Certain soft computing techniques for detecting and tracking of moving vehicles

Abstract

Deployment of effective surveillance and security measures is important in today s scenario The system designed to handle the surveillance must be able to provide access and track the movement of different types of vehicles and people entering the secured premises to avoid any mishap There are many existing approaches which are used for tracking objects Edge matching Divide and Conquer search Gradient matching Histograms of receptive field responses Pose clustering Scale Invariant Feature Transform Speeded Up Robust Features are some of the approaches applied All these approaches are either appearance based or feature based methods They have certain drawbacks in one way or the other when it comes to real time application So there is a need for creating a new system that extracts and tracks objects using blob extraction method In the first phase of the work the thesis proposes a modified approach for car detection and classification to a whole new level by devising a system that takes the video of a vehicle as input detects and classifies the vehicle based on its make and model It takes into consideration four prominent features namely Logo of vehicle its number plate colour and shape