收稿：2017-09-18，
录用：2018-2-12，
纸质出版：2019-09
移动端阅览
基于光学遥感影像的区域滑坡普查易受云雾天气的影响，存在滑坡体调查不全面的问题，无法满足震后应急调查与恢复重建的需求。本文提出了一种极化SAR卫星数据滑坡普查方法，采用高分三号全极化SAR卫星影像数据，以九寨沟地震震区为实验区，在深入分析滑坡体和其他地物类型散射特征的基础上，融合极化特征、纹理特征和地形特征等多维特征信息，结合高分二号影像获取的训练样本，构建基于BP神经网络的全极化SAR数据滑坡自动识别模型，实现滑坡体的自动快速识别。与高分辨率光学影像与无人机航空影像目视解译结果相比较，总体识别精度为92.8%，Kappa系数为0.715，识别准确度满足地震应急实际应用的需求。研究成果可用于震区大区域滑坡体的普查，为后续开展无人机高分辨率影像滑坡体详查、灾后应急与景区恢复提供辅助信息支撑，并促进国产高分SAR卫星数据在防震减灾中的应用。
Conventional landslide identification model is only suitable for multispectral images. Optical images can directly reflect the information of ground objects and provide people a real and intuitive feeling. Earthquake areas are often hit with inclement weather after the occurrence of earthquakes. Effective optical images are difficult to obtain in the presence of clouds and fog
thus leading to the incomplete recognition of landslide information. Given that SAR satellite technology is not affected by clouds and breaks through the limitations of optics
SAR data have gradually become the mainstream data for earthquake disaster response and assessment. With the development of SAR sensors
SAR has developed into a multiband
multi-polarization
multi-angle
and variable working model from the first single mode of operation. SAR data guarantee flexibility in its application to seismic landslide identification. Existing SAR image landslide identification methods mainly use single characteristics of texture features or polarization features of landslide information in SAR images. Multi-source features in SAR images have not been fused
especially the characteristics of multi-polarization SAR image data. Thus
landslide survey accuracy is low and cannot meet actual application needs. Taking the Jiuzhaigou earthquake as an example
this study adopts the first C-band multi-polarization GF-3 satellite data with a resolution of 1 m as the data source. Polarization and texture features of the image are extracted based on an in-depth analysis of the characteristics of multi-polarization image data. Afterward
GF-2 satellite data obtained post-earthquake are carefully registered with the GF-3 satellite data. Typical landslide samples are selected from the GF-2 images
which are used as training samples for classification. Finally
back propagation neural network is used to extract the landslide in the whole area through the comprehensive utilization of polarization characteristics
texture
and terrain feature information based on the training samples. To meet the urgency of the disaster
identification accuracy can be improved as much as possible while meeting the efficiency of information identification. The findings can provide a reference for the restoration
reconstruction
and scientific exploration of the Jiuzhaigou earthquake. A comparison of the results of visual interpretation of GF-2 optical images and the unmanned aerial vehicle images revealed that the overall extraction accuracy of the landslide is 92.8% and the Kappa coefficient is 0.715. The scattering characteristics of the ridge on the image are easily confused with the bright spots formed by the landslide because these characteristics are more obvious. The spatial distribution feature of the slope can eliminate partial landslide information and eliminate the influence of the ridge. Taking the Jiuzhaigou earthquake as an example and using the homemade GF-3 full polarization SAR satellite data
this study proposes a fully polarimetric data seismic landslide automatic recognition method based on integrated polarization features
texture features
and terrain features. The method is used for a general investigation of landslides in the entire earthquake area of Jiuzhaigou. The extraction results meet the requirements of earthquake emergency
post-earthquake recovery
and reconstruction. The method also promotes the application of GaoFen satellites in the earthquake prevention and disaster reduction industry.
Bovolo F and Bruzzone L. 2005. A detail-preserving scale-driven approach to change detection in multitemporal SAR Images. IEEE Transactions on Geoscience and Remote Sensing, 43(12): 2963–2972
陈劲松, 邵芸, 李震. 2004. 基于目标分解理论的全极化SAR图像神经网络分类方法. 中国图象图形学报, 9(5): 552–556
Chen J S, Shao Y and Li Z. 2004. Neural networks classification of quad-polarization SAR data based on target decomposition ABSTRACT. Journal of Image and Graphics, 9(5): 552–556
陈莹, 孙洪泉, 赵祥, 唐宏, 周廷刚. 2011. 地震灾区河谷滑坡检测的遥感分析——以北川县滑坡为例. 自然灾害学报, 20(1): 97–104
Chen Y, Sun H Q, Zhao X, Tang H and Zhou T G. 2011. Remote sensing detection analysis of valley landslide in earthquake disaster area: a case study of landslides in Beichuan county. Journal of Natural Disasters, 20(1): 97–104
