Please wait a minute...
国土资源遥感  2019, Vol. 31 Issue (2): 180-186    DOI: 10.6046/gtzyyg.2019.02.25
  技术应用 本期目录 | 过刊浏览 | 高级检索 |
无人机遥感影像面向对象分类的冻土热融滑塌边界提取
梁林林1,2,江利明1,2(),周志伟1,陈玉兴1,2,孙亚飞1,2
1.中国科学院测量与地球物理研究所大地测量与地球动力学国家重点实验室,武汉 430077
2.中国科学院大学,北京 100049
Object-oriented classification of unmanned aerial vehicle image for thermal erosion gully boundary extraction
Linlin LIANG1,2,Liming JIANG1,2(),Zhiwei ZHOU1,Yuxing CHEN1,2,Yafei SUN1,2
1.State Key Laboratory of Geodesy and Earth’s Dynamics, Institute of Geodesy and Geophysics, Chinese Academy of Sciences, Wuhan 430077, China;
2.University of Chinese Academy of Sciences, Beijing 100049, China
全文: PDF(3779 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

全球气候变暖及人类活动导致青藏高原大面积冻土退化、热融滑塌等问题,严重影响了多年冻土区工程建设和生态环境。利用无人机高空间分辨率影像和面向对象分类技术进行了黑河上游俄博岭垭口冻土区热融滑塌监测实验,详细分析了最邻近、K-最邻近、决策树、支持向量机(support vector machine,SVM)和随机森林5种面向对象监督学习方法提取冻土热融滑塌边界的性能和精度,并使用野外实测数据对实验结果进行验证。结果表明,面向对象分析中分割尺度对热融滑塌提取结果影响较小,而不同组合的分类特征影响较大,因此选择合适的分类特征是关键; 5种分类方法的总体精度均在90%以上,其中SVM方法的Kappa系数高于其他4种分类方法,表明该方法在本次实验研究中更适合无人机遥感影像冻土热融滑塌边界提取。无人机高空间分辨率遥感与面向对象分类方法相结合在冻土热融滑塌监测中具有广阔的应用前景。

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
梁林林
江利明
周志伟
陈玉兴
孙亚飞
关键词 冻土热融滑塌无人机遥感黑河上游俄博岭冻土区高空间分辨率影像面向对象分析    
Abstract

Global climate warming and human activities have caused large areas of permafrost degradation and thermal erosion gully in the Tibetan Plateau, seriously affecting the engineering construction and the ecological environment in permafrost regions. In this study, high resolution unmanned aerial vehicle (UAV) images and object-oriented classification approaches were applied to extracting the thermal erosion gullies in Eboling Mountain of Heihe River. Five kinds of object-oriented supervised learning algorithms, namely nearest neighbor, K-nearest neighbor, decision tree, support vector machine (SVM), and random forest, were analyzed for the capability and accuracy of the extraction of thermal erosion gullies in detail. The field GPS data were used for evaluating the classification accuracy. The results show that, in the object-oriented image analysis, the segmentation scale parameters have little effect on the extraction of thermal erosion gullies, wheres classification features have a greater impact, so it is important to select the appropriate classification features. The overall accuracies of the five machine learning methods are all over 90%, among which the Kappa coefficient of the SVM is higher than the other four classification methods. This means that SVM is more suitable for the thermal erosion gullies boundary extraction of UAV images in this study. The combination of high resolution UAV images and object-oriented classification methods has broad application prospects in the extraction of the thermal erosion gullies.

Key wordsthermal erosion gully of permafrost    unmanned aerial vehicle    Eboling Mountain of Heihe River permafrost region    high spatial resolution images    object-oriented analysis
收稿日期: 2018-03-19      出版日期: 2019-05-23
ZTFLH:  TP79  
基金资助:中国科学院前沿科学重点研究项目“空—地协同观测的青藏冻土活动层厚度反演与水碳释放量定量评估”(QYZDB-SSWDQC027);中国科学院战略性先导科技专项子课题“三极环境大数据分析方法库及其科学应用示范”(XDA19070104);国家自然科学基金重点项目“喀喇昆仑—喜马拉雅冰川物质平衡的空间大地测量研究”(41431070);国家自然科学基金创新群体项目“现代大地测量及其地学应用的研究”共同资助(41621091)
通讯作者: 江利明     E-mail: jlm@whigg.ac.cn
作者简介: 梁林林(1993-),女,研究生,主要从事高分辨率影像处理和信息提取方面的研究。Email: lianglinlin16@mails.ucas.ac.cn。
引用本文:   
梁林林,江利明,周志伟,陈玉兴,孙亚飞. 无人机遥感影像面向对象分类的冻土热融滑塌边界提取[J]. 国土资源遥感, 2019, 31(2): 180-186.
Linlin LIANG,Liming JIANG,Zhiwei ZHOU,Yuxing CHEN,Yafei SUN. Object-oriented classification of unmanned aerial vehicle image for thermal erosion gully boundary extraction. Remote Sensing for Land & Resources, 2019, 31(2): 180-186.
