Multi-Camera Collaborative Network Experimental Study Design of Video Surveillance System for Violated Vehicles Identification

Abstract

In this paper, we propose an experimental study of multi-camera collaborative network for surveillance the highway traffic turn in real life scenario, the target of surveillance based offline video processing is capturing the violated vehicles that driving violated paths in many cases specified by user-defined rules. Best topology of the experiment zone is considered and covered by four pillars; each has two (fixed and motorized) cameras that casing the entire specific effective field of view. As to author knowledge, there is no such available experiment, and hence, it could serve researchers that interested in. However, the experiment is done for around 180 recorded hours for 8 videos during 9 days, each video for one camera. It is designed based on the collaborative cameras principle for intelligent video surveillance systems and the outcomes show that the surveillance and the tracking of violated vehicles have been successes in most user-defined rules cases for more than 90 % cases.