基于高光谱激光雷达的林木病虫害样本分类研究

Research on Classification of Pest and Disease Tree Samples Based on Hyperspectral Lidar

本研究搭建一套91通道、光谱分辨率为5 nm、波长范围为650~1100 nm、生物安全性高的可调谐高光谱激光雷达系统,并完成臭椿、云南松和栾树等林木样本的探测实验。通过实验探测目标回波强度,进而获得目标光谱反射率,最后利用支持向量机分类器对不同种类的健康与染病样本进行分类与识别,臭椿样本的分类精度可以达到96.98%、云南松样本的分类精度可以达到91.21%、栾树样本的分类精度可以达到66.21%。该实验结果具有研究意义和参考价值,为林业病虫害监测提供一种新的发展方向。

In this study,a set of tunable hyperspectral lidar system with 91 channels,spectral resolution of 5 nm,wavelength range of 650--1100 nm,and high biological safety is built,and the detection experiments of forest tree samples such as Ailanthus altissima,Pinus yunnanensis,and Koelreuteria paniculata are completed.The target echo intensity is detected through experiments,and the target spectral reflectance is obtained.Finally,the support vector machine classifier is used to classify and identify different types of healthy and diseased samples.The classification accuracy of Ailanthus altissima samples can reach 96.98%.The classification accuracy of Pinus yunnanensis samples can reach 91.21%,and the classification accuracy of Koelreuteria paniculata samples can reach 66.21%.The experimental results have research significance and reference value,and provide a new development direction for forestry pest monitoring.