Search: WFRF:(Lin Guosheng) >
Sequence Searching ...
Sequence Searching With Deep-Learnt Depth for Condition- and Viewpoint-Invariant Route-Based Place Recognition
-
- Milford, Michael (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia
-
- Shen, Chunhua (author)
- Australian Centre for Robotic Vision, The University of Adelaide, Adelaide, Australia
-
- Lowry, Stephanie, 1979- (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia,AASS MRO Group
-
show more...
-
- Sünderhauf, Niko (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia
-
- Shirazi, Sareh (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia
-
- Lin, Guosheng (author)
- Australian Centre for Robotic Vision, The University of Adelaide, Australia, Adelaide, Australia
-
- Liu, Fayao (author)
- Australian Centre for Robotic Vision, The University of Adelaide, Australia, Adelaide, Australia
-
- Pepperell, Edward (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia
-
- Cadena, Cesar (author)
- Australian Centre for Robotic Vision, The University of Adelaide, Australia, Adelaide, Australia
-
- Upcroft, Ben (author)
- Australian Centre for Robotic Vision, Queensland University of Technology Australia, Brisbane, Australia
-
- Reid, Ian (author)
- Australian Centre for Robotic Vision, The University of Adelaide, Australia, Adelaide, Australia
-
show less...
-
(creator_code:org_t)
- IEEE conference proceedings, 2015
- 2015
- English.
-
In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops. - : IEEE conference proceedings. ; , s. 18-25
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Vision-based localization on robots and vehicles remains unsolved when extreme appearance change and viewpoint change are present simultaneously. The current state of the art approaches to this challenge either deal with only one of these two problems; for example FAB-MAP (viewpoint invariance) or SeqSLAM (appearance-invariance), or use extensive training within the test environment, an impractical requirement in many application scenarios. In this paper we significantly improve the viewpoint invariance of the SeqSLAM algorithm by using state-of-the-art deep learning techniques to generate synthetic viewpoints. Our approach is different to other deep learning approaches in that it does not rely on the ability of the CNN network to learn invariant features, but only to produce "good enough" depth images from day-time imagery only. We evaluate the system on a new multi-lane day-night car dataset specifically gathered to simultaneously test both appearance and viewpoint change. Results demonstrate that the use of synthetic viewpoints improves the maximum recall achieved at 100% precision by a factor of 2.2 and maximum recall by a factor of 2.7, enabling correct place recognition across multiple road lanes and significantly reducing the time between correct localizations.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- route-based place recognition
- deep learning
- Computer Science
- Datavetenskap
Publication and Content Type
- vet (subject category)
- kon (subject category)
To the university's database
- By the author/editor
-
Milford, Michael
-
Shen, Chunhua
-
Lowry, Stephanie ...
-
Sünderhauf, Niko
-
Shirazi, Sareh
-
Lin, Guosheng
-
show more...
-
Liu, Fayao
-
Pepperell, Edwar ...
-
Cadena, Cesar
-
Upcroft, Ben
-
Reid, Ian
-
show less...
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Computer Science ...
- Articles in the publication
- 2015 IEEE Confer ...
- By the university
-
Örebro University