Skip to Content
No preview available

Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

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

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 (σ ∽ 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. This is the evaluation data set used in the work and comprises the images and associated ground truth measurements used for the results within the paper (doi: 10.1109/ICIP.2015.7351744).

Descriptions

Resource type
Dataset
Contributors
Creator: Breckon, Toby P. 1
Creator: Cavestany, Pedro 1
Contact person: Breckon, Toby P. 1
1 Durham University, UK
Funder
Higher Education Funding Council for England
Science and Technology Regional Office, Séneca Foundation, Murcia (Spain).
Research methods
Other description
Data set used in research paper doi:10.1109/ICIP.2015.7351744
Keyword
Structure from motion, Mobile robot, Omnidirectional, Noise, Feature filtering
Subject
Computer science
Location
Durham
Language
English
Cited in
doi:10.1109/ICIP.2015.7351744
Identifier
doi:10.15128/3n203z084
ark:/32150/3n203z084
Rights
Creative Commons Attribution 4.0 International (CC BY)

Publisher
Durham University
Date Created
September 2015

File Details

Depositor
T. Breckon
Date Uploaded
Date Modified
17 October 2016, 15:10:17
Audit Status
Audits have not yet been run on this file.
Characterization
File format: zip (ZIP Format)
Mime type: application/zip
File size: 13647039
Last modified: 2016:01:21 18:11:53+00:00
Filename: cavestany15robot-sfm.zip
Original checksum: cb51ac41d86b8d81dfe80e7d706aa2b7
Activity of users you follow
User Activity Date
User S. Palucha has updated Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots - Evaluation Dataset almost 4 years ago
User T. Breckon has updated Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots - Evaluation Dataset over 4 years ago
User T. Breckon has updated Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots - supporting data set over 4 years ago
User T. Breckon has updated Improved 3D Sparse Maps for High-performance Structure from Motion with Low-cost Omnidirectional Robots - supporting data set over 4 years ago
User T. Breckon has deposited cavestany15robot-sfm.zip over 4 years ago