Vehicle Objects Detection of Video Images Based on Gray-Scale Characteristics

Abstract

An integrated approach to detect moving vehicles, by using of gray-scale images with complicated background, applied in intelligent traffic surveillance is proposed. In this paper, firstly, color images are converted to gray-scale images in the images pre-processing. Then the methods of frame differencing and selective background updating are utilized to generate initial background and update current background. Furthermore, every processed image is filtered by fast median filter to remove noise caused by vidicon movement or background jitter. When the current background is obtained, moving objects in the video can be detected effectively by background frame differencing complemented with inter-frame differencing. Finally, morphological filtering is used for decreasing accumulative errors. The experimental result shows this approach can detect moving vehicles effectively in real time, which is suitable for video traffic surveillance system.