From Cows to Crops: Computer Vision for Precision Agriculture

by Yulia Ivanova

Recent technological advances have allowed a step-change in the way the farmers, agronomists and plant breeders can gather and analyse data. Automated livestock welfare management, precision weed control and measurement of phenotypic traits in plants all allow greater yields with fewer inputs - such as feed and agricultural chemicals. Central to many of these systems is the concept of computer vision, the process of analysing images or videos to automatically obtain meaningful measurements, without the need for manual intervention. At the RE•WORK Future of Food Summit, Ian Hales, a Research Associate in 3D Machine Vision at Bristol Robotics Lab, will discuss these systems and how they directly benefit the agricultural and plant science community, using real-world, state-of-the-art examples currently under development.   Ian's most recent project is the development of a system for automated health and welfare management in dairy cattle, taking advantage of the wealth of rich data that can be garnered from 3D imagery to measure traits affected by lameness and condition, with the aim of detecting them early and preventing unnecessary suffering, whilst also maximising yield. We caught up with Ian, ahead of his presentation at the event on 21 June, to hear his thoughts on the AgTech industry.What do you feel are the most urgent challenges within the food and agricultural industries?The dairy industry is under constant pressure to lower prices, with many farmers famously reporting losses on the cost of production. A cow’s milk production can be directly correlated to its state of wellbeing, and as such maintaining good body condition is key to maximising yield. Condition scoring in dairy cattle has been shown to be a somewhat subjective process, prone to discrepancies not just between different observers but also between observations of the same animal by the same observer. Reliable detection of lameness has also been shown to be non-trivial as livestock will often attempt to mask the symptoms from human observers.How can these problems be solved with technology?Commercial computer vision systems are currently under development to autonomously examine, record and report dairy cattle condition repeatedly and over prolonged periods. The advantages of such systems are three-fold:

  1. The dairy farmer can maintain an accurate and lasting record of herd condition
  2. The measurements of said condition are objective and not subject to human influence
  3. The animals themselves are not influenced by the presence of humans, so are less likely to attempt to mask symptoms, thus allowing earlier and more accurate detection of lameness.

What new developments in AgTech and FoodTech can we expect to see in the next 5 years?Computer vision systems are already being commercially implemented to augment existing farm machinery, such as the Garford InRow weeder; however there is often still a strong human element. We are just starting to see fully autonomous robotic systems emerging as speciality and research tools (e.g. the Bosch BoniRob) and I believe this is the direction towards which we can expect to see commercial systems move, particularly as the EU maintains its Horizon 2020 focus on food security. What are the top three things you would like to see changed or invented in the food industry by 2050?

  1. Fully autonomous robotic systems across the entire cereal crop farming chain (from preparation, through growth, to harvest)
  2. The eradication of wide-scale weed control chemical usage in favour of non-chemical methodologies (mechanical, heat, electrical current)
  3. Indoor hydroponics and vertical farming to lower the cost of fresh produce whilst maximising yield in areas of limited space

Ian Hales will be speaking at the RE•WORK Future of Food Summit, held during London Technology Week on 21 June 2016. Other speakers include Florian Pinel, Lead Engineer, IBM Chef Watson; Abi Glencross, PhD in Cellular Agriculture, King's College London; Nick Holzherr, Founder & CEO of Whisk.com; Richard Ballard, Co-Founder of Growing Underground; Ian Hales, Research Associate, Bristol Robotics Lab, and more.

Early Bird tickets are available until 29 April, for more information visit the event page here. Our previous foodtech event sold out, so book early to avoid disappointment!