链接本文:  
http://www.gtzyyg.com/CN/10.6046/gtzyyg.2019.02.25      或      http://www.gtzyyg.com/CN/Y2019/V31/I2/180
Fig.1  研究区影像
Fig.2  研究区内热融滑塌现象
Fig.3  UX5固定翼无人机
Fig.4  GPS现场测量
波段权重(R,G,B,
DSM, slope)
光谱信
息权重
紧致度
权重
分割
尺度
1,1,1,1,1 0.7 0.8 150
1,1,1,1,1 0.7 0.8 220
Tab.1  分割参数
实验
序号
分割参数(分割尺
度,光谱信息权重,
紧致度权重)
滑塌、非滑塌分类特征提取
SY1 150,0.7,0.8 所有波段的平均值、标准差和比率
SY2 220,0.7,0.8 所有波段的平均值、标准差和比率
SY3 220,0.7,0.8 绿光、红光和坡度波段的标准差及蓝光、绿光波段的比率
Tab.2  分类特征提取参数
Fig.5  SY1样本分布和分类结果
分类方法 类型 滑塌 非滑塌 总数 制图精度/% 用户精度/% 总体精度/% Kappa
最邻近 滑塌 2 149 1 651 3 800 83 57 97 0.66
非滑塌 433 78 830 79 263 98 99
KNN 滑塌 2 150 1 600 3 750 83 57 98 0.67
非滑塌 432 78 881 79 313 98 99
决策树 滑塌 2 195 2 577 4 772 85 46 96 0.58
非滑塌 387 77 904 78 291 97 100
SVM 滑塌 2 011 903 2 914 78 69 98 0.72
非滑塌 571 79 578 80 149 99 99
随机森林 滑塌 2 160 1 363 3 523 84 61 98 0.70
非滑塌 422 79 118 79 540 98 99
Tab.3  SY1分类混淆矩阵
分类方法 类型 滑塌 非滑塌 总数 制图精度/% 用户精度/% 总体精度/% Kappa
最邻近 滑塌 2 251 1 681 3 932 87 57 98 0.68
非滑塌 331 78 788 79 119 98 100
KNN 滑塌 2 213 1 680 3 893 86 57 98 0.67
非滑塌 369 78 801 79 170 98 100
决策树 滑塌 1 897 1 899 3 796 73 50 97 0.58
非滑塌 685 78 582 79 267 98 99
SVM 滑塌 2 096 1 298 3 394 81 62 98 0.69
非滑塌 486 79 183 79 669 98 99
随机森林 滑塌 1 984 1 908 3 892 77 51 97 0.60
非滑塌 598 78 573 79 171 98 99
Tab.4  SY2分类混淆矩阵
分类方法 类型 滑塌 非滑塌 总数 制图精度/% 用户精度/% 总体精度/% Kappa
最邻近 滑塌 2 267 2 598 4 865 88 47 96 0.58
非滑塌 315 77 782 78 097 97 100
KNN 滑塌 2 265 3 041 5 306 88 43 96 0.55
非滑塌 316 77 414 77 730 96 100
决策树 滑塌 2 431 7 595 10 026 94 24 91 0.35
非滑塌 151 72 886 73 037 91 100
SVM 滑塌 2 213 2 325 4 538 86 49 97 0.61
非滑塌 369 78 156 78 525 97 100
随机森林 滑塌 2 296 6 461 8 757 89 26 92 0.37
非滑塌 286 74 020 74 306 92 100
Tab.5  SY3分类混淆矩阵
Fig.6  5种分类方法Kappa系数比较
[1] 周幼吾, 郭东信, 邱国庆 , 等. 中国冻土[M]. 北京: 科学出版社, 2000.
Zhou Y W, Guo D X, Qiu G Q , et al. Chinese Frozen Soil[M]. Beijing: Science Press, 2000.
[2] Zhang T, Barry R G, Knowles K , et al. Statistics and characteristics of permafrost and ground ice distribution in the Northern Hemisphere[J]. Polar Geography, 1999,23(2):147-169.
[3] Williams P J, Smith M W. The Frozen Earth [M]. New York: Cambridge University Press, 1989.
[4] 周幼吾, 郭东信 . 我国多年冻土的主要特征[J]. 冰川冻土, 1982,4(1):1-19.
Zhou Y W, Guo D X . Principal characteristics of permafrost in China[J]. Journal of Glaciology and Cryopedology, 1982,4(1):1-9.
[5] 牟翠翠, 张廷军, 曹斌 , 等. 祁连山区黑河上游俄博岭多年冻土区活动层碳储量研究[J]. 冰川冻土, 2013,35(1):1-9.
doi: 10.7522/j.issn.1000-0240.2013.0001
Mu C C, Zhang T J, Cao B , et al. Study of the organic carbon storage in the active layer of permafrost over the Eboling Mountain in the upper reaches of the Heihe River in the eastern Qilian Mountains[J]. Journal of Glaciology and Geocryology, 2013,35(1):1-9.
doi: 10.7522/j.issn.1000-0240.2013.0001
[6] 马立峰 . 多年冻土地区热融滑塌及其工程危害性的研究[D]. 兰州:中国科学院寒区旱区环境与工程研究所, 2006.
