Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop (CVPPP) 2015

Editors: S. A. Tsaftaris, H. Scharr, and T. Pridmore BMVA Press, September 2015, ISBN 1-901725-55-3


It was our great pleasure to welcome all workshop participants of the 26th British Machine Vision Conference (BMVC) to Swansea. BMVC is one of the top events in the field of Computer Vision and we were happy to host this yearÕs edition of the Computer Vision Problems in Plant Phenotyping workshop, following the first and successful CVPPP at ECCV 2014.

Plant phenotyping is the identification of effects on plant structure and function (the phenotype) resulting from genotypic differences (i.e., differences in the genetic code) and the environmental conditions a plant has been exposed to. While collection of phenotypic traits was previously manual, non-invasive, image-based methods are now increasingly utilized in plant phenotyping and the resulting images need to be analysed in a high throughput, robust, accurate, and reliable manner. The problems raised differ from the usual tasks addressed by the computer vision community, due to the requirements posed by this challenging application scenario. Unfortunately, without automated and accurate computer vision to extract the phenotypes, a bottleneck is formed, hampering our understanding of plant biology. Our goal with this workshop was to continue to showcase these challenges, discuss current methods and advance the state-of-the-art.

We were happy that this year we also introduced new features to CVPPP. We had an exciting keynote by Prof. Tim Cootes who gave inspiring insight into how active shape and appearance models could be applied to problems in agriculture, plants, and phenotyping. We also had two challenges: a follow up to last yearÕs leaf segmentation challenge; and a new leaf counting challenge. For both, machine learning approaches gave the best results.

We had a good number of high-quality accepted papers. Presenters were both from Europe and the USA. We had close to 30 participants in the audience, out of which, we were excited that more than half were walk ins, having seen our workshop advertisements at the main conference. We were also really excited that we had individuals not only from major companies within the field but also from major corporations.

Overall, we were extremely happy with the outcome and we hope to continue such events in the future. CVPPP aims to help bridge the gap between computer vision and the agricultural sciences, which is essential to not only literally help feed the world, but also for feed, fibre and fuel production.

Finally, we would like to thank our keynote speaker Prof. Cootes, authors, reviewers, participants, funding agencies, and the BMVC organizers for their respective contributions.

Sotirios A Tsaftaris, Hanno Scharr, Tony Pridmore,
CVPPP 2015 Organizers

Programme Committee

Eren Aksoy, Karlsruher Institut für Technologie, Germany
Arijit Biswas, Xerox Research Center India
Tim Brown, Australian National University, Australia
Babette Dellen, University of Applied Sciences Koblenz, Germany
Guillerme Desouza, University of Missouri-Columbia,USA
Andrew French, University of Nottingham, UK
Jurgen Fripp, CSIRO, Australia
Pablo M. Granitto, CIFASIS, Argentina
Markus Hoeferlin, Robert Bosch Start-up, Germany
Gustavo Pereyra Irujo, CONICET, Argentina
Toni Kazic, University of Missouri, USA
Christian Klukas, LemnaTec, Germany
Gert Kootstra, Wageningen, The Netherlands
Xiaoming Liu, Michigan State University, USA
Guillaume Lobet, Université de Liège, Belgium
B. S. Manjunath, University of California, Santa Barbara, USA
Vasileios Mezaris, CERTH-Information Technologies Institute
Massimo Minervini, IMT Lucca, Italy
Marie Neal, Aberystwyth University, UK
Gerrit Polder, Wageningen, The Netherlands
David Rousseau, Univ. of Lyon, France
Kyle Simek, University of Arizona, USA
Concetto Spampinato, University of Catania, Italy
Junsong Yuan, Nanyang Technological University, Singapore
Rick van de Zedde, Wageningen, The Netherlands