Anomaly Detection on Traffic Videos Based on Trajectory Simplification

detecting anomalies in the Traffic Control Systems(TCS) could be very useful for the accident analysis, faultdetection and other traffic-related topics. In this article wepropose a general framework for the trajectory-based anomalydetection, which is fast and reliable. Experimental results showthat the system could be used on a vast variety of camera typesand configurations. We have used a semi-supervised anomalydetection in the framework which learns from the trajectories of normal movements and detects the trajectories that does not fiton the trained model. The trajectories are simplified using a linesimplification algorithm to improve the performance whileincreasing robustness on the noisy inputs.

کلیدواژه ها:

Anomaly detection ، Trajectory ، Trajectory Simplification ، Semi-Supervise Anomaly Detection ، Traffic Control Systems