文献类型：期刊文献

英文题名：Dynamic Obstacle Detection and Tracking Based on 3D Lidar

作者：Zhong, Qixue[1,3];Liu, Yuansheng[1,4,5];Guo, Xiaoxiao[2];Ren, Lijun[2]

第一作者：Zhong, Qixue

通讯作者：Liu, YS[1]

机构：[1]Beijing Union Univ, Beijing Engn Res Ctr Smart Mech Innovat Design Se, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[3]Beijing Engn Res Ctr Smart Mech Innovat Design Se, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[4]Beijing Union Univ, Coll Robot, 97 Beisihuan East Rd, Beijing 100101, Peoples R China;[5]Beijing Union Univ, Coll Robot, Wheeled Mobile Robot Dept, 97 Beisihuan East Rd, Beijing 100101, Peoples R China

第一机构：北京联合大学

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Engn Res Ctr Smart Mech Innovat Design Se, 97 Beisihuan East Rd, Beijing 100101, Peoples R China.|[11417]北京联合大学;

年份：2018

卷号：22

期号：5

起止页码：602-610

外文期刊名：JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS

收录：EI(收录号：20183905866679);Scopus(收录号：2-s2.0-85053769304);WOS:【ESCI(收录号:WOS:000446003800003)】；

基金：This work was financially supported by Academic Human Resources Development in Beijing Union University (Grant number: BPHR2017EZ02), Talents Cultivation and Cooperation Oriented to Intelligent Vehicle Industrialization (Grant number: UK-CIAPP\324), Newton Fund Project supported by Royal Academy of Engineering of UK, the Program Projects of Beijing Municipal Education Commission (No. SQKM201411417006), Supporting Plan for Cultivating High Level Teachers in Colleges and Universities in Beijing (Grant number: IDHT20170511), and Graduate Funded Project of Beijing Union University.

语种：英文

外文关键词：autonomous vehicles; clustering; MHT; spatio-temporal characteristics; nearest neighbor

摘要：Detection and tracking of dynamic obstacle is one of the research hotspot in autonomous vehicles. In this paper, a dynamic obstacle detection and tracking method based on 3D lidar is proposed. The nearest neighborhood method is used to cluster the data obtained by the laser lidar. The characteristic parameters of the clustering obstacles are analyzed. Multiple hypothesis tracking model (MHT) algorithm and the nearest neighbor association algorithm are used for data association of two consecutive frames of obstacle information. The dynamic and static state of obstacles are analyzed through the temporal and spatial correlation of the obstacle. Finally, we use linear Kalman filter to predict the movement state of the obstacle. The experimental results on a low-speed driverless vehicle "small whirlwind" which is an autonomous sightseeing vehicle show that the method can accurately detect the dynamic obstacles in unknown environment with effectiveness and real-time performance.