Lidar-Based Multiple Object Tracking with Occlusion Handling

研究成果: Conference contribution同行評審

摘要

Occlusion remains an issue in multiple object tracking, which could cause ambiguity in object detection, such as incorrect or missing detection. Under occlusion, a track could experience an early termination, resulting in identity switches and/or fragmentation. To recover from different lengths of occlusions, the track should be maintained by considering its occlusion status. To address the issues mentioned above, we propose an indicator that can model the track's occlusion extent via geometric information provided by LiDAR data. Through incorporating the indicator into the track management and data association process, it is feasible to prevent tracks from premature termination. The proposed method is evaluated on the collected dataset which undergoes frequent and severe occlusions. Compared to the state-of-the-art probabilistic tracking approach, our approach achieves improvements of 3.26% in MOTA and 5.36% in IDF1. Additionally, we obtain 9.89% improvements in IDF1 specifically for objects experiencing severe occlusions.

原文English
主出版物標題2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面9043-9048
頁數6
ISBN(電子)9781665491907
DOIs
出版狀態Published - 2023
事件2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023 - Detroit, United States
持續時間: 1 10月 20235 10月 2023

出版系列

名字IEEE International Conference on Intelligent Robots and Systems
ISSN(列印)2153-0858
ISSN(電子)2153-0866

Conference

Conference2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
國家/地區United States
城市Detroit
期間1/10/235/10/23

指紋

深入研究「Lidar-Based Multiple Object Tracking with Occlusion Handling」主題。共同形成了獨特的指紋。

引用此