SEGMENTATION AND MATCHING OF VEHICLES IN ROAD IMAGES

The use of image processing for the segmentation and matching of vehicles in road images is described. Two cameras sense images of the road at different sites in order to estimate the travel time required for a vehicle to travel between two points in a road network. The color images are digitized and analyzed so that moving vehicles can be extracted and segmented into identifiable parts such as the roof, hood, trunk, sides, and wheels. These parts and their attributes such as shape and color are then used to match the vehicles observed from the two different sites. A good match implies that the same vehicle has been sensed by both cameras.