Road traffic and traffic congestion is major problem worldwide. This system uses video surveillance as it comes as the most economical technique for monitoring road traffic. Researchers have worked on different methodologies for video processing. The problems in existing methods are occlusions and variable lightening conditions. Also recent research on Indian roads proved that current image processing systems shows 55% median error on vehicle count. Proposed system looks into both day time as well as night time conditions to monitor traffic. Also it provides vehicle classification, traffic density, vehicle count, license plate detection and Incident detection. It combines many existing methods like background subtraction, kalman filter, 2-linesalgorithm, headlight detection, license plate detection algorithm The proposed system implements 2-lines algorithm and vehicle classification using kalman filter for day time and headlight based detection for night time which helps in successful tracking of vehicles. The license plate detection uses Edge detection, Gaussian Analysis, Feature extraction and character recognition which makes it robust to detect license plates in both day and night conditions. Median error was reduces to 11% by use of 2-lines algorithm. Vehicle classification using kalman filters gives accuracy of 82%. The proposed system will give median error less than 10% and accuracy of more than 90% in counting and classifying vehicles. The proposed system will be tested on MIT traffic data sets, MediaLab LPR database. (C) 2016 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the Organizing Committee of ICCCV 2016
