DocumentCode :
2920019
Title :
Nonlinear shape manifolds as shape priors in level set segmentation and tracking
Author :
Prisacariu, Victor Adrian ; Reid, Ian
Author_Institution :
Univ. of Oxford, Oxford, UK
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
2185
Lastpage :
2192
Abstract :
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level set-based segmentation and tracking. Unlike previous work, we represent shapes with elliptic Fourier descriptors and learn their lower dimensional latent space using Gaussian Process Latent Variable Models. Segmentation is done by a nonlinear minimisation of an image-driven energy function in the learned latent space. We combine it with a 2D pose recovery stage, yielding a single, one shot, optimisation of both shape and pose. We demonstrate the performance of our method, both qualitatively and quantitatively, with multiple images, video sequences and latent spaces, capturing both shape kinematics and object class variance.
Keywords :
Gaussian processes; elliptic equations; image representation; image segmentation; image sequences; object tracking; probability; video signal processing; 2D pose recovery stage; Gaussian process latent variable models; elliptic Fourier descriptors; image-driven energy function; level set segmentation; level set tracking; nonlinear method; nonlinear minimisation; nonlinear shape manifolds; probabilistic method; shape kinematics; shape representation; variational method; video sequences; Convergence; Equations; Image segmentation; Minimization; Optimization; Principal component analysis; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4577-0394-2
Type :
conf
DOI :
10.1109/CVPR.2011.5995687
Filename :
5995687
Link To Document :
بازگشت