Sciweavers

ACCV
2006
Springer
13 years 10 months ago
Theory and Calibration for Axial Cameras
Although most works in computer vision use perspective or other central cameras, the interest in non-central camera models has increased lately, especially with respect to omnidire...
Srikumar Ramalingam, Peter F. Sturm, Suresh K. Lod...
ACCV
2006
Springer
13 years 10 months ago
Performance Evaluation of Object Detection and Tracking in Video
The need for empirical evaluation metrics and algorithms is well acknowledged in the field of computer vision. The process leads to precise insights to understanding current techn...
Vasant Manohar, Padmanabhan Soundararajan, Harish ...
ACCV
2006
Springer
13 years 10 months ago
Object Detection Using a Cascade of 3D Models
Abstract. We present an alignment framework for object detection using a hierarchy of 3D polygonal models. One difficulty with alignment methods is that the high-dimensional transf...
Hon-Keat Pong, Tat-Jen Cham
ACCV
2006
Springer
13 years 10 months ago
Probabilistic Modeling for Structural Change Inference
We view the task of change detection as a problem of object recognition from learning. The object is defined in a 3D space where the time is the 3rd dimension. We propose two com...
Wei Liu, Véronique Prinet
ACCV
2006
Springer
13 years 10 months ago
Vision Based Speech Animation Transferring with Underlying Anatomical Structure
We present a novel method to transfer speech animation recorded in low resolution videos onto realistic 3D facial models. Unsupervised learning is utilized on a speech video corpus...
Yuru Pei, Hongbin Zha
ACCV
2006
Springer
13 years 10 months ago
Surface-Independent Direct-Projected Augmented Reality
Some issues on direct-projected augmented reality (DirectAR) are addressed: the projection may be geometrically distorted due to the non-planar surface (geometric distortion); the ...
Hanhoon Park, Moon-Hyun Lee, Sang-Jun Kim, Jong-Il...
ACCV
2006
Springer
13 years 10 months ago
Virtual Fashion Show Using Real-Time Markerless Motion Capture
Abstract. This paper presents a motion capture system using two cameras that is capable of estimating a constrained set of human postures in real time. We first obtain a 3D shape ...
Ryuzo Okada, Björn Stenger, Tsukasa Ike, Nobu...
ACCV
2006
Springer
13 years 10 months ago
Occlusion Invariant Face Recognition Using Selective LNMF Basis Images
In this paper, we propose a novel occlusion invariant face recognition algorithm based on Selective Local Nonnegative Matrix Factorization (S-LNMF) technique. The proposed algorith...
Hyun Jun Oh, Kyoung Mu Lee, Sang Uk Lee, Chung-Hyu...
ACCV
2006
Springer
13 years 10 months ago
Minimal Weighted Local Variance as Edge Detector for Active Contour Models
Performing segmentation of narrow, elongated structures with low contrast boundaries is a challenging problem. Boundaries of these structures are difficult to be located when noise...
Max W. K. Law, Albert C. S. Chung
ACCV
2006
Springer
13 years 10 months ago
Visual Surveillance Using Less ROIs of Multiple Non-calibrated Cameras
With a large number of surveillance cameras, it is not an easy task to determine which camera should be monitored and which region of the camera images should be checked so that al...
Takashi Nishizaki, Yoshinari Kameda, Yuichi Ohta