A Thermal Image Recognition Method for Detecting Vehicle Positions and Their Movements Using both Spatio-Temporal Processing and Pattern Recognition

Abstract

We propose a method for recognizing vehicle positions and their movements by using thermal images. Our method specifies the area of moving vehicles based on 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 to every frame of 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. We expect to realize a robust automatic monitoring for road traffic around the clock even in changeable weather with our method of using thermal images.