Adaptive fusion of particle filtering and spatio-temporal motion energy for human tracking
- Submitting institution
-
Brunel University London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 022-94828-10071
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2014.05.006
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 3552
- Volume
- 47
- Issue
- 11
- ISSN
- 0031-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- URL
-
http://bura.brunel.ac.uk/handle/2438/11487
- 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
-
4
- Research group(s)
-
4 - Sensors & Digital Systems
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Object tracking becomes very challenging in scenes which include occlusion and pose/illumination changes. This work tackles this challenge successfully by fusing two important cues about the object of interest, namely colour and motion energy. This is a joint research work with Leicester University and two overseas collaborators from Chinese universities. The developed algorithm evaluates the reliability of both cues and determines their levels of importance in contributing to the overall tracking decision. The developed object tracking algorithm achieves higher tracking accuracy than state of the art techniques.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -