Drone-Based Diseased Plant Detection Using RetinaNet and Transfer Learning

Abstract

Machine learning and deep learning have significantly transformed various domains, including medicine, engineering, and agriculture. In this work, we propose a novel deep learning-based approach for detecting stressed potato plants using drone-captured images. Early detection of crop stress, particularly due to insufficient water, is critical as stressed potato plants exhibit symptoms such as leaf yellowing, which can be difficult and time-consuming to monitor manually in large-scale fields. A RetinaNet architecture, a single-stage object detector developed by Facebook, to identify and classify stressed potato crops is employed in the work. The model was trained on an augmented dataset of 1,400 drone images of potato fields using TensorFlow and Keras. Experimental results demonstrate that the trained model effectively detects and classifies stressed plants, offering a reliable alternative to manual field inspection. The proposed system has the potential to save farmers substantial time and labour, thereby enhancing productivity and resource management. Future work will focus on extending the model to multiple crops and disease types, improving accuracy, and exploring faster detection architectures for real-time applications.

Plant phenotyping relevance

ドローン画像からジャガイモのストレス状態を検出・分類する画像解析手法が研究の中心であり、植物状態の直接的な推定に該当する。

Code and data availability

The paper describes a drone-image dataset (360 patches with XML/CSV annotations) and a Keras-RetinaNet model, but provides no public deposit, repository, or availability statement for the dataset, annotations, code, or trained model. The only URL present (vikaspedia) is a cited reference page on potato diseases, not a

No evidence-backed public reproduction asset is currently recorded.