116 search results - page 4 / 24 » Towards using multiple cues for robust object recognition |
ICVGIP
2008
13 years 7 months ago
2008
Recognition of object categories from their images is extremely challenging due to the large intra-class variations, and variations in pose, illumination and scale, in addition to...
ICCV
2005
IEEE
14 years 7 months ago
2005
IEEE
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
CVPR
1998
IEEE
14 years 7 months ago
1998
IEEE
We present a 3-D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matchin...
CVPR
2007
IEEE
14 years 7 months ago
2007
IEEE
We consider the problem of detecting and accounting for the presence of occluders in a 3D scene based on silhouette cues in video streams obtained from multiple, calibrated views....
ECCV
2002
Springer
14 years 7 months ago
2002
Springer
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...