Intelligent traffic analysis system for Indian road conditions

Abstract

Now-a-days, security and surveillance has become an integral part of our everyday life. There is a need for an Intelligent Surveillance systems for the being developed Smart Cities to ensure safety at all levels. The Objective of this paper is to demonstrate an Integrated framework for Vehicle detection and classification from real-time video captured from the road traffic. This work proposed a complete framework for Surveillance System for Indian smart cities with an aim to improve the security and surveillance of vehicles in varying weather conditions. To realize road traffic flow surveillance under various environments which contain poor visibility conditions, this paper provides a solution to extract the required information from surveillance video under different weather condition like day, night and rain. Also proposed system will dynamically choose the respective algorithm based on identified nature of the weather. In Vehicle count and classification, algorithm which is used based on image segmentation using a Laplacian of Gaussian edge detector (LoG), morphological filtering of the edge map objects and classification into small, medium and large vehicles on the basis of size using a nearest centroid minimum distance classifier. The proposed approach can be used for both stationary and fast moving traffic in contrast to motion detection based approaches. The algorithm was implemented in Python and average detection and classification accuracies of 96.0% and 89.4% respectively were achieved for fast moving traffic, while for slow moving traffic, 82.1% and 83.8% respectively were achieved.