We present an algorithm for segmentation of traffic scenes that distinguishes moving objects from cast shadows. Three image features at each pixel site are considered: brightness,...
Ivana Mikic, Pamela C. Cosman, Greg T. Kogut, Moha...
This paper presents a new method for the incremental integration of overlapped range images. It is assumed thatframe transformations between all pairs of views can be reliably com...
In this paper we describe a voxel-based 3-D reconstruction technique from multiple calibrated camera views that makes explicit use of the finite size footprint of a voxel when pr...
Eckehard G. Steinbach, Bernd Girod, Peter Eisert, ...
The use of local features in computer vision has shown to be promising. Local features have several advantages including invariance to image transformations, independence of the ba...
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such...