvature of the lane line,
    C 3表示车道线的曲率变换。 C 3 represents the curvature transformation of the lane line.
  9. 如权利要求8所述的车道线地图的构建系统，其特征在于，A system for constructing a lane line map according to claim 8, wherein
    所述GPS传感器获取车辆在第i时刻的位置信息记作：The position information of the GPS sensor acquiring the vehicle at the ith time is recorded as:
    Figure PCTCN2018074403-appb-100014
    Figure PCTCN2018074403-appb-100014
    其中，o，v表示：o表示在大地坐标系下，v表示车辆。Where o, v means: o means that in the geodetic coordinate system, v represents the vehicle.
  10. 如权利要求9所述的车道线地图的构建系统，其特征在于，A system for constructing a lane line map according to claim 9, wherein
    所述处理器进行如下处理：The processor performs the following processing:
    将第i时获得的车道线上的车辆位置坐标表示为：The vehicle position coordinates on the lane line obtained at the ith are expressed as:
    Figure PCTCN2018074403-appb-100015
    Figure PCTCN2018074403-appb-100015
    在车辆坐标系下的摄像头传感器的位置表示为：The position of the camera sensor in the vehicle coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100016
    Figure PCTCN2018074403-appb-100016
    将摄像头传感器坐标系下车道线上的最近的点的位置转换到车辆坐标系下的位置表示为：Converting the position of the nearest point on the lane line under the camera sensor coordinate system to the position in the vehicle coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100017
    Figure PCTCN2018074403-appb-100017
    由此，作为车道线曲线信息，如下式那样获得第i时刻的车道线上的位置坐标：Thus, as the lane line curve information, the position coordinates on the lane line at the i-th time are obtained as follows:
    Figure PCTCN2018074403-appb-100018
    Figure PCTCN2018074403-appb-100018
  11. 如权利要求10所述的车道线地图的构建系统，其特征在于，所述处理器进行如下处理：A system for constructing a lane line map according to claim 10, wherein said processor performs the following processing:
    第i时刻在大地坐标系下的车道线上的点的位置表示为：The position of the point on the lane line in the geodetic coordinate system at the i-th moment is expressed as:
    Figure PCTCN2018074403-appb-100019
    Figure PCTCN2018074403-appb-100019
    将在大地坐标系下第i时刻的车辆位置表示为：The position of the vehicle at the i-th moment in the geodetic coordinate system is expressed as:
    Figure PCTCN2018074403-appb-100020
    Figure PCTCN2018074403-appb-100020
    利用下式将车辆坐标系下的摄像头传感器的位置转换为大地坐标系下：The position of the camera sensor in the vehicle coordinate system is converted to the geodetic coordinate system by:
    Figure PCTCN2018074403-appb-100021
    Figure PCTCN2018074403-appb-100021
    其次，利用下式将摄像头传感器坐标系下的车道线上的点的位置转换为大地坐标系下：Secondly, the position of the point on the lane line under the camera sensor coordinate system is converted to the geodetic coordinate system by the following formula:
    Figure PCTCN2018074403-appb-100022
    Figure PCTCN2018074403-appb-100022
    由此，作为车道线的轨迹，利用下式求得第i时刻在大地坐标系下的车道线上的点的位置：Thus, as the trajectory of the lane line, the position of the point on the lane line in the geodetic coordinate system at the ith time is obtained by the following equation:
    Figure PCTCN2018074403-appb-100023
    Figure PCTCN2018074403-appb-100023
    其中，θ为第i时刻在大地坐标系下,车辆纵轴与大地坐标系横坐标的夹角。Where θ is the angle between the longitudinal axis of the vehicle and the abscissa of the geodetic coordinate system in the geodetic coordinate system at the ith time.
  12. 如权利要求11所述的车道线地图的构建系统，其特征在于，A system for constructing a lane line map according to claim 11, wherein
    所述处理器进行如下处理：The processor performs the following processing:
    将所述车道线的轨迹、即第i时刻在大地坐标系下的车道线上 的点连接起来得到构成车道线地图，其中i＝1，2，3，….N，N为正数。The trajectory of the lane line, i.e., the point at the i-th moment on the lane line in the geodetic coordinate system, is connected to form a lane line map, where i = 1, 2, 3, ..., N, and N is a positive number.
  13. 一种储存设备，其中，储存有多条指令，所述指令适于由处理器加载并执行权利要求1～6任意一项所记载的车道线地图的构建方法。A storage device in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor and to execute a method of constructing a lane line map according to any one of claims 1 to 6.
PCT/CN2018/074403 2017-06-13 2018-01-29 Camera sensor based lane line map construction method and construction system WO2018227980A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710441856.6A CN109084782B (en) 2017-06-13 2017-06-13 Lane line map construction method and construction system based on camera sensor
CN201710441856.6 2017-06-13

