基于真实物体模型的空间对象检索技术研究  

Research of spatial retrieval based on real objects model

作　　者：尹伟哲[1] 邓成玉[1] 刘永山[1] 

机构地区：[1]燕山大学信息科学与工程学院,河北秦皇岛066004

出　　处：《计算机工程与设计》2010年第9期2120-2123,共4页Computer Engineering and Design

摘　　要：针对MBR模型只适合检索联通的空间对象且查准率较低的问题,建立了真实物体模型。依据空间对象在平面上的几何投影的方法建立真实物体模型,采用深度方向关系矩阵表示真实物体模型之间的方向关系,利用该模型可以很好地将矩形代数良好的计算性质应用于空间对象检索技术中,简化了检索的过程,实现了矩形代数与真实物体模型的有效结合,使其检索的范围变的更加广泛。同时提出了一种改进的R*树算法,有效地提高了真实物体模型的检索精确度,降低了错误匹配的发生率。实验结果表明,该算法可以有效地提高检索的查准率,提高空间对象检索的效率。For the problem that the model of MBR just suit for connected objects, a new real objects model is proposed. Firstly, the model is built by spatial objects in plane geometry projection and the direction-relation among the real objects model by using deep direction-relation matrix. The model can conveniently process spatial retrieval technology, because the rectangle algebra has outstanding properties of spatial retrieval, so the model suit for more kinds of objects. An enhanced algorithm of R＊-tree is presented, the precision of spatial retrieval in real objects model is increased and the rate of false match is decreased. Experimental results demonstrate that the algorithm can increase the precision effectively and improve the efficiency of the spatial search.

关 键 词：空间对象检索 真实物体模型 R＊树 深度方向关系矩阵 MBR 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]