We develop a local image-correspondence algorithm which performs well near occluding boundaries. Unlike traditional robust methods, our method can find correspondences when the on...
We use the color cooccurrence histogram (CH) for recognizing objects in images. The color CH keeps track of the number of pairs of certain colored pixels that occur at certain sep...
This paper proposes a novel method for matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem: p...
Flat appearance-based systems, which combine clever image representations with standard classifiers, might be the most effective way to recognize objects using current technologie...
This paper presents a novel statistical shape model that can be used to detect and localise feature points of a class of objects in images. The shape model is inspired from the 3D...