Sciweavers

ECCV
2006
Springer
14 years 10 days ago
View-Invariant Modeling and Recognition of Human Actions Using Grammars
In this paper, we represent human actions as short sequences of atomic body poses. The knowledge of body pose is stored only implicitly as a set of silhouettes seen from multiple ...
Abhijit S. Ogale, Alap Karapurkar, Yiannis Aloimon...
ECCV
2006
Springer
14 years 10 days ago
Articulated-Body Tracking Through Anisotropic Edge Detection
This paper addresses the problem of articulated motion tracking from image sequences. We describe a method that relies on both an explicit parameterization of the extremal contours...
David Knossow, Joost van de Weijer, Radu Horaud, R...
ECCV
2006
Springer
14 years 10 days ago
Articulated Motion Segmentation Using RANSAC with Priors
Articulated motions are partially dependent. Most of the existing segmentation methods, e.g. Costeira and Kanade[2], can not be applied to articulated motions. We propose a novel ...
Jingyu Yan, Marc Pollefeys
ECCV
2006
Springer
14 years 10 days ago
Nonparametric Estimation of Multiple Structures with Outliers
Common problem encountered in the analysis of dynamic scene is the problem of simultaneous estimation of the number of models and their parameters. This problem becomes difficult a...
Wei Zhang, Jana Kosecká
ECCV
2006
Springer
14 years 10 days ago
Robust 3D Segmentation of Multiple Moving Objects Under Weak Perspective
A scene containing multiple independently moving, possibly occluding, rigid objects is considered under the weak perspective camera model. We obtain a set of feature points tracke...
Levente Hajder, Dmitry Chetverikov
ECCV
2006
Springer
14 years 10 days ago
Motion Segmentation Using an Occlusion Detector
We present a novel method for the detection of motion boundaries in a video sequence based on differential properties of the spatio-temporal domain. Regarding the video sequence as...
Doron Feldman, Daphna Weinshall
ECCV
2006
Springer
14 years 10 days ago
Direct Segmentation of Multiple 2-D Motion Models of Different Types
We propose a closed form solution for segmenting mixtures of 2-D translational and 2-D affine motion models directly from the image intensities. Our approach exploits the fact that...
Dheeraj Singaraju, René Vidal
ECCV
2006
Springer
14 years 10 days ago
The Space of Multibody Fundamental Matrices: Rank, Geometry and Projection
We study the rank and geometry of the multibody fundamental matrix, a geometric entity characterizing the two-view geometry of dynamic scenes consisting of multiple rigidbody moti...
Xiaodong Fan, René Vidal
ECCV
2006
Springer
14 years 10 days ago
Segmentation and Guidance of Multiple Rigid Objects for Intra-operative Endoscopic Vision
Abstract. This paper presents an endoscopic vision framework for modelbased 3D guidance of surgical instruments used in robotized laparoscopic surgery. In order to develop such a s...
Christophe Doignon, Florent Nageotte, Michel de Ma...