DS-KCF : a real-time tracker for RGB-D data
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 95888960
- Type
- D - Journal article
- DOI
-
10.1007/s11554-016-0654-3
- Title of journal
- Journal of Real-Time Image Processing
- Article number
- -
- First page
- 1439
- Volume
- 16
- Issue
- -
- ISSN
- 1861-8200
- Open access status
- Compliant
- Month of publication
- November
- 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
-
7
- Research group(s)
-
C - Visual Information Lab
- Citation count
- 27
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This consolidated work describes the first real-time RGB-D domain KCF tracker, extending a BMVC publication (DOI:10.5244/C.29.145). It was evaluated on public datasets and the codebase is public (https://data.bris.ac.uk/data/dataset/1mddmf1o6f54d18zgr2jvahs8p) counting hundreds of downloads and significant external use (e.g. [Xiao'18, IEEE Transactions on Cybernetics] , [Kart'19, CVPR]). In terms of accuracy and speed, it was ranked highest for RGB-Depth data (Princeton Tracking Benchmark http://tracking.cs.princeton.edu/eval.php). Performed under the £12M EPSRC SPHERE (EP/K031910/1), it underpinned the follow-on £7M EPSRC SPHERE-Next-Steps (EP/R005273/1). Invited seminars include: IET Healthcare Symposium, Madrid University and Sharif University of Technology. It has 6897 accesses (https://link.springer.com/article/10.1007/s11554-016-0654-3) and 3,063 views on YouTube.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -