1D Self-Attention Network for Point Cloud Semantic Segmentation Using Omnidirectional LiDAR

EasyChair Preprint 7026

Abstract

Understanding the environment around a vehicle is essential for automated driving technology. For this purpose, omnidirectional LiDAR is used for obtaining surrounding information, and point cloud-based semantic segmentation methods have been proposed. However, these methods require time to acquire point cloud data and to process the point cloud, which causes a significant positional shift of objects in practical application scenarios. In this paper, we propose a 1D self-attention network (1D-SAN) for LiDAR-based point-cloud semantic segmentation, which is based on a 1D-CNN for real-time pedestrian detection of omnidirectional LiDAR data. Because the proposed method can sequentially process segmentation during data acquisition with omnidirectional LiDAR, we can reduce the processing time and suppress positional shift. Moreover, for improving segmentation accuracy, we use the intensity as input data and introduce a self-attention mechanism into the method. The intensity enables us to consider object texture. The self-attention mechanism can consider the relationship between point clouds. Experimental results with the SemanticKITTI dataset show that the intensity input and the self-attention mechanism in the proposed method improve accuracy. In particular, the mechanism contributes to improving the accuracy for small objects. Also, we show that the processing time of the proposed method is faster than the other point-cloud segmentation methods.

Keyphrases: Automated Driving, Distance Value, LiDAR, Mean IoU, Reflection intensity, autonomous driving, computer vision, d point cloud, lidar based point cloud, neighboring point, omnidirectional lidar, omnidirectional lidar data, pattern recognition, point cloud, point cloud data, point cloud segmentation, processing speed, processing time, real-time, segmentation method, self-attention, self-attention mechanism, semantic segmentation, semantic segmentation method, semantickitti dataset

@booklet{EasyChair:7026,
  author    = {Takahiro Suzuki and Tsubasa Hirakawa and Takayoshi Yamashita and Hironobu Fujiyoshi},
  title     = {1D Self-Attention Network  for Point Cloud Semantic Segmentation Using Omnidirectional LiDAR},
  howpublished = {EasyChair Preprint 7026},
  year      = {EasyChair, 2021}}