三维小样本元学习模型的大豆食心虫虫害高光谱检测

为降低大豆食心虫对大豆产量以及品质的影响，实现对大豆食心虫虫害的快速检测，提出了一种基于三维关系网络小样本元学习（3D-RN）模型的大豆食心虫虫害的检测方法。首先分别对附着虫卵的，附着食心虫幼虫的，被啃食的及正常的大豆各20颗进行高光谱图像采集，提取感兴趣区，建立基于高光谱图像的3D-RN模型。最终模型的正确率达82%±2.50%。对比与模型无关的元学习和匹配网络元学习模型，3D-RN模型能够充分度量样本特征间的距离，识别效果大大提升。研究表明，基于高光谱图像的3D-RN模型能够在少量样本情况下实现对大豆食心虫虫害的检测，将小样本元学习与高光谱结合的方法为虫害检测提供一种新思路。

Hyperspectral Imaging for Detection of Leguminivora Glycinivorella Based on 3D Few-Shot Meta-Learning Model

In order to reduce the influence of leguminivora glycinivorella on soybean production and quality, and to realize the rapid detection of leguminivora glycinivorella, this paper proposed a leguminivora glycinivorella detection model based on 3D-Realtion Network (3D-RN) model. Firstly, collect the hyperspectral images of 20 soybeans that are attached to eggs, larvae, gnawed and normal soybeans, respectively, and extract the region of interest (ROI) to establish a 3D-RN model based on hyperspectral images. The accuracy of the final model reached 82%±2.50%. Compared to the Model-Agnostic Meta-Learning (MAML) and Matching Network (MN) models, the 3D-RN model can fully measure the distance between sample features, and the recognition effect is greatly improved. Thus, this research shows that the 3D-RN model based on the hyperspectral image can detect leguminivora glycinivorella in a small number of samples. The method of combining few-shot meta-learning with hyperspectral provides a new idea for pest detection.