Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

UAV- and cloud-based application for high throughput phenotyping utilizing deep learning

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2020 ASABE Annual International Virtual Meeting  2000775.(doi:10.13031/aim.202000775)
Authors:   Yiannis Ampatzidis, Victor Partel, Lucas Costa
Keywords:   artificial intelligence, machine learning, UAV, specialty crops.

Abstract. Unmanned aerial vehicles (UAVs) equipped with various sensors can provide a precise and efficient crop management tool, simplify surveying procedures, decrease data collection time, and reduce production costs. To accurate and rapidly analyze and visualize data collected from UAVs and other platforms (e.g. small airplanes, satellites), a cloud and artificial intelligence (AI) based application, named Agroview, was developed. This interactive and user-friendly platform can: (i) detect, count and geo-locate plants and plant gaps (locations with dead plants or no plants); (ii) measure plant height and canopy size (plant inventory); (iii) develop individual plant stress maps (health index maps). The Agroview application comprised a machine vision algorithm (AI-based) that uses deep learning to effectively detect individual plants on aerial maps. This cloud-based application has a great potential to provide individual plant analysis over large areas and to compare phenotypic characteristics on different sets of plants. It provides a consistent, more direct, cost-effective and rapid method for field survey and plant phenotyping.

(Download PDF)    (Export to EndNotes)