A Model-Based Approach to Recovering the Structure of a Plant from Images

Handle URI:
http://hdl.handle.net/10754/556196
Title:
A Model-Based Approach to Recovering the Structure of a Plant from Images
Authors:
Ward, Ben; Bastian, John; van den Hengel, Anton; Pooley, Daniel; Bari, Rajendra; Berger, Bettina; Tester, Mark A. ( 0000-0002-5085-8801 )
Abstract:
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.
KAUST Department:
Center for Desert Agriculture
Publisher:
Springer International Publishing
Journal:
Computer Vision - ECCV 2014 Workshops
Conference/Event name:
13th European Conference on Computer Vision, ECCV 2014
Issue Date:
19-Mar-2015
DOI:
10.1007/978-3-319-16220-1_16
ARXIV:
arXiv:1503.03191
Type:
Conference Paper
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-319-16220-1_16; http://arxiv.org/abs/1503.03191
Appears in Collections:
Conference Papers; Center for Desert Agriculture

Full metadata record

DC FieldValue Language
dc.contributor.authorWard, Benen
dc.contributor.authorBastian, Johnen
dc.contributor.authorvan den Hengel, Antonen
dc.contributor.authorPooley, Danielen
dc.contributor.authorBari, Rajendraen
dc.contributor.authorBerger, Bettinaen
dc.contributor.authorTester, Mark A.en
dc.date.accessioned2015-06-03T08:37:04Zen
dc.date.available2015-06-03T08:37:04Zen
dc.date.issued2015-03-19en
dc.identifier.doi10.1007/978-3-319-16220-1_16en
dc.identifier.urihttp://hdl.handle.net/10754/556196en
dc.description.abstractWe 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.en
dc.publisherSpringer International Publishingen
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-16220-1_16en
dc.relation.urlhttp://arxiv.org/abs/1503.03191en
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16220-1_16en
dc.subjectPlant phenotypingen
dc.subjectImage processingen
dc.subjectPlant architectureen
dc.titleA Model-Based Approach to Recovering the Structure of a Plant from Imagesen
dc.typeConference Paperen
dc.contributor.departmentCenter for Desert Agricultureen
dc.identifier.journalComputer Vision - ECCV 2014 Workshopsen
dc.conference.date2014-09-06 to 2014-09-12en
dc.conference.name13th European Conference on Computer Vision, ECCV 2014en
dc.conference.locationZurich, CHEen
dc.eprint.versionPost-printen
dc.contributor.institutionSchool of Computer Science, The University of Adelaide, Adelaide, Australiaen
dc.contributor.institutionBayer CropScience, Ghent, Belgiumen
dc.contributor.institutionThe Plant Accelerator, The University of Adelaide, Adelaide, Australiaen
dc.identifier.arxividarXiv:1503.03191en
kaust.authorTester, Mark A.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.