Real-time Classification and Counting of Vehicles from CCTV Videos for Traffic Surveillance Applications

Abstract

Traffic Analysis has been a problem that city planners have dealt with for years. Smarter ways are being developed to analyze traffic and streamline the process. Analysis of traffic may account for the number of vehicles in an area per arbitrary time and the class of vehicles. People have designed such mechanisms for decades now but most of them involve use of sensors to detect the vehicles i.e., a couple of proximity sensors to calculate the direction of the moving vehicle and to keep the vehicle count. Even though over time these systems have matured and are highly effective, they are not very budget friendly. The problem is such systems require maintenance and periodic calibration. Therefore, this project has proposed a vision-based vehicle counting and classification system. The system involves capturing of frames from the video to perform background subtraction in order detect and count the vehicles using Gaussian Mixture Model (GMM) background subtraction then it classifies the vehicles by comparing the contour areas to the assumed values. The substantial contribution of the work is the comparison of two classification methods. Classification has been implemented using Contour Comparison (CC) as well as Bag of Features (BoF) method.