Point Cloud Instance Segmentation and Classification for Roadside LiDAR

Ciyun Lin

doi:10.1109/JSEN.2025.3613255

Point Cloud Instance Segmentation and Classification for Roadside LiDAR

2025-11-01

0

PRE

AI

DOI：10.1109/JSEN.2025.3613255

Original

Original request for help

Save

Abstract

En 中文

Point cloud segmentation is an essential and efficient task in high-definition trajectory-level traffic information extraction for roadside light detection and ranging (LiDAR). State-of-the-art methods use conventional step-bystep in-sequence or all-in-one deep learning methods to process point cloud data. While effective in many applications, their deployment in complex traffic scenarios often faces constraints of computational resources and real-time requirements. To complement these approaches, a novel point cloud segmentation method was proposed jointing with background filtering and object classification to segment the objects in a single-point cloud frame. First, a novel multiscale mapping clustering algorithm was introduced for instance segmentation to address the issue of over- and under-segmentation caused by occlusions in traffic scenarios. A passage space feature was then proposed to better characterize the properties of instances in traffic scenarios. Finally, a local hierarchical classifier (HiClass) was employed to enhance the accuracy of object classification. Experimental results showed that the proposed point cloud segmentation method achieved more than 80% homogeneity, with the object classification accuracy increasing to 98%. Furthermore, the data processing rate is 8.67 ms per point cloud frame. These experimental outcomes highlight the robustness, accuracy, and efficiency of the proposed method in point cloud segmentation.

Keywords:

Background filtering

object classification

point cloud segmentation

roadside light detection and ranging (LiDAR)

Point Cloud Instance Segmentation and Classification for Roadside LiDAR

Abstract

Journal

Organization