Proceedings Article10.1109/CVPR.1994.323929
Motion estimation and vector splines
Suter
- 21 Jun 1994
- pp 939-942
156
TL;DR: A decomposition of the smoothness constraint into two partsrelated to the divergence of the vector field and one related to the curl or vorticity is introduced, which allows one to "tune" the smootherness to the properties of the data.
read more
Abstract: Many formulations of visual reconstruction problems (e.g. optic flow, shape from shading, biomedical motion estimation from CT data) involve the recovery of a vector field. Often the solution is characterized via a generalized spline or regularization formulation using a smoothness constraint. This paper introduces a decomposition of the smoothness constraint into two parts: one related to the divergence of the vector field and one related to the curl or vorticity. This allows one to "tune" the smoothness to the properties of the data. One can, for example, use a high weighting on the smoothness imposed upon the curl in order to preserve the divergent parts of the field. For a particular spline within the family introduced by this decomposition process, we derive an exact solution and demonstrate the approach on examples. >
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Robot vision
Y.J. Tejwani
- 01 Jan 1989
TL;DR: A scheme is developed for classifying the types of motion perceived by a humanlike robot and equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented.
2K
Dense estimation of fluid flows
TL;DR: A dedicated minimization-based motion estimator based on an integrated version of the continuity equation of fluid mechanics, which is compatible with large displacements and associated with an original second-order div-curl regularization.
Variational fluid flow measurements from image sequences: synopsis and perspectives
TL;DR: This work outlines promising research directions and points out the potential of variational techniques in combination with correlation-based PIV methods, for improving the consistency of fluid flow estimation and simulation.
Fluid experimental flow estimation based on an Optical-flow scheme
TL;DR: The proposed technique is an extension of “optical-flow” schemes used in the computer vision community, which includes a specific enhancement for fluid mechanics applications, and enables to provide accurate dense motion fields.
228
Ill-posed problems in early vision: from computational theory to analogue networks
Tomaso Poggio,Christof Koch +1 more
TL;DR: A theoretical framework is outlined that leads from the computational nature of early vision to algorithms for solving them and finally to a specific class of analogue and parallel hardware for the efficient solution of these algorithms.
125
References
•Book
Spline models for observational data
Grace Wahba
- 01 Mar 1990
TL;DR: In this paper, a theory and practice for the estimation of functions from noisy data on functionals is developed, where convergence properties, data based smoothing parameter selection, confidence intervals, and numerical methods are established which are appropriate to a number of problems within this framework.
6.9K
•Proceedings Article
Robot vision
Y.J. Tejwani
- 01 Jan 1989
TL;DR: A scheme is developed for classifying the types of motion perceived by a humanlike robot and equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented.
2K
Performance of optical flow techniques
John L. Barron,David J. Fleet,Steven S. Beauchemin,T.A. Burkitt +3 more
- 15 Jun 1992
TL;DR: The performance of six optical flow techniques is compared, emphasizing measurement accuracy, and it is found that some form of confidence measure/threshold is crucial for all techniques in order to separate the inaccurate from the accurate.
741
The variational approach to shape from shading
TL;DR: In this article, the shape-from-shading problem is formulated as a nonlinear first-order partial differential equation in surface elevation and the problem of finding a surface orientation field that minimizes the integral of the brightness error is solved.
Computation of 3-D velocity fields from 3-D cine CT images of a human heart
S.M. Song,Richard M. Leahy +1 more
TL;DR: A method of computing the three-dimensional (3-D) velocity field from 3-D cine computer tomographs (CTs) of a beating heart using the Euler-Lagrange method and the results are presented.
214