Abstract
This paper deals with video segmentation for MPEG-4 and MPEG-7 applications. Region-based active contour is a powerful technique for segmentation. However most of these methods are implemented using level sets. Although level-set methods provide accurate segmentation, they suffer from large computational cost. We propose to use a regular B-spline parametric method to provide a fast and accurate segmentation. Our B-spline interpolation is based on a fixed number of points 2j depending on the level of the desired details. Through this spatial multiresolution approach, the computational cost of the segmentation is reduced. We introduce a length penalty. This results in improving both smoothness and accuracy. Then we show some experiments on real-video sequences.
Highlights
IntroductionEdge Γn object domain, and Γn(τ) is the frontier between these domains
Ωn,out(t)Moving object Ωn,in(t)Edge Γn object domain, and Γn(τ) is the frontier between these domains.this criterion is differentiated in an Eulerian framework [7]: J (τ) =k(out) − k(in) − k(b) · κ + ∇k(b) · N · v ds. (3) Γ(τ)according to the inequality of Cauchy-Schwartz, the fastest decrease of J(τ) is obtained by choosing v = vN
Parametric implementations: the B-spline interpolation of the contour presented in this paper highly reduces the computational cost while topological changes are not managed
Summary
Edge Γn object domain, and Γn(τ) is the frontier between these domains. This criterion is differentiated in an Eulerian framework [7]: J (τ) =. According to the inequality of Cauchy-Schwartz, the fastest decrease of J(τ) is obtained by choosing v = vN. We obtain the following partial differential equation (PDE): ∂Γn(t) ∂t = vN
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have