Purdue Develops Drone Technology Using Thermal Imaging Sensors to Help Scout Farm Fields – 95.3 MNC

Purdue Develops Drone Technology Using Thermal Imaging Sensors to Help Scout Farm Fields – 95.3 MNC

Keith Cherkauer, from left, Michael Montgomery, an undergraduate in Purdue Polytechnic Institute’s School of Aviation and Transportation Technology, and Kevin Lee, a doctoral candidate in agricultural and biological engineering, prepare a drone for test flights at the university’s Agronomy Center Purdue Research and Education. (Purdue Agricultural Communications photo/Tim Thompson)

Say you’re an agricultural scientist and you know there’s a technology that could change the game in your research. But its application in agriculture is still relatively new, so finding someone who can help you use it is challenging.

This is the case with thermal remote sensing technology – equipping drones or unmanned aerial vehicles (UAVs) with thermal sensors that produce images of fields based on temperature and processing this data for researchers to analyze and apply.

The Purdue Plant Sciences team has now created a protocol to enable the application of UAV-based remote sensing thermal imaging. The protocol takes advantage of innovative UAV technologies provided by STRONGa company founded at Purdue and is able to provide information-rich data to scientists in various disciplines.

“Our goal is to create a protocol that agricultural researchers can rely on,” says Sungchan “Sun” Oh, computing infrastructure specialist on the Plant Sciences team led by Mitch Tuinstra, Wickersham Chair of Excellence in Agricultural Research and scientific director of the Purdue Institute for Plant Sciences, and Yang Yang, director of digital phenomena.

Many agricultural researchers have adopted remote sensing technologies in which UAVs carry sensors that allow them to not only view fields from the air, but also measure structural and functional characteristics of crops. Their utility is applicable to a wide range of fields that researchers study – plant varieties, irrigation, various fertilizers or pesticides, and many others.

For agricultural applications, reliable processing protocols have made RGB and LiDAR UAV-based sensors. From the RGB remote sensor, the measurements show how green the plot is. LiDAR measures detailed geometric properties, such as plant height or volume. However, the application of thermal sensors to reliably measure the surface temperature of a target, which cannot be estimated by visual observation, has been more challenging.

The thermal properties of a crop cannot be extracted by other remote sensors such as RGB imaging or LiDAR. Thermal images also look different, so transforming raw thermal data into a human-friendly format requires carefully defined processes.

x

Thermal imaging

“After several complicated steps, we can finally measure the temperature using the acquired thermal images of a target. Think of it as measuring temperature with your eyes,” Oh explains. “Brighter colors like orange mean higher temperatures, while darker ones like indigo or purple represent areas with lower temperatures. We do it almost automatically with our processing algorithm.”

Based on thermal measurements, a researcher investigates the relationship between their research interests—for example, the amount of fertilizer or different varieties of corn—with temperature.

Temperature information is essential because it is closely related to plant health and performance. “It can be related to a corn plant’s height, leaf size, growth rate, yield and even taste. Temperature can also be the key to uncovering the underlying reasons why some varieties perform well under certain harsh conditions while others do not,” explains Oh.

Researchers are still learning how to apply thermal data to their studies. “Our Plant Sciences team is trying to become a bridge between the agricultural scientist and the behind-the-scenes technologies,” says Oh. “We are striving to provide accurate, usable and actionable data to agricultural researchers.”

Their goal is not a sophisticated product, he adds: “Our protocol is trying to create a thermal data product that researchers can easily use with prior knowledge and skills.”

At Purdue, users and potential users are primarily scientists at Purdue Agriculture or third-party companies that do not have remote sensing platforms and sensors. “However, we are ready to work with anyone who wants to understand how plants adapt to the changing environment,” Oh says.

To create thermal data products for users, the Plant Sciences team first flies drones over research plots and brings the raw data from the UAV to a computer workstation. Data processing converts raw data into thermal properties in image format. The next step is to extract the thermal information from each plot and summarize it as a table. The team then advises the researcher on how to use the data products for their analysis.

x

GRYFN Technology

GRYFN is critical to the protocol, Oh says. “GRYFN uses high-end sensors for accurate measurements. When we load the data product from the GRYFN platform, it accurately co-registers with Google maps or satellite imagery and makes it easy to monitor the thermal properties of a parcel over the season.”

Researchers at various universities and research institutes are also developing remote thermal sensing protocols, Oh says. “We are one of them, because there is not yet a gold standard method for data processing.”

GRYFN is also developing its own protocols, not only with thermals, but also with RGB or other remote sensors. “We are actively discussing how our team and the GRYFN team can work together to make the thermal sensor protocol more user-friendly,” Oh says.

Click HERE to learn more about Purdue-based startup GRYFN.

x
Sungchan “Sun” Oh, computational infrastructure specialist in the Plant Sciences team at Purdue University. Photo: Tom Campbell / Purdue Agricultural Communications.

Written by Nancy Alexander, Purdue Agricultural Communications.

Leave a Comment

Your email address will not be published. Required fields are marked *