Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.169
For the growing number of accidents caused by poor visibility, visibility measurement which can alert drivers and inform traffic division managements when poor visibility occurs is a key parameter in driving assistance system. This paper is to implement a visibility measurement system that based on traffic video-surveillance system can both detect fog and estimate visibility distance. We propose a method to detect visibility distance by contrast of road surface with distance information. The method integrates the targets’ contrast and curve fitting to get visibility distance. The system is operative in every kind of weather in day-time. The experimental results in practical are uniform to human perception.
visibility detection, objects edge, contrast threshold, curve fitting
C. Qi-mei, C. Zhao-zheng and L. Jia, "Real-Time Video Detection of Road Visibility Conditions," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 472-476.