Vehicle detection and identification in an unconstrained environment
Lavanya Herle, Poonam Sharma · 2017 International Conference on Recent Innovations in Signal processing and Embedded Systems (RISE) · 2017
Detection and identification of vehicles in traffic surveillance videos is very important to automate the surveillance system and also to build an intelligent transportation system. In this paper a robust method to detect and identify vehicles is proposed which deals with problem like change in illumination. Background subtraction is done using both Gaussian Mixture Model and Visual Background Extractor and supports dynamic changes in background. Vehicles are detected by finding contours in the image frame. Vehicles are tracked by assigning unique ID for each vehicles. Distance between the centroid of detected vehicle and existing vehicles is calculated. If the distance is greater than threshold value then vehicle is considered to be arrived newly and a unique ID is assigned for further tracking. Otherwise, it is the vehicle will get the same ID as in previous frame. Detected vehicle is classified using Support Vector Machine in each frame and final decision is taken when the vehicle is about to exit from the scene.