【作者】 杜培军； 陈云浩；

【Author】 Du Peijun,Chen Yunhao(Department of Remote Sensing and Geographical Information Science,China University of Mining and Technology, XuZhou City, Jiangsu Province, 221008, P.R.China;College of Resources, Beijing Normal University, Beijing 100875, P.R.China)

【机构】 中国矿业大学地理信息与遥感科学系； 北京师范大学资源学院；

【摘要】 针对高空间分辨率卫星遥感影像用于地理信息更新的特点,设计了一个遥感和GIS集成理论支持下具有良好遥感、GIS接口和信息处理功能的地理信息更新系统。遥感影像用于地理信息更新时,一方面应对多源遥感信息进行融合,特别是发展决策层融合算法;另一方面应对多时相遥感信息融合和变化检测进行研究,提出了一种新的多时相遥感影像融合算法体系结构,并设计了两种新算法。针对自动信息更新的要求,提出了遥感数据挖掘应重点解决的关键问题和在地理信息自动更新中能够发挥的作用。最后,面向快速影像提取和检索的目标,研究了基于内容的遥感影像检索技术,并指出应重点发展基于纹理特征、形状特征、光谱特征和空间特征的检索技术。更多还原

【Abstract】 Oriented to the demands and properties of applying Remote Sensing (RS) Image to update geographical information, a profession system used to update geographical information based on the integration of RS and geographical information system (GIS) was designed. When RS image was used to update geographical information, both multi-source and multi-temporal RS image fusion was important. In multi-source fusion, decision-level fusion should be emphasized. A new framework of multi-temporal RS information fusion and dynamic analysis including four levels were proposed and two new approaches were put forward. According to the demands of automatic information updating, RS Data Mining is proposed, and some key problems were discussed further, also the applications of RS Data Mining were analyzed. Finally, content-based RS image retrieval used to extract interested images from image database was discussed, and it was pointed out that the retrieval based on texture, shape, spectral and spatial features should be emphasized.更多还原