Ohio State University (OSU) researchers have combined machine learning and flying drones into a tool for assessing the health of crop fields.
After filtering the image set, the researchers learned about 67,000 images could be labeled healthy, while almost 30,000 indicated defoliation.
None of the algorithms they tested on this dataset could precisely classify crop health, so they developed Defonet, a neural network that can probe and answer the study's original defoliation queries correctly.
Said Zhang, "This new architecture is tailored toward this workload. It has better performance than currently available tools in accuracy, precision, and efficacy."
From Ohio State News
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found