Interactive Perception-Based Multiple Object Tracking via CVIS and AV

Abstract

Cooperative Vehicle and Infrastructure System (CVIS) and Autonomous Vehicle (AV) are two mainstream technologies to improve urban traffic efficiency and vehicle safety in the Intelligent Transportation System (ITS). However, there remain significant obstacles that must be overcome before fully unmanned applications are ready for widespread adoption in a transportation system. To achieve fully driverless driving, the perception ability of vehicle should be accurate, fast, continuous, and wide-ranging. In this paper, an interactive perception framework is proposed, which combines the visual perception of AV and information interaction of CVIS. Based on the framework, an interactive perception-based multiple object tracking (IP-MOT) method is presented. IP-MOT can be divided into two parts. First, a Lidaronly multiple object tracking (L-MOT) method obtains the status of surroundings using the voxel cluster algorithm. Second, the preliminary tracking result is fused with the interactive information to generate the trajectories of target vehicles. Two simulation platforms are established to verify the proposed methods: CVIS simulation platform and Virtual Reality (VR) test platform. The L-MOT algorithm is tested on a public dataset and the IP-MOT algorithm is tested on our simulation platform. The results show that the IP-MOT algorithm can improve the accuracy of object tracking as well as expand the vehicle perception range via combination of CVIS and AV.INDEX TERMS Cooperative vehicle and infrastructure system, autonomous vehicle, perception mode, multiple object tracking.

Perception Methods for Adverse Weather Based on Vehicle Infrastructure Cooperation System: A Review

“…Zhao et al [ 113 ] utilized lane detection tags from roadside infrastructures and ICVs to compute uncertainty using the Dempster–Shafer theory. Shangguan et al [ 114 ] integrated a multi-target tracking method [ 115 ] and a voxel clustering algorithm to obtain the perception results for the environment around the target vehicle using on-board data. To achieve an accurate vehicle trajectory, the perception results from the target vehicle were merged with those from roadside units and other ICVs.…”

Cooperative Perception Technology of Autonomous Driving in the Internet of Vehicles Environment: A Review

“…The results show that the detection effect at a range of 20 m is improved by about 10%, and the further distance is improved by about 30%. Wei et al [ 32 ] used a multi-target tracking method [ 33 ] based on vehicle-mounted LiDAR and a voxel clustering algorithm to obtain the state of the surrounding environment. This method fuses the preliminary tracking results with the perception information of the RSU and other vehicles to generate the motion trajectory of the target vehicle.…”

Platoon Separation Strategy Optimization Method Based on Deep Cognition of a Driver’s Behavior at Signalized Intersections

“…The real test site has the properties of a high cost, limited scenarios, and a long construction period. To address the above issues, a virtual test was carried out [31]. We established an interactive intelligent driving simulation platform in a virtual reality environment, as shown in Fig.…”