A Robust Traffic-Aware City-Scale Multi-Camera Vehicle Tracking Of Vehicles

Abstract

Multi-Target Multi-Camera Tracking (MTMC) has an immense domain of Intelligent Traffic Surveillance System applications. Multifarious tasks manage to apply MTMC trackings, such as crowd analysis and city-scale traffic management. This paper describes our framework using spatial constraints for the Task of the Track 1 multi-camera vehicle tracking in the 2022 AI City Challenge. The framework includes single-camera detection and tracking, vehicle re-identification, and multi-camera track matching. To improve the system’s accuracy, we proposed Region-Aware for the precision of vehicle detection and tracking, leading to the effective service of vehicle re-identification models to extract targets and appearance features. We use Crossing-Aware for a tracker to utilize the rich feature to find the tracklets and operate trajectory matching for multi-camera tracklets connection. Finally, the Inter-Camera Matching generated the global IDs for vehicle trajectory. Our method acquired an IDF1 score of 0.8129 on the AI City 2022 Challenge Track 1 public leaderboard.