FFD : Fast Feature Detector
- Submitting institution
-
Aberystwyth University / Prifysgol Aberystwyth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 41430095
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2020.3042057
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- 9292438
- First page
- 1153
- Volume
- 30
- Issue
- -
- ISSN
- 1057-7149
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2020
- 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
-
2
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Introduces a novel feature detector that is about 20 times faster than the SIFT detector, and shows excellent repeatability and robustness when compared to a range of state-of-the-art multiscale and learnt detectors. When evaluated using visual localisation and 3D reconstruction as example applications it shows better results than state-of-the-art techniques in most experiments on benchmark datasets. Published in IEEE Transaction on Image Processing, the premier journal in image processing.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -