Sciweavers

75 search results - page 3 / 15
» Features for Recognition: Viewpoint Invariance for Non-Plana...
Sort
View
ACIVS
2006
Springer
13 years 11 months ago
Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform
Scene understanding is an important problem in intelligent robotics. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the...
Seung-Bin Im, Sung-Bae Cho
ACCV
2007
Springer
14 years 1 months ago
Viewpoint Insensitive Action Recognition Using Envelop Shape
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...
Feiyue Huang, Guangyou Xu
ICMCS
2006
IEEE
111views Multimedia» more  ICMCS 2006»
14 years 1 months ago
Sign Language Recognition from Homography
It is difficult to recognize sign language in different viewpoint. The HMM method is hindered by the difficulty of extracting view invariant features. The general template matchin...
Qi Wang, Xilin Chen, Chunli Wang, Wen Gao
ICPR
2008
IEEE
14 years 8 months ago
Illumination invariants based on Markov random fields
We propose textural features, which are invariant to illumination spectrum and extremely robust to illumination direction. They require only a single training image per texture an...
Pavel Vacha, Michal Haindl
BMVC
2010
13 years 5 months ago
Live Feature Clustering in Video Using Appearance and 3D Geometry
We present a method for live grouping of feature points into persistent 3D clusters as a single camera browses a static scene, with no additional assumptions, training or infrastr...
Adrien Angeli, Andrew Davison