摘要
针对常规遥感影像的空间分辨率较低,导致无法准确提取影像信息的问题,该文提出含有限水体介质的地震灾害高分遥感影像信息提取方法。首先,利用高分遥感技术,以扫描方式采集影像信息;其次,分析有限水体介质与地壳应力场的关系,计算含水层水流速度及其流量特征;再者,选取渗流区域任意单元体,得到含水层系统流量计算结果;然后,增强图像特征,减少干扰,完成遥感影像分割;最后,利用深度置信网络,设置目标像元特征值,获取相关集序列中间值,实现含有限水体介质的地震灾害高分遥感影像信息提取。
In order to solve the problem that the spatial resolution of conventional remote sensing images is low,which makes it impossible to extract image information accurately,a high score remote sensing image information extraction method for seismic disasters with limited water bodies is proposed.Firstly,the image information is collected by scanning by using high resolution remote sensing technology.Secondly,the relationship between limited water medium and crustal stress field is analyzed,and the flow velocity and flow characteristics of aquifer are calculated.Furthermore,any unit body in seepage area is selected to obtain the flow calculation results of aquifer system.Then,the image characteristics are enhanced,the interference is reduced,and the remote sensing image segmentation is completed.Finally,the phase is obtained by setting the eigenvalues of the target pixel by using the depth confidence network.The intermediate value of Guan set sequence is used to extract the high score remote sensing image information of earthquake disaster with limited water medium.Using PIEOrtho satellite image mapping and processing software,a simulation comparative experiment is designed to verify the information extraction effect of the proposed method.The experimental results show that,compared with the conventional method,the proposed method is less affected by the mixed ground objects,and can obtain the point group distribution characteristic information with clear boundary,and the effectiveness of the proposed method is strong.
作者
任君宇
REN Junyu(Institute of Science and Technology History,Inner Mongolia Normal University,Hohhot 010022,China)
出处
《灾害学》
CSCD
北大核心
2020年第3期67-70,共4页
Journal of Catastrophology
基金
内蒙古自然科学基金项目(2017MS0601)。
关键词
水体介质
地震灾害
遥感影像
信息提取
water medium
earthquake disaster
remote sensing image
information extraction
