Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: A case study of lettuce production

Bauer, Alan, Bostrom, Aaron George ORCID: https://orcid.org/0000-0002-7300-6038, Ball, Joshua, Applegate, Christopher, Cheng, Tao, Laycock, Stephen, Rojas, Sergio Moreno, Kirwan, Jacob and Zhou, Ji (2019) Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: A case study of lettuce production. Horticulture Research, 2019 (6). pp. 1-12. ISSN 2052-7276

[thumbnail of AirSurf_MS_JZ_Final-Clean]
Preview
PDF (AirSurf_MS_JZ_Final-Clean) - Accepted Version
Download (6MB) | Preview
[thumbnail of Published_Version]
Preview
PDF (Published_Version) - Published Version
Available under License Creative Commons Attribution.

Download (5MB) | Preview

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.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 03 Jun 2019 14:48
Last Modified: 09 Mar 2024 01:14
URI: https://ueaeprints.uea.ac.uk/id/eprint/71241
DOI: 10.1038/s41438-019-0151-5

Actions (login required)

View Item View Item