Sciweavers

1401 search results - page 4 / 281
» Probabilistic Object Tracking Using Multiple Features
Sort
View
ICIP
2005
IEEE
14 years 9 months ago
Off-line multiple object tracking using candidate selection and the Viterbi algorithm
This paper presents a probabilistic framework for off-line multiple object tracking. At each timestep, a small set of deterministic candidates is generated which is guaranteed to ...
Anil C. Kokaram, François Pitié, Roz...
ATAL
2006
Springer
13 years 11 months ago
Multi-model motion tracking under multiple team member actuators
Autonomous robots need to track objects. Object tracking relies on predefined robot motion and sensory models. Tracking is particularly challenging if the robots can actuate on th...
Yang Gu, Manuela M. Veloso
CVPR
2004
IEEE
14 years 9 months ago
A Probabilistic Framework for Combining Tracking Algorithms
For the past few years researches have been investigating enhancing tracking performance by combining several different tracking algorithms. We propose an analytically justified, ...
Ido Leichter, Michael Lindenbaum, Ehud Rivlin
ICCV
2005
IEEE
14 years 9 months ago
Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation
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...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
ICIP
2004
IEEE
14 years 9 months ago
A probabilistic cooperation between trackers of coupled objects
Much work has been done in the field of visual object tracking, yielding a wide range of trackers, including ones aimed for multiple objects. In many cases, there may be a couplin...
Ido Leichter, Michael Lindenbaum, Ehud Rivlin