A Study of the Retinex-based Vehicles Color Resolution in Low-lighting RoadA Study of the Retinex-based Vehicles Color Resolution in Low-lighting Road Han-shuang Li 1, Yuan FANG 2*, Zhuang-tu Guo 1 , Wei-zhen Wang 3 , Nian-yu Zou 1 (1:School of Information Science and Engineering, Dalian Polytechnic University, China 2:School of Engineering Practice and Innovation-Entrepreneurship Education, Dalian Polytechnic University, China 3: Human Factors and Intelligent Design Research Center, Dalian Polytechnic University, China)
Abstract—In low-lighting road environments, the human eyesight has been limited in discriminating distorted vehicle colors, and often produces errors under the influence of complex lighting sources. To deal with the color distortion problem, Multiscale Retinex Algorithm with Color Recovery method is used to recover the image color, which is used to improve the accuracy of the machine in recognizing the vehicle color, and then human-computer comparison experiments are carried out to analyze the experimental results. The experimental results show that after the image processing, the computer can distinguish 97.33% of the colors of low-light vehicles. Keywords-Vehicles color recognition; image processing; human-computer comparison；low lighting |