Publications (1)

Publication Number Publication Date
WO2018227980A1 true WO2018227980A1 (en) 2018-12-20

Family

ID=64659772

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/074403 WO2018227980A1 (en) 2017-06-13 2018-01-29 Camera sensor based lane line map construction method and construction system

Country Status (2)

Country Link
CN (1) CN109084782B (en)
WO (1) WO2018227980A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111516673A (en) * 2020-04-30 2020-08-11 重庆长安汽车股份有限公司 Lane line fusion system and method based on intelligent camera and high-precision map positioning
US20220236074A1 (en) * 2021-01-25 2022-07-28 Nio Technology (Anhui) Co., Ltd Method and device for building road model

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108242145B (en) * 2016-12-26 2020-10-16 阿里巴巴（中国）有限公司 Abnormal track point detection method and device
CN111316284A (en) * 2019-02-13 2020-06-19 深圳市大疆创新科技有限公司 Lane line detection method, device and system, vehicle and storage medium
CN109724615B (en) * 2019-02-28 2021-06-29 北京经纬恒润科技股份有限公司 Method and system for verifying lane line identification result
CN109931944B (en) * 2019-04-02 2021-12-07 阿波罗智联(北京)科技有限公司 AR navigation method, AR navigation device, vehicle-side equipment, server side and medium
CN110288675B (en) * 2019-06-30 2022-05-13 武汉中海庭数据技术有限公司 Lane reference line construction method and device and storage medium
CN110345952A (en) * 2019-07-09 2019-10-18 同济人工智能研究院(苏州)有限公司 A kind of serializing lane line map constructing method and building system
CN110645996B (en) * 2019-09-17 2021-07-16 武汉中海庭数据技术有限公司 Method and system for extracting perception data
CN113405558B (en) * 2020-02-29 2024-04-09 华为技术有限公司 Automatic driving map construction method and related device
CN111273674A (en) * 2020-03-12 2020-06-12 深圳冰河导航科技有限公司 Distance measurement method, vehicle operation control method and control system
CN112050821B (en) * 2020-09-11 2021-08-20 湖北亿咖通科技有限公司 Lane line polymerization method
CN112632208B (en) * 2020-12-25 2022-12-16 际络科技(上海)有限公司 Traffic flow trajectory deformation method and device
CN112734927B (en) * 2021-03-31 2021-06-25 湖北亿咖通科技有限公司 Method and device for simplifying high-precision map lane line and computer storage medium
CN114510055B (en) * 2022-02-18 2022-11-08 科大国创合肥智能汽车科技有限公司 Method for constructing rear lane line
CN114719873B (en) * 2022-06-02 2022-09-02 四川省公路规划勘察设计研究院有限公司 Low-cost fine map automatic generation method and device and readable medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150117723A1 (en) * 2013-10-31 2015-04-30 Toyota Motor Engineering & Manufacturing North America, Inc. Method for generating accurate lane level maps
KR20150061445A (en) * 2013-11-27 2015-06-04 부산대학교 산학협력단 Apparatus for building 3D Load map and recognizing lane
CN105260699A (en) * 2015-09-10 2016-01-20 百度在线网络技术（北京）有限公司 Lane line data processing method and lane line data processing device
CN106441319A (en) * 2016-09-23 2017-02-22 中国科学院合肥物质科学研究院 System and method for generating lane-level navigation map of unmanned vehicle
CN106525057A (en) * 2016-10-26 2017-03-22 陈曦 Generation system for high-precision road map

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102006038018A1 (en) * 2006-08-14 2008-02-21 Robert Bosch Gmbh A driver assistance method and apparatus by generating lane information to support or replace lane information of a video-based lane information facility
US8311283B2 (en) * 2008-07-06 2012-11-13 Automotive Research&Testing Center Method for detecting lane departure and apparatus thereof
KR101225626B1 (en) * 2010-07-19 2013-01-24 포항공과대학교 산학협력단 Vehicle Line Recognition System and Method
KR101358329B1 (en) * 2012-09-03 2014-02-04 현대모비스 주식회사 Lane keeping control system and method
CN106096525B (en) * 2016-06-06 2019-07-19 重庆邮电大学 A kind of compound lane recognition system and method
CN106767853B (en) * 2016-12-30 2020-01-21 中国科学院合肥物质科学研究院 Unmanned vehicle high-precision positioning method based on multi-information fusion

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150117723A1 (en) * 2013-10-31 2015-04-30 Toyota Motor Engineering & Manufacturing North America, Inc. Method for generating accurate lane level maps
KR20150061445A (en) * 2013-11-27 2015-06-04 부산대학교 산학협력단 Apparatus for building 3D Load map and recognizing lane
CN105260699A (en) * 2015-09-10 2016-01-20 百度在线网络技术（北京）有限公司 Lane line data processing method and lane line data processing device
CN106441319A (en) * 2016-09-23 2017-02-22 中国科学院合肥物质科学研究院 System and method for generating lane-level navigation map of unmanned vehicle
CN106525057A (en) * 2016-10-26 2017-03-22 陈曦 Generation system for high-precision road map

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HE, YONG ET AL.: "Generation of Precise Lane-level Maps Based on Multi-sensors", JOURNAL OF CHANG'AN UNIVERSITY ( NATURAL SCIENCE EDITION), vol. 35, 15 January 2015 (2015-01-15), pages 274 - 277, ISSN: 1671-8879 *
HE, YONG: "Research of GPS Navigation Method Based on HD-map", CHINESE MASTER'S THESES FULL-TEXT DATABASE ( ENGINEERING SCIENCE AND TECHNOLOGY II )., 15 February 2016 (2016-02-15), pages C035 - 131, ISSN: 1674-0246 *
ZHENG, BIN ET AL.: "Mapping for Lane-level Digital Maps Based on Mobile Mapping System", MODERN SURVEYING AND MAPPING, vol. 39, no. 6, 25 November 2016 (2016-11-25), pages 42 - 45, ISSN: 1672-4097 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111516673A (en) * 2020-04-30 2020-08-11 重庆长安汽车股份有限公司 Lane line fusion system and method based on intelligent camera and high-precision map positioning
CN111516673B (en) * 2020-04-30 2022-08-09 重庆长安汽车股份有限公司 Lane line fusion system and method based on intelligent camera and high-precision map positioning
US20220236074A1 (en) * 2021-01-25 2022-07-28 Nio Technology (Anhui) Co., Ltd Method and device for building road model

Also Published As

Publication number Publication date
CN109084782B (en) 2024-03-12
CN109084782A (en) 2018-12-25

Similar Documents

Publication Publication Date Title
WO2018227980A1 (en) Camera sensor based lane line map construction method and construction system
KR102273559B1 (en) Method, apparatus, and computer readable storage medium for updating electronic map
CN108362295B (en) Vehicle path guiding apparatus and method
CN109470254B (en) Map lane line generation method, device, system and storage medium
US10240934B2 (en) Method and system for determining a position relative to a digital map
CN110530372B (en) Positioning method, path determining device, robot and storage medium
JP4370869B2 (en) Map data updating method and map data updating apparatus
US10942519B2 (en) System and method for navigating an autonomous driving vehicle
CN110969055B (en) Method, apparatus, device and computer readable storage medium for vehicle positioning
CN110119138A (en) For the method for self-locating of automatic driving vehicle, system and machine readable media
JP6975513B2 (en) Camera-based automated high-precision road map generation system and method
CN110608746B (en) Method and device for determining the position of a motor vehicle
JP4596566B2 (en) Self-vehicle information recognition device and self-vehicle information recognition method
KR102475039B1 (en) Apparatus, method and system for updating map database
CN110728720B (en) Method, apparatus, device and storage medium for camera calibration
US20220187095A1 (en) Landmark location estimation apparatus and method, and computer-readable recording medium storing computer program programmed to perform method
JP2015194397A (en) Vehicle location detection device, vehicle location detection method, vehicle location detection computer program and vehicle location detection system
US20210048819A1 (en) Apparatus and method for determining junction
CN116380088B (en) Vehicle positioning method and device, vehicle and storage medium
KR20200002257A (en) Corner detection-based road sign detecting method and apparatus
JP2021103160A (en) Autonomous traveling vehicle meaning map establishment system and establishment method
KR102475042B1 (en) Apparatus and method for establishing a hd map
US20220404170A1 (en) Apparatus, method, and computer program for updating map
WO2022116572A1 (en) Target positioning method and apparatus
CN111351497A (en) Vehicle positioning method and device and map construction method and device

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: 18818855

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: 18818855

Country of ref document: EP

Kind code of ref document: A1