This paper describes an object matching system which is able to extract objects of interest from outdoor scenes and match them. Our application (in the domain of IVHS) involves measuring the average travel time in a road network. The extraction of the object of interest is performed by fusing multiple cues including motion, color, edges, and model information. Two objects extracted from images captured by two independent cameras at different times are then matched to evaluate their similarity. Color indexing based on histogram matching is used to avoid matching all possible pairs of objects. To resolve ambiguities, further matching is done by measuring the Hausdorff distance between two sets of edge points. The object matching system was given 2 sets of 40 vehicles. It was able to identify 23 of the 30 correct matches and all the false matches were rejected. Color indexing reduced the number of candidates for a match from 40 to 2. This matching accuracy is adequate to obtain a reliable estimate of the average travel time.>

The purpose of object matching is to decide the similarity between two objects. This paper introduces 24 possible distance measures based on the Hausdorff distance between two point sets. These measures can be used to match two sets of edge points extracted from any two objects. Based on experiments on synthetic images containing various levels of noise, the authors determined that one of these distance measures, called the modified Hausdorff distance (MHD) has the best performance for object matching. The advantages of MHD ever other distances are also demonstrated on several edge snaps of objects extracted from real images.

A new approach to the extraction of the contour of a moving object is presented. The method is based on the integration of a motion segmentation technique using image substraction and a color segmentation technique based on the split-and-merge algorithm. The advantages of this method are: it can detect large moving objects and extract their boundaries; the background can be arbitrarily complicated and contain many non-moving objects occluded by the moving object; and it requires only three image frames that need not be consecutive, provided that the object is entirely contained in each of the three frames. The method is applied to a large number of color images of vehicles moving on a road and a highway ramp. The results are promising. The moving object boundaries are correctly extracted in 66 out of 73 test image sequences. The authors describe how this contour can be used as an input to a recognition system that classifies the vehicles into five generic categories. Of the 73 vehicles, 67 are correctly classified.>