Enhanced Smart Crop Health Assessment using Interactive Masked Vision Transformer with Multi Network Attention Mechanism on UAV Imager

Abstract

Soybeans have become one of the most significant oilseed and food crops worldwide. However, soybean crops are susceptible to numerous factors. Damage due to pests, illnesses, and other factors exceeds 20 per cent of the world's manufacturing. The usage of Unmanned Aerial Vehicles (UAVs) in crop fields was found to be a significant tool for identifying disease patches, enabling professionals and agriculturalists to make better decisions. Furthermore, in this context, deep learning (DL) has made important developments in Artificial Intelligence (AI). As a result, several studies have employed DL to solve a wide range of diverse problems. In the agricultural sector, DL has gained significant interest in improving crop productivity. This study introduces an Unmanned Aerial Vehicle-Based Soybean Crop Health Monitoring Using Advanced Deep Learning Architectures (UAVSCHM-DLA) model. The aim is to present an intelligent system that is capable of monitoring and assessing soybean crop health using integrated UAV and leaf images. Initially, Histogram Equalisation (HE) and Bilateral Filtering (BF) methods are applied to perform image pre-processing. For effective feature extraction, a vision transformer with the Interactive Mask Self-Attention (IMViT) method is employed. Finally, multiple neural networks with an attention mechanism (MNet-Attn) method are implemented for classification. The comparison of the UAVSCHM-DLA technique illustrated superior accuracies of 98.20% and 97.01% on the leaf and UAV datasets, respectively.

Plant phenotyping relevance

UAV・葉画像からダイズの健康状態／病害を分類する画像解析システムを提案し、前処理・ViT特徴抽出・ニューラルネットワーク分類を評価しているため、植物状態の取得・推定手法が中心である。

Code and data availability

The paper's experiments rely on the public MH-SoyaHealthVision dataset (Shinde & Attar, Data in Brief 2025, ref [28]), which is a paper-specific public image dataset. However, the supplied blocks contain no authors' public URL, repository, or identifier for the dataset, analysis code, or trained models — only citation-

No evidence-backed public reproduction asset is currently recorded.