#AIatUF

Invention of the Year: AI-based Software to Analyze and Visualize UAV-collected Data

By Raychel Rabon

Agricultural and Biological Engineering Assistant Professor Yiannis Ampatzidis and his team received the UF Invention of the Year award from the UF Innovate | Tech Licensing for his cloud and artificial intelligence (AI) based application, Agroview.

Agroview is a software and application designed to use drone, satellite, and ground images to access plant qualities, quantities, and growth factors or impacts using AI. This software and application was developed to help producers take better care of their crops while also saving money.

For pest and disease detection and field phenotyping, traditional technologies rely on manual sampling. These methods are time consuming and labor-intensive. With the limited availability of personnel trained for field scouting, the use of unmanned aerial vehicles (UAVs) has increased.

Using UAVs equipped with sensor technology simplifies surveying procedures, decreases data collection time, and reduces cost.

Agroview is used to accurately and rapidly process, analyze, and visualize data collected from UAVs and other platforms (e.g. small airplanes, satellites, ground platforms).

The workflow of the entire process for the cloud-based application (Agroview)

“This interactive and user-friendly application can: (i) detect, count and geo-locate plants and plant gaps (locations with dead or no plants); (ii) measure plant height and canopy size (plant inventory); (iii) develop plant health (or stress) maps,” (Ampatzidis et al., 2020).

This application uses deep learning to effectively detect individual plants on aerial maps by utilizing an AI-based machine vision algorithm.

The Agroview application has the potential to provide analysis for individual plants over large areas and compare phenotypic characteristics on different sets of plants. With the ability to create accurate tree inventories in a short time, this application can reduce data collection and analysis time and cost by up to 90%.

Watch:

References:
Ampatzidis, Y., Partel, V., & Costa, L. (2020) Agroview: Cloud-based application to process, analyze and visualize UAV- collected data for precision agriculture applications utilizing artificial intelligence. Elsevier B.V., Volume 174. https://doi.org/10.1016/j.compag.2020.105457

This story originally appeared on UF IFAS.

Check out more stories on the UF A.I. Initiative.