Title:
Learning Visibility of Landmarks for Vision-Based Localization

Thumbnail Image
Author(s)
Alcantarilla, Pablo F.
Oh, Sang Min
Mariottini, Gian Luca
Bergasa, Luis M.
Dellaert, Frank
Authors
Advisor(s)
Advisor(s)
Editor(s)
Associated Organization(s)
Series
Supplementary to
Abstract
We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from the image with the map elements at the current location. Although the problem of data association has greatly benefited from recent advances in appearance-based matching methods, less attention has been paid to the effective use of the geometric relations between the 3D map and the camera in the matching process. In this paper we propose to exploit the geometric relationship between the 3D map and the camera pose to determine the visibility of the features. In our approach, we model the visibility of every map feature w.r.t. the camera pose using a non-parametric distribution model. We learn these non-parametric distributions during the 3D reconstruction process, and develop efficient algorithms to predict the visibility of features during localization. With this approach, the matching process only uses those map features with the highest visibility score, yielding a much faster algorithm and superior localization results. We demonstrate an integrated system based on the proposed idea and highlight its potential benefits for the localization in large and cluttered environments.
Sponsor
Date Issued
2010
Extent
Resource Type
Text
Resource Subtype
Post-print
Proceedings
Rights Statement
Rights URI