Please wait a minute...
 
国土资源遥感  2018, Vol. 30 Issue (1): 95-101    DOI: 10.6046/gtzyyg.2018.01.13
  本期目录 | 过刊浏览 | 高级检索 |
利用KPCA法检测高分一号影像中的森林覆盖变化
尹凌宇1(), 覃先林1(), 孙桂芬1, 刘树超1, 祖笑锋1, 陈小中2
1.中国林业科学研究院资源信息所,北京 100091
2.四川省林业信息中心,成都 610081
The method for detecting forest cover change in GF-1images by using KPCA
Lingyu YIN1(), Xianlin QIN1(), Guifen SUN1, Shuchao LIU1, Xiaofeng ZU1, Xiaozhong CHEN2
1. Research Institute of Forest Resource Information Technique, Chinese Academy of Forestry, Beijing 100091, China
2. ForestInformation Center of Sichuan Province, Chengdu 610081, China
全文: PDF(873 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

为了研究利用高分一号宽幅影像(GF-1 WFV)监测森林覆盖变化的方法,选取四川省甘孜州雅江县为研究区,利用2014年和2016年2期GF-1WFV数据,采用迭代加权多元变化检测(iteration re-weight multivariate alteration detection,IR-MAD)法对数据进行辐射归一化; 分别对2期影像进行核主成分分析(kernel principal component analysis,KPCA)方法变换,采用最大类间方差法(OTSU)确定自动识别阈值,对2期GF-1WFV影像中的森林覆盖变化区域进行检测和精度验证; 并与变化矢量分析(change vector analysis,CVA)法检测结果进行对比分析。研究结果表明: 所用2种变化检测算法的总体检测精度都超过了80%,其中,KPCA法的总体精度为89.27%,未变化区用户精度达93.88%,变化区用户精度为80.28%; 基于KPCA法的精度均较优于传统CVA检测算法,说明 KPCA算法通过数据变换后,可减少变量间的相关性、增强影像信噪比,从而提高了对变化区域的识别精度。

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
尹凌宇
覃先林
孙桂芬
刘树超
祖笑锋
陈小中
关键词 高分一号(GF-1)迭代加权多元变化检测(IR-MAD)核主成分分析(KPCA)最大类间方差法(OTSU)    
Abstract

In order to study the methods for forest cover change monitoring by using GF-1 images, the Yajiang County in Sichuan Province was selected as the research area to extract the information of forest coverage based on the two GF-1 WFV data. Firstly, the data were normalized by using the iteration re-weight multivariate alteration detection(IR-MAD)method. The two images were transformed by kernel principal component analysis(KPCA)method, and formed differencing image. Then, the changed area was extracted using the method of maximum between class variances(OTSU)for automatic threshold selection. Finally, the change detection results were validated using OTSU with the field sample data, and the extracted results were verified by way of precision test, and comparatively analyzed with the change vector analysis(CVA). The research results show that the overall accuracy of the two change detection methods is higher than 80%, and the overall accuracy of the KPCA method is 89.27%. The user precision of unchanged area is 93.88%, and the user's accuracy of changed area is 80.28%. The accuracy of the KPCA method is better than that of the algorithm based on the traditional CVA method. It is shown that, after the data transformation, KPCA algorithm can reduce the correlation between the variables and enhance the signal to noise ratio of the image, thus improving the recognition accuracy for the changed area.

Key wordsGF-1    iteration re-weight multivariate alteration detection(IR-MAD)    kernel principal component analysis(KPCA)    method of maximum between class variance(OTSU)
收稿日期: 2016-08-05      出版日期: 2018-02-08
:  TP79  
基金资助:国防科工局重大专项项目“高分林业遥感应用示范系统”(编号: 21-Y30B05-9001-13/15)和民用航天预研项目“基于多源空间数据的森林火灾综合监测技术与应用示范”共同资助
作者简介:

第一作者: 尹凌宇(1989-),男,硕士研究生,主要研究方向为光学遥感影像处理和森林灾害监测方法。Email:1656641660@qq.com

引用本文:   
尹凌宇, 覃先林, 孙桂芬, 刘树超, 祖笑锋, 陈小中. 利用KPCA法检测高分一号影像中的森林覆盖变化[J]. 国土资源遥感, 2018, 30(1): 95-101.
Lingyu YIN, Xianlin QIN, Guifen SUN, Shuchao LIU, Xiaofeng ZU, Xiaozhong CHEN. The method for detecting forest cover change in GF-1images by using KPCA. Remote Sensing for Land & Resources, 2018, 30(1): 95-101.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2018.01.13      或      https://www.gtzyyg.com/CN/Y2018/V30/I1/95
载荷 波段号 谱段范围/μm 空间分辨率/m 幅宽/km 侧摆能力/(°) 重访时间/d
多光谱相机 1
2
3
4
0.45~0.52
0.52~0.59
0.63~0.69
0.77~0.89
16 800
(4台相机组合)
±35° 4
Tab.1  GF-1卫星WFV参数
Fig.1  各波段未变化像元散点图及回归方程

(目标影像为2016年GF-1影像,参考影像为2014年GF-1影像)

类别 B1 B2 B3 B4
目标影像(2016年) 435.939 4 160.580 9 151.038 7 838.843 8
参考影像(2014年) 113.770 0 143.727 7 189.128 4 901.870 9
辐射归一化后目标影像 113.787 0 143.685 0 189.172 2 902.127 9
Tab.2  相对辐射归一化前后目标影像和参考影像各波段反射率均值
年份 KPCA主成
分序号
特征值 方差贡献率
/%
累计方差
贡献率/%
2014 1 481 531.37 93.990 93.990
2 30 326.56 5.920 99.901
3 369.81 0.072 99.982
4 45.89 0.018 100.000
2016 1 433 300.52 91.710 91.710
2 38 609.56 8.170 99.880
3 462.11 0.098 99.978
4 89.24 0.022 100.000
Tab.3  GF-1影像KPCA主成分方差分布
Fig.2  雅江县东部局部影像
Fig.3  变化区域二值影像
Fig.4  变化区域提取结果
变化检测法 类别 检验样本点/个 列总数 用户
精度/%
变化区 未变化区
KPCA法 变化区 114.00 28.00 142 80.28
未变化区 17.00 261.00 278 93.88
行总数 131.00 289.00 420
生产者精度/% 87.02 90.32
总体精度/% 89.27
CVA法 变化区 92.00 31.00 123 74.80
未变化区 39.00 258.00 297 86.87
行总数 131.00 289.00 420
生产者精度/% 70.23 89.28
总体精度/% 83.33
Tab.4  2种变化检测方法精度
[1] Fazakas Z,Nilsson M,Olsson H. Regional forest biomass and wood volume estimation using satellite data and ancillary data[J].Agricultural and Forest Meteorology,1999,98-99:417-425.
[2] 李俊明,邢艳秋,杨超,等.基于环境与灾害监测预报小卫星的树种识别[J].东北林业大学学报,2013,41(11):41-45,50.
Li J M,Xing Y Q,Yang C,et al.Forest type identification based on hyperspectral remote sensing image of environment and disaster monito-ring satellite[J].Journal of Northeast Forestry University,2013,41(11):41-45,50.
[3] 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):82-87.
Wu X Q,Qin X L,Zhou R L,et al.Progress of study on forest cover change detection by using remote sensing technique[J]. Forest Resources Management, 2010(4):82-87.
[4] 钟家强,王润生.基于独立成分分析的多时相遥感图像变化检测[J].电子与信息学报,2006,28(6):994-998.
Zhong J Q,Wang R S.Multitemporal remote sensing images change detection based on ICA[J].Journal of Electronics & Information Technology,2006,28(6):994-998.
[5] 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.
Li S M,Wang Z H,Han X W,et al.Overview of forest resources change detection methods using remote sensing techniques[J].Journal of Beijing Forestry University,2011,33(3):132-138.
[6] 覃先林,陈尔学,李增元,等.基于MODIS数据的森林覆盖变化监测方法研究[J].遥感技术与应用,2006,21(3):178-183.
Qin X L,Chen E X,LI Z Y,et al.Forest cover change monitoring using MODIS data[J].Remote Sensing Technology and Application,2006,21(3):178-183.
[7] Platt R V,Schoennagel T.An object-oriented approach to assessing changes in tree cover in the Colorado front range 1938―1999[J].Forest Ecology and Management,2009,258(7):1342-1349.
