S-SMART: a unified Bayesian framework for Simultaneous Semantic Mapping, Activity Recognition and Tracking
- Submitting institution
-
University of Sussex
- Unit of assessment
- 12 - Engineering
- Output identifier
- 335131_56648
- Type
- D - Journal article
- DOI
-
10.1145/2824286
- Title of journal
- ACM Transactions on Intelligent Systems and Technology
- Article number
- -
- First page
- 34
- Volume
- 7
- Issue
- 3
- ISSN
- 2157-6904
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2016
- URL
-
http://dx.doi.org/10.1145/2824286
- 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)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The show a SLAM framework solving several problems jointly: locating a person's indoors (tracking); identifying where frequent actions take place (semantic mapping); and recognising key everyday activities (activity recognition). The unique aspect of this work is that the landmarks which SLAM needs are obtained without any need for sensing the environment: instead they are purely obtained from wearable sensors by detecting key unique gestures (e.g. turning a door handle). This work was presented at the Home Office Centre for Applied Science and Technology in 2017 as a possible technology to track or guide police or firemen in indoor spaces.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
