LiDAR Target Detection for Automatic Berthing and De-berthing Scenarios
- DOI
- 10.2991/978-94-6463-514-0_33How to use a DOI?
- Keywords
- Poly YOLO detector; Dilated convolution; Self attention module (SAM); Point cloud
- Abstract
Intelligent ships face the problem of accurate and real-time perception of the surrounding environment during the berthing and de-berthing. This paper proposes a Poly YOLO detector based on the YOLOv3 network. Firstly, the detection rate and efficiency of the Poly-YOLO structure is enhanced by introducing the dilated convolution and self-attention module into it; secondly, the LIDAR point cloud data is projected onto the 2D plane, the information of the 2D sparse depth map is enriched to generate the dense depth map using the depth up-sampling method, the data is fed back to the Poly-YOLO detection and recognition network, and the detection is accomplished by using the detection head. The experimental results show that this method can effectively improve the accuracy of the detection of point clouds and ensure real-time performance.
- Copyright
- © 2024 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Liang Yue AU - Chuang Zhang AU - Muzhuang Guo PY - 2024 DA - 2024/09/28 TI - LiDAR Target Detection for Automatic Berthing and De-berthing Scenarios BT - Proceedings of the 2024 7th International Symposium on Traffic Transportation and Civil Architecture (ISTTCA 2024) PB - Atlantis Press SP - 311 EP - 317 SN - 2352-5401 UR - https://doi.org/10.2991/978-94-6463-514-0_33 DO - 10.2991/978-94-6463-514-0_33 ID - Yue2024 ER -