[8] Hese S,Schmullius C. Forest cover change in Siberia-results from the Siberia-II project[EB/OL].(2011-01-11)[2016-08-01]..
[9] Collins J B,Woodcock C E.An assessment of several linear change detection techniques for mapping forest mortality using multitemporal Landsat TM data[J].Remote Sensing of Environment,1996,56(1):66-77.
[10] 黄维,黄进良,王立辉,等.基于PCA的变化向量分析法遥感影像变化检测[J].国土资源遥感,2016,28(1):22-27.doi:10.6046/gtzyyg.2016.01.04.
Huang W,Huang J L,Wang L H,et al.Remote sensing image change detection based on change vector analysis of PCA component[J].Remote Sensing for Land and Resources,2016,28(1):22-27.doi:10.6046/gtzyyg.2016.01.04.
[11] 刚慧龙. 基于IR-MAD算法的多元遥感影像变化检测方法研究[D].青岛:山东科技大学,2014.
Gang H L.The Study of Change Detection Method for Multivariate Remote Sensing Data based on the IR-MAD Algorithm[D].Qingdao:Shandong University of Science and Technology,2014.
[12] 沈照庆,陶建斌.基于模糊核主成分分析的高光谱遥感影像特征提取研究[J].国土资源遥感,2009,21(3):41-44,99.doi:10.6046/gtzyyg.2009.03.08.
Shen Z Q,Tao J B.Hyperspectral remote sensing image feature extraction based on fuzzy kernel principal component analysis[J].Remote Sensing for Land and Resources,2009,21(3):41-44,99.doi:10.6046/gtzyyg.2009.03.08.
[13] 杨帆,马洁.基于KPCA数据重构的参数优化方法[J].北京信息科技大学学报,2014,29(6):46-50.
Yang F,Ma J.Parameter optimization method based on KPCA data reconstruction[J].Journal of Beijing Information Science and Technology University,2014,29(6):46-50.
[14] 王国胜. 核函数的性质及其构造方法[J].计算机科学,2006,33(6):172-174,178.
Wang G S.Properties and construction methods of kernel in support vector machine[J].Computer Science,2006,33(6):172-174,178.
[15] Malila W A.Change vector analysis:An approach for detecting forest changes with Landsat[C]//Proceedings of Sixth International Symposium on Machine Processing of Remotely Sensed Data.West Lafayette,Indiana:Purdue University,1980.
[16] 林克正,班守峰,张玉双.一种基于变化向量分析的变化检测方法[J].哈尔滨理工大学学报,2008,13(4):47-49.
Lin K Z,Ban S F,Zhang Y S.A change detection based on change vector analysis[J].Journal of Harbin University of Science and Technology,2008,13(4):47-49.
[17] 魏伟一. 基于小波域灰度拉伸的Ostu图像分割[J].西北师范大学学报(自然科学版),2009,45(6):46-48.
Wei W Y.New Ostu image segmentation based on intensity stretching on DWT fields[J].Journal of Northwest Normal University(Natural Science),2009,45(6):46-48.
[18] 蔡燕伟,崔红霞.基于彩色空间的二维OSTU的图像分割算法[J].电子设计工程,2014,22(5):131-133.
Cai Y W,Cui H X.Image segmentation algorithm based on two-dimensional OSTU of color space[J].Electronic Design Engineering,2014,22(5):131-133.
[1] 廖戬, 顾行发, 占玉林, 张雅洲, 任芯雨, 师帅一. 高分一号卫星影像谐波模型模拟方法研究[J]. 国土资源遥感, 2018, 30(3): 106-112.
[2] 杨军, 裴剑杰. 一种改进的ICM遥感影像分割算法[J]. 国土资源遥感, 2018, 30(3): 18-25.
[3] 王瑞军, 闫柏琨, 李名松, 董双发, 孙永彬, 汪冰. 甘肃红山地区重要控矿地质单元GF-1数据遥感解译与应用[J]. 国土资源遥感, 2018, 30(2): 162-170.
[4] 张策, 揭文辉, 付丽华, 魏本赞. 新疆新源县滑坡灾害遥感影像特征及分布规律[J]. 国土资源遥感, 2017, 29(s1): 81-84.
[5] 张幼莹, 余江宽, 张丹丹, 林华暖. 国产卫星影像本底数据更新的实用方案——以地质灾害易发区遥感影像为例[J]. 国土资源遥感, 2017, 29(1): 149-157.
[6] 路云阁, 刘采, 王姣. 基于国产卫星数据的矿山遥感监测一体化解决方案——以西藏自治区为例[J]. 国土资源遥感, 2014, 26(4): 85-90.
[7] 白杨, 赵银娣. 基于KPCA和FCM的HJ-1A星遥感数据分类[J]. 国土资源遥感, 2013, 25(1): 71-76.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发