Multiresolution elastic matching
Computer Vision, Graphics, and Image Processing
Performance of optical flow techniques
International Journal of Computer Vision
Diffeomorphisms Groups and Pattern Matching in Image Analysis
International Journal of Computer Vision
Computing optical flow via variational techniques
SIAM Journal on Applied Mathematics
Design and Use of Linear Models for Image Motion Analysis
International Journal of Computer Vision
Detecting and Tracking Multiple Moving Objects Using Temporal Integration
ECCV '92 Proceedings of the Second European Conference on Computer Vision
A Multiresolution Algorithm for Signal and Image Registration
ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 3 - Volume 3
| Hi-index | 0.00 |
We address the theoretical problems of optical flow estimation and image registration in a multi-scale framework in any dimension. We start by showing, in the translation case, that convergence to the global minimum is made easier by applying a low pass filter to the images hence making the energy "convex enough". In order to keep convergence to the global minimum in the general case, we introduce a local rigidity hypothesis on the unknown deformation. We then deduce a new natural motion constraint equation (MCE) at each scale using the Dirichlet low pass operator. This allows us to derive sufficient conditions for convergence of a new multi-scale and iterative motion estimation/registration scheme towards a global minimum of the usual nonlinear energy instead of a local minimum as did all previous methods. We then use an implicit numerical approach. We illustrate our method on synthetic and real examples (Motion, Registration, Morphing).