Space-time segmentation based on a joint entropy with estimation of nonparametric distributions

Authors:
Ariane Herbulot;Sylvain Boltz;Eric Debreuve;Michel Barlaud;Gilles Aubert
Affiliations:
Laboratoire I3S, CNRS, Université de Nice-Sophia Antipolis, France;Laboratoire I3S, CNRS, Université de Nice-Sophia Antipolis, France;Laboratoire I3S, CNRS, Université de Nice-Sophia Antipolis, France;Laboratoire I3S, CNRS, Université de Nice-Sophia Antipolis, France;Laboratoire Dieudonné, CNRS, Université de Nice-Sophia Antipolis, France
Venue:
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Year:
2007

Citing 10
Cited 0

The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
Geodesic Active Contours

International Journal of Computer Vision
Shapes and geometries: analysis, differential calculus, and optimization

Shapes and geometries: analysis, differential calculus, and optimization
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint

Journal of Mathematical Imaging and Vision
Mean Shift Analysis and Applications

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation

International Journal of Computer Vision
A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape

International Journal of Computer Vision
Motion-based background subtraction using adaptive kernel density estimation

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Near real-time motion segmentation using graph cuts

DAGM'06 Proceedings of the 28th conference on Pattern Recognition
A nonparametric statistical method for image segmentation using information theory and curve evolution

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with video segmentation based on motion and spatial information. Classically, the nucleus of the motion term is the motion compensation error (MCE) between two consecutive frames. Defining a motion-based energy as the integral of a function of the MCE over the object domain implicitly results in making an assumption on the MCE distribution: Gaussian for the square function, Laplacian for the absolute value, or other parametric distributions for functions used in robust estimation. However, these assumptions are generally false. Instead, it is proposed to integrate a function of (an estimation of) the MCE distribution. The function is taken such that the integral is the Ahmad-Lin entropy of the MCE, the purpose being to be more robust to outliers. Since a motion-only approach can fail in homogeneous areas, the proposed energy is the joint entropy of the MCE and the object color. It is minimized using active contours.