116 search results - page 2 / 24 » Towards using multiple cues for robust object recognition |
PAMI
2008
13 years 4 months ago
2008
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 po...
ICRA
2008
IEEE
13 years 11 months ago
2008
IEEE
— Integrating information coming from different sensors is a fundamental capability for autonomous robots. For complex tasks like topological localization, it would be desirable ...
HUMO
2007
Springer
13 years 11 months ago
2007
Springer
In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in...
CVPR
2010
IEEE
14 years 29 days ago
2010
IEEE
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person’s activities. An egocentric camera as worn on the body enjoys many...
ICCV
2001
IEEE
14 years 6 months ago
2001
IEEE
Robust, real-time tracking of objects from visual data requires probabilistic fusion of multiple visual cues. Previous approaches have either been ad hoc or relied on a Bayesian n...