Sciweavers

5695 search results - page 773 / 1139
» Using Many Cameras as One
Sort
View
CVPR
2003
IEEE
16 years 8 months ago
Evaluation of Local Models of Dynamic Backgrounds
Background subtraction is the first step of many video surveillance applications. What is considered background varies by application, and may include regular, systematic, or comp...
Robert Pless, John Larson, Scott Siebers, Ben West...
CVPR
2005
IEEE
16 years 8 months ago
Learning Spatiotemporal T-Junctions for Occlusion Detection
The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly stro...
Nicholas Apostoloff, Andrew W. Fitzgibbon
CVPR
2006
IEEE
16 years 8 months ago
Shape from Shading: Recognizing the Mountains through a Global View
Resolving local ambiguities is an important issue for shape from shading (SFS). Pixel ambiguities of SFS can be eliminated by propagation approaches. However, patch ambiguities st...
Qihui Zhu, Jianbo Shi
CVPR
2007
IEEE
16 years 8 months ago
Discovery of Collocation Patterns: from Visual Words to Visual Phrases
A visual word lexicon can be constructed by clustering primitive visual features, and a visual object can be described by a set of visual words. Such a "bag-of-words" re...
Junsong Yuan, Ying Wu, Ming Yang
CVPR
2008
IEEE
16 years 8 months ago
A unified framework for generalized Linear Discriminant Analysis
Linear Discriminant Analysis (LDA) is one of the wellknown methods for supervised dimensionality reduction. Over the years, many LDA-based algorithms have been developed to cope w...
Shuiwang Ji, Jieping Ye