Sciweavers

80 search results - page 14 / 16
» Using scene features to improve wide-area video surveillance
Sort
View
ICIP
2006
IEEE
14 years 8 months ago
Prioritized Sequential 3D Reconstruction in Video Sequences with Multiple Motions
In this study, an algorithm is proposed to solve the multi-frame structure from motion (MFSfM) problem for monocular video sequences in dynamic scenes. The algorithm uses the epip...
Evren Imre, Sebastian Knorr, A. Aydin Alatan, Thom...
ICPR
2010
IEEE
13 years 6 months ago
Fast Odometry Integration in Local Bundle Adjustment-Based Visual SLAM
The Simultaneous Localisation And Mapping (SLAM) for a camera moving in a scene is a long term research problem. Here we improve a recent visual SLAM which applies Local Bundle Ad...
Alexandre Eudes, Maxime Lhuillier, Sylvie Naudet-C...
CVPR
2007
IEEE
14 years 8 months ago
Unsupervised Activity Perception by Hierarchical Bayesian Models
We propose a novel unsupervised learning framework for activity perception. To understand activities in complicated scenes from visual data, we propose a hierarchical Bayesian mod...
Xiaogang Wang, Xiaoxu Ma, Eric Grimson
ICMCS
2005
IEEE
179views Multimedia» more  ICMCS 2005»
13 years 12 months ago
Estimation of Speaking Speed for Faster Face Detection in Video-Footage
We previously reported a face detection system based on color segmentation using HSV. It was shown that the color is more effective than other colors not only in accurate segmenta...
Osamu Ikeda
CIVR
2007
Springer
195views Image Analysis» more  CIVR 2007»
14 years 13 days ago
Towards optimal bag-of-features for object categorization and semantic video retrieval
Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as ...
Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang 0003