Computation of discontinuous optical flow by domain decomposition and shape optimization
International Journal of Computer Vision
Methods of engineering mathematics
Methods of engineering mathematics
International Journal of Computer Vision
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shapes and geometries: analysis, differential calculus, and optimization
Shapes and geometries: analysis, differential calculus, and optimization
Shape and topology constraints on parametric active contours
Computer Vision and Image Understanding
Fast Local and Global Projection-Based Methods for Affine Motion Estimation
Journal of Mathematical Imaging and Vision
International Journal of Computer Vision
Motion Competition: Variational Integration of Motion Segmentation and Shape Regularization
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Deformable Model with Non-euclidean Metrics
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A Statistical Approach to Snakes for Bimodal and Trimodal Imagery
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Variational Space-Time Motion Segmentation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Information-Theoretic Active Polygons for Unsupervised Texture Segmentation
International Journal of Computer Vision
Designing Spatially Coherent Minimizing Flows for Variational Problems Based on Active Contours
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Segmentation of a Vector Field: Dominant Parameter and Shape Optimization
Journal of Mathematical Imaging and Vision
A geometric formulation of gradient descent for variational problems with moving surfaces
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
An analysis of variational alignment of curves in images
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
Local or global minima: flexible dual-front active contours
CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
A new diamond search algorithm for fast block-matching motion estimation
IEEE Transactions on Image Processing
B-spline snakes: a flexible tool for parametric contour detection
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Efficient energies and algorithms for parametric snakes
IEEE Transactions on Image Processing
Robust real-time segmentation of images and videos using a smooth-spline snake-based algorithm
IEEE Transactions on Image Processing
Combining shape prior and statistical features for active contour segmentation
IEEE Transactions on Circuits and Systems for Video Technology
Variational B-spline level-set: a linear filtering approach for fast deformable model evolution
IEEE Transactions on Image Processing
Towards full 3D Helmholtz stereovision algorithms
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
International Journal of Computer Vision
Hi-index | 0.00 |
A variational approach to image or video segmentation consists in defining an energy depending on local or global image characteristics, the minimum of which being reached for objects of interest. This study focuses on energies written as an integral on a domain of a function which can depend on this domain. The derivative of the energy with respect to the domain, the so-called shape derivative, is a function of a velocity field applied to the domain boundary. For a given, non-optimal domain, the velocity should be chosen such that the shape derivative is negative, thus indicating a way to deform the domain in order to decrease its energy. Minimizing the energy through an iterative deformation process is known as the active contour method. In the continuous framework, setting the velocity to the opposite of the gradient associated with the L 2 inner product is a common practice. In this paper, it is noted that the negativity of the shape derivative is not preserved, in general, by the discretization of this velocity required by implementation. In order to guarantee that the negativity condition holds in the discrete framework, it is proposed to choose the velocity as a linear combination of pre-defined velocities. This approach also gives more flexibility to the active contour process by allowing to introduce some a priori knowledge about the optimal domain. Some experimental results illustrate the differences between the classical and the proposed approach.