• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Pixels, Objects, Intelligence: GEOgraphic Object Based Image Analysis for the 21st Century >INTERIMAGE: AN OPEN SOURCE KNOWLEDGE BASED FRAMEWORK FOR AUTOMATIC INTERPRETATION OF REMOTE SENSING DATA
【24h】

INTERIMAGE: AN OPEN SOURCE KNOWLEDGE BASED FRAMEWORK FOR AUTOMATIC INTERPRETATION OF REMOTE SENSING DATA

机译：Antimagage：基于开源知识的自动解释遥感数据的框架

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper introduces the InterIMAGE System, an open source knowledge based framework for automatic interpretation of remote sensing data being developed at the Computer Vision Lab (LVC) of the Catholic University of Rio de Janeiro, with the collaboration of the Brazilian National Institute for Spacial Research (INPE), among other scientific institutions. InterIMAGE is an extension of an earlier project called GeoAIDA, developed by the Insitut fur Informationsverarbeitung (TNT) of the Leibniz Universitat Hannover, and has inherited from that system the basic functional design and control mechanisms. The interpretation strategy implemented on the system is based on a knowledge model defined by the user, structured as a semantic network. The nodes of the network represent concepts, classes of image objects expected to be found in a scene. Specialized image processing operators can be attached to the system, which controls their execution. The interpretation process performed by InterIMAGE has two sequential and complementary phases. The first phase, called the top-down step, is model driven and generates, through the operators associated to the different nodes of the semantic network, hypotheses of the occurrence of image objects on the scene. The final instance network results from the bottom-up analysis, responsible from judging those hypotheses, validating or discarding them based on user defined rules, also associated to the nodes of the semantic network. In order to make a comprehensive introduction of the system, the methodology for the creation of an interpretation model in InterIMAGE will be presented, and the interpretation process will be discussed with the aid of an exemplary interpretation problem based on synthetic data.
机译：本文介绍了一个开源知识的遥测自动解释遥控数据，用于在里约热内卢天主教大学的计算机视图实验室（LVC）的自动解释的开放源知识框架，并于巴西国家间歇研究所的合作（INPE），以及其他科学机构。 Interimages是一个名为Geoaida的早期项目的延伸，由Leibniz Univeritat Hannover的Insitut毛皮信息verarbeitung（TNT）开发，并从该系统继承了基本功能设计和控制机制。在系统上实现的解释策略基于用户定义的知识模型，其构造为语义网络。网络的节点代表概念，预期在场景中找到的图像对象的类。专门的图像处理操作员可以连接到系统，控制其执行。由interimages执行的解释过程具有两个顺序和互补阶段。通过与语义网络的不同节点相关联的运算符，称为自上而下步骤的第一阶段是模型驱动和生成的。最终实例网络从自下而上的分析中导致，负责根据用户定义的规则判断这些假设，验证或丢弃它们，也与语义网络的节点相关联。为了全面引入系统，将呈现用于创建中的解释模型的方法，并且将借助于基于合成数据的示例性解释问题讨论解释过程。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号