Novel CropdocNet Model for Automated Potato Late Blight Disease Detection from Unmanned Aerial Vehicle-Based Hyperspectral Imagery
Novel CropdocNet Model for Automated Potato Late Blight Disease Detection from Unmanned Aerial Vehicle-Based Hyperspectral Imagery
复制标题
DOI：
10.3390/rs14020396
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Yue Shi;Liangxiu Han;Anthony Kleerekoper;Sheng Chang;Tongle Hu
中科院分区：
文献类型：
--
作者：
Yue Shi;Liangxiu Han;Anthony Kleerekoper;Sheng Chang;Tongle Hu
马铃薯晚疫病是危害最大的马铃薯病害之一，对其进行准确、自动化的诊断是精准农业控制和管理的关键。遥感和深度学习方面的最新进展为应对这一挑战提供了机会。该研究提出了一种新的端到端深度学习模型(CropdocNet)，用于从基于无人机的高光谱图像中准确和自动化地诊断晚疫病。该方法考虑了冠层结构多样性可能引起的疾病特异性反射辐射变化，并引入多个胶囊层来模拟光谱空间特征与目标类之间的局部到整体关系，以表示目标类在特征空间中的旋转不变性。我们用实际无人机上的受控和自然条件下的HSI数据对该方法进行了评估。在测试数据集和独立数据集上对分层特征的有效性进行了定量评估，并与现有的代表性机器学习/深度学习方法进行了比较。实验结果表明，当考虑光谱-空间特征的层次结构时，该模型显著提高了准确率，测试数据集的平均准确率为98.09%，独立数据集的平均准确率为95.75%。
The accurate and automated diagnosis of potato late blight disease, one of the most destructive potato diseases, is critical for precision agricultural control and management. Recent advances in remote sensing and deep learning offer the opportunity to address this challenge. This study proposes a novel end-to-end deep learning model (CropdocNet) for accurate and automated late blight disease diagnosis from UAV-based hyperspectral imagery. The proposed method considers the potential disease-specific reflectance radiation variance caused by the canopy’s structural diversity and introduces multiple capsule layers to model the part-to-whole relationship between spectral–spatial features and the target classes to represent the rotation invariance of the target classes in the feature space. We evaluate the proposed method with real UAV-based HSI data under controlled and natural field conditions. The effectiveness of the hierarchical features is quantitatively assessed and compared with the existing representative machine learning/deep learning methods on both testing and independent datasets. The experimental results show that the proposed model significantly improves accuracy when considering the hierarchical structure of spectral–spatial features, with average accuracies of 98.09% for the testing dataset and 95.75% for the independent dataset, respectively.