Traffic Sign Based Point Cloud Data Registration with Roadside LiDARs in Complex Traffic Environments

Abstract

The intelligent road is an important component of the intelligent vehicle infrastructure cooperative system, the latest development of intelligent transportation systems. As an advanced sensor, Light Detection and Ranging (LiDAR) has gradually been used to collect high-resolution micro-traffic data on the roadside of intelligent roads. Furthermore, a fusion of multiple LiDARs has become a current hot spot to extend the data collection range and improve detection accuracy. This paper focuses on point cloud registration in a complex traffic environment and proposes a three-dimensional (3D) registration method based on traffic signs and prior knowledge of traffic scenes. Traffic signs with their reflective films are used as reference targets to register 3D point cloud data from roadside LiDARs. The proposed method consists of a vertical registration and a horizontal registration. For the vertical registration, we propose a panel rotation algorithm to rotate the initial point cloud to register it vertically, converting the 3D point cloud registration into a two-dimensional (2D) rigid body transformation. For the vertical registration, our system registers traffic signs from different LiDARs. Our method has been verified in some actual scenarios. Compared with previous methods, the proposed method is automatic and does not need to search reference targets manually. Furthermore, it is suitable for actual engineering use and can be applied to sparse point cloud data from LiDAR with few beams, realizing point cloud registration of large disparity.

Improving Autonomous Vehicle Perception through Evaluating LiDAR Capabilities and Handheld Retroreflectivity Assessments

“…Additionally, the functionality of AV sensors can be affected by challenges in detecting objects with similar colors and light reflectivity, as pointed out by ref. [ 18 ]. To address these challenges, research has explored various methodologies for traffic sign recognition in AVs, including color-based categorization, shape-based detection, deep learning methods, and edge detection techniques [ 2 ].…”

Design, Implementation and Experimental Investigation of a Pedestrian Street Crossing Assistance System Based on Visible Light Communications

“…The LIDAR sensor has been included in the test due to its high precision and long detection range [ 48 , 49 , 50 , 51 , 52 ]. Based on these unique features, LIDAR sensors are widely used in automotive applications, being one of the most advanced solutions used for object identification and localization [ 48 , 49 , 50 , 51 , 52 ]. The LIDAR V3 sensor has a range of up to 40 m while providing a centimeter accuracy, (i.e., less than ±10 cm).…”

Object Detection Based on Roadside LiDAR for Cooperative Driving Automation: A Review

“…The fusion of multiple LiDAR point clouds with spatial diversity characteristics to achieve regional cooperative perception can significantly improve the accuracy of scene perception. Cooperative perception can fuse data from multiple LiDAR sensors through V2I [ 90 , 91 , 92 ] or I2I [ 19 , 93 , 94 ], to realize information sharing and reduce sensor deployment costs. Based on the general procedure of 3D object detection, cooperative perception can be classified into three categories depending on the sensing information to be shared between LiDAR: raw, feature, and object-level cooperative perception [ 95 ].…”