Close

Search

Search Menu
Photonics Media Photonics Buyers' Guide Photonics Spectra BioPhotonics EuroPhotonics Vision Spectra Photonics Showcase Photonics ProdSpec Photonics Handbook
More News

Machine Learning and Computer Vision Lead to Smarter, More Precise Crop Management

Facebook Twitter LinkedIn Email Comments
Researchers at the Earlham Institute (EI), working with G’s Growers in Ely, England, have developed a machine learning platform that works with computer vision and ultra-large-scale images taken from the air to help categorize lettuce crops in fields.

To quantify millions of in-field lettuces acquired by fixed-wing light aircraft equipped with sensors, the researchers customized the platform, called AirSurf, by combining computer-vision algorithms and a deep-learning classifier trained with over 100,000 labeled lettuce signals. The tailored platform, AirSurf-Lettuce, demonstrated the capability to score and categorize iceberg lettuces with an accuracy of more than 98%.

The team also developed novel analysis functions to map lettuce size distribution across the field, based on associated GPS-tagged harvest regions, to enable growers to precisely track size distribution of lettuce in fields in order to improve yield and crop marketability before the harvest. AirSurf-Lettuce is able to measure iceberg lettuce in a high-throughput mode, identify the precise quantity and location of lettuce plants, and distinguish whether lettuce heads are small, medium, or large.

Machine learning for crop optimization, Earlham Institute and G's Growers.
Transplanting lettuce at Gs Growers plantation field, near Ely, England. Courtesy of G’s Growers.

“This cross-disciplinary collaboration integrates computer vision and machine learning with the lettuce growing business to demonstrate how we can improve crop yields using machine learning,” said scientist Alan Bauer, a member of the Zhou Group at EI.

Using technology like AirSurf could help growers to understand the variability in their fields and crops at a higher level of detail than is possible with previous techniques. “The decisions that can then be taken from this information, such as varying applications of inputs and irrigation, changing harvest strategies, and planning the optimum time to sell crop, will all contribute toward increasing on farm yields and improving farm productivity,” said Jacob Kirwan, innovation manager at G’s Growers.

The AirSurf technology could be applied to other crops, said the researchs, widening its potential for making a positive impact across the agri-food sector.

The research was published in Horticulture Research (https://doi.org/10.1038/s41438-019-0151-5). 

Vision-Spectra.com
Jun 2019
Research & TechnologyeducationEuropeEarlham Instituteimagingcamerasdeep learningmachine learningcomputer visionPrecision agricultureAir-Surfaerial imagingSensors & Detectorsenvironment

Comments
Submit a Feature Article Submit a Press Release
Terms & Conditions Privacy Policy About Us Contact Us
Facebook Twitter Instagram LinkedIn YouTube RSS
©2019 Photonics Media, 100 West St., Pittsfield, MA, 01201 USA, info@photonics.com

Photonics Media, Laurin Publishing
x We deliver – right to your inbox. Subscribe FREE to our newsletters.
We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.