Research teams from North Carolina State University and Iowa State University have developed automated technology that accurately measures the angle of leaves on corn plants in the field — potentially offering plant breeders useful data for breeding better corn plants.

According to the researchers, the angle of a plant’s leaves in relation to its stem affects how efficiently the plant performs photosynthesis.

Source: North Carolina State UniversitySource: North Carolina State University

"For example, in corn, you want leaves at the top that are relatively vertical, but leaves further down the stalk that are more horizontal. This allows the plant to harvest more sunlight. Researchers who focus on plant breeding monitor this sort of plant architecture, because it informs their work.

"However, conventional methods for measuring leaf angles involve measuring leaves by hand with a protractor — which is both time-consuming and labor-intensive," the researchers explained. "We wanted to find a way to automate this process — and we did."

As such, the team developed what it calls AngleNet, which is a combination of hardware and software that makes data collection on leaf angles more efficient than conventional methods carried out manually with protractors.

The AngleNet features a robot on wheels that can be manually steered and is narrow enough to traverse the spaces between crop rows, spaced 30 inches apart. The robot also features four tiers of cameras for capturing leaves at different heights. As the robot traverses the rows of plants, it captures stereoscopic images of each plant it passes.

The captured data is then input into an accompanying software program that will compute the angle of leaves at assorted heights. All of this visual data is then fed into a software program that then computes the leaf angle for the leaves of each plant at different heights.

The team tested the accuracy of AngleNet, reporting that when they compared leaf angle measurements captured by the robot to those taken manually, AngleNet’s measurements were within 5° of the angle measurements taken manually.

An article detailing the system, "Field-based robotic leaf angle detection and characterization of maize plants using stereo vision and deep convolutional neural networks," appears in the Journal of Field Robotics.

To contact the author of this article, email