Detection of Traffic and Road Condition Based on SVM and PHOW

To avoid the defects of physical detection methods, such as road spoiling, complex algorithms and equipment maintenance, SVM (Support Vector Machine) and PHOW (Pyramid Histogram of Words) are explored to detect the traffic and road condition. Experimental results show that the average accuracies go beyond 82.5% in the case of different weather. The proposed method can effectively classify 4 types of traffic and road condition images.