How machine learning and computer vision can help farmers harvest better lettuces

Researchers at the Earlham Institute have developed a machine learning platform called AirSurf-Lettu

Researchers at the Earlham Institute have developed a machine learning platform called AirSurf-Lettuce, which works with computer vision and ultra-scale aerial images to categorise lettuce crops in fields. Picture: Earlham Institute. - Credit: Earlham Institute

Artificial intelligence, computer vision and ultra-scale imagery have been combined in a hi-tech project to help East Anglian farmers harvest better lettuce crops.

Researchers at the Earlham Institute (EI) on the Norwich Research Park have teamed up with Ely-based salad specialists G's Growers to developed a system called AirSurf-Lettuce to accurately analyse and categorise lettuces in the field - giving farmers detailed data on which to base their harvesting decisions.

The advanced software combines "machine learning" with sophisticated, ultra-wide-scale imaging analysis to measure the precise quantity, size and location of lettuce plants to help farmers track the exact size and distribution of their crop, and get it to market in the most efficient way possible.

Lettuce is big business in East Anglia, but up to 30pc of yield can be lost due to inefficiencies in the growing process and harvest strategies.

The project partners said if farmers could be given a precise understanding of when crops will become harvest-ready, they could optimise the planning of logistics, trading and marketing their produce - improving their efficiency and profitability.

You may also want to watch:

Jacob Kirwan, innovation manager at G's Growers, said: "Farming at a large scale means that precision is essential when ensuring that we are producing crops in an environmentally and economically-sustainable way. Using technology like AirSurf means that growers are able to understand the variability in their fields and crops at a much higher level of detail that was previously possible.

"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 towards increasing on-farm yields and improving farm productivity."

Most Read

EI group leader Dr Ji Zhou said: "My lab is keen to seek every possible approach to translate our public-funded research in algorithm design, machine learning, computer vision, and crop phenomics to techniques and tools that can be used by academic and industrial partners to address challenging problems in crop research and crop production.

"We have partnered with G's, leading vegetable growers in the UK, to equip our agri-food sector with smart and precise crop surveillance and analytical methods, for which we are confident that better crop management decisions and enhanced crop marketability could be achieved through our joint efforts."

Become a Supporter

This newspaper has been a central part of community life for many years. Our industry faces testing times, which is why we're asking for your support. Every contribution will help us continue to produce local journalism that makes a measurable difference to our community.

Become a Supporter
Comments powered by Disqus