Robust vehicles extraction in a video-based intelligent transportation systems

With the increase of vehicle possession, video-based intelligent transportation systems have been of major importance for enforcing traffic management policies. We propose a real-time and robust method for detecting vehicles from a sequence of traffic images taken by a single roadside mounted camera. The proposed algorithm includes three stages: first, extract moving object region from the current input image by the background subtraction method, second, eliminate moving cast shadow which is caused by moving vehicle, and finally, detect the vehicle so that there can be a unique object associated with each vehicle. The proposed method has been tested on a number of monocular traffic-image sequences and the experimental results on the real-world videos show that the algorithm is effective and real-time. The correct rate of vehicle detection is higher than 93 percent, independent of environmental conditions.

I. Introduction

In recent years, the advent of Intelligent Transportation Systems (ITS) has significantly enhanced the ability to alleviate congestion and augment the quality of vehicular flow. Aiming at the advanced traffic management systems for online surveillance and detailed information gathering on traffic conditions, techniques from image analysis and computer vision can be applied to traffic video analysis, such as vehicle counting, vehicle classification and queue detection.