Results 11 - 20 of 828

Curvature-based algorithms for nonrigid motion and correspondence estimation

by Pavel Laskov, Chandra Kambhamettu - PAMI , 2003
"... Two new algorithms for estimation of non-rigid motion in range data in the absense of correspondence information are presented. We derive a new relationship between Gaussian curvatures and other differential-geometric parameters before and after small deformation. This relationship depends linearly ..."
Abstract - Cited by 8 (1 self) - Add to MetaCart
Two new algorithms for estimation of non-rigid motion in range data in the absense of correspondence information are presented. We derive a new relationship between Gaussian curvatures and other differential-geometric parameters before and after small deformation. This relationship depends linearly

Nonrigid Motion Analysis Based on Dynamic Refinement of Finite Element Models

by Leonid V. Tsap, Dmitry B. Goldgof, Sudeep Sarkar - IEEE Trans. on Pattern Analysis and Machine Intelligence , 1998
"... In this paper we propose new algorithms for accurate nonrigid motion tracking. Given only a set of sparse correspondences and incomplete or missing information about geometry or material properties, we recover dense motion vectors using nonlinear finite element models. The method is based on the ite ..."
Abstract - Cited by 28 (7 self) - Add to MetaCart
In this paper we propose new algorithms for accurate nonrigid motion tracking. Given only a set of sparse correspondences and incomplete or missing information about geometry or material properties, we recover dense motion vectors using nonlinear finite element models. The method is based

Spatio-temporal analysis of nonrigid motion from 4D data

by Chahab Nastar, Nicholas Ayache - In IEEE Workshop on Motion of Non-rigid and Articulated Objects , 1994
"... We present a method for analysis of nonrigid motion in time sequences of volume images (4D data). In this method nonrigid motion of the deforming object contour is dynamically approximated by a deformable surface. In order to reduce the number of parameters describing the deformation, we make use of ..."
Abstract - Cited by 9 (3 self) - Add to MetaCart
We present a method for analysis of nonrigid motion in time sequences of volume images (4D data). In this method nonrigid motion of the deforming object contour is dynamically approximated by a deformable surface. In order to reduce the number of parameters describing the deformation, we make use

3D nonrigid motion analysis under small deformations

by Ra Kambhamettu A, Dmitry Goldgof B, Matthew He C, Pavel Laskov D
"... We present a novel method for estimating motion parameters and point correspondences between 3D surfaces under small nonrigid motion. A vector point function is utilized as the motion parameter, called the displacement function. Differential-geometric changes of surfaces are then used in tracking sm ..."
Abstract - Add to MetaCart
We present a novel method for estimating motion parameters and point correspondences between 3D surfaces under small nonrigid motion. A vector point function is utilized as the motion parameter, called the displacement function. Differential-geometric changes of surfaces are then used in tracking

Frequency Based Nonrigid Motion Analysis: Application to Four Dimensional Medical Images

by Chahab Nastar, Nicholas Ayache
"... Abstract-We present a method for nonrigid motion analysis in time sequences of volume images (4D data). In this method, nonrigid motion of the deforming object contour is dynamically approximated by a physically-based deformable surface. In order to reduce the number of parameters describing the def ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Abstract-We present a method for nonrigid motion analysis in time sequences of volume images (4D data). In this method, nonrigid motion of the deforming object contour is dynamically approximated by a physically-based deformable surface. In order to reduce the number of parameters describing

Discriminating rigid from nonrigid motion: Minimum points and views

by Myron L. Braunstein, Donald D. Hoffman, Frank E. Pollick - Perception & Psychophysics , 1990
"... Theoretical investigations of structure from motion have demonstratedthat an ideal observer candiscriminate rigid from nonrigid motion from two views of as few as four points. We report three experiments that demonstrate similar abilities in human observers: In one experiment, 4 of 6 subjects made t ..."
Abstract - Cited by 16 (2 self) - Add to MetaCart
Theoretical investigations of structure from motion have demonstratedthat an ideal observer candiscriminate rigid from nonrigid motion from two views of as few as four points. We report three experiments that demonstrate similar abilities in human observers: In one experiment, 4 of 6 subjects made

Visual information about rigid and nonrigid motion: A geometric analysis

by James T. Todd - Journal of Experimental Psychology: Human Perception and Performance , 1982
"... A mathematical analysis is presented that attempts to describe the available visual information about rigid and nonrigid motion and the three-dimensional structure of rigidly moving objects. Unlike other approaches, the analysis is based on the geometric relations among a set of trajectories defined ..."
Abstract - Cited by 26 (0 self) - Add to MetaCart
A mathematical analysis is presented that attempts to describe the available visual information about rigid and nonrigid motion and the three-dimensional structure of rigidly moving objects. Unlike other approaches, the analysis is based on the geometric relations among a set of trajectories

Hierarchical Structure and Nonrigid Motion Recovery from 2D Monocular Views

by Lin Zhou, Chandra Kambhamettu , 2000
"... Inferring both 3D structure and motion of nonrigid objects from monocular images is an important problem in computational vision. The challenges stem not only from the absence of point correspondences but also from the structure ambiguity. In this paper, a hierarchical method which integrates both l ..."
Abstract - Cited by 9 (2 self) - Add to MetaCart
Inferring both 3D structure and motion of nonrigid objects from monocular images is an important problem in computational vision. The challenges stem not only from the absence of point correspondences but also from the structure ambiguity. In this paper, a hierarchical method which integrates both

Fusion of Physically-Based Registration and Deformation Modeling for Nonrigid Motion Analysis

by Leonid V. Tsap, Dmitry B. Goldgof, Sudeep Sarkar , 2001
"... In our previous work we used finite element models to determine nonrigid motion parameters and recover unknown local properties of objects given correspondence data recovered with snakes or other tracking models. In this paper we present a novel multiscale approach to recovery of nonrigid motion fro ..."
Abstract - Cited by 7 (0 self) - Add to MetaCart
In our previous work we used finite element models to determine nonrigid motion parameters and recover unknown local properties of objects given correspondence data recovered with snakes or other tracking models. In this paper we present a novel multiscale approach to recovery of nonrigid motion

Model-Based Nonrigid Motion Analysis Using Natural Feature Adaptive Mesh

by Yong Zhang, Dmitry B. Goldgof, Sudeep Sarkar, Leonid V. Tsap - Proceedings of International Conference on Pattern Recognition , 2000
"... The success of nonrigid motion analysis using physical finite element model is dependent on the mesh that characterizes the object's geometric structure. We suggest a deformable mesh adapted to the natural features of images. The adaptive mesh requires much fewer number of nodes than the fixed ..."
Abstract - Cited by 3 (2 self) - Add to MetaCart
The success of nonrigid motion analysis using physical finite element model is dependent on the mesh that characterizes the object's geometric structure. We suggest a deformable mesh adapted to the natural features of images. The adaptive mesh requires much fewer number of nodes than the fixed
Results 11 - 20 of 828