A Robust Method for Detecting Vehicle Positions and Their Movements Even in Bad Weather Using Infrared Thermal Images

Abstract

We propose a method for detecting vehicle positions and their movements by using thermal images obtained through an infrared thermography camera. Our method specifies the area of moving vehicles based on the variations of pixel values, i.e. the standard deviations of pixel values along the time direction of spatio-temporal images. It also specifies vehicle positions by applying the pattern recognition algorithm which uses Haar-like features per frame of the images. The results of our experiments show that the information about both vehicle positions and their movements can be obtained by combining those two kinds of detection. Our method has the advantage of distinguishing between smooth traffic flows and heavy ones. In addition, there is a possibility that traffic accidents, vehicle troubles, and illegal parking can be detected with our method. We also expect to realize a robust automatic monitoring for road traffic around the clock even in changeable weather with our method of using thermal images.