Perception for Coupler Rod of Freight Train Based on Image and Point Clouds | |
Renjie Guo2,3; Jun Feng1; Huachang Yang1; Dejie Luan31; Guodong Yang2,3; En Li2,3 | |
2022-11 | |
会议日期 | 25-27 November 2022 |
会议地点 | Xiamen, China |
英文摘要 | In the construction of automated marshaling yards, the automatic uncoupling operation of freight trains has always been the research and development direction. The coupler rod is the operation object of the uncoupling operation. The identification of coupler rod type and estimating position and posture are the prerequisites to realizing automatic uncoupling operation. In this paper, we propose a perception method of coupler rod by RGB image combined with the point cloud. We use an RGBD camera to synchronously collect frame-aligned RGB and depth images and generate point cloud data with colors according to the mapping relationship. Then, we use the YOLOv5 neural network to detect the collected RGB images and recognize the type of coupler rod in the image. Clear clutter in the point cloud and the bounding box is mapped to a spatial coordinate system for straight-through filtering of the point cloud. We use RANSAC for coarse registration and ICP for fine registration. The result of registration is carried out with the lower sampling point cloud model to achieve the registration of the coupler rod. Experiments show that this method can effectively segment the point cloud of the region of interest with high robustness. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52183] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Guodong Yang |
作者单位 | 1.China Academy of Railway Sciences Corporation Limited 2.University of Chinese Academy of Sciences 3.Institute of Automation, CAS |
推荐引用方式 GB/T 7714 | Renjie Guo,Jun Feng,Huachang Yang,et al. Perception for Coupler Rod of Freight Train Based on Image and Point Clouds[C]. 见:. Xiamen, China. 25-27 November 2022. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论