Peanut is a significant oilseed crop that is often affected by peanut southern blight, a disease that greatly reduces crop yield and quality. Therefore, accurate and timely monitoring of this disease is crucial to ensure crop safety and minimize the need for pesticides. Spectral features combined with texture features have been widely applied in plant disease monitoring. However, previous studies have mostly used original texture features, and its combination form has been rarely considered. This study presents a novel approach for monitoring peanut southern blight, integrating multiple spectral indices and textural indices (TIs). Firstly, a total of 20 vegetation indices (VIs) were extracted from the unmanned aerial vehicle multispectral images, while three TIs were constructed based on original textural features. Subsequently, Otsu-CIgreen algorithm was used to find the optimal threshold to eliminate the complex background of the image. Lastly, monitoring models for peanut southern blight were constructed using three machine learning models based on the screened VIs, VIs combined with TIs. Among these models, the K-nearest neighbor model using VIs combined with TIs demonstrates the best performance, with accuracy and F1 score on the test set reaching 91.89% and 91.39% respectively. The results indicate that the monitoring models utilizing VIs and TIs were more effective compared to models using only VIs. This approach provides valuable insights for non-destructive and accurate monitoring of peanut southern blight.

花生是一种重要的油籽作物，经常受到花生白斑病的影响，这种病害会大大降低作物的产量和质量。因此，准确及时地监测该病害对于确保作物安全并最大限度地减少农药需求至关重要。光谱特征与纹理特征相结合已广泛应用于植物病害监测。然而，以往的研究大多使用原始纹理特征，很少考虑其组合形式。本研究提出了一种监测花生白斑病的新方法，整合了多个光谱指数和质地指数（TI）。首先，从无人机多光谱图像中提取了总共20个植被指数（VI），同时根据原始纹理特征构建了3个TI。随后，利用Otsu-CIgreen算法寻找最佳阈值来消除图像的复杂背景。最后，基于筛选的VI、VI与TI的结合，利用三种机器学习模型构建了花生白叶枯病的监测模型。其中，使用VI与TI相结合的K近邻模型表现出最好的性能，在测试集上的准确率和F1分数分别达到91.89%和91.39%。结果表明，使用 VI 和 TI 的监测模型比仅使用 VI 的模型更有效。这种方法为花生白叶枯病的无损和准确监测提供了宝贵的见解。