Browse Articles

Article|01 Jun 2019|OPEN
Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: A case study of lettuce production
Alan Bauer1,2,3 , Aaron George Bostrom1 , Joshua Ball1 , Christopher Applegate1 , Tao Cheng4 , Stephen Laycock3 and Sergio Moreno Rojas5 , Jacob Kirwan5 , , Ji Zhou,1,2,3 ,
1Earlham Institute, Norwich Research Park, Norwich NR4 7UZ, UK
2Plant Phenomics Research Center, China-UK Plant Phenomics Research Centre, Nanjing Agricultural University, Nanjing 210095 Jiangsu, China
3School of Computing Sciences, University of East Anglia, Norwich Research Park, Norwich NR4 7TJ, UK
4National Engineering and Technology Center for Information Agriculture, MARA Key Laboratory for Crop System Analysis and Decision Making, Jiangsu Key Laboratory for Information Agriculture, Nanjing Agricultural University, Nanjing 210095 Jiangsu, China
5G’s Growers Limited, Ely, Cambridgeshire CB7 5TZ, UK
*Corresponding author. E-mail: Jacob.Kirwan@GS-Growers.com,Ji.Zhou@njau.edu.cn

Horticulture Research 6,
Article number: 70 (2019)
doi: https://doi.org/10.1038/s41438-019-0151-5
Views: 1054

Received: 08 Jan 2019
Revised: 01 Apr 2019
Accepted: 08 Apr 2019
Published online: 01 Jun 2019

Abstract

Aerial imagery is regularly used by crop researchers, growers and farmers to monitor crops during the growing season. To extract meaningful information from large-scale aerial images collected from the field, high-throughput phenotypic analysis solutions are required, which not only produce high-quality measures of key crop traits, but also support professionals to make prompt and reliable crop management decisions. Here, we report AirSurf, an automated and open-source analytic platform that combines modern computer vision, up-to-date machine learning, and modular software engineering in order to measure yield-related phenotypes from ultra-large aerial imagery. To quantify millions of in-field lettuces acquired by fixed-wing light aircrafts equipped with normalised difference vegetation index (NDVI) sensors, we customised AirSurf by combining computer vision algorithms and a deep-learning classifier trained with over 100,000 labelled lettuce signals. The tailored platform, AirSurf-Lettuce, is capable of scoring and categorising iceberg lettuces with high accuracy (>98%). Furthermore, novel analysis functions have been developed to map lettuce size distribution across the field, based on which associated global positioning system (GPS) tagged harvest regions have been identified to enable growers and farmers to conduct precision agricultural practises in order to improve the actual yield as well as crop marketability before the harvest.