Detecting and tracking moving objects is a key technology for autonomous driving vehicle in dynamic urban environment. In this paper, we present a hybrid system of multiple moving target tracking (MMTT) for autonomous driving vehicles using 3D-Lidar sensor. To detect targets, geometric model-based method is adopted in the hybrid system. In further, we propose a novel hypothesis trajectory model to detect moving targets. The targets detected by the two methods are fused under Extend Kalman Filter. Besides, a bipartite graph model-based method with the Hungary algorithm is presented to optimize data association matrix. Our tracking algorithm is tested on school road and Beijing's 3rd ring road using an experimental vehicle with velodyne-32-E. And, the experiment results illustrate the hybrid method performs well in real time.
Multiple moving target tracking with hypothesis trajectory model for autonomous vehicles
2017-10-01
513557 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multiple Hypothesis Tracking for Multiple Target Tracking
Online Contents | 2004
|LSTM-Based Trajectory Tracking Control for Autonomous Vehicles
British Library Conference Proceedings | 2022
|