In order to see how well a corn plant is performing photosynthesis, you need to check the angle of its leaves relative to its stem. And while scientists ordinarily have to do so manually with a protractor, a new robotic system can now do the job much more quickly and easily.
Developed by a team from North Carolina State University and Iowa State University, the AngleNet system combines an existing PhenoBot 3.0 wheeled agricultural robot with special machine-learning-based software. Mounted on the robot are four PhenoStereo camera modules, each one consisting of two cameras and a set of strobe lights. The modules are arranged one above the other, with spaces in between.
As the remotely controlled robot moves along rows of corn plants, the cameras automatically capture stereoscopic side-view photographs of the leaves on each plant at different heights. The software combines those images to form three-dimensional models of those leaves, from which the angles of the leaves relative to the stem can be calculated.
Additionally, because the camera modules are mounted at known heights, it’s possible to determine how high the leaves are located above the ground – which is another important piece of information.
“In corn, you want leaves at the top that are relatively vertical, but leaves further down the stalk that are more horizontal,” said NC State’s Asst. Prof. Lirong Xiang, first author of the study. “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.”
In a test of the technology, leaf angles measured by the AngleNet system were found to fall within five degrees of those measured by hand. According to the scientists, this amount is well within the accepted margin of error for purposes of plant breeding.
“We’re already working with some crop scientists to make use of this technology, and we’re optimistic that more researchers will be interested in adopting the technology to inform their work,” said Xiang. “Ultimately, our goal is to help expedite plant breeding research that will improve crop yield.”
A paper on the research was recently published in the Journal of Field Robotics. And for another example of a leaf-inspecting bot, check out the University of Illinois’ Crop Phenotyping Robot.
Source: North Carolina State University