Global Wheat Head Detection Challenges: Winning Models and Application for Head Counting

Etienne David; Franklin Ogidi; Daniel Smith; Scott Chapman; Benoit de Solan; Wei Guo; Frederic Baret; Ian Stavness

doi:10.34133/plantphenomics.0059

Global Wheat Head Detection Challenges: Winning Models and Application for Head Counting

Plant Phenomics. 2023 Jun 26:5:0059. doi: 10.34133/plantphenomics.0059. eCollection 2023.

Authors

Etienne David^{1

2}, Franklin Ogidi³, Daniel Smith⁴, Scott Chapman⁴, Benoit de Solan², Wei Guo⁵, Frederic Baret¹, Ian Stavness³

Affiliations

¹ UMR 1114 EMMAH, INRAE, Avignon, France.
² Arvalis - Institut du Végétal, Paris, France.
³ Department of Computer Science, University of Saskatchewan, Saskatoon, Canada.
⁴ School of Food and Agricultural Sciences, University of Queensland, Brisbane, Australia.
⁵ Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan.

Abstract

Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems. Data competitions have a rich history in plant phenotyping, and new outdoor field datasets have the potential to embrace solutions across research and commercial applications. We developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions. We analyze the winning challenge solutions in terms of their robustness when applied to new datasets. We found that the design of the competition had an influence on the selection of winning solutions and provide recommendations for future competitions to encourage the selection of more robust solutions.

Grants and funding

The work received support from ANRT for the CIFRE grant of E.D., cofunded by Arvalis. The study was partly supported by several projects, including: Canada: The Canada First Research Excellence Fund and the Global Institute Food Security, University of Saskatchewan supported the organization of the competition. France: PIA #Digitag Institut Convergences Agriculture Numérique, Hiphen supported the organization of the competition and the Agence Nationale de la Recherche projects ANR-11-INBS-0012 (Phenome). Japan: Kubota supported the organization of the competition. Australia: Grains Research and Development Corporation (UOQ2002-008RTX Machine learning applied to high-throughput feature extraction from imagery to map spatial variability and UOQ2003-011RTX INVITA - A technology and analytics platform for improving variety selection) supported competition and data provision/discussions.