Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images

Chao CHEN; Jiaoqi FU; Xinxin SUI; Xu LU; Anhui TAN

doi:10.11834/jrs.20188044

Technology and Methodology | Views : 0 下载量: 114 CSCD: 8 更多指标

PDF
Export
Share
Collection
Album

Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images
Vol. 22, Issue 5, Pages: 792-801(2018)
Published： 2018-9 ，

Accepted： 26 March 2018
DOI： 10.11834/jrs.20188044

扫描看全文

陈超, 傅姣琪, 随欣欣, 鲁旭, 谭安辉. 2018. 面向灾后水体遥感信息提取的知识决策树构建及应用. 遥感学报, 22(5): 792–801

Chen C, Fu J Q, Sui X X, Lu X and Tan A H. 2018. Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images. Journal of Remote Sensing, 22(5): 792–801
陈超, 傅姣琪, 随欣欣, 鲁旭, 谭安辉. 2018. 面向灾后水体遥感信息提取的知识决策树构建及应用. 遥感学报, 22(5): 792–801 DOI： 10.11834/jrs.20188044.

Chen C, Fu J Q, Sui X X, Lu X and Tan A H. 2018. Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images. Journal of Remote Sensing, 22(5): 792–801 DOI： 10.11834/jrs.20188044.

摘要

灾害发生以后，悬浮物质、波浪和水深等“同物异谱”会导致水体信息提取不完整，而阴影、沥青路面、浓密植被等“异物同谱”也会降低水体信息提取精度。针对此问题，提出一种特征知识引导的灾后水体信息提取方法。首先，分析水体遥感图像特征(光谱特征、几何特征、纹理特征、空间关系特征)，构建灾后水体信息提取知识决策树；其次，对遥感图像进行面向对象分割，获取对象基元，并计算特征参数；然后，在知识决策树的支持下提取灾后水体信息；最后，对水体信息提取结果进行后处理，以去除噪声和填充孔洞。选取“5·12汶川地震”遥感图像开展验证实验，结果表明，水体信息提取结果位置准确，边界清晰，生产者精度和用户精度分别为0.85和0.94，该方法能够有效提取复杂背景下的灾后水体信息。

Abstract

After a disaster

the same object with different spectra (such as suspended material

wave

and water depth

each of them having more than one spectrum) leads to incomplete extraction of water body information. Different objects with the same spectrum

such as shadow

asphalt pavement

and dense vegetation

decrease the extraction precision of water body information. To address this problem

the extraction method of water body information based on its characteristics after a disaster is presented in this study. First

the characteristics (i.e.

spectra

geometry

texture

and spatial relationship) of water body information are analyzed on remote sensing images to construct a knowledge decision tree. Second

object-oriented segmentation is performed on remote sensing images to obtain object elements and calculate the characteristic parameters. Third

water body information after a disaster is extracted with the support of the knowledge decision tree. Finally

the water body information is post-processed. A validation experiment was performed using the high-spatial resolution remote sensing images of “5.12 Wenchuan Earthquake.” The location of the extracted water is accurate and the boundary is clear. The accuracies of the producer and the user are 0.85 and 0.94

respectively. Results showed that the method can effectively extract water body information after a disaster even when the background is complex.

关键词

特征知识决策树汶川地震灾后水体信息精度评价

Keywords

characteristic knowledgedecision treeWenchuan Earthquakewater body information extraction after disasteraccuracy evaluation

references

Chen C, Qin Q M, Chen L, Zheng H, Fa W Z, Ghulam A and Zhang C Y. 2015. Photometric correction and reflectance calculation for lunar images from the Chang’E-1 CCD stereo camera. Journal of the Optical Society of America A, 32(12): 2409–2422

Chen C, Qin Q M, Zhang N, Li J, Chen L, Wang J, Qin X B and Yang X C. 2014. Extraction of bridges over water from high-resolution optical remote-sensing images based on mathematical morphology. International Journal of Remote Sensing, 35(10): 3664–3682

陈鹏鹏, 冉鑫. 2010. 基于决策树的海上搜救目标检测算法. 上海海事大学学报, 31(3): 1–4

Chen P P and Ran X. 2010. Marine rescue target detection algorithm based on decision tree. Journal of Shanghai Maritime University, 31(3): 1–4 (

陈述彭, 童庆禧, 郭华东. 1998. 遥感信息机理研究. 北京: 科学出版社

Chen S P, Tong Q X and Guo H D. 1998. Mechanism of Remote Sensing Information. Beijing: Science Press

