结合植被指数和卷积神经网络的遥感植被分类方法  

Remote Sensing Vegetation Classification Method Based on Vegetation Index and Convolution Neural Network

作　　者：许明珠 徐浩[2] 孔鹏 吴艳兰[1,3,4] Xu Mingzhu;Xu Hao;Kong Peng;Wu Yanlan(School of Resources and Environmental Engineering,Anhui University,Hefei 230601,Anhui,China;Institute of Spacecraft System Engineering,Beijing 100094,China;Information Materials and Intelligent Sensing Laboratory of Anhui Province,Hefei 230601,Anhui,China;Anhui Engineering Research Center for Geographical Information Intelligent Technology,Hefei 230601,Anhui,China)

机构地区：[1]安徽大学资源与环境工程学院,安徽合肥230601 [2]北京空间飞行器总体设计部,北京100094 [3]信息材料与智能感知安徽省实验室,安徽合肥230601 [4]安徽省地理信息智能技术工程研究中心,安徽合肥230601

出　　处：《激光与光电子学进展》2022年第24期265-277,共13页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41971311);安徽省科技重大专项(201903a07020014)。

摘　　要：针对高分辨率遥感影像由于原始光谱信息较少而难以有效区分各类型植被,而且城乡植被差异往往被忽视等问题,并考虑到部分植被指数可以在一定程度上增大各植被类型间的差异,提出一种结合植被指数的深度学习植被分类网络,该网络在并联网络结构的基础上,引入密集连接模块与空洞空间金字塔池化模块,增强各类型植被特征信息差异,有效提高分类精度。除此之外,本文充分考虑城乡植被差异,分别对城市区域和农村区域进行验证分析,城市区域植被分类提取中整体精度为96.73%,F1得分为80.71%,交并比为69.91%,农村区域植被分类提取中整体精度为91.35%,F1得分为90.28%,交并比为82.41%,各项精度指标均高于其他深度学习方法。结果表明提出方法能够较好地区分各植被类型,且适用于多源遥感影像的植被分类提取,在城市绿地规划、农村基本农田监管等方面具有一定的应用价值。Due to the lack of original spectral information,high-resolution remote sensing images are difficult to effectively distinguish various types of vegetation,and the differences between urban and rural vegetation are often ignored and considering that certain vegetation indices somewhat increase the differences among different vegetation types,this paper proposes a deep learning vegetation classification network based on a vegetation index that combines artificial features and spectral information.Based on a parallel network structure,a dense connection module and atrous spatial pyramid pooling module are introduced to enhance the differences in vegetation feature information and effectively improve classification accuracy.Besides,taking full account of the differences between urban and rural vegetation,this paper verifies and analyzes urban and rural areas,respectively.The overall accuracy of urban vegetation classification and extraction is 96.73%,the F1 score is 80.71%,and the intersection-merge ratio is 69.91%.The overall accuracy in classifying and extracting vegetation in rural areas is 91.35%,the F1 score is 90.28%,and the intersection-merge ratio is82.41%.Each accuracy index exceeds that of other depth learning methods.The results confirm that this method better distinguishes different vegetation types,is suitable for classifying and extracting vegetation from multi-source remote sensing images,and has a definite value for urban green space planning,rural basic farmland supervision,etc.

关 键 词：遥感与传感器 深度学习 遥感 国产高分二号 植被指数 植被分类 

分 类 号：O436[机械工程—光学工程]