Automatic isolation and classification of vehicles in a traffic video

Among the diverse applications of computer and communication technologies, Intelligent Transport System aids in simplifying transport problems. Its aim is to gather data and provide timely feedback to traffic managers (traffic policemen) and road users. The various problems involved in processing real-time traffic data has been addressed in several areas of research that includes vehicle detection, tracking and classification. This paper proposes a technique for isolation and classification of vehicles at an abstract level. The isolation technique aims at locating regions of interest (vehicles) within the image to be classified. Classification is performed in two categories. The first category is to identify the predominant color and the second is to classify the vehicle as light or heavy. The experimental results show an accuracy of 82% even for traffic video sequences involving complicated scenes.