Content_based classification of traffic videos using symbolic features

In this paper, we propose a symbolic approach for classification of traffic videos based on their content. We propose to represent a traffic video by an interval valued features. Unlike the conventional methods, the interval valued feature representation is able to preserve the variations existing among the extracted features of a traffic video. Based on the proposed symbolic representation, we present a method of classifying traffic videos. The proposed classification method makes use of symbolic similarity computation and dissimilarity computation to classify the traffic videos into light, medium, and heavy traffic congestion. An experimentation is carried out on a benchmark traffic video database. Experimental results reveal the ability of the proposed model for classification of traffic videos based on their content.