Multi-Target Tracking and Occlusion Handling With Learned Variational Bayesian Clusters and a Social Force Model
- Submitting institution
-
The University of Leicester
- Unit of assessment
- 12 - Engineering
- Output identifier
- 1520
- Type
- D - Journal article
- DOI
-
10.1109/TSP.2015.2504340
- Title of journal
- IEEE Transactions on Signal Processing
- Article number
- -
- First page
- 1320
- Volume
- 64
- Issue
- 5
- ISSN
- 1053-587X
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
https://doi.org/10.1109/TSP.2015.2504340
- 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
- Human tracking in busy occupied environments such as airports or railway stations is a crucial element of video-based security systems. This collaborative activity with Sheffield and Newcastle Universities was extremely significant as it proposed a state-of-the-art multiple human tracking algorithm suitable for complex and fast-changing environments. It was the key outcome of an EPSRC-funded project (EP/K021516/1), and triggered a very successful special session in the world-leading International Conference in Information FUSION (http://www.fusion2014.org/special-sessions/ss11-mdlt.html) and strategic collaboration with Thales {angus.johnson@uk.thalesgroup.com}.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -