Learning appearance and transparency manifolds of occluded objects in layers
- 21 November 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 15, 45
- https://doi.org/10.1109/cvpr.2003.1211336
Abstract
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, images of a person walking can be mapped to a 1-dimensional manifold that measures the phase of the person's gait. However, when the object is moving around the frame and being occluded by other objects, standard manifold modeling techniques (e.g., principal components analysis, factor analysis, locally linear embedding) try to account for global motion and occlusion. We show how factor analysis can be incorporated into a generative model of layered, 2.5-dimensional vision, to jointly locate objects, resolve occlusion ambiguities, and learn models of the appearance manifolds of objects. We demonstrate the algorithm on a video consisting of four occluding objects, two of which are people who are walking, and occlude each other for most of the duration of the video. Whereas standard manifold modeling techniques fail to extract information about the gaits, the layered model successfully extracts a periodic representation of the gait of each person.Keywords
This publication has 19 references indexed in Scilit:
- Motion-based recognition of people in EigenGait spacePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Mixtures of local linear subspaces for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Separating appearance from deformationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Design and Use of Linear Models for Image Motion AnalysisInternational Journal of Computer Vision, 2000
- Transformed component analysis: joint estimation of spatial transformations and image componentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- GTM: The Generative Topographic MappingNeural Computation, 1998
- EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based RepresentationInternational Journal of Computer Vision, 1998
- Parametric feature detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Real-time tracking of image regions with changes in geometry and illuminationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991