Conference paper

VEĽAS Martin, ŠPANĚL Michal and HEROUT Adam. Collar Line Segments for Fast Odometry Estimation from Velodyne Point Clouds. In: Proceedings of IEEE International Conference on Robotics and Automation. Stockholm: IEEE Computer Society, 2016, pp. 4486-4491. ISBN 978-1-4673-8025-6. Available from: http://ieeexplore.ieee.org/document/7487648/
Publication language:english
Original title:Collar Line Segments for Fast Odometry Estimation from Velodyne Point Clouds
Title (cs):Rychlý výpočet odometrie z mračna bodů pro Velodyne LiDAR pomocí liniových segmentů
Pages:4486-4491
Proceedings:Proceedings of IEEE International Conference on Robotics and Automation
Conference:2016 IEEE International Conference on Robotics and Automation
Place:Stockholm, SE
Year:2016
URL:http://ieeexplore.ieee.org/document/7487648/
ISBN:978-1-4673-8025-6
Publisher:IEEE Computer Society
Files: 
+Type Name Title Size Last modified
iconICRA16_0157_MS.pdf3,64 MB2015-09-11 10:34:59
^ Select all
With selected:
Keywords
Velodyne LiDAR, point cloud registration, odometry estimation, collar line segments, ICP, generalized ICP, SLAM
Annotation
We present a novel way of odometry estimation from Velodyne LiDAR point cloud scans. The aim of our work is to overcome the most painful issues of Velodyne data - the sparsity and the quantity of data points - in an efficient way, enabling more precise registration. Alignment of the point clouds which yields the final odometry is based on random sampling of the clouds using Collar Line Segments. The closest line segment pairs are identified in two sets of line segments obtained from two consequent Velodyne scans. From each pair of correspondences,  a transformation aligning the matched line segments into a 3D plane is estimated. By this, significant planes (ground, walls, ...) are preserved among aligned point clouds.
Evaluation using the KITTI dataset shows that our method outperforms publicly available and commonly used state-of-the-art method GICP for point cloud registration in both accuracy and speed, especially in cases where the scene lacks significant landmarks or in typical urban elements. For such environments, the registration error of our method  is reduced by 75% compared to the original GICP error.
BibTeX:
@INPROCEEDINGS{
   author = {Martin Ve{\'{l}}as and Michal {\v{S}}pan{\v{e}}l and Adam
	Herout},
   title = {Collar Line Segments for Fast Odometry Estimation from
	Velodyne Point Clouds},
   pages = {4486--4491},
   booktitle = {Proceedings of IEEE International Conference on Robotics and
	Automation},
   year = {2016},
   location = {Stockholm, SE},
   publisher = {IEEE Computer Society},
   ISBN = {978-1-4673-8025-6},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10960}
}

Your IPv4 address: 54.226.172.30
Switch to IPv6 connection

DNSSEC [dnssec]