Sciweavers

2235 search results - page 134 / 447
» Robot Localization Using a Computer Vision Sextant
Sort
View
183
Voted
CVPR
2012
IEEE
13 years 5 months ago
Background modeling using adaptive pixelwise kernel variances in a hybrid feature space
Recent work on background subtraction has shown developments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussi...
Manjunath Narayana, Allen R. Hanson, Erik G. Learn...
ICCV
2011
IEEE
14 years 2 months ago
Optimal Landmark Detection using Shape Models and Branch and Bound
Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
Brian Amberg, Thomas Vetter
ACCV
2010
Springer
14 years 9 months ago
Finding Human Poses in Videos Using Concurrent Matching and Segmentation
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
Hao Jiang
150
Voted
CVPR
2012
IEEE
13 years 5 months ago
Multi-view hair capture using orientation fields
Reconstructing realistic 3D hair geometry is challenging due to omnipresent occlusions, complex discontinuities and specular appearance. To address these challenges, we propose a ...
Linjie Luo, Hao Li, Sylvain Paris, Thibaut Weise, ...
CVPR
2012
IEEE
13 years 5 months ago
Road network extraction from airborne LiDAR data using scene context
We presented a novel procedure to extract ground road networks from airborne LiDAR data. First point clouds were separated into ground and non-ground parts, and ground roads were ...
Jiaping Zhao, Suya You