Authors: Li Bai William Tompkinson Yan Wang
Publish Date: 2005/05/20
Volume: 7, Issue: 4, Pages: 365-372
Abstract
This paper describes an application of computer vision techniques to road surveillance It reports on a project undertaken in collaboration with the Research and Innovation group at the Ordnance Survey The project aims to produce a system that detects and tracks vehicles in real traffic scenes to generate meaningful parameters for use in traffic management The system has now been implemented using two different approaches a featurebased approach that detects and groups corner features in a scene into potential vehicle objects and an appearancebased approach that trains a cascade of classifiers to learn the appearances of vehicles as an arrangement of a set of predefined simple Haar features Potential vehicles detected are then tracked through an image sequence using the Kalman filter motion tracker Experimental results of the algorithms are presented in this paper
Keywords: