An Improved SOTracker in LiDAR Point Cloud Sequences
- Resource Type
- Conference
- Authors
- Wan, Mengyue; Ma, Zhixiong; Zhu, Xichan; Bai, Jie
- Source
- 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) Automation, Electronics and Electrical Engineering (AUTEEE), 2022 IEEE 5th International Conference on. :171-175 Nov, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Point cloud compression
Electrical engineering
Laser radar
Target tracking
Automation
Linear programming
Object tracking
single object tracking
LiDAR
model-free
state estimation
- Language
- ISSN
- 2831-4549
Object tracking stays at the core of autonomous driving, which estimates the states of surrounding traffic participants. This paper proposes an optimization-based single-object tracking method. Our approach improves on SOTracker, which utilizes the weighted sum of the four objective functions to optimize the state of the tracking object. We introduce the Boundary Term and optimize the tracking order. The experimental results show that the proposed method dramatically improves single-object tracking compared with SOTracker.