杜云艳, 周成虎. 1998. 水体的遥感信息自动提取方法. 遥感学报, 2(4): 264–269

Du Y Y and Zhou C H. 1998. Automatically extracting remote sensing information for water bodies. Journal of Remote Sensing, 2(4): 264–269 (

范一大, 吴玮, 王薇, 刘明, 温奇. 2016. 中国灾害遥感研究进展. 遥感学报, 20(5): 1170–1184

Fan Y D, Wu W, Wang W, Liu M and Wen Q. 2016. Research progress of disaster remote sensing in China. Journal of Remote Sensing, 20(5): 1170–1184 (

Ji L, Zhang L and Wylie B K. 2009. Analysis of dynamic thresholds for the normalized difference water index. Photogrammetric Engineering and Remote Sensing, 75(11): 1307–1317

李斌. 2011. 长江中游洪涝灾害的MODIS时序监测与分析. 泰安: 山东农业大学

Li B. 2011. Flood monitoring and analysis over the middle reaches of Yangtze River Basin with MODIS time-series imagery. Tai’an: Shandong Agricultural University

李德仁, 陈晓玲, 蔡晓斌. 2008. 空间信息技术用于汶川地震救灾. 遥感学报, 12(6): 841–851

Li D R, Chen X L and Cai X B. 2008. Spatial information techniques in rapid response to Wenchuan Earthquake. Journal of Remote Sensing, 12(6): 841–851 (

李德仁, 童庆禧, 李荣兴, 龚健雅, 张良培. 2012. 高分辨率对地观测的若干前沿科学问题. 中国科学: 地球科学, 42(6): 805–813

Li D R, Tong Q X, Li R X, Gong J Y and Zhang L P. 2012. Current issues in high-resolution Earth observation technology. Science China: Earth Sciences, 42(6): 805–813 (

李景刚, 黄诗峰, 李纪人. 2010. ENVISAT卫星先进合成孔径雷达数据水体提取研究—改进的最大类间方差阈值法. 自然灾害学报, 19(3): 139–145

Li J G, Huang S F and Li J R. 2010. Research on extraction of water body from ENVISAT ASAR images: amodified Otsu threshold method. Journal of Natural Disasters, 19(3): 139–145 (

李加林, 曹罗丹, 浦瑞良. 2014. 洪涝灾害遥感监测评估研究综述. 水利学报, 45(3): 253–260

Li J L, Cao L D and Pu R L. 2014. Progresses on monitoring and assessment of flood disaster in remote sensing. China Environment Science, 45(3): 253–260 (

林卉, 邵聪颖, 李海涛, 顾海燕, 王李娟. 2017. 高分辨率遥感影像5种面向对象分类方法对比研究. 测绘通报(11): 17–21

Lin H, Shao C Y, Li H T, Gu H Y and Wang L J. 2017. Five object-oriented classification methods analysis based on high-resolution remote sensing image. Bulletin of Surveying and Mapping(11): 17–21 (

骆剑承. 2000. 遥感影像智能图解及其地学认知问题探索. 地理科学进展, 19(4): 289–296

Luo J C. 2000. Remote-sensing intelligent geo-interpretation model and its geo-cognition issue. Progress in Geography, 19(4): 289–296 (

骆剑承, 吴田军, 夏列刚. 2016. 遥感图谱认知理论与计算. 地球信息科学学报, 18(5): 578–589

Luo J C, Wu T J and Xia L G. 2016. The theory and calculation of spatial-spectral cognition of remote sensing. Journal of Geo-Information Science, 18(5): 578–589 (

McFeeters S K. 1996. The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7): 1425–1432

梅安新, 彭望琭, 秦其明, 刘慧平. 2001. 遥感导论. 北京: 高等教育出版社

Mei A X, Peng W L, Qin Q M and Liu H P. 2001. An Introduction to Remote Sensing. Beijing: Higher Education Press

孟令奎, 李珏, 王锐, 张文. 2017. 数学形态学与拓扑约束支持的单条河流骨架线提取. 遥感学报, 21(5): 785–795

Meng L K, Li J, Wang R and Zhang W. 2017. Single river skeleton extraction method based on mathematical morphology and topology constraints. Journal of Remote Sensing, 21(5): 785–795 (

明冬萍, 骆剑承, 沈占峰. 2009. 基于GMRF-SVM的高分辨率遥感影像目标区域划分方法. 测绘科学, 34(2): 33–37

Ming D P, Luo J C and Shen Z F. 2009. Research on region partition in high resolution remote sensing image based on GMRF-SVM. Science of Surveying and Mapping, 34(2): 33–37 (

