Plane-based scan registration with moving vehicles exclusion

详细信息    查看全文

• 作者：Chongyang Wei^a ; ^{cyzq3566@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ruili Wang^b ; ^{r.wang@massey.ac.nz" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Tao Wu^a ; ^{wtt09.cs@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Tongtong Chen^a ; ^{chentongtong5208@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yuqiang Fang^a ; ^{yqfang.cs@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Hao Fu^a ; ^{fuhao927@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Scan registration ; Moving vehicle detection ; Likelihood-field-based model ; Plane-based criterion ; Autonomous vehicles
• 刊名：Robotics and Autonomous Systems
• 出版年：2016
• 出版时间：September 2016
• 年：2016
• 卷：83
• 期：Complete
• 页码：261-274
• 全文大小：4114 K

文摘

Moving vehicles have a considerable negative effect on the accuracy of scan registration and lidar odometry. To remove the negative effect, we propose an extended 2D virtual scan to obtain all moving objects in the sensing range of lidar by a scan differencing operation between two consecutive scans. The dynamic objects’ poses are estimated with our proposed likelihood-field-based vehicle measurement model and the motion evidence is utilized to classify the objects as moving vehicles or not. In this way, the moving/dynamic vehicles are detected and the points hitting them are removed. The remaining points are then taken as an input into the alignment.

In the registration, we adjust the raw distorted points by modeling the lidar motion as the constant angular and linear velocities within a scan interval, and then exploit the probabilistic framework to model the local plane structure of the matched feature points instead of the original point-to-point mode. The transform is achieved by the combination of coarse motion estimation and fine batch adjustment. The algorithm has been validated by a large set of qualitative tests on our collected point clouds and quantitative comparisons with the excellent methods on the public Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) odometry datasets.