FarNet: An Attention-Aggregation Network for Long-Range Rail Track Point Cloud Segmentation

• Published in: IEEE transactions on intelligent transportation systems Vol. 23; no. 8; pp. 13118 - 13126
• Main Authors: Wang, Zhangyu, Yu, Guizhen, Chen, Peng, Zhou, Bin, Yang, Songyue
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-08-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Agglomeration; Feature extraction; Image segmentation; Laser radar; LiDAR; Modules; point cloud; rail track; Rail transportation; Rails; Railway tracks; Semantic segmentation; Semantics; Sensors
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2021.3119900

Rail track segmentation is key to environmental perception of autonomous train. However, due to the complexity of railway track environment, critical issues such as the detection of rail tracks with different curvatures remain to be overcome. In this study, a novel architecture called FarNet is proposed for long-range railway track point cloud segmentation. The proposed FarNet is mainly divided into three parts, i.e., spherical projection, attention-aggregation network and results refinement. Specifically, spherical projection converts the LiDAR point cloud into a pseudo range image, and attention-aggregation network enables railway track detection using the pseudo range image. Furthermore, in the attention-aggregation network two components, i.e., spatial attention module and information aggregation module, are proposed to enhance the capability of rail track segmentation. Last, the results refinement helps further filter out the noise points after segmentation. Experimental results show that the proposed FarNet achieved 98.0% mean intersection-over-union (MIoU) and 98.9% mean pixel accuracy (MPA) for rail track segmentation.