【摘要】 针对当前采用野外人工调查和遥感目视解译获取地震灾区滑坡信息存在主观性强、耗时费力等缺点。以汶川震区为实验区,应用资源三号(ZY-3)卫星影像,采用多尺度最优分割方法构建多层次识别对象,融合光谱、纹理、几何等影像特征和地形特征建立多维滑坡识别规则集合,以及基于高分辨率影像认知模式与场景理解过程提出滑坡分层识别模型,从而实现滑坡空间分布及其滑源区、滑移区和堆积区的快速识别。通过实验结果发现最低识别精度为82.97%,而滑坡的堆积区最容易识别。研究结果验证了该方法及资源三号卫星数据快速识别地震滑坡信息的有效性,可为震区滑坡调查提供技术支持,并可促进国产卫星的推广应用。更多还原

【Abstract】 Presently,regional earthquake-induced landslides is mainly obtained by field survey and visual interpretation from remote sensing images;but these methods are objective,and time-consuming.In this study,with a main data source of domestic high-resolution remote sensing images from ZY-3 satellite as well as the study area of the Wenchuan earthquake region,objects of multilevel landslides were established using the multi-scale optimum partition method based on in-depth analysis of landslide features.A recognition rule set of multi-dimensional landslides was also built through the combination of topographic features and image features,such as spectrum,texture,and geometry.Additionally,recognition models for landslide stratification were proposed based on the recognition models of high-resolution images and an understanding of the scenes.Through all of the aforementioned efforts,the spatial distribution of the seismic landslide as well as the sliding source area,transport area,and depositional area can be identified intelligently.The analysis results of the experimental area showed a minimum recognition accuracy of 82.97%,with the depositional zone of landslides being the easiest zone to recognize,and the effectiveness of the proposed method as well as ZY-3 data.These findings may provide technical support for regional earthquake-induced landslides investigations and further promote geological hazard application of domestic high-resolution satellites.更多还原