A Biologically Inspired Appearance Model for Robust Visual Tracking
- Submitting institution
-
The University of Leicester
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1395
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2016.2586194
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 2357
- Volume
- 28
- Issue
- 10
- ISSN
- 1045-9227
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
https://doi.org/10.1109/TNNLS.2016.2586194
- 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
-
5
- Research group(s)
-
-
- Citation count
- 72
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Visual tracking is a task that continuously infers the state of a specific target from a video. This is an unsolved problem in computer vision which attracts increasing interest. This paper reports a novel framework simulating the primary visual cortex to construct a five-layer architecture for object tracking. Our proposed layered sparse representation was used by Lan et al. (IEEE TIP, 2018) in a multiple metric learning context. Our work supports the research of an Newton Advanced Fellowship award (NA160342). Part of the proposed technology has been used by others (e.g. Zhou et al. IEEE TCYBER, 2018).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -