Sciweavers

ICPR
2008
IEEE
15 years 22 days ago
Training sequential on-line boosting classifier for visual tracking
On-line boosting allows to adapt a trained classifier to changing environmental conditions or to use sequentially available training data. Yet, two important problems in the on-li...
Helmut Grabner, Horst Bischof, Jan Sochman, Jiri M...
ICPR
2008
IEEE
15 years 22 days ago
Hand posture recognition with co-training
As an emerging human-computer interaction approachvision based hand interaction is more natural and efficient. Howeverin order to achieve high accuracy, most of the existing hand ...
Yikai Fang, Jian Cheng, Jinqiao Wang, Kongqiao Wan...
ICPR
2008
IEEE
15 years 22 days ago
Recovering audio-to-video synchronization by audiovisual correlation analysis
Audio-to-video synchronization (AV-sync) may drift and is difficult to recover without dedicated human effort. In this work, we develop an interactive method to recover the drifte...
Yoichi Sato, Yuyu Liu
ICPR
2008
IEEE
15 years 22 days ago
A covariance-based method for dynamic background subtraction
Background subtraction in dynamic scenes is an important and challenging task. In this paper, we present a novel and effective method for dynamic background subtraction based on c...
Hongxun Yao, Shaohui Liu, Shengping Zhang, Wen Gao...
ICPR
2008
IEEE
15 years 22 days ago
Efficient triangulation based on 3D Euclidean optimization
This paper presents a method for triangulation of 3D points given their projections in two images. Recent results show that the triangulation mapping can be represented as a linea...
Klas Nordberg
ICPR
2008
IEEE
15 years 22 days ago
Efficient background modeling through incremental Support Vector Data Description
Background modeling is an essential and important part of many high-level video processing applications. Recently, the Support Vector Data Description (SVDD) has been introduced f...
Alireza Tavakkoli, Mircea Nicolescu, George Bebis,...
ICPR
2008
IEEE
15 years 22 days ago
Visual features with semantic combination using Bayesian network for a more effective image retrieval
In many vision problems, instead of having fully annotated training data, it is easier to obtain just a subset of data with annotations, because it is less restrictive for the use...
Sabine Barrat, Salvatore Tabbone
ICPR
2008
IEEE
15 years 22 days ago
Object detection at multiple scales improves accuracy
For detecting objects in natural visual scenes, several powerful image features have been proposed which can collectively be described as spatial histograms of oriented energy. Th...
Stanley M. Bileschi
ICPR
2008
IEEE
15 years 22 days ago
Enforcing image consistency in multiple 3-D object modelling
In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is ...
Adrian G. Bors, Matthew Grum
ICPR
2008
IEEE
15 years 22 days ago
Robust auto-calibration of a PTZ camera with non-overlapping FOV
We consider the problem of auto-calibration of cameras, which are fixed in location but are free to rotate while changing their internal parameters by zooming. Our method is based...
Hassan Foroosh, Nazim Ashraf