For several years, agricultural research has been using sensors to observe plants at key moments in their development. However, some important plant traits are still measured manually. One example of this is the manual counting of wheat ears from digital images - a long and tedious job. Factors that make it difficult to manually count wheat ears from digital images include the possibility of overlapping ears, variations in appearance according to maturity and genotype, the presence or absence of barbs, head orientation and even the wind.
There is the need for a robust and accurate computer model that is capable of counting wheat ears from digital images. This model will benefit phenotyping research and help producers around the world assess ear density, health and maturity more effectively. Some work has already been done in deep learning, though it has resulted in too little data to have a generic model.
The Global Wheat Head Challenge, an international data science competition, was created to address this need. The objective is to design a software model capable of locating ears on a wide variety of data, without bias. Data scientists, hackers, scientists and the curious are invited to participate in helping solve this global challenge!
- The competition will run on the Kaggle platform from May 4 to August 4, 2020.
- International consortium, Global Wheat Dataset, has made more than 190,000 wheat ears available for this competition. Participants are invited to submit software models, based on this dataset, for counting wheat ears effectively.
- The University of Saskatchewan, Canada.
- The University of Tokyo, NARO, Japan.
- The University of Queensland, Australia.
- UMT CAPTE (INRAe - Arvalis - HIPHEN), France.
- Rothamsted Research, United Kingdom.
- ETH Zurich, Switzerland.
- Nanjing Agricultural University, China.
The total prize for the competition is $15,000 USD, sponsored by the Global Institute for Food Security and the Plant Phenotyping and Imaging Research Centre at the University of Saskatchewan, Canada:
1st Prize: $8000.
2nd Prize: $4000.
3rd Prize: $3000.
Full details on the competition and on how to participate are available at www.kaggle.com/c/global-wheat-detection.