Sciweavers

430 search results - page 75 / 86
» 3D Gait Recognition Using Multiple Cameras
Sort
View
ICPR
2006
IEEE
15 years 10 months ago
Detection-Assisted Initialization, Adaptation and Fusion of Body Region Trackers for Robust Multiperson Tracking
In this paper, we present a system for simultaneous tracking of multiple persons in a smartroom using multiple cameras. Robust person tracks are created, continuously adapted, and...
Keni Bernardin, Alexander Elbs, Rainer Stiefelhage...
CVPR
2004
IEEE
15 years 11 months ago
Video Repairing: Inference of Foreground and Background under Severe Occlusion
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recov...
Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, Chi-Keung Tan...
ASSETS
2006
ACM
15 years 3 months ago
Lecture adaptation for students with visual disabilities using high-resolution photography
Visual content in lectures can be enhanced for use by students with visual disabilities by using high-resolution digital still cameras. This paper presents a system which uses two...
Gregory Hughes, Peter Robinson
CVIU
2006
171views more  CVIU 2006»
14 years 9 months ago
Free viewpoint action recognition using motion history volumes
Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understand...
Daniel Weinland, Rémi Ronfard, Edmond Boyer
ICCV
2009
IEEE
14 years 7 months ago
Fast realistic multi-action recognition using mined dense spatio-temporal features
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
Andrew Gilbert, John Illingworth, Richard Bowden