Monitoring potato phenotypic traits accurately is essential for improving the quality and yield of superior potato varieties, especially considering susceptibility to diseases like early blight and the direct influence of growth characteristics on yield. Traditional manual height sampling for monitoring crop growth faces limitations in estimating height due to complex potato crop canopies.

A novel solution utilizing DeepLab implemented in detectron 2 enables an automated system using Unmanned Aerial Vehicles (UAVs) to process data, including Digital Surface Models and orthomosaics. This system effectively evaluates critical crop traits like height, volume, and coverage for different potato varieties. The study also examines the impact of UAV flight parameters on data accuracy by comparing altitudes, aiming to identify optimal conditions for assessing phenotypic traits.

The research’s goal is to revolutionize potato variety assessment through UAV technology and advanced data processing, streamlining UAV-generated data analysis to enhance precision in estimating essential crop properties and contributing to the development of superior potato varieties with improved quality and yield.

Read the full article here: Effect of varying UAV height on the precise estimation of potato crop growth.