Skip to main content

Research Repository

Advanced Search

Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots

Cavestany, P.; Rodríguez, A.L.; Martínez-Barberá, H.; Breckon, T.P.

Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots Thumbnail


Authors

P. Cavestany

A.L. Rodríguez

H. Martínez-Barberá



Abstract

We consider the use of low-budget omnidirectional platforms for 3D mapping and self-localisation. These robots specifically permit rotational motion in the plane around a central axis, with negligible displacement. In addition, low resolution and compressed imagery, typical of the platform used, results in high level of image noise (_ ∽ 10). We observe highly sparse image feature matches over narrow inter-image baselines. This particular configuration poses a challenge for epipolar geometry extraction and accurate 3D point triangulation, upon which a standard structure from motion formulation is based. We propose a novel technique for both feature filtering and tracking that solves these problems, via a novel approach to the management of feature bundles. Noisy matches are efficiently trimmed, and the scarcity of the remaining image features is adequately overcome, generating densely populated maps of highly accurate and robust 3D image features. The effectiveness of the approach is demonstrated under a variety of scenarios in experiments conducted with low-budget commercial robots.

Citation

Cavestany, P., Rodríguez, A., Rodriguez, A., Martínez-Barberá, H., Martinez-Barbera, H., & Breckon, T. (2015). Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots. In Proc. Int. Conf. on Image Processing (4927-4931). https://doi.org/10.1109/ICIP.2015.7351744

Conference Name Proceedings of IEEE International Conference on Image Processing
Conference Location Québec City, Canada
Publication Date 2015
Deposit Date Oct 4, 2015
Publicly Available Date Mar 29, 2024
Publisher Institute of Electrical and Electronics Engineers
Pages 4927-4931
Book Title Proc. Int. Conf. on Image Processing
DOI https://doi.org/10.1109/ICIP.2015.7351744
Keywords structure from motion, ill-conditioned baseline configurations, omnidirectional 3D, robot sensing, robot vision, 3D visual sensing, point clouds, robot scene mapping
Public URL https://durham-repository.worktribe.com/output/1153486
Publisher URL https://breckon.org/toby/publications/papers/cavestany15robot.pdf
Related Public URLs http://community.dur.ac.uk/toby.breckon/publications/papers/cavestany15robot.pdf

Files

Accepted Conference Proceeding (695 Kb)
PDF

Copyright Statement
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.





You might also like



Downloadable Citations