SeDAR: reading floorplans like a human—using deep learning to enable human-inspired localisation
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-11706
- Type
- D - Journal article
- DOI
-
10.1007/s11263-019-01239-4
- Title of journal
- International Journal of Computer Vision
- Article number
- -
- First page
- 1286
- Volume
- 128
- Issue
- 5
- ISSN
- 0920-5691
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2020
- URL
-
http://eprints.gla.ac.uk/218210/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: Proposes new paradigm for robot localisation based on recognising semantic landmarks from a floorplan, in contrast to classical point-based approaches, and demonstrates that accurate localisation can be achieved without the need for a depth sensor. SIGNIFICANCE: The use of semantic information for robot planning and localisation is an important step for more intuitive human-robot collaboration and the removal of the need for depth sensors allow for cheaper, less energy demanding robotic platforms. RIGOUR: The results were demonstrated in an extensive set of robotic experiments. IJCV is a premier computer vision and pattern recognition journal.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -