Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (1): 208-216    DOI: 10.11873/j.issn.1004-0323.2021.1.0208
遥感应用     
基于GF⁃1 PMS数据的森林覆盖变化检测
王崇阳(),田昕()
中国林业科学研究院资源信息研究所,北京 100091
Forest Cover Change Detection based on GF-1 PMS Data
Chongyang Wang(),Xin Tian()
Institute of Forest Resource Information Techniques,Chinese Academy of Forestry,Beijing 100091,China
 全文: PDF(6151 KB)   HTML
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(IR-MAD)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。

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    
Abstract:

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 EnMAP-Box 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.

Key words: Gaofen-1    Change detection    Iteratively Re-weighted Multivariate Alteration Detection(IR-MAD)    Random forest
收稿日期: 2019-12-30 出版日期: 2021-04-13
ZTFLH:  TP79  
基金资助: 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)
通讯作者: 田昕     E-mail: wangcy99@126.com;tianxin@ifrit.ac.cn
作者简介: 王崇阳(1994-),男,山东滕州人,硕士研究生,主要从事遥感技术应用研究。E?mail:wangcy99@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
王崇阳
田昕

引用本文:

王崇阳,田昕. 基于GF⁃1 PMS数据的森林覆盖变化检测[J]. 遥感技术与应用, 2021, 36(1): 208-216.

Chongyang Wang,Xin Tian. Forest Cover Change Detection based on GF-1 PMS Data. Remote Sensing Technology and Application, 2021, 36(1): 208-216.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.1.0208        http://www.rsta.ac.cn/CN/Y2021/V36/I1/208

传感器影像波段名称波段/μm空间分辨率/m

全色多光谱相机(PMS)

全色全色波段0.45~0.902
多光谱Band1:蓝光0.45~0.528
Band2:绿光0.52~0.598
Band3:红光0.63~0.698
Band4:近红外0.77~0.898
表1  GF-1 PMS数据参数
图1  高峰林场地理位置及外业调查点分布图(图中影像为GF?1 PMS,R: band3, G: band2, B: band1)
图2  ImageRF分类流程图
差异影像最小值最大值均值标准差
迭代15次差异影像0.000 602385 885499.082 2394718.513 749
迭代30次差异影像0.001 244431 455549.301 1135174.835 201
迭代50次差异影像0.001 244431 455549.301 1135174.835 201
表2  不同迭代次数差异影像像元统计表
图3  IR-MAD变化检测结果图
图4  IR-MAD森林覆盖变化检测结果图
图5  ImageRF分类结果图
图6  ImageRF森林覆盖变化检测结果图

检测

方法

检测变化

类型

实际变化类型

生产者精度

/%

用户

精度 /%

总体精度

/%

Kappa

系数

森林增加森林减少
IR-MAD直接比较分析法森林增加1 051 8692 92489.7499.7289.310.80
森林减少13 359823 83188.7798.40
ImageRF分类后比较法森林增加695 3057374.9299.9986.020.75
森林减少7 1521 111 37594.8199.36
表3  变化检测结果混淆矩阵
图7  变化区域检测结果对比图
1 Li Shiming, Wang Zhihui, Han Xuewen, et al. Overview of Forest Resources Change Detection Methods Using Remote Sensing Techniques[J]. Journal of Beijing Forest University, 2011, 33(3): 132-138.
1 李世明, 王志慧, 韩学文,等. 森林资源变化遥感监测技术研究进展[J]. 北京林业大学学报, 2011, 33(3): 132-138.
2 Wu Xueqiong, Qin Xianlin, Zhou Ruliang, et al. Progress of Study on Forest Cover Change Detection by Using Remote Sensing Technique[J]. Forest Resources Management, 2010(4): 84-89.吴雪琼, 覃先林, 周汝良, 等. 森林覆盖变化遥感监测方法研究进展[J]. 林业资源管理, 2010(4): 84-89.
3 Hao Xinrong. Forest Cover Change Detection Method Using GF-1 Multi-spectral Data[D]. Xi’an:Xi’an University of Science and Technology, 2016.
3 郝荣欣. 基于GF-1多光谱影像的林地变化检测方法研究[D]. 西安:西安科技大学, 2016.
4 Zhang Liyun, Zhao Tianzhong, Xia Chaozong, et al. Application of Change Detection Technologies of Remote Sensing to Forestry[J]. World Forestry Research, 2016, 29(2): 44-48.
4 张丽云, 赵天忠, 夏朝宗, 等. 遥感变化检测技术在林业中的应用[J]. 世界林业研究, 2016, 29(2): 44-48.
5 Zhou Qiming. Review on Change Detection Using Multi-temporal Remotely Sensed Imagery[J]. Geomatics World, 2011, 9(2): 28-33.
5 周启鸣. 多时相遥感影像变化检测综述[J]. 地理信息世界, 2011, 9(2): 28-33.
6 Yan Wei, Zhou Wen, Yi Lilong, et al. Research Progress of Remote Sensing Classification and Change Monitoring on Forest Types[J]. Remote Sensing Technology and Application, 2019, 34(3): 445-454.
6 颜伟, 周雯, 易利龙, 等. 森林类型遥感分类及变化监测研究进展[J]. 遥感技术与应用, 2019, 34(3): 445-454.
7 Chen Xinbiao. A Summary of Change Detection Techniques of Remote Sensing Imagery[J]. Geomatics & Spatial Information Technology, 2012, 35(9): 38-41.
7 陈鑫镖. 遥感影像变化检测技术发展综述[J]. 测绘与空间地理信息, 2012, 35(9): 38-41.
8 Jin S, Yang L, Danielson P, et al. A Comprehensive Change Detection Method for Updating The National Land Cover Database to Circa 2011[J]. Remote Sensing of Environment, 2013, 132(10): 159-175.
9 Ozdogan M. A Practical and Automated Approach to Large Area Forest Disturbance Mapping with Remote Sensing[J]. Plos One,2014, 9(4): e78438. doi:10.1371/Journal.pone. 0078438.
doi: 10.1371/Journal.pone. 0078438
10 Huang L, Fang Y M, Zuo X Q, et al. Automatic Change Detection Method of Multitemporal Remote Sensing Images based on 2D-Otsu Algorithm Improved by Firefly Algorithm[J].Journal of Sensors,2015: 1-8.doi:10.1155/2015/327123.
doi: 10.1155/2015/327123
11 Ma L, Li M, Ma X, et al. A Review of Supervised Object-based Land Cover Image Classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130: 277-293.
12 Xiang Tao, Li Tao, Zhao Xuezhuan, et al. Random Forests for Accurate Object Detection[J]. Application Research of Computers, 2016, 33(9): 2837-2840.
12 向涛, 李涛, 赵雪专, 等. 基于随机森林的精确目标检测方法[J]. 计算机应用研究, 2016, 33(9): 2837-2840.
13 Ren Chong, Ju Hongbo, Zhang Huaiqing, et al. Research on Remote Sensing Monitoring Technology of Forest Land Dynamic Change in Tianshui in Recent 30 Years[J]. Forest Research, 2017, 30(1): 25-33.
13 任冲, 鞠洪波, 张怀清, 等. 天水市近30年林地动态变化遥感监测研究[J]. 林业科学研究, 2017, 30(1): 25-33.
14 Zhang Lianhua, Li Chungan. Automatic Extraction of Forest Training Sample and Their Application in Change Detection Using High Resolution Remote Sensing Image[J]. Journal of Nanjing Forestry University (Natural Sciences Edition), 2015, 35(3): 13-17.
14 张连华, 李春干. 高分辨率遥感图像森林训练样本自动提取及其在变化检测中的应用[J]. 南京林业大学学报(自然科学版), 2015, 35(3): 13-17.
15 Woodcock C E, Macomber S A, Pax-Lenney M, et al. Monitoring Large Ares for Forest Change Using +Landsat: Generalization Across Space, Time and Landsat Sensors[J]. Remote Sensing of Environment, 2001, 78(1/2): 194-203.
16 Tang J, Hu Y, Chen X, et al. A Method of Land Use/land Cover Change Detection from Remote Sensing Image based on Support Vector Machines[C]∥ Second International Conference on Space Information Technology, 2007:6795.
17 Canty M J, Nielsen A. Automatic Radiometric Normalization of Multitemporal Satellite Imagery with The Iteratively Re-Weighted MAD Transformation[J]. Remote Sensing of Environment, 2008, 112(3): 1025-1036.
18 Dempster A P. Maximum Likelihood from Incomplete Data Via The EM Algorithm[J]. Journal of Royal Statistical Society B, 1977, 39(1):1-38.
19 Nielsen A, Conradsen K, Simpson J. Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies[J]. Remote Sensing of Environment, 1998, 64(1): 1-19.
20 Liao Mingsheng, Zhu Pan, Gong Jianya. Multivariate Change Detection based on Canonical Transformation[J]. Journal of Remote Sensing, 2000, 4(3): 197-201.
20 廖明生, 朱攀, 龚健雅. 基于典型相关分析的多元变化检测[J]. 遥感学报, 2000, 4(3): 197-201.
21 Sheng Hui, Liao Mingsheng, Zhang Lu. Determination of Threshold in Change Detection based on Canonical Correlation Analysis[J]. Journal of Remote Sensing, 2004, 8(5): 451-457.
21 盛辉, 廖明生, 张路. 基于典型相关分析的变化检测中变化阈值的确定[J]. 遥感学报, 2004, 8(5): 451-457.
22 Marpu P R, Gamba P, Canty M J. Improving Change Detection Results of IR-MAD by Eliminating Strong Changes[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(4): 799-803.
23 Otsu N. A Threshold Selection Method from Gray-level Histograms[J]. IEEE Transactions on Systems Man & Cybernetics, 2007, 9(1): 62-66.
24 Zhao Yingshi. Principles and Methods of Remote Sensing Application Analysis[M].Beijing: Science Press,2003.
24 赵英时.遥感应用分析原理与方法[M]. 北京: 科学出版社, 2003.
25 Zhang Zhaopeng. Forest Land Types Precise and Change Monitoring based on Multi-source Remote Sensing Date[D]. Xi'an: Xi'an University of Science and Technology, 2018.
25 张兆鹏. 基于多源遥感数据的林地类型精细分类识别与变化监测研究[D]. 西安:西安科技大学, 2018.
26 Breiman L. Random Forests[J]. Machine Learning, 2001, 45(1): 5-32.
27 Zhong Longshen. Random Forest Improved Processing of Unbalanced Data and Its Parallelization[D]. Guangzhou: Guangdong University of Technology, 2016.
27 钟龙申. 随机森林算法处理不平衡数据的改进及其并行化[D]. 广州: 广东工业大学, 2016.
[1] 马腾耀,肖鹏峰,张学良,马威,郭金金. 基于特征优选的GF-3全极化数据积雪识别[J]. 遥感技术与应用, 2020, 35(6): 1292-1302.
[2] 王一帆,徐涵秋. 基于客观阈值与随机森林Gini指标的水体遥感指数对比[J]. 遥感技术与应用, 2020, 35(5): 1089-1098.
[3] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[4] 张坤,刘乃文,高帅,赵书慧. 数据驱动的植被总初级生产力估算方法研究[J]. 遥感技术与应用, 2020, 35(4): 943-949.
[5] 李净,温松楠. 基于3种机器学习法的太阳辐射模拟研究[J]. 遥感技术与应用, 2020, 35(3): 615-622.
[6] 董超,赵庚星. 时序数据集构建质量对土地覆盖分类精度的影响研究[J]. 遥感技术与应用, 2020, 35(3): 558-566.
[7] 柴旭荣,李明,周义,王金风,田庆春. 影像的土地覆被快速分类[J]. 遥感技术与应用, 2020, 35(2): 315-325.
[8] 唐廷元,付波霖,何素云,娄佩卿,闭璐. 基于GF-1和Sentinel-1A的漓江流域典型地物信息提取[J]. 遥感技术与应用, 2020, 35(2): 448-457.
[9] 罗家顺,邱建秀,赵天杰,王大刚. 基于Sentinel-1数据的黑河中游土壤水分反演[J]. 遥感技术与应用, 2020, 35(1): 23-32.
[10] 何浩,刘修国,沈永林. 基于视差的高分辨率遥感影像建筑物变化检测[J]. 遥感技术与应用, 2019, 34(6): 1315-1323.
[11] 刘培,余志远,马威,韩瑞梅,陈正超,王涵,杨磊库. 基于地形信息的Landsat与Radarsat-2遥感数据协同分类研究[J]. 遥感技术与应用, 2019, 34(6): 1269-1275.
[12] 王源,陈富龙,胡祺,唐攀攀. COSMO-SkyMed时序影像南京城市变化检测研究[J]. 遥感技术与应用, 2019, 34(5): 1054-1063.
[13] 张因果,陈芸芝. 一种基于改进土地覆盖更新方法的新增建设用地自动提取[J]. 遥感技术与应用, 2019, 34(5): 1073-1081.
[14] 李哲,张沁雨,彭道黎. 基于高分二号遥感影像的树种分类方法[J]. 遥感技术与应用, 2019, 34(5): 970-982.
[15] 申祎,王超,胡佳乐. 一种结合空间与光谱信息的改进CVA变化检测方法[J]. 遥感技术与应用, 2019, 34(4): 799-806.