179 search results - page 25 / 36 » Adaptive Background Mixture Models for Real-Time Tracking |
168
click to vote
IROS
2007
IEEE
16 years 4 days ago
2007
IEEE
Abstract— We present the Binocular Sparse Feature Segmentation (BSFS) algorithm for vision-based person following with a mobile robot. BSFS uses Lucas-Kanade feature detection an...
208
click to vote
CVPR
2005
IEEE
15 years 11 months ago
2005
IEEE
The paper proposes a method to keep the tracker robust to background clutters by online selecting discriminative features from a large feature space. Furthermore, the feature sele...
177
click to vote
CVPR
2005
IEEE
16 years 7 months ago
2005
IEEE
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
184
click to vote
FGR
2000
IEEE
15 years 10 months ago
2000
IEEE
A computer vision system for tracking multiple people in relatively unconstrained environments is described. Trackerformed at three levels of abstraction: regions, people and grou...
173
click to vote
BMVC
2010
15 years 3 months ago
2010
Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...