三维小样本元学习模型的大豆食心虫虫害高光谱检测 |
| |
作者单位: | 浙江理工大学信息学院,浙江 杭州 310018;浙江理工大学机械与自动控制学院,浙江 杭州 310018 |
| |
基金项目: | 国家重点研发计划项目(2016YFD0700203),浙江省自然科学基金项目(LY20C130008)资助 |
| |
摘 要: | 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。
|
关 键 词: | 虫害检测 大豆食心虫 高光谱 卷积神经网络 小样本元学习 三维 |
收稿时间: | 2020-07-11 |
Hyperspectral Imaging for Detection of Leguminivora Glycinivorella Based on 3D Few-Shot Meta-Learning Model |
| |
Authors: | GUI Jiang-sheng FEI Jing-yi FU Xia-ping |
| |
Institution: | 1. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
2. Faculty of Mechanical Engineering & Automation, Zhejiang Sci-Tech University, Hangzhou 310018, China |
| |
Abstract: | 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. |
| |
Keywords: | Pest detection Leguminivora glycinivorella Hyperspectral Convolutional neural network Few-shot meta-learning Three-dimensional |
本文献已被 CNKI 万方数据 等数据库收录! |
| 点击此处可从《光谱学与光谱分析》浏览原始摘要信息 |
| 点击此处可从《光谱学与光谱分析》下载免费的PDF全文 |