论文部分内容阅读
利用震后高分辨率卫星遥感影像提取建筑物损毁空间分布和破坏程度信息,对于地震灾情评估具有重要作用.本文以2010年海地地震巨灾为例,选用震后高分辨率卫星遥感影像Geoeye-1为数据源,在分析建筑物瓦砾可分离性的基础之上,利用监督分类方法提取损毁建筑物的瓦砾.结果表明,在震后高分辨率卫星遥感影像中,瓦砾是建筑物损毁的明显震害标志;瓦砾的生产者精度为87.23%,大于总体分类精度63.14%;瓦砾的Kappa系数为0.62,高于总体Kappa系数0.54.研究表明,基于瓦砾纹理特征的遥感信息提取方法能够从震后复杂的城市地物类型中识别出大部分瓦砾,该方法得到的结果可以应用于地震灾情应急评估,辅助应急救援等.
The use of post-earthquake high-resolution satellite remote sensing images to extract information on the spatial distribution and damage of buildings damages plays an important role in the assessment of earthquake disaster.Taking the Catastrophic Hazards in Haiti as an example, this paper selects the post-earthquake high resolution satellite remote sensing Geoeye- 1 as the data source, based on the analysis of the detachability of building rubble, the rubble of damaged buildings was extracted by supervised classification method.The results show that rubble is the obvious damage of buildings in post-earthquake high-resolution satellite remote sensing images The accuracy of rubble producers is 87.23%, which is greater than the overall classification accuracy of 63.14%. The Kappa coefficient of rubble is 0.62, which is higher than the overall Kappa coefficient of 0.54. The research shows that the remote sensing information extraction method based on the rubble texture feature Most of the rubble is identified in the complex urban landform types. The results obtained by this method can be applied to the emergency assessment of earthquake disaster and auxiliary emergency rescue.