Architecture of Vehicle Trajectories Extraction With Roadside LiDAR Serving Connected Vehicles

• Main Authors: Jingrong Chen, Sheng Tian, Hao Xu, Rui Yue, Yuan Sun, Yuepeng Cui
• Format: Article
• Language: English
• Published: IEEE 2019-01-01
• Series: IEEE Access
• Subjects: Connected-vehicle; vehicle trajectory; roadside LiDAR
• Online Access: https://ieeexplore.ieee.org/document/8766831/

This paper developed a data processing procedure for detection and tracking of multi-lane multi-vehicle trajectories with a roadside Light Detection and Ranging (LiDAR) sensor. Different from the existing perception methods for the autonomous vehicle system, this procedure was explicitly developed to extract trajectories from a roadside LiDAR sensor. The proposed procedure includes five main steps: region of interest (ROI) selection, ground surface filtering, point clustering, vehicle/non-vehicle classification, and geometrical vehicle tracking. The case study showed that the trajectories of vehicles can be generated with the proposed method. This paper is the start of the new-generation connected infrastructures serving connected/autonomous vehicles with the roadside LiDAR sensors. It will accelerate the deployment of connected-vehicle technologies to improve traffic safety, mobility, and fuel efficiency.