Sciweavers

942 search results - page 62 / 189
» Structure From Motion for Scenes Without Features
Sort
View
WACV
2008
IEEE
15 years 4 months ago
Segmentation of Salient Regions in Outdoor Scenes Using Imagery and 3-D Data
This paper describes a segmentation method for extracting salient regions in outdoor scenes using both 3-D laser scans and imagery information. Our approach is a bottomup attentiv...
Gunhee Kim, Daniel F. Huber, Martial Hebert
99
Voted
CVPR
2007
IEEE
16 years 5 days ago
Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model
We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
Liang Wang, David Suter
ICPR
2006
IEEE
15 years 11 months ago
Accurate 3-D Motion Tracking with an Application to Super-Resolution
Many of the existing image processing applications, in particular the construction of super-resolution videos, require an accurate high-speed motion tracking algorithm. This paper...
Kin-hong Wong, Michael Ming-Yuen Chang, Siu-Hang O...
ICCV
2007
IEEE
16 years 3 days ago
Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes
We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...
CVPR
2003
IEEE
16 years 5 days ago
Finding and Tracking People from the Bottom Up
We describe a tracker that can track moving people in long sequences without manual initialization. Moving people are modeled with the assumption that, while configuration can var...
Deva Ramanan, David A. Forsyth