Automatic Identification of Vehicle Partial Occlusion in Data Collected by Roadside LiDAR Sensors

Abstract

Light detection and ranging (LiDAR) sensors are receiving an increasing amount of attention in traffic detection because of their powerful capacity for providing accurate trajectory data of vehicles and non-motorized road users. When installed at the roadside, LiDAR faces the same occlusion problem as other over-roadway sensors (such as video cameras)—the integrity and reliability of object detection can be reduced when occlusion occurs. Existing occlusion reasoning methods are either developed for video sensors or require sensor fusion. Fast and accurate occlusion determination is an indispensable step in the process of vehicle detection, classification, and tracking. This paper presents a novel algorithm to automatically identify the occurrence of vehicle partial occlusion and the corresponding occluding/occluded relationship from roadside LiDAR data. According to the inherent characteristics of LiDAR sensors, two specifically designed heatmaps (ClusterID heatmap and Distance heatmap) were generated and used as the basis for fast occlusion search. Using the field data collected from two testbeds, it was shown that the proposed method could achieve about 95.60% accuracy for partial occlusion identification and a processing speed of 2 ms per frame (32-laser LiDAR sensor with 0.1 s per frame).

Proactive Safety Analysis Using Roadside LiDAR Based Vehicle Trajectory Data: A Study of Rear-End Crashes

“…A more detailed explanation of the algorithm can be found in previous studies by the authors ( 45 , 46 ). Figure 2 a shows the roadside LiDAR sensors mounted on a traffic signal during the data collection performed by the authors.…”

Object recognition from on-the-road traffic data

“…9 An improved technique of automatically detecting a partial occlusion in point cloud data from roadside LiDAR has been developed providing an accurate method for automatically identifying partial occlusion (merging) from point cloud LiDAR data. 10 For autonomous driving in a city environment, the geometric model-free approach with a particle filter (GMFA-PF) has been developed as a tracking method with state estimation, 11 where the GMFA-PF can accurately track and estimate the moving objects in the point clouds. VoxelNet and LUNet networks have been used to develop a machine learning (ML) based object detection system from point clouds of KITTI automobile detection benchmark collection.…”