A team of researchers from North Carolina State University (NCSU) and Iowa State University has developed a robot that can sense the angle of the leaves of corn plants in a field. With this data, plant breeders can later make adjustments to their breeds.
“The angle of a plant’s leaves relative to its stem is important because the leaf angle affects how efficiently the plant photosynthesizes,” says Lirong Xiang, assistant professor of biological and agricultural engineering at NCSU. “With corn, for example, you want the leaves to be relatively vertical at the top, while the leaves lower down the stalk are more horizontal. This allows the plant to absorb more sunlight.”
Until now, the blade angles had to be measured manually: a time-consuming and labor-intensive process. The AngleNet robot that Xiang and his colleagues developed automates this process, according to the study published in the Journal of Field Robotics “Field-based robotic leaf angle detection and characterization of maize plants using stereo vision and deep convolutional neural networks” emerges.
Desirable genetic traits
The manually controlled robot is so wide that it can drive between rows of plants. Several cameras are attached to masts on four levels on the four-wheeled vehicle. In this way, it is possible to take stereoscopic images of the leaves at four different heights of the plants and to create a 3D model of the plant. An algorithm uses this data to determine the leaf angle for the leaves of each individual plant. It also records how high the leaves are above the ground. Using this data, breeders can identify those plants that have the desired genetic traits.
The researchers compared the accuracy of the blade angles measured by AngleNet with those of manually measured blade angles. They found that the deviation was less than 5 degrees, which is an acceptable margin of error.
The research team is already working with crop production scientists to further test and refine the technique. The goal is to accelerate research in the field of plant breeding. The scientists hope that the yields can be further increased with new plant varieties.
(olb)