Vehicle Detection and Classification for Cluttered Urban Intersection

Abstract

As more vehicles continuously appear on our roads by the daycausing congestion and accidents. A traffic monitoring system capable of detecting , counting and classifying the passed vehicles is needed to provide in advance information to relevant authoritie s on the road traffic demand. Background subtraction and kalman filter algorithm are used to detect and track individual vehicles throughout the detection zone. The detected vehicles blob-area is used to trigger the segmentationunit which inturn extracts the vehicle while at a point closest to the camera. Finally, both geometric and appearance features of the segmented vehicles are passed to the LDA classifier for proper categorisation. The system achieved a high counting performance of 97.37% with corres ponding classification rate of 87.82 %