Cooperative multi-camera vehicle tracking and traffic surveillance with edge artificial intelligence and representation learning

Hao (Frank) Yang, Jiarui Cai, Chenxi Liu, Ruimin Ke, Yinhai Wang

Abstract: Highlights•An edge-server cooperative IoT workflow for multi-camera vehicle tracking and traffic perception is presented, extensively evaluated and real implemented for extracting traffic information for multiple public agencies.•A multi-task deep feature extraction workflow is proposed and optimized for the edge devices, including vehicle detection, tracking and objects’ representation selection.•To match the edge inputs precisely, a novel clip-based deep vehicle Re-ID model, with the hierarchical feature extraction and fusion mechanism is proposed and integrated into the cooperative perception workflow.•Besides, to extract the accurate information from various camera pairs with differing Re-ID accuracies, a precision-aware kernel density estimator is integrated in the proposed system instead of using brute-force sampling approach.•The cost of the proposed cooperative multi-caemra perception system is significantly reduced on the server hardware, including the GPUs (only with 25% cost) and data storage (with less than 10% of original data volume), together with the communication bandwidth.

External IDs:doi:10.1016/j.trc.2022.103982