基于局部尺度不变特征的快速目标识别  

Fast object recognition using local scale-invariant features

作　　者：周志强[1] 汪渤[1] 杨杰[1] 吕冀[1] 

机构地区：[1]北京理工大学信息科学技术学院自动控制系,北京100081

出　　处：《光学技术》2008年第5期742-745,共4页Optical Technique

基　　金：国家部委预研项目(51405030404BQ0171)

摘　　要：介绍了图像局部尺度不变特征的提取方法,将局部尺度不变特征用于目标识别,为提高识别实时性,提出利用金字塔和尺度空间的混合多尺度表示方法,按照从大尺度到小尺度的顺序对待识别图像的特征点进行检测与匹配,直到完成识别为止,有效地提高了识别速度。Methods for generating local scale invariant features are introduced. These scale invariant features are used in object recognition. In order to improve the efficiency of object recognition, the feature points are detected and matched from large scale to small scale using hybrid multi-scale representation, which has integrated the advantages of pyramids and scale-space representation. This repeat process doesn＇ t terminate until the recognition has completed. Experiment results show that this method has reduced the time of recognition effectivdy.

关 键 词：尺度不变特征 尺度空间 目标识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]