Prior knowledge-based deep learning method for indoor object recognition and application
- Submitting institution
-
The University of Hull
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1398040
- Type
- D - Journal article
- DOI
-
10.1080/21642583.2018.1482477
- Title of journal
- Systems Science and Control Engineering
- Article number
- -
- First page
- 249
- Volume
- 6
- Issue
- 1
- ISSN
- 2164-2583
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- URL
-
https://www.tandfonline.com/doi/full/10.1080/21642583.2018.1482477
- 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
-
9
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- An essential task in robot vision is how to efficiently detect and recognise indoor objects. This paper proposes a novel solution to address this problem by using a knowledge-based deep learning method which precisely detects indoor objects in a real-time situation. The key contribution is that the prior knowledge, based on colour and scene, makes it easy to make a real-time decision when a detection request is launched. This original piece of research has received funding from Natural Science Foundation of Anhui Province China and the National Natural Science Foundation of China.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -