Dictionary learning in stereo imagingReport as inadecuate




Dictionary learning in stereo imaging - Download this document for free, or read online. Document in PDF available to download.

Published in: IEEE Transactions on Image Processing (ISSN: 1057-7149), vol. 20, num. 4, p. 921-934 Institute of Electrical and Electronics Engineers, 2011

This paper presents a new method for learning overcomplete dictionaries adapted to efficient joint representation of stereo images. We first formulate a sparse stereo image model where the multi-view correlation is described by local geometric transforms of dictionary atoms in two stereo views. A maximum-likelihood method for learning stereo dictionaries is then proposed, which includes a multi-view geometry constraint in the probabilistic modeling in order to obtain dictionaries optimized for the joint representation of stereo images. The dictionaries are learned by optimizing the maximum-likelihood objective function using the expectation- maximization algorithm. We illustrate the learning algorithm in the case of omnidirectional images, where we learn scales of atoms in a parametric dictionary. The resulting dictionaries provide both better performance in the joint representation of stereo omnidirectional images and improved multi- view feature matching. We finally discuss and demonstrate the benefits of dictionary learning for distributed scene representation and camera pose estimation.

Keywords: Sparse approximations ; dictionary learning ; multi-view imaging ; omnidirectional cameras ; LTS4 Reference EPFL-ARTICLE-138749doi:10.1109/TIP.2010.2081679View record in Web of Science





Author: Tosic, I.; Frossard, P.

Source: https://infoscience.epfl.ch/record/138749?ln=en







Related documents