Jiasong Zhu
Indoor Topological Localization Using a Visual Landmark Sequence
Zhu, Jiasong; Li, Qing; Cao, Rui; Sun, Ke; Liu, Tao; Garibaldi, Jonathan; Li, Qingquan; Liu, Bozhi; Qiu, Guoping
Authors
Qing Li
Rui Cao
Ke Sun
Tao Liu
Prof. JONATHAN GARIBALDI jon.garibaldi@nottingham.ac.uk
Professor of Computer Science
Qingquan Li
Bozhi Liu
GUOPING QIU GUOPING.QIU@NOTTINGHAM.AC.UK
Professor of Visual Information Processing
Abstract
© 2019 by the authors. This paper presents a novel indoor topological localization method based on mobile phone videos. Conventional methods suffer from indoor dynamic environmental changes and scene ambiguity. The proposed Visual Landmark Sequence-based Indoor Localization (VLSIL) method is capable of addressing problems by taking steady indoor objects as landmarks. Unlike many feature or appearance matching-based localization methods, our method utilizes highly abstracted landmark sematic information to represent locations and thus is invariant to illumination changes, temporal variations, and occlusions. We match consistently detected landmarks against the topological map based on the occurrence order in the videos. The proposed approach contains two components: a convolutional neural network (CNN)-based landmark detector and a topological matching algorithm. The proposed detector is capable of reliably and accurately detecting landmarks. The other part is the matching algorithm built on the second order hidden Markov model and it can successfully handle the environmental ambiguity by fusing sematic and connectivity information of landmarks. To evaluate the method, we conduct extensive experiments on the real world dataset collected in two indoor environments, and the results show that our deep neural network-based indoor landmark detector accurately detects all landmarks and is expected to be utilized in similar environments without retraining and that VLSIL can effectively localize indoor landmarks.
Citation
Zhu, J., Li, Q., Cao, R., Sun, K., Liu, T., Garibaldi, J., …Qiu, G. (2019). Indoor Topological Localization Using a Visual Landmark Sequence. Remote Sensing, 11(1), Article 73. https://doi.org/10.3390/rs11010073
Journal Article Type | Article |
---|---|
Acceptance Date | Dec 30, 2018 |
Online Publication Date | Jan 3, 2019 |
Publication Date | Jan 3, 2019 |
Deposit Date | Jan 11, 2019 |
Publicly Available Date | Jan 11, 2019 |
Journal | Remote Sensing |
Electronic ISSN | 2072-4292 |
Publisher | MDPI |
Peer Reviewed | Peer Reviewed |
Volume | 11 |
Issue | 1 |
Article Number | 73 |
DOI | https://doi.org/10.3390/rs11010073 |
Keywords | General Earth and Planetary Sciences |
Public URL | https://nottingham-repository.worktribe.com/output/1464770 |
Publisher URL | https://www.mdpi.com/2072-4292/11/1/73 |
Files
remotesensing-11-00073
(8.9 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/
You might also like
Particle reinforced thermoplastic foams under quasi-static compression
(2019)
Journal Article
Bio-inspired self-healing polymer foams with bilayered capsule systems
(2020)
Journal Article