Vehicle Trajectory Extraction in Traffic Scene Based on Monocular Vision

Abstract

Accurately extracting the trajectory information of multiple vehicles in urban traffic videos is of great significance in applications. It can help analyze and predict drivers’ behavior, count road flow, and restore accident scenarios. However, due to the complexity of the interaction between vehicles and the environment, it is still a challenging problem to accurately extract the trajectory of multi-target vehicles in urban traffic scenes, which often requires the assistance of a variety of different devices, which increases the practicality and difficulty of application. A method is proposed based on the combination of detection and tracking. This method only needs to use a video stream captured by a fixed panoramic camera and the coordinate information of several feature points in the scene to extract the speed and trajectory information of the vehicle in the scene. Different optimization methods are used in each link to reduce errors, and build a simulation environment for the test scenario, reconstruct and verify the extracted trajectory information in the simulation environment. Experiments have proved that the effect of the method is basically satisfactory. It has the advantages of fewer constraints, convenient deployment, and accurate restoration while ensuring a certain real-time performance, which has practical engineering significance.