Video-based pedestrian crossing the cordon detection system
Jianming Cui, Xiaojian Li, Xiaojun Zhang, Wenxiu Kong · 2020
In order to strengthen protection of personal safety and important places, this paper designs a pedestrian crossing the cordon detection system to process the image information captured by the camera intelligently in real time. Firstly, Gaussian mixture model is established to detect pedestrians. The detected target image is processed and initialized. Then target information is transferred to the Camshift algorithm for tracking, which solves the problem of manually selecting tracking targets. The Camshift algorithm combined with the Kalman filter which has update and prediction functions can overcome tracking failure due to interference and occlusion especially in the dark environment. On this basis, system can achieve crossing the cordon warning and information reporting to ensure the safety of people and important places. This system can be used in mines, culverts, tunnels and other dangerous and dark areas for safety protection, and has great practical application value.