A Model-Based Approach to Recovering the Structure of a Plant from Images
Type
Conference PaperAuthors
Ward, BenBastian, John
van den Hengel, Anton
Pooley, Daniel
Bari, Rajendra
Berger, Bettina
Tester, Mark A.

KAUST Department
Biological and Environmental Science and Engineering (BESE) DivisionCenter for Desert Agriculture
Plant Science
Plant Science Program
The Salt Lab
Date
2015-03-19Preprint Posting Date
2015-03-11Online Publication Date
2015-03-19Print Publication Date
2015Permanent link to this record
http://hdl.handle.net/10754/556196
Metadata
Show full item recordAbstract
We present a method for recovering the structure of a plant directly from a small set of widely-spaced images for automated analysis of phenotype. Structure recovery is more complex than shape estimation, but the resulting structure estimate is more closely related to phenotype than is a 3D geometric model. The method we propose is applicable to a wide variety of plants, but is demonstrated on wheat. Wheat is composed of thin elements with few identifiable features, making it difficult to analyse using standard feature matching techniques. Our method instead analyses the structure of plants using only their silhouettes. We employ a generate-and-test method, using a database of manually modelled leaves and a model for their composition to synthesise plausible plant structures which are evaluated against the images. The method is capable of efficiently recovering accurate estimates of plant structure in a wide variety of imaging scenarios, without manual intervention.Citation
Ward, B., Bastian, J., van den Hengel, A., Pooley, D., Bari, R., Berger, B., & Tester, M. (2015). A Model-Based Approach to Recovering the Structure of a Plant from Images. Lecture Notes in Computer Science, 215–230. doi:10.1007/978-3-319-16220-1_16Publisher
Springer NatureConference/Event name
13th European Conference on Computer Vision, ECCV 2014arXiv
1503.03191Additional Links
http://link.springer.com/chapter/10.1007%2F978-3-319-16220-1_16http://arxiv.org/abs/1503.03191
ae974a485f413a2113503eed53cd6c53
10.1007/978-3-319-16220-1_16