基于sift的简化算法下图像快速匹配

被引:6
作者
裴聪
戴立玲
卢章平
机构
[1] 江苏大学机械工程学院
关键词
SIFT; 高斯差分尺度空间; 尺度不变; 图像匹配;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
提出一种基于SIFT算法的简化特征匹配算法SSIFT(simplified Scale Invariant FeatureTransform),该算法采用基于圆形窗口的12维向量有效的表示一个特征点,同时在算法方面保留了原算法的旋转不变性、光照不变性等多项优点。实验结果表明,该算法在保持了较好匹配率的前提下,在场景不太复杂的场景下,实时性获得了很好的表现,适合于实时性要求较高的场合。
引用
收藏
页码:132 / 135
页数:4
相关论文
共 12 条
[1]  
Scale-space theory: A basic tool for analyzing structures at different scales. Lindeberg T. Journal of Applied Mechanics . 1994
[2]  
A Combined Corner and Edge Detector. Harris C,Stephens M. Proceedings of The Fourth Alvey Vision Conference . 1988
[3]  
Image registration using blur-invari-ant phase correlation. Ojansivu V,Heikkila J. IEEE Signal Processing Letters . 2007
[4]  
Distinctive Image Features from Scale-Invariant Keypoints. David G Lowe. International Journal of Computer Vision . 2004
[5]  
Hierarchical building recognition. Wei Zhang,Jana KOsecka. Iamge and Vision Computing . 2007
[6]  
Object recognition from local scale-invariant features. David G Lowe. Proceedings of the 7th IEEE International Conference on Computer Vision(ICCV ’99) . 1999
[7]  
A Performance Evaluation of Local Descriptors. Krystian Mikolajczyk,Cordelia Schmid. .
[8]  
Evaluation of Features Det-ectors and Descriptors based on 3D objects. Pierre Moreels,Pietro Perona. .
[9]  
Image resist ration using blur invariant phasecorrelation. Ville O,Janne H. IEEE Signal Processing Letters . 2007
[10]  
Scale-space theory: a basic tool for analyzing structures at different scales[J] . Tony Lindeberg. &nbspJournal of Applied Statistics . 1994 (1-2)