Analysis of Image Enhancement Methods for Outdoor-Applications

Abstract

For autonomous robots and driver assistance systems it is necessary to react adequately to sudden changes in the surrounding area. Camera-systems are often affected by environmental influences like sun light, shades or sunreflecting surfaces which makes it hard to obtain well exposed images for further utilization. In this paper, two algorithms for image enhancement are compared in several test scenes to examine the ir performance with regard to contrast enhancement and computing time. In comparison one off-the-shelf high dynamic range camera is tested, too. The results from this study show that histogram equalization works significantly faster than the successive mean quantization transform. Both algorithms are appropriate to be used for autonomous robots and driver assistance systems if the camera is incapable to high dynamic range images.