A family of globally optimal branch-and-bound algorithms for 2D–3D correspondence-free registration
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9006741_1
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2019.04.002
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 36-54
- Volume
- 93
- Issue
- -
- ISSN
- 0031-3203
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- 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
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research makes major theoretical and practical advances to the state of the art in correspondence-free 2D-3D registration using points and lines by introducing the first globally optimal solutions to this challenging problem. This generalises the authors’ original formulation presented at the premier computer vision conference ICCV2015, adding full theoretical rigour with a 5-page supplementary proof of convergence and an extensive experimental evaluation on multiple benchmarks datasets. Practical applications of this research in the context of 2D/3D multimodal data indexing were evaluated in collaboration with industry partners (Double Negative, Filmlight) as part of EC FP7 project IMPART (grant #13968).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -