However, getting an idea of how many flowers are on the plants can be time-consuming and subjective, which results in data inconsistencies. What if a drone could do it with a camera”

That's the question agricultural engineers at the Arkansas Agricultural Experiment Station are trying to answer in collaboration with the Department of Horticulture. So far, they have proven the concept.

Cengiz Koparan, assistant professor of precision agriculture technology, worked with Akwasi Tagoe, a graduate student in the Department of Agricultural Education, Communications and Technology, to develop a system for measuring flower density using a camera-equipped drone. They call the measurement the flower-to-vegetation ratio, or FVR for short, which was validated by comparing the results to human counts.

"Now we can quantify flower coverage and vegetation coverage with a standardized measurement," said Koparan, who works in the departments of Agricultural Education, Communications and Technology and Biological and Agricultural Engineering. "We also now know the flowers produced per given vegetation for a specific variety. It gives us a little bit more insight about the phenotype."

Although the task may appear simple on the surface, there are multiple layers of complexity woven into the project of decoding natural phenomena with digital tools. Overcoming that complexity required rethinking how drone imagery could be processed and interpreted.

"We sought to turn drone imagery into actionable data for growers and breeders," Tagoe said. "By quantifying flowers and canopy growth using open-source software, and subsequently computer vision, we look forward to moving from manual counting to scalable, real-time decision support that improves yield prediction and agricultural systems management."