基于植被指数的林地变化检测技术研究  

Research on Technique of Forest Land Change Detection Based on Vegetation Index

作　　者：包广道[1] 刘存发 程岩 王丽丽[4] 衣晓雨 李秀娥 刘婷 张忠辉[1] BAO Guangdao;LIU Cunfa;CHENG Yan;WANG Lili;YI Xiaoyu;LI Xiu-e;LIU Ting;ZHANG Zhonghui(Jilin Provincial Academy of Forestry Sciences,Changchun 130033,China;Jilin Wild Animal Conservation and Breeding Center,Changchun 130122,China;Three Lakes National Nature Reserve Administration of Jilin Songhua River,Jilin 132000,China;Forest Science Academy of Jilin City,Jilin 132000,China;Jilin Provincial Forestry Technology Popularizing Station,Changchun 130022,China;Forest Pest Control and Quarantine Station of Huinan County,Tonghua 135100,China)

机构地区：[1]吉林省林业科学研究院,吉林长春130033 [2]吉林省野生动物救护繁育中心,吉林长春130122 [3]吉林松花江三湖国家级自然保护区管理局,吉林吉林132000 [4]吉林市林业科学研究院,吉林吉林132000 [5]吉林省林业技术推广站,吉林长春130022 [6]辉南县森林病虫防治检疫站,吉林通化135100

出　　处：《吉林林业科技》2020年第5期21-26,共6页Journal of Jilin Forestry Science and Technology

基　　金：吉林省科技厅中青年科技创新领军人才及团队项目(2018051920JH);吉林省林业厅林业科技项目(2018-001);吉林省科技厅创新基地项目(20180623058TC);吉林省公益项目(GY-2017-04)。

摘　　要：本文以长岭县为研究区域,选取2015年和2017年15 m分辨率的Landsat 8-OLI遥感影像为主要数据源,分别计算NDVI值确定阈值进行林地信息提取,以相应年份的土地利用数据做掩膜,去除非林地的干扰。对两期林地信息进行波段运算,快速识别研究区的林地变化情况。结果表明:林地不变、林地减少和林地增加的准确率分别为90.2%、84.3%和70.4%。This paper took Changling County as the research area,and selected 15m resolution Landsat 8-OLI remote sensing images from 2015 and 2017 as the main data source,to calculate the NDVI value and determine the threshold to extract forest land information,the land use data of the corresponding year was used as a mask,removing interference from non-forest land.Band calculation was performed on the two-stage forest land information to quickly identify the forest land changes in the study area.The results showed that the accuracy rates of unchanged forest land,reduced forest land and increased forest land were 90.2%,84.3%and 70.4%.

关 键 词：遥感影像 林地 植被指数 变化检测 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] X87[自动化与计算机技术—控制科学与工程]