This paper presents an new framework for homographybased analysis of pedestrian-vehicle activity in crowded scenes. Planar homography constraint is exploited to extract view-invar...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
This paper presents a realtime, incremental multibody visual SLAM system that allows choosing between full 3D reconstruction or simply tracking of the moving objects. Motion recon...
Copyright 2004 IEEE. Published in Conference on Computer Vision and Pattern Recognition (CVPR-2004), June 27 - July 2, 2004, Washington DC. Personal use of this material is permit...