Displacement Following of Hidden Objects in a Video Sequence

Authors:
Olivia Sanchez;Françoise Dibos
Affiliations:
CEREMADE, Université Paris IX-Dauphine, Place du Maréchal de Lattre de Tassigny, 75775 Paris, Cedex 16, France. sanchez@ceremade.dauphine.fr;CEREMADE, Université Paris IX-Dauphine, Place du Maréchal de Lattre de Tassigny, 75775 Paris, Cedex 16, France. fd@ceremade.dauphine.fr
Venue:
International Journal of Computer Vision
Year:
2004

Citing 9
Cited 1

Performance of optical flow techniques

International Journal of Computer Vision
Variational methods in image segmentation

Variational methods in image segmentation
Non Uniform Multiresolution Method for Optical Flow and Phase Portrait Models: Environmental Applications

International Journal of Computer Vision
A mathematical study of the relaxed optical flow problem in the space BV(&OHgr;)

SIAM Journal on Mathematical Analysis
Image inpainting

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Reliable Estimation of Dense Optical Flow Fields with Large Displacements

International Journal of Computer Vision
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint

Journal of Mathematical Imaging and Vision
Optical flow: a curve evolution approach

IEEE Transactions on Image Processing
Filling-in by joint interpolation of vector fields and gray levels

IEEE Transactions on Image Processing

Segmentation of a Vector Field: Dominant Parameter and Shape Optimization

Journal of Mathematical Imaging and Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In a video sequence, computing the motion of an object requires the continuity of the apparent velocity field. This property does not hold when the object is hidden by an occlusion during its motion. The minimization of an energy functional leads to a simple algorithm which allows the recovery of the most likely trajectory of the occluded object from optical flow data at the border of the occlusion. Optical flow used for developing our method is an improvement on any variational technique of computing it. This improvement is based on a multichannel segmentation.