Chorowicz J, Scanvic J Y, Rouzeau O and Vargas Cuervo G. 1998. Observation of recent and active landslides from SAR ERS-1 and JERS-1 imagery using a stereo-simulation approach: example of the Chicamocha valley in Colombia. International Journal of Remote Sensing, 19(16): 3187–3196
郭华东, 李新武. 2011. 新一代SAR对地观测技术特点与应用拓展. 科学通报, 56(15): 1155–1168
Guo H D and Li X W. 2011. Technical characteristics and potential application of the new generation SAR for earth observation. Chinese Science Bulletin, 56(15): 1155–1168
李松, 李亦秋, 安裕伦. 2010. 基于变化检测的滑坡灾害自动识别. 遥感信息(1): 27–31
Li S, Li Y Q and An Y L. 2010. Automatic recognition of landslides based on change detection. Remote Sensing Information(1): 27–31
李松, 邓宝昆, 徐红勤, 王治福. 2015. 地震型滑坡灾害遥感快速识别方法研究. 遥感信息, 30(4): 25–28
Li S, Deng B K, Xu H Q and Wang Z F. 2015. Fast interpretation methods of landslides triggered by earthquake using remote sensing imagery. Remote Sensing Information, 30(4): 25–28
李渝生, 黄超, 易树健, 伍纯昊. 2017. 九寨沟7.0级地震的地震断裂及震源破裂的构造动力学机理研究. 工程地质学报, 25(4): 1141–1150
Li Y S, Huang C, Yi S J and Wu C H. 2017. Study on seismic fault and source rupture tectonic dynamic mechanism of Jiuzhaigou M s 7.0 earthquake. Journal of Engineering Geology, 25(4): 1141–1150
Lu P, Stumpf A, Kerle N and Casagli N. 2011. Object-oriented change detection for landslide rapid mapping. IEEE Geoscience and Remote Sensing Letters, 8(4): 701–705
骆剑承, 周成虎, 杨艳. 2001. 人工神经网络遥感影像分类模型及其与知识集成方法研究. 遥感学报, 5(2): 122–129
Luo J C, Zhou C H and Yang Y. 2001. ANN remote sensing classification model and its integration approach with geo-knowledge. Journal of Remote Sensing, 5(2): 122–129
Martha T R, Kerle N, Jetten V, van Westen C J and Kumar K V. 2010. Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods. Geomorphology, 116(1/2): 24–36
Mondini A C, Marchesini I, Rossi M, Chang K T, Pasquariello G and Guzzetti F. 2013. Bayesian framework for mapping and classifying shallow landslides exploiting remote sensing and topographic data. Geomorphology, 201: 135–147
屈晓晖, 庄大方, 彭望碌, 乔玉良. 2007. 基于ANN分类的农田遥感动态监测模型研究. 自然资源学报, 22(2): 193–197
Qu X H, Zhuang D F, Peng W L and Qiao Y L. 2007. Studies on remote sensing dynamic detection model of cropland based on the classification of artificial neural network. Journal of Natural Resources, 22(2): 193–197
Rott H and Nagler T. 2006. The contribution of radar interferometry to the assessment of landslide hazards. Advances in Space Research, 37(4): 710–719
Singh A. 1989. Review article digital change detection techniques using remotely-sensed data. International Journal of Remote Sensing, 10(6): 989–1003
Stumpf A and Kerle N. 2011. Combining random forests and object-oriented analysis for landslide mapping from very high resolution imagery. Procedia Environmental Sciences, 3: 123–129
王超, 张红, 陈曦, 刘智, 闫冬梅. 2008. 全极化合成孔径雷达图像处理. 北京: 科学出版社
Wang C, Zhang H, Chen X, Liu Z and Yan D M. 2008. Polarimetric SAR Image Processing. Beijing: Science Press
王旭, 王宏, 王文辉. 2000. 人工神经元网络原理与应用. 沈阳: 东北大学出版社
Wang X, Wang H and Wang W H. 2000. Principles and Applications of Artificial Neural Networks. Shenyang: Northeastern University Press
王兴玲, 胡德勇, 唐宏, 舒阳. 2014. 基于Bayes决策的机载全极化SAR图像滑坡信息提取. 国土资源遥感, 26(2): 121–127
Wang X L, Hu D Y, Tang H and Shu Y. 2014. Extraction of landslide information from airborne polarimetric SAR images based on Bayes decision theory. Remote Sensing for Land and Resources, 26(2): 121–127
徐黎明, 王清, 陈剑平, 潘玉珍. 2013. 基于BP神经网络的泥石流平均流速预测. 吉林大学学报(地球科学版), 43(1): 186–191
Xu L M, Wang Q, Chen J P and Pan Y Z. 2013. Forcast for average velocity of debris flow based on BP neural network. Journal of Jilin University (Earth Science Edition), 43(1): 186–191
Zhai W, Shen H F, Huang C L and Pei W S. 2016. Fusion of polarimetric and texture information for urban building extraction from fully polarimetric SAR imagery. Remote Sensing Letters, 7(1): 31–40
赵祥, 李长春, 苏娜. 2009. 滑坡泥石流的多源遥感提取方法. 自然灾害学报, 18(6): 29–32
Zhao X, Li C C and Su N. 2009. Extraction of landslide/debris flow information based on multi-source remote sensing data. Journal of Natural Disasters, 18(6): 29–32
赵一博, 邹焕新, 秦先祥. 2013. 一种基于RBF神经网络的极化SAR图像分类方法. 现代雷达, 35(8): 24–27
Zhao Y B, Zou H X and Qin X X. 2013. Classification of polarimetric SAR image based on the RBF neural network. Modern Radar, 35(8): 24–27
朱矩波, 马士林. 1998. 函数逼近神经网络的一种快速学习算法. 红外与毫米波学报, 17(4): 303–307
Zhu J B and Ma S L. 1998. A fast learning algorithm of neural networks for approximating function. Journal of Infrared and Millimeter Waves, 17(4): 303–307
朱林. 2016. 遥感图像变化检测技术的研究及应用. 北京: 中国地质大学(北京)
Zhu L. 2016. Research and Application of Remote Sensing Image Change Detection Technology. Beijing: China University of Geosciences (Beijing)
相关作者
相关机构
京公网安备11010802024621
