摘要
提出了一种基于支持向量机的地形背景场适配/误配区自动识别和划分的方法。该方法通过分析地形背景场特征参量的主成分及显著性,借助支持向量机来构建输入地形特征参量与匹配性能的映射关系,最终实现地形背景场误配/适配区的自动识别和划分。
A new method for recognition and classification of appropriate background area, base on SVM, is presented. The method can be used to solve false matching problem in terrain matching navigation. Firstly, the rela- tionship between statistical parameters and the precision of matching are established according to the statistical pa- rameters with higher significance got from statistics of background area. Secondly, the statistical parameters men- tioned above are input to train the network with SVM. Trial results prove that the method is the feasible and effi- cient.
出处
《大地测量与地球动力学》
CSCD
北大核心
2013年第6期72-77,共6页
Journal of Geodesy and Geodynamics
基金
国家自然科学基金(40976061)
关键词
水下地形匹配导航
支持向量机
适配区划分
自动识别
地形特征参量
underwater terrain matching navigation
SVM （Support Vector Machine）
identification of the adapta-ble matching area
automatic identification
terrain statistical parameter
