Sciweavers

36 search results - page 4 / 8
» Learning on lie groups for invariant detection and tracking
Sort
View
CVIU
2008
229views more  CVIU 2008»
13 years 7 months ago
Estimating pedestrian counts in groups
The goal of this work is to provide a system which can aid in monitoring crowded urban environments, which often contain tight groups of people. In this paper, we consider the pro...
Prahlad Kilambi, Evan Ribnick, Ajay J. Joshi, Osam...
EMMCVPR
2005
Springer
14 years 1 months ago
Segmentation Informed by Manifold Learning
In many biomedical imaging applications, video sequences are captured with low resolution and low contrast challenging conditions in which to detect, segment, or track features. Wh...
Qilong Zhang, Richard Souvenir, Robert Pless
IJCV
2007
363views more  IJCV 2007»
13 years 7 months ago
Image Analysis and Reconstruction using a Wavelet Transform Constructed from a Reducible Representation of the Euclidean Motion
Abstract. Inspired by the early visual system of many mammalians we consider the construction of-and reconstruction from- an orientation score Uf : R2 ×S1 → C as a local orienta...
Remco Duits, Michael Felsberg, Gösta H. Granl...
PAMI
2007
245views more  PAMI 2007»
13 years 7 months ago
Tracking People by Learning Their Appearance
—An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of p...
Deva Ramanan, David A. Forsyth, Andrew Zisserman
ICPR
2008
IEEE
14 years 8 months ago
Detecting global motion patterns in complex videos
Learning dominant motion patterns or activities from a video is an important surveillance problem, especially in crowded environments like markets, subways etc., where tracking of...
Min Hu, Mubarak Shah, Saad Ali