An improved Otsu image segmentation algorithm for path mark detection under variable illumination

Abstract

Variable illumination is a difficult problem for path mark detection of high-speed vision-based vehicle. It is vitally important to adopt an effective real-time method to solve the problem. In this paper a new grayscale image automatic thresholding algorithm is presented to segment the path mark from the image under different illumination conditions. The new method aims at enhancing its real-time performance which derives from Otsu automatic thresholding algorithm The experimental results show that the new improved algorithm dramatically reduces the operating time in image segmentation while ensures the final image segmentation quality.