Unfalsified visual servoing for simultaneous object recognition and pose tracking
- Submitting institution
-
The University of Hull
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1398037
- Type
- D - Journal article
- DOI
-
10.1109/TCYB.2015.2495157
- Title of journal
- IEEE Transactions on Cybernetics
- Article number
- -
- First page
- 3032
- Volume
- 46
- Issue
- 12
- ISSN
- 2168-2267
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2016
- URL
-
http://ieeexplore.ieee.org/document/7583713/
- 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
-
3
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The data-driven unfalsified control proposed in this work recognizes a target by matching image features with a 3D model. This then tracks those targets through dynamic visual servoing and deals with failures caused by various disturbances, such as fast motion, occlusions and illumination variation. This is significant because earlier approaches were usually fragile to spurious feature matching and local convergence for pose determination therefore, where a failure happened, these approaches lacked a mechanism to recover automatically.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -