Wrong Way Vehicle Detection in Single and Double Lane

Wrong-way driving is one of the primary causes traffic jams and accidents globally. It possible to identify vehicles going wrong direction, which lessens congestion. Surveillance footage has become an important source data due accessibility less priced cameras expanding use real-time management systems. In this paper, we propose a technique for automatically identifying automobiles moving against traffic. Our system uses You Only Look Once (CNN) algorithm recognize track from video inputs centroid tracking method determine each vehicle's orientation inside given region interest (ROI) in order traveling direction. functions three steps. The Deep sort particularly good detecting objects, can effectively monitor direction travel. Experiments with variety films show that suggested detect wrong-way lighting weather scenarios. interface quite simple easy use.