Active Vision and Surface Reconstruction for 3D Plant Shoot Modelling
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1502782
- Type
- D - Journal article
- DOI
-
10.1109/TCBB.2019.2896908
- Title of journal
- IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Article number
- -
- First page
- 1907
- Volume
- 17
- Issue
- 6
- ISSN
- 1545-5963
- Open access status
- Compliant
- Month of publication
- April
- 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
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- 3D models of plants are required in a variety of measurement, modelling and simulation tasks in the biological sciences. Plants’ physical complexity and structural variability makes the quality of 3D reconstructions obtained from multiple views highly dependent on the images used. Previous methods have used fixed cameras, reducing both coverage and accuracy. This paper describes the first 3D plant reconstruction method to place the camera under active control, placing it in response to the emerging model of the given plant. The resulting, improved, representations were evaluated against ground truth obtained by x-ray imaging, the first work to do this.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
