New image-analysis tech to help feed the world

visual-analysis-small

Remarkable Adelaide research is developing innovative image-analysis technology to dramatically accelerate identification of robust crop varieties capable of producing higher yields in harsh, climate-change-affected conditions.

Food security has been on the international agenda for some time. But the projected impact of climate change, together with rising population, has elevated the issue to emergency status. With total arable land already decreasing at a worrying rate—it’s estimated nearly 33% has been lost across the planet over the past 40 years through erosion and pollution—a further increase in global average temperatures could be catastrophic.

Here in Australia, for example, climate models suggest drought could be as much as 20% more common by 2030 across much of the country, and up to 80% by 2070 in south-western Australia, an area currently responsible for much of our cereal cropping.

Clearly, the rapid development of new crop varieties able to grow and produce higher yields in harsher, more marginal conditions is becoming critical; and research at the University of Adelaide is helping to make it happen.

A team led by the School of Computer Science’s Australian Centre for Visual Technologies (ACVT) is developing world-first image-analysis technology capable of accurately estimating potential new cereal varieties’ yields after very short periods of growth.

“This novel approach promises to absolutely transform crop breeding,” says lead researcher and director of the ACVT Professor Anton van den Hengel.

“By using image analysis to understand the shape and structure of plants at all stages of growth, we’ll be able to identify and automatically measure attributes associated with high yields early in test plants’ lifespans, rather than waiting for them to mature.”

The system will use multiple images taken from numerous angles to construct computerised 3D models of the plants for analysis. Once completed, it will be incorporated into the state-of-the-art Plant Accelerator at the University’s Waite Campus.

According to Professor van den Hengel, this advanced facility will provide vital complementary capability for the research team. “The Plant Accelerator’s fully robotic plant management system allows automatic and repeatable control of the growing conditions of up to 2400 plants at a time, and will enable automatic delivery of those plants to our imaging stations.

“That’s going to allow us to rapidly provide detailed, accurate estimations of vast numbers of crop varieties’ potential yields under all kinds of climate-change-related stresses, such as high salinity or drought.

“We’ve no doubt that will expedite the development of hardy, high-yield varieties and help improve both Australia’s agricultural competitiveness, and global food security.”

Industry partner Bayer CropScience will assist with commercialisation of the groundbreaking technology.

Related links:
Food Innovation
School of Computer Science’s Australian Centre for Visual Technologies
Professor Anton van den Hengel – researcher profile
Plant Accelerator at the University’s Waite Campus