Database/Software Article | Open Access

Volume 2021 |Article ID 9846158 | https://doi.org/10.34133/2021/9846158

Global Wheat Head Detection 2021: An Improved Dataset for Benchmarking Wheat Head Detection Methods

Etienne David iD ,^1,2 Mario SerouartiD ,^1,2 Daniel SmithiD ,³ Simon MadeciD ,^1,3 Kaaviya VelumaniiD ,^2,4 Shouyang LiuiD ,⁵ Xu WangiD ,⁶ Francisco PintoiD ,⁷ Shahameh Shafiee,⁸ Izzat S. A. TahiriD ,⁹ Hisashi TsujimotoiD ,¹⁰ Shuhei NasudaiD ,¹¹ Bangyou ZhengiD ,¹² Norbert KirchgessneriD ,¹³ Helge AaseniD ,¹³ Andreas HundiD ,¹³ Pouria Sadhegi-TehraniD ,¹⁴ Koichi NagasawaiD ,¹⁵ Goro IshikawaiD ,¹⁶ Sébastien DandrifosseiD ,¹⁷ Alexis CarlieriD ,¹⁷ Benjamin DumontiD ,¹⁸ Benoit MercatorisiD ,¹⁷ Byron EversiD ,⁶ Ken KurokiiD ,¹⁹ Haozhou WangiD ,¹⁹ Masanori Ishii,¹⁹ Minhajul A. BadhoniD ,²⁰ Curtis PozniakiD ,²¹ David Shaner LeBaueriD ,²² Morten LillemoiD ,⁸ Jesse PolandiD ,⁶ Scott ChapmaniD ,^3,12 Benoit de SolaniD ,¹ Frédéric BaretiD ,² Ian StavnessiD ,²⁰ and Wei GuoiD ¹⁹

¹Arvalis, Institut du végétal, 3 Rue Joseph et Marie Hackin, 75116 Paris, France
²UMR1114 EMMAH, INRAE, Centre PACA, Bâtiment Climat, Domaine Saint-Paul, 228 Route de l’Aérodrome, CS 40509, 84914 Avignon Cedex, France
³School of Food and Agricultural Sciences, The University of Queensland, Gatton, 4343 QLD, Australia
⁴Hiphen SAS, 120 Rue Jean Dausset, Agroparc, Bâtiment Technicité, 84140 Avignon, France
⁵Plant Phenomics Research Center, Nanjing Agricultural University, Nanjing, China
⁶Wheat Genetics Resource Center, Dep. of Plant Pathology, Kansas State Univ., 4024 Throckmorton Plant Sciences Center, Manhattan, Kansas, USA
⁷Global Wheat Program, International Maize and Wheat Improvement Centre (CIMMYT), Mexico, D.F., Mexico
⁸Faculty of Biosciences, Norwegian University of Life Sciences, P.O. Box 5003, NO-1432 Ås, Norway
⁹Agricultural Research Corporation, Wheat Research Program, P.O. Box 126, Wad Medani, Sudan
¹⁰Arid Land Research Center, Tottori University, Tottori 680-0001, Japan
¹¹Laboratories of Plant Genetics and Plant Breeding, Graduate School of Agriculture, Kyoto University, Japan
¹²CSIRO Agriculture and Food, Queensland Biosciences Precinct, 306 Carmody Road, St Lucia, 4067 QLD, Australia
¹³Institute of Agricultural Sciences, ETH Zurich, Universitätstrasse 2, 8092 Zurich, Switzerland
¹⁴Plant Sciences Department, Rothamsted Research, Harpenden, UK
¹⁵Institute of Crop Science, National Agriculture and Food Research Organization, Japan
¹⁶Hokkaido Agricultural Research Center, National Agriculture and Food Research Organization, Japan
¹⁷Biosystems Dynamics and Exchanges, TERRA Teaching and Research Center, Gembloux Agro-Bio Tech, University of Liège, 5030 Gembloux, Belgium
¹⁸Plant Sciences, TERRA Teaching and Research Center, Gembloux Agro-Bio Tech, University of Liège, 5030 Gembloux, Belgium
¹⁹Graduate School of Agricultural and Life Sciences, The University of Tokyo, 1-1-1 Midori-cho, Nishitokyo City, Tokyo, Japan
²⁰Department of Computer Science, University of Saskatchewan, Canada
²¹Department of Plant Sciences, University of Saskatchewan, Canada
²²College of Agriculture and Life Sciences, University of Arizona, Tucson, Arizona, USA

Abstract

The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience, a few avenues for improvements have been identified regarding data size, head diversity, and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and complemented by adding 1722 images from 5 additional countries, allowing for 81,553 additional wheat heads. We now release in 2021 a new version of the Global Wheat Head Detection dataset, which is bigger, more diverse, and less noisy than the GWHD_2020 version.