文献类型：期刊文献

中文题名：基于GF-1 PMS数据的森林覆盖变化检测

英文题名：Forest Cover Change Detection based on GF-1 PMS Data

作者：王崇阳[1] 田昕[1]

第一作者：王崇阳

机构：[1]中国林业科学研究院资源信息研究所,北京100091

年份：2021

卷号：36

期号：1

起止页码：208-216

中文期刊名：遥感技术与应用

外文期刊名：Remote Sensing Technology and Application

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD2021_2022】；

基金：高分重大专项共性关键技术项目“GF-6卫星宽幅相机林地类型精细分类与制图技术”(21-Y20A06-9001-17/18);国家自然科学基金项目“森林地上生物量动态信息时空协同分析及建模”(41871279)。

语种：中文

中文关键词：高分一号(GF-1);变化检测;迭代加权多元变化检测;随机森林;

外文关键词：Gaofen-1;Change detection;Iteratively Re-weighted Multivariate Alteration Detection(IR-MAD);Random forest;

分类号：TP79

摘要：我国南方人工林场经营强度大,森林覆盖变化频繁,因此,准确、快速地获取森林覆盖变化信息,对研究生态环境变化和经营管理具有重要意义。目前应用较多的森林覆盖变化检测方法主要有直接比较分析法和先分类后比较法,为了探究直接比较分析法和先分类后比较法两种变化检测方法在经营强度大且地形复杂的我国南方人工林场森林覆盖变化检测中的适用性和有效性。以广西高峰林场为研究区,选取两期GF-1 PMS影像为数据源,比较了迭代加权多元变化检测(IRMAD)和基于EnMAP-Box的随机森林(ImageRF)分类后比较法两种变化检测方法,对研究区森林覆盖变化检测结果进行了对比研究。结果表明:迭代加权多元变化检测结果的总体精度为89.31%,Kappa系数达到0.80;基于EnMAP-Box的随机森林分类后比较法检测结果的总体精度为86.02%,Kappa系数为0.75。前者的精度和提取效果均优于后者。说明该方法可以较为快速、准确地掌握研究区森林覆盖变化情况,为研究林场森林生态环境变化和经营管理提供技术支持。
The management of artificial forest farms in the south of China is slightly large and the forest cover changes frequently.Therefore,accurately and quickly obtaining forest change information is of great significance for studying ecological environment changes and management.At present,the more commonly used forest cover change detection methods are the direct comparison analysis method and the post-classification comparison method.In order to explore the applicability and effectiveness of the two change detection methods,the direct comparison analysis method and the post-classification comparison method in the detection of forest cover change in southern China’s artificial forest farms with high management intensity and complex terrain.In this study,the Guangxi Gaofeng Forest Farm was used as the research area,and the GF-1 PMS images were selected as the data source.The Iterative Re-weighted Multiple Change Detection(IR-MAD)and the EnMAPBox based random forest(ImageRF)post-classification comparison methods.After the two comparison methods of change method,the change detection of the two-stage image forest cover in the study area was carried out.The results show that the overall accuracy of the iterative weighted multivariate change detection result is 89.31%,and the Kappa coefficient reaches 0.80.The overall accuracy of the EnMAP-Box based random forest(ImageRF)post-classification comparison method is 86.02%,and the Kappa coefficient is 0.75.The former has better accuracy and extraction effect than the latter.It shows that this method can quickly and accurately grasp the change of forest cover in the study area,and provide technical support for studying the change of forest ecological environment and management of forest farms.