明冬萍, 骆剑承, 周成虎, 汪闽, 郑江, 陈秋晓, 沈占峰. 2005. 高分辨率遥感影像信息提取及块状基元特征提取. 数据采集与处理, 20(1): 34–39

Ming D P, Luo J C, Zhou C H, Wang M, Zhang J, Chen Q X and Shen Z F. 2005. Information extraction from high resolution remote sensing image and parcel unit extraction based on features. Journal of Data Acquisition and Processing, 20(1): 34–39 (

Otsu N. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1): 62–66

Rahman M S and Di L P. 2017. The state of the art of spaceborne remote sensing in flood management. Natural Hazards, 85(2): 1223–1248

夏列钢, 沈占峰, 李均力, 骆剑承. 2013. 复杂背景下多样水体遥感自动解译. 中国图象图形学报, 18(11): 1513–1519

Xia L G, Shen Z F, Li J L and Luo J C. 2013. Automatic interpretation of diverse water bodies from remotely sensed images in complex background. Journal of Image and Graphics, 18(11): 1513–1519 (

徐涵秋. 2005. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究. 遥感学报, 9(5): 589–595

Xu H Q. 2005. A study on information extraction of water body with the modified normalized difference water index (MNDWI). Journal of Remote Sensing, 9(5): 589–595 (

Xu H Q. 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14): 3025–3033

徐涵秋. 2008. 从增强型水体指数分析遥感水体指数的创建. 地球信息科学, 10(6): 776–780

Xu H Q. 2008. Comment on the enhanced water index (EWI): a discussion on the creation of a water index. Geo-Information Science, 10(6): 776–780 (

杨树文, 薛重生, 刘涛, 李铁鲲. 2010. 一种利用TM影像自动提取细小水体的方法. 测绘学报, 39(6): 611–617

Yang S W, Xue C S, Liu T and Li T K. 2010. A method of small water information automatic extraction from TM remote sensing images. Acta Geodaetica et Cartographica Sinica, 39(6): 611–617 (

Yin J H, Qv H, Luo X Y and Jia X P. 2017. Segment-oriented depiction and analysis for hyperspectral image data. IEEE Transactions on Geoscience and Remote Sensing, 55(7): 3982–3996

张猛, 曾永年, 朱永森. 2017. 面向对象方法的时间序列MODIS数据湿地信息提取——以洞庭湖流域为例. 遥感学报, 21(3): 479–492

Zhang M, Zeng Y N and Zhu Y S. 2017. Wetland mapping of Dongting Lake Basin based on time-series MODIS data and object-oriented method. Journal of Remote Sensing, 21(3): 479–492 (

张倩, 黄昕, 张良培. 2011. 多尺度同质区域提取的高分辨率遥感影像分类研究. 武汉大学学报(信息科学版), 36(1): 117–121

Zhang Q, Huang X and Zhang L P. 2011. Multiscale image segmentation and classification with supervised ECHO of high spatial resolution remotely sensed imagery. Geomatics and Information Science of Wuhan University, 36(1): 117–121 (

张渊智, 陈楚群, 段洪涛. 2011. 水质遥感理论、方法及应用. 北京: 高等教育出版社

Zhang Y Z, Chen C Q and Duan H T. 2011. Principles, Methods and Applications in Remote Sensing of Water Quality. Beijing: Higher Education Press

Zhao X, Wang P, Chen C, Jiang T, Yu Z G and Guo B Y. 2017. Waterbody information extraction from remote-sensing images after disasters based on spectral information and characteristic knowledge. International Journal of Remote Sensing, 38(5): 1404–1422

周小成, 沈占峰, 汪小钦, 吴波. 2009. 基于特征基元的高分辨率遥感影像道路网自动提取技术. 测绘科学, 34(3): 114–117

Zhou X C, Shen Z F, Wang X Q and Wu B. 2009. Research on urban road network extraction from high resolution remote sensing image based on feature units. Science of Surveying and Mapping, 34(3): 114–117 (

Alert me when the article has been cited

提交

Accuracy evaluation of multi-source DEM data based on the analysis of vegetation-induced penetration rate in the forest area

Remote sensing anomalies of multiple geospheres before the Wenchuan earthquake and its spatiotemporal correlations

Research progress on methods of automatic coastline extraction based on remote sensing images

Earthquake-induced landslide recognition using high-resolution remote sensing images

Intelligence fusion method research of multisource high-resolution remote sensing images