Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram
The 3D perception system functions as one of the core components for the safe operation of autonomous-rail rapid tram. Addressing the limitations of LiDAR systems used for autonomous-rail rapid tram in complex urban environments, such as challenges in perceiving distant objects, insensitivity to col...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2023-10-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.05.005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849224972185108480 |
|---|---|
| author | WANG Zeyuan LIN Jun YUAN Xiwen XU Yanghan YUE Wei XIONG Qunfang |
| author_facet | WANG Zeyuan LIN Jun YUAN Xiwen XU Yanghan YUE Wei XIONG Qunfang |
| author_sort | WANG Zeyuan |
| collection | DOAJ |
| description | The 3D perception system functions as one of the core components for the safe operation of autonomous-rail rapid tram. Addressing the limitations of LiDAR systems used for autonomous-rail rapid tram in complex urban environments, such as challenges in perceiving distant objects, insensitivity to color, and potential failure, this paper proposes a pure-vision monocular 3D perception system for autonomous-rail rapid tram. Comprising data preprocessing, model training and model deployment, this vision-based scheme with a full coverage from data collection to on-board deployment enables the 3D perception of obstacles around autonomous-rail rapid tram, thereby improving the operational reliability in complex urban environments. The test results based on the autonomous-rail rapid transit dataset and Waymo open dataset show that the system can effectively perceive the complex road scenes in autonomous-rail rapid transit, achieving a final 3D average precision (AP) of 0.53, reasoning a single-frame of image about 56 ms, and meeting the real-time requirements of autonomous-rail rapid tram for the obstacle perception algorithm. |
| format | Article |
| id | doaj-art-a48c797141034e149525a92853cfe4c5 |
| institution | Kabale University |
| issn | 2096-5427 |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Editorial Office of Control and Information Technology |
| record_format | Article |
| series | Kongzhi Yu Xinxi Jishu |
| spelling | doaj-art-a48c797141034e149525a92853cfe4c52025-08-25T06:48:33ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272023-10-01253267224493Research on the Monocular 3D Perception System for Autonomous-rail Rapid TramWANG ZeyuanLIN JunYUAN XiwenXU YanghanYUE WeiXIONG QunfangThe 3D perception system functions as one of the core components for the safe operation of autonomous-rail rapid tram. Addressing the limitations of LiDAR systems used for autonomous-rail rapid tram in complex urban environments, such as challenges in perceiving distant objects, insensitivity to color, and potential failure, this paper proposes a pure-vision monocular 3D perception system for autonomous-rail rapid tram. Comprising data preprocessing, model training and model deployment, this vision-based scheme with a full coverage from data collection to on-board deployment enables the 3D perception of obstacles around autonomous-rail rapid tram, thereby improving the operational reliability in complex urban environments. The test results based on the autonomous-rail rapid transit dataset and Waymo open dataset show that the system can effectively perceive the complex road scenes in autonomous-rail rapid transit, achieving a final 3D average precision (AP) of 0.53, reasoning a single-frame of image about 56 ms, and meeting the real-time requirements of autonomous-rail rapid tram for the obstacle perception algorithm.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.05.005autonomous-rail rapid tramautomatic drivingvisual perceptionattention mechanismobject detectionmonocular 3D algorithmmodel deployment |
| spellingShingle | WANG Zeyuan LIN Jun YUAN Xiwen XU Yanghan YUE Wei XIONG Qunfang Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram Kongzhi Yu Xinxi Jishu autonomous-rail rapid tram automatic driving visual perception attention mechanism object detection monocular 3D algorithm model deployment |
| title | Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram |
| title_full | Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram |
| title_fullStr | Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram |
| title_full_unstemmed | Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram |
| title_short | Research on the Monocular 3D Perception System for Autonomous-rail Rapid Tram |
| title_sort | research on the monocular 3d perception system for autonomous rail rapid tram |
| topic | autonomous-rail rapid tram automatic driving visual perception attention mechanism object detection monocular 3D algorithm model deployment |
| url | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.05.005 |
| work_keys_str_mv | AT wangzeyuan researchonthemonocular3dperceptionsystemforautonomousrailrapidtram AT linjun researchonthemonocular3dperceptionsystemforautonomousrailrapidtram AT yuanxiwen researchonthemonocular3dperceptionsystemforautonomousrailrapidtram AT xuyanghan researchonthemonocular3dperceptionsystemforautonomousrailrapidtram AT yuewei researchonthemonocular3dperceptionsystemforautonomousrailrapidtram AT xiongqunfang researchonthemonocular3dperceptionsystemforautonomousrailrapidtram |