Ma L F . Study on Thaw Slump and Its Hazardness to Engineering in Permafrost Regions[D].Lanzhou:Cold and Arid Regions Environmental and Engineering Research Institute, Chinese Academy of Sciences, 2006.
[7] Daniel H, Petra F, Francesco A , et al. A semi-automated object-based approach for landslide detection validated by persistent scatterer interferometry measures and landslide inventories[J]. Remote Sensing, 2012,4(5):1310-1336.
doi: 10.3390/rs4051310
[8] 甘甜, 李金平, 李小强 , 等. 面向对象的高分辨率遥感影像建筑物震害信息提取[J]. 测绘工程, 2015,24(4):11-15.
Gan T, Li J P, Li X Q , et al. Object-oriented method of building damage extraction from high-resolution images[J]. Engineering of Surveying and Mapping, 2015,24(4):11-15.
[9] 孙娜, 高志强, 王晓晶 , 等. 基于高分遥感影像的黄土高原地区水体高精度提取[J]. 国土资源遥感, 2017,29(4):173-178.doi: 10.6046/gtzyyg.2017.04.26.
doi: 10.6046/gtzyyg.2017.04.26
Sun N, Gao Z Q, Wang X J , et al. High-precise extraction for water on the Loess Plateau region from high resolution satellite image[J]. Remote Sensing for Land and Resources, 2017,29(4):173-178.doi: 10.6046/gtzyyg.2017.04.26.
doi: 10.6046/gtzyyg.2017.04.26
[10] 王岩, 王晓青, 窦爱霞 . 面向对象遥感分类方法在汶川地震震害提取中的应用[J]. 地震, 2009,29(3):54-60.
Wang Y, Wang X Q, Dou A X . Building damage detection of the 2008 Wenchuan,China earthquake based on object-oriented classification method[J]. Earthquake, 2009,29(3):54-60.
[11] Kraaijenbrink P D A, Shea J M, Pellicciotti F , et al. Object-based analysis of unmanned aerial vehicle imagery to map and characterise surface features on a debris-covered glacier[J]. Remote Sensing of Environment, 2016,186:581-595.
doi: 10.1016/j.rse.2016.09.013
[12] Colomina I, Molina P . Unmanned aerial systems for photogrammetry and remote sensing:A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014,92(2):79-97.
doi: 10.1016/j.isprsjprs.2014.02.013
[13] 李德仁, 李明 . 无人机遥感系统的研究进展与应用前景[J]. 武汉大学学报(信息科学版), 2014,39(5):505-513.
doi: 10.13203/j.whugis20140045
Li D R, Li M . Research advance and application prospect of unmanned aerial vehicle remote sensing system[J]. Geomatics and Information Science of Wuhan University, 2014,39(5):505-513.
doi: 10.13203/j.whugis20140045
[14] Baatz M,Sch?pe A .An optimization approach for high quality multi-scale image segmentation[EB/OL]. http://test.ecognition.com/sites/default/files/405_baatz_fp_12.pdf.
[15] 王旭东, 段福洲, 屈新原 , 等. 面向对象和SVM结合的无人机数据建筑物提取[J]. 国土资源遥感, 2017,29(1):97-103.doi: 10.6046/gtzyyg.2017.01.15.
doi: 10.6046/gtzyyg.2017.01.15
Wang X D, Duan F Z, Qu X Y , et al. Building extraction based on UAV imagery data with the synergistic use of objected-based method and SVM classifier[J]. Remote Sensing for Land and Resources, 2017,29(1):97-103.doi: 10.6046/gtzyyg.2017.01.15.
doi: 10.6046/gtzyyg.2017.01.15
[16] Trimble Germany GmbH. eCognition Developer 8.64.1 User Guide[M]. Munchen:Trimble Germany Trappentreustre, 2011.
[17] Benz U C, Hofmann P, Willhauck G , et al. Multi-resolution,object-oriented fuzzy analysis of remote sensing data for GIS-ready information[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2004,58(3):239-258.
doi: 10.1016/j.isprsjprs.2003.10.002
[1] 吴永亮, 陈建平, 姚书朋, 徐彬. 无人机低空遥感技术应用[J]. 国土资源遥感, 2017, 29(4): 120-125.
[2] 金鼎坚, 支晓栋, 王建超, 张丹丹, 尚博譞. 面向地质灾害调查的无人机遥感影像处理软件比较[J]. 国土资源遥感, 2016, 28(1): 183-189.
[3] 唐远彬, 刘文, 任少华. 基于无人机遥感技术的潮间带高程测量方法[J]. 国土资源遥感, 2013, 25(2): 42-46.
[4] 秦其明, 金川, 陈德智, 李杰. 无人机遥感数据压缩解压缩系统的设计和实现[J]. 国土资源遥感, 2006, 18(2): 31-34.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《国土资源遥感》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 Email:gtzyyg@agrs.cn; gtzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发