An automatic image recognition system for winter road surface condition classification

This paper investigates the feasibility of classifying winter road surface conditions using images from low cost cameras mounted on regular vehicles. RGB features along with gradients have been used as feature vectors. A Support Vector Machine (SVM) is trained using the extracted features and then used to classify the images into their respective categories. Different training schemes and their effect on the classification rate are also discussed along with the possibility of developing an automated winter road surface classification system in future.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Long Le,et al.  Road condition monitoring system based on a stereo camera , 2009, 2009 IEEE 5th International Conference on Intelligent Computer Communication and Processing.

[3]  Liping Fu,et al.  Comparison of Alternative Models for Road Surface Condition Classification , 2010 .

[4]  Mike Foedisch,et al.  Performance evaluation of color based road detection using neural nets and support vector machines , 2003, 32nd Applied Imagery Pattern Recognition Workshop, 2003. Proceedings..

[5]  Liu Shu The Machine Vision and Its Application , 2000 .