Enhancing appearance-based robot localization using sparse disparity maps

Josep Porta 1 Jakob Verbeek 1 Ben Krose 1
1 IvI - Instituut voor Informatica
Abstract : In this paper, we enhance appearance-based robot localization by using disparity maps. Disparity maps provide the same type of information as range based sensors (distance to objects) and thus, they are likely to be less sensitive to changes of illumination than plain images, that are the source of information generally used in appearance-based localization. The main drawback of disparity maps is that they can include very noisy depth values: points for which the algorithms can not determine reliable depth information. These noisy values have to be discarded resulting in missing values. The presence of missing values makes Principal Component Analysis (the standard method used to compress images in the appearance-based framework) unfeasible. We describe a novel Expectation-Maximization algorithm to determine the principal components of a data set including missing values and we apply it to disparity maps. The results we present show that disparity maps are a valid alternative to increase the robustness of appearance-based localization.
Keywords : principal component analysis robots sensor fusion
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

PVK03.png
PVK03.png
https://hal.inria.fr/inria-00321488
Contributor : Jakob Verbeek <>
Submitted on : Tuesday, March 8, 2011 - 3:07:07 PM
Last modification on : Monday, September 25, 2017 - 10:08:04 AM
Long-term archiving on : Thursday, June 9, 2011 - 2:45:30 AM

Files

verbeek03iros.pdf
Files produced by the author(s)

Identifiers

Citation

Josep Porta, Jakob Verbeek, Ben Krose. Enhancing appearance-based robot localization using sparse disparity maps. IEEE/RSJ International Conference on Intelligent Robots & Systems (IROS '03), Oct 2003, Las Vegas, United States. pp.980 - 985, ⟨10.1109/IROS.2003.1250755⟩. ⟨inria-00321488v2⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

203

Files downloads

421

Contact


archive-ouverte@inria.fr