Risk analysis for smart homes and domestic robots using robust shape and physics descriptors, and complex boosting techniques
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-21-1353
- Type
- D - Journal article
- DOI
-
10.1016/j.ins.2016.08.075
- Title of journal
- Information Sciences
- Article number
- -
- First page
- 359
- Volume
- 372
- Issue
- -
- ISSN
- 0020-0255
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2016
- URL
-
-
- 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
-
-
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work introduces the concept of risk analysis for domestic robots. Novel computer vision methods were proposed to allow robots to understand risky and dangerous situations for humans and themselves. Cases that involve sharp objects, items placed at unstable locations and scenarios that include human behaviour simulation were considered. For the first time, physics engines were combined with computer vision to provide real-time outcomes. Furthermore, a dataset was created including scenes and object associated to different levels of risk. This work has applications in areas related to domestic robots, smart homes, and laboratory safety and security.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
