Nonlinear shape manifolds as shape priors in level set segmentation and tracking

Authors:
V. A. Prisacariu;I. Reid
Affiliations:
Univ. of Oxford, Oxford, UK;Univ. of Oxford, Oxford, UK
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 6

PWP3D: Real-Time Segmentation and Tracking of 3D Objects

International Journal of Computer Vision
Simultaneous monocular 2d segmentation, 3d pose recovery and 3d reconstruction

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Robust object tracking in crowd dynamic scenes using explicit stereo depth

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Statistical Model of Shape Moments with Active Contour Evolution for Shape Detection and Segmentation

Journal of Mathematical Imaging and Vision
Joint view-identity manifold for infrared target tracking and recognition

Computer Vision and Image Understanding
Regressing Local to Global Shape Properties for Online Segmentation and Tracking

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

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.