摘要
小流域植被状况的快速、高精度和低成本监测是评价退耕还林还草与生态环境建设功效的基础工作。为丰富植被指数多样性,本文旨在提出一种适宜黄土高原小流域植被状况监测的可见光植被指数。基于无人机遥感技术获取小流域可见光影像,论文构建了简化可见光植被指数(Simplified visible light vegetation index,SVVI),结合样本统计法确定阈值,以支持向量机(Support vector machine,SVM)的监督分类结果对比了8种常用可见光植被指数提取效果,并以黄土高原2个典型流域为例,以混淆矩阵检验指数精度及其适用性。结果表明:1)SVVI能有效抑制非植被地物信息,在提取地物种类丰富且植被覆盖度相对较低的区域时,SVVI提取精度高达96%。2)在地物相对单一且植被覆盖度较高的验证区,SVVI提取精度依然在90%以上,表明SVVI有较好的适用性。相比较于监督分类结果,基于SVVI进行植被覆盖度计算可以有效保留植被信息,实现黄土高原小流域植被状况高精度监测。
Rapid,high-precision and low-cost monitoring of vegetation status in small watersheds is basis for evaluating the efficacy of returning farmland to grassland and ecological environment construction.In order to enrich the diversity of vegetation index,this paper aims to propose a visible light vegetation index suitable for monitoring the vegetation status of small watersheds on the Loess Plateau.Based on the orthophoto images of small watersheds obtained by the UAV remote sensing technology,a simplified visible light vegetation index(SVVI)was developed for two small typical watersheds on the Loess Plateau.Then,the threshold was determined by the sample statistics,and the extraction effects of eight common visible vegetation indexes were compared with the supervised classification results of support vector machine(SVM).Finally,the accuracy and applicability of the SVVI were tested by the confusion matrix.The results showed:1)The SVVI can effectively suppress the information of non-vegetation features.When extracting areas with rich types of features and relatively low vegetation coverage,the extraction accuracy of SVVI reached as high as 96%.2)In the verification area with relatively single features and high vegetation coverage,the extraction accuracy of SVVI was still more than 90%,indicating that SVVI had a good applicability.Compared with the supervised classification results,the vegetation coverage calculation based on the SVVI can effectively retain the vegetation information and realize high-precision monitoring of vegetation status in small watershed of Loess Plateau.
作者
贺仓国
佘冬立
张翔
杨震
HE Cang-guo;SHE Dong-li;ZHANG Xiang;YANG Zhen(College of Agricultural Science and Engineering,Hohai University,Nanjing,Jiangsu 211100,China;State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau,Institute of Soil and Water Conservation,Chinese Academy of Sciences and Ministry of Water Resources,Yangling,Shaanxi 712100,China)
出处
《农业现代化研究》
CSCD
北大核心
2022年第3期504-512,共9页
Research of Agricultural Modernization
基金
中国科学院“西部之光”计划项目。
关键词
黄土高原
无人机遥感
SVVI
植被信息提取
可见光植被指数
Loess Plateau
UAV remote sensing
SVVI
vegetation information extraction
visible light vegetation index
