减少有理函数模型中高次项的初步研究  

Research on reducing term of higher order in RFM model

作　　者：赵利平[1] 刘凤德[1] 李健[1] 王薇[2] 

机构地区：[1]中国测绘科学研究院,北京100039 [2]中科院地理科学与资源研究所

出　　处：《测绘科学》2007年第4期14-17,共4页Science of Surveying and Mapping

摘　　要：本文简要介绍了有理函数模型(RFM)的原理与方法,给出了利用地面控制点分别针对单片和立体影像的RFM系统误差改正方法。在实际应用中,虽然全三次项形式的RFM可以保证高精度,但是其计算量非常庞大,为此,我们探讨了减少RFM中高次项的可行性,并研究了其在立体模型重构与正射影像纠正中对精度的影响。最后,使用中国西藏、北京和芬兰的三个IKONOS影像立体像对数据进行了相关试验,结果表明,在一定影像范围内,RFM和地形无关,不论是平原、丘陵,还是高山地,在一定影像范围内仅使用RFM的二次项形式可以满足单片正射影像纠正和立体模型重构等应用要求。In this paper, principles of Rational Function Model (RFM) and its construction methods are briefly introduced. In RFM model application, full third order polynomial RFM model could ensure very high geometric accuracy, but also brings very large calculation load. Therefore, the possibility of reducing terms of higher order in RFM Model and the accuracy loss on stereo model reconstruction and ortho-image rectification are discussed in this paper. Experiments are carried out using IKONOS stereo pairs of Tibet, Beijing and Finland. And the results show that within certain image range (11km2), second order RFM model could meet the accuracy requirements of general applications no matter in plain, hilly area or mountainous area.

关 键 词：有理函数模型 RFM 定位精度 高次项 系统误差 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]