Estimation of corn crop damage caused by wildlife in UAV images

Abstract

PURPOSE: This paper proposes a low-cost and low-effort solution for determining the area of corn crops damaged by the wildlife facility utilising field images collected by an unmanned aerial vehicle (UAV). The proposed solution allows for the determination of the percentage of the damaged crops and their location. METHODS: The method utilises image segmentation models based on deep convolutional neural networks (e.g., UNet family) and transformers (SegFormer) trained on over 300 hectares of diverse corn fields in western Poland. A range of neural network architectures was tested to select the most accurate final solution. RESULTS: The tests show that despite using only easily accessible RGB data available from inexpensive, consumer-grade UAVs, the method achieves sufficient accuracy to be applied in practical solutions for agriculture-related tasks, as the IoU (Intersection over Union) metric for segmentation of healthy and damaged crop reaches 0.88. CONCLUSION: The proposed method allows for easy calculation of the total percentage and visualisation of the corn crop damages. The processing code and trained model are shared publicly.

Plant phenotyping relevance

UAV画像からトウモロコシの健全・損傷状態をセグメンテーションし、損傷面積率と位置を推定する手法が研究の中心であり、植物状態の定量的フェノタイピングに該当する。

Code and data availability

The authors publicly share processing code, trained models, and a data sample for their corn damage segmentation at the PUTvision GitHub repository; the full training dataset is not public due to commercial restrictions. The QGIS deepness plugin is a generic third-party inference tool, not a paper-specific asset.