Multi-Camera Vehicle Tracking Using Edge Computing and Low-Power Communication

Abstract

Typical approaches to visual vehicle tracking across large area require several cameras and complex algorithms to detect, identify and track the vehicle route. Due to memory requirements, computational complexity and hardware constrains, the video images are transmitted to a dedicated workstation equipped with powerful graphic processing units. However, this requires large volumes of data to be transmitted and may raise privacy issues. This paper presents a dedicated deep learning detection and tracking algorithms that can be run directly on the camera’s embedded system. This method significantly reduces the stream of data from the cameras, reduces the required communication bandwidth and expands the range of communication technologies to use. Consequently, it allows to use short-range radio communication to transmit vehicle-related information directly between the cameras, and implement the multi-camera tracking directly in the cameras. The proposed solution includes detection and tracking algorithms, and a dedicated low-power short-range communication for multi-target multi-camera tracking systems that can be applied in parking and intersection scenarios. System components were evaluated in various scenarios including different environmental and weather conditions.

Recent Trends on IoT Systems for Traffic Monitoring and for Autonomous and Connected Vehicles

“…The special issue is characterized by 11 original research papers [1][2][3][4][5][6][7][8][9][10][11]. The first paper [1], "Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction", is written by M. V. Peppa, T. Komar, Wen Xiao, P. James, C. Robson, Jin Xing, and S. Barr from the University of Newcastle, UK; and the University of Melbourne, Australia.…”

“…The special issue is characterized by 11 original research papers [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 ].…”

Aerial Video Trackers Review

“…As the sensing field of a single UAV is limited and the 3D feature information of the target and scene is lost, it is necessary to cooperatively utilize multiple UAVs. However, in multiple-UAV cooperative tracking, since the information surveillance camera is discrete, there is a lack of information for the rapid integration mechanism among multiple cameras, and multicamera coordination is necessary for efficient target tracking [ 92 , 93 ]. Thus, the problem of cooperative path planning [ 94 ] is also encountered.…”

Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction

“…However, the aforementioned sensor infrastructure requires a particular installation and can be relatively costly for traffic management bureaus when installed at multiple locations across an entire city or in hundreds of taxis. An alternative low-cost [ 2 ] and widely available sensor infrastructure can be closed-circuit television (CCTV) systems which have been primarily employed for traffic surveillance, vehicle detection (e.g., automatic number plate recognition (ANPR) systems; [ 20 ]) and tracking [ 21 ] as well as event recognition applications [ 22 , 23 , 24 ], but not explicitly used for traffic prediction. Compared to studies using loop detectors and GNSS sensors, relatively little research on prediction has been conducted with CCTV datasets in recent years (e.g., in [ 25 ]).…”