Research on Vehicle Detection Method based On LIDAR in UGV Leader-Follower Systems

DOI

10.2991/mecae-17.2017.19How to use a DOI?

Keywords

LIDAR, Clustering, Median filter, UGV Leader-follower Systems, Vehicle Detection

Abstract

Aiming at the practical problem of target vehicle detection and tracking in the UGV Leader-follower Systems, a method of detecting and tracking vehicle by using LIDAR is proposed. As an active sensor, LIDAR can obtain the distance and angle information of the object in real time, and has high resolution and robustness. In this method, the LIDAR is installed on the following vehicle, and the two-dimensional laser scanning data in the environment is acquired in real time. Then the nearest neighbor clustering method is used to segment and cluster the LIDAR data. Then, the vehicle tail data is identified from the segmented data by using the straight line tail recognition method designed by the shape feature information of the vehicle, and the position information of the vehicle tail relative to the following vehicle is obtained. By using the data of LIDAR before and after the location of the contrast, determined the speed of the vehicle. Finally, the experiment proves that the method can meet the requirements of vehicle detection and tracking in the UGV Leader-follower Systems.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ziyong Jia
AU  - Guoquan Ren
AU  - Dongwei Li
PY  - 2017/03
DA  - 2017/03
TI  - Research on Vehicle Detection Method based On LIDAR in UGV Leader-Follower Systems
BT  - Proceedings of the 2017 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2017)
PB  - Atlantis Press
SP  - 108
EP  - 112
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecae-17.2017.19
DO  - 10.2991/mecae-17.2017.19
ID  - Jia2017/03
ER  -