Automatic Extraction of Multi-Vehicle Trajectory Based on Traffic Videotaping from Quadcopter Model

Abstract

This dissertation proposes a new approach for vehicular trajectory detecting. A radio-controlled quadcopter is used to shoot live traffic flow videos which can be flexible enough to meet the requirements of various road conditions. A self-developed software is created to analyze traffic videos efficiently, which can extract the coordinate of each vehicle from the video and draw the trajectories of those vehicles automatically. The system only produces a relatively small bias, which is allowed in the practical field of traffic engineering. The proposed detection system can not only get the trajectory of vehicle conveniently, but also provide an easy way to collect the data on the velocity and the acceleration of vehicles and, even, set a foundation for driving behavior monitoring and analysis on the roads.