Early Detection of Citrus Huanglongbing by UAV Remote Sensing Based on MGA-UNet

Citrus Huanglongbing (HLB), also known as citrus greening, is a severe disease that has caused substantial economic damage to the global citrus industry. Early detection is challenging due to the lack of distinctive early symptoms, making current diagnostic methods often ineffective. Therefore, there is an urgent need for an intelligent and timely detection system for HLB. This study leverages multispectral imagery acquired via unmanned aerial vehicles (UAVs) and deep convolutional neural networks. We introduce a novel model, MGA-UNet, specifically designed for HLB recognition. This image segmentation model enhances feature transmission by integrating channel attention and spatial attention within the skip connections. Furthermore, we evaluate the comparative effectiveness of high-resolution and multispectral images in HLB detection, finding that multispectral imagery offers superior performance. To address data imbalance and augment the dataset, we employ a generative model, DCGAN, for data augmentation, significantly boosting the model's recognition accuracy. Our proposed model achieved a mIoU of 0.89, a mPA of 0.94, a precision of 0.95, and a recall of 0.94 in identifying diseased trees. The intelligent monitoring method for HLB presented in this study offers a cost-effective and highly accurate solution, holding considerable promise for the early warning of this disease.柑橘黄龙病（Citrus Huanglongbing，以下简称HLB），又称柑橘绿病，是一种极具破坏性的病害，已对全球柑橘产业造成巨额经济损失。由于该病害早期缺乏典型症状，早期检测极具挑战性，导致当前常用的诊断方法往往效果不佳，因此亟需一套智能且及时的HLB检测系统。本研究借助无人机（Unmanned Aerial Vehicles，以下简称UAV）获取的多光谱图像与深度卷积神经网络开展相关研究，提出了一种专为HLB识别设计的新型模型MGA-UNet。该图像分割模型通过在跳跃连接中融入通道注意力与空间注意力机制，强化了特征传递能力。此外，我们对比评估了高分辨率图像与多光谱图像在HLB检测中的应用效果，结果表明多光谱图像的表现更优。为解决数据不平衡问题并扩充数据集，我们采用深度卷积生成对抗网络（DCGAN）进行数据增强，显著提升了模型的识别精度。所提模型在病株识别任务中取得了0.89的平均交并比（mean Intersection over Union，mIoU）、0.94的平均像素准确率（mean Pixel Accuracy，mPA）、0.95的精确率以及0.94的召回率。本研究提出的HLB智能监测方法提供了一种兼具高性价比与高精度的解决方案，在该病害的早期预警领域具有可观的应用前景。