基于方向约束的改进SIFT匹配算法

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 125-128.

基于方向约束的改进SIFT匹配算法

齐乃新,曹立佳,杨小冈,李冰

第二炮兵工程大学304室西安710025;第二炮兵工程大学304室西安710025;第二炮兵工程大学303室西安710025;第二炮兵驻第四研究院军事代表室西安710025

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受自然科学基金项目:飞行器前视红外视觉导航基准图制备的理论与方法研究(61203189)资助

Improved SIFT Matching Algorithm Based on Orientation Constraint

QI Nai-xin,CAO Li-jia,YANG Xiao-gang and LI bing

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： SIFT算法对图像的旋转、尺度变换、亮度变化等情况具有较好的不变性,广泛应用于图像匹配中,但SIFT特征向量生成过程复杂,导致算法实时性不理想,同时匹配结果还存在一定的误匹配点,影响了算法的精确性。为此,对SIFT算法进行改进,提出采用栅格形式选取种子点简化特征向量的生成过程,并利用关键点的方向约束性进一步剔除具有方向差异的误匹配点,从而简化计算量,提高匹配率。实验结果表明,改进后的算法能在保持原有SIFT算法稳定性的基础上提高近一倍的特征向量描述速度,初匹配结果经方向约束后能够有效地剔除具有方向差异的误匹配点,提高匹配率,大大增强了算法的精确性。

关键词: SIFT,特征向量,图像匹配,方向约束,匹配率中图法分类号TP391.41文献标识码A

Abstract: SIFT algorithm has good invariance in rotation,scaling the image,brightness change,etc.,and is widely used in image matching．But the generation process of SIFT feature vector is complicated,and results in that the real-time of the algorithms is not ideal．In the same time,there are still some matching mistakes in the matching result,affecting the accuracy of the algorithm．Therefore,we improved the SIFT algorithm,and proposed to use the grid in the selection of seed points to simplify the feature vector generation process,and used the orientation constraint of the key points to reject matching points with directional differences,thus simplifying computation and improving the matching rate．Experimental results show that the improved algorithm can maintain the basic stability of the original SIFT algorithm and improves the speed of feature vectors described nearly doubled．Through orientation constraint of the key points,the false match point with direction differences is rejected,and the matching rate is improved,greatly enhancing the accuracy of the algorithm.

Key words: SIFT,Feature vector,Image matching,Orientation constraint,Matching rate

齐乃新,曹立佳,杨小冈,李冰. 基于方向约束的改进SIFT匹配算法[J]. 计算机科学, 2014, 41(Z6): 125-128. https://doi.org/

QI Nai-xin,CAO Li-jia,YANG Xiao-gang and LI bing. Improved SIFT Matching Algorithm Based on Orientation Constraint[J]. Computer Science, 2014, 41(Z6): 125-128. https://doi.org/

参考文献

[1] Moravec H P．Towards automatic visual obstacle avoidance[C]∥Proceedings of International Joint Conference on Artificial Intelligence.Cambridge,MA,USA,1977:5842
[2] Harris C,Stephens M．A Combined Corner and Edge Detector[C]∥Manchester:Proceedings of the 4th Alvey Vision Confe-rence．1988:147-151
[3] Smith S M,Brady J M．SUSAN:A New Approach to Low LevelImage Processing [J]．International Journal of Computer Vision,1997,23(1): 45-78
[4] David G．Object Recognition from Local Scale invariant Features[J]．International Conference on Computer Vision,1999,9(2):1150-1157
[5] Lowe D G．Distinctive image features from scale-invariant keypoints[J]．International journal of computer vision,2004,0(2):91-110
[6] 吴建,马跃．一种改进的SIFT算法[J]．计算机科学,2013,40(7):270-272
[7] 管学伟,刘先志,杜天军．一种基于SIFT算法的目标匹配方法[C]∥第十四届全国图象图形学学术会议．2008
[8] 张羽,丹朱,王玉良．一种改进的快速SIFT特征匹配算法[J]．微计算机信息,2008,24(11):220-222
[9] 高健,等．一种简化的SIFT图像特征点提取算法[J]．计算机应用研究,2008,25(7):2213-2215,2
[10] 赵启兵,王养柱,胡永浩．基于改进SIFT算法的无人机遥感影像匹配[J]．电光与控制,2012,19(3):36-39,5
[11] 祁燕,王琰,王明宇．改进的SIFT特征图像配准算法[J]．沈阳理工大学学报,2012,34(4):6-10
[12] 杨幸芳,等．一种提高SIFT特征匹配效率的方法[J]．中国机械工程,2012,23(11):1297-1301
[13] 石钊铭,耿伯英,董银文．基于改进SIFT的航拍图像快速匹配方法[J]．指挥控制与仿真,2013,35(1):106-110
[14] 刘立,等．采用简化SIFT算法实现快速图像匹配[J]．红外与激光工程,2008,37(1):181-184
[15] 孙韬,方俊永,刘学,等．基于SIFT特征匹配的全自动辐射归一化算法[J]．红外与毫米波报,2012,1(4):355-359

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed