顾及数字地图中车道走向的车辆跟踪增强算法  

Vehicle tracking enhancement based on the lane orientation priori from digital maps

作　　者：庄瀚洋 王晓亮 王春香 杨明[3,4,5] ZHUANG Hanyang;WANG Xiaoliang;WANG Chunxiang;YANG Ming(University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai 200240, China;Guangxi Key Laboratory of Automobile Components and Vehicle Technology, Guangxi University of Science and Technology, Liuzhou 545006, China;Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China;Shanghai Engineering Research Center of Intelligent Control and Management, Shanghai 200240, China)

机构地区：[1]上海交通大学密西根学院,上海200240 [2]广西科技大学广西汽车零部件与整车技术重点实验室,广西柳州545006 [3]上海交通大学自动化系,上海200240 [4]系统控制与信息处理教育部重点实验室,上海200240 [5]上海工业智能管控工程技术研究中心,上海200240

出　　处：《测绘学报》2021年第11期1522-1533,共12页Acta Geodaetica et Cartographica Sinica

基　　金：广西汽车零部件与整车技术重点实验室开放研究课题(2020GKLACVTKF02);国家自然科学基金联合基金项目(U1764264)。

摘　　要：车辆跟踪技术旨在从连续场景中估计目标车辆的状态,对智能车辆的环境感知、场景理解和目标行为预测起着至关重要的作用。基于激光雷达的感知系统能够提供准确的车辆检测结果,但依据检测结果进行车辆跟踪时,存在车辆朝向估计失准导致跟踪误差大、轨迹预测稳定性差的难题,尤其在目标距离较远、点云较为稀疏的情况下。考虑到大多数时刻车辆行驶方向与车道线方向基本一致,本文提出一种基于数字地图中车道朝向先验信息的车辆跟踪增强方法,将局部车道线的识别结果与OpenStreetMap地图中的车道线信息进行融合,建立道路模型并获取道路朝向的先验约束;在基于扩展卡尔曼滤波的车辆跟踪框架下,利用该约束优化车辆的朝向估计,进而提升车辆跟踪的精度与轨迹预测稳定性。在KITTI数据集上的定性与定量试验证明,本文所提出的方法在多目标跟踪指标上提升至少0.33%,平均位移误差降低了0.014 m以上,同时,对于60 m外车辆目标的跟踪误差降低了0.08 m以上。Vehicle tracking aims at estimating the target vehicle state from continuous temporal measurement.It is the core for intelligent vehicle to understand the environment and predict the targets’behaviors.LiDAR-based perception system of intelligent vehicle provides precise vehicle detection results,which are the basis of vehicle tracking.However,the tracking process suffers from issues of orientation mis-estimation and low stability of tracking trace,especially when the target vehicles are far away from LiDAR.The sparseness of point cloud at long distance is the key problem.Therefore,this paper proposes an enhanced vehicle tracking method based on the lane orientation priori from a digital map.It utilizes the OpenStreetMap digital map to fuse with the local lane markers detection results.The road model is built to obtain the constraint of lane orientation.Based on the vehicle tracking method built on extended Kalman filter,this lane orientation constraint is utilized to improve the vehicle orientation estimation.Consequently,the vehicle tracking accuracy and stability can then be reached.The tracking result indicates the multiple objects tracking accuracy can be increased by 0.33%while the average translation error can be reduced by at least 0.014 m.Moreover,the target vehicle at 60 m away from the host vehicle can be improved to reduce the error of 0.08 m.

关 键 词：数字地图 车辆跟踪 扩展卡尔曼滤波 智能车辆 

分 类 号：P208[天文地球—地图制图学与地理信息工程]