Walker_DeepLearningNavigation Corrected.pdf (392.51 kB)
Using deep autoencoders to investigate image matching in visual navigation
conference contribution
posted on 2023-06-09, 08:57 authored by Christopher Walker, Paul GrahamPaul Graham, Andy PhilippidesAndy PhilippidesThis paper discusses the use of deep autoencoder networks to find a compressed representation of an image, which can be used for visual naviga-tion. Images reconstructed from the compressed representation are tested to see if they retain enough information to be used as a visual compass (in which an image is matched with another to recall a bearing/movement direction) as this ability is at the heart of a visual route navigation algorithm. We show that both reconstructed images and compressed representations from different layers of the autoencoder can be used in this way, suggesting that a compact image code is sufficient for visual navigation and that deep networks hold promise for find-ing optimal visual encodings for this task.
History
Publication status
- Published
File Version
- Accepted version
Journal
Biomimetic and Biohybrid Systems. Living Machines 2017ISSN
0302-9743Publisher
Springer, ChamExternal DOI
Volume
10384Page range
465-474Event name
Conference on Biomimetic and Biohybrid SystemsEvent type
conferenceISBN
9783319635361Series
Lecture Notes in Computer ScienceDepartment affiliated with
- Informatics Publications
Research groups affiliated with
- Centre for Computational Neuroscience and Robotics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2017-11-21First Open Access (FOA) Date
2017-11-21First Compliant Deposit (FCD) Date
2017-11-21Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC