Selective sampling importance resampling particle filter tracking with multibag subspace restoration
- Submitting institution
-
Glasgow Caledonian University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 33575203
- Type
- D - Journal article
- DOI
-
10.1109/TCYB.2016.2631660
- Title of journal
- IEEE Transactions on Cybernetics
- Article number
- -
- First page
- 264
- Volume
- 48
- Issue
- 1
- ISSN
- 2168-2267
- Open access status
- Compliant
- Month of publication
- December
- 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
-
3
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work focuses on the significant problem of model drift in visual object tracking which results in a gradual decrease in accuracy over time and eventually lost targets. Incorporating a bank of previous models allows for the detection of drift through comparison with the current and previous model. This work was a key contributor to later work as part of KTP9801 with GCU and Geckotech Solutions Ltd which won ‘Best KTP’ and was shortlisted for ‘Engineering Excellence’ at the Knowledge Transfer Partnership 2019 Best of the Best Awards.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -