异源图像特征点边缘描述与匹配

计算机科学 ›› 2013, Vol. 40 ›› Issue (7): 277-279.

异源图像特征点边缘描述与匹配

朱英宏,李俊山,杨威,杨亚威,朱艺娟

武警福建总队厦门支队厦门361000;第二炮兵工程大学402室西安710025;第二炮兵工程大学402室西安710025;第二炮兵指挥学院工程保障系武汉430012;第二炮兵工程大学402室西安710025;武警福建总队漳州支队漳州363100

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(61075025,61175120)资助

Edges Description and Matching Algorithm for Different-source Images

ZHU Ying-hong,LI Jun-shan,YANG Wei,YANG Ya-wei and ZHU Yi-juan

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 针对红外与可见光图像中特征点匹配的难题,提出一种基于特征点邻域边缘的描述与匹配算法。首先采用基于曲率尺度空间的角点检测算法进行特征点提取；再对特征点邻域的边缘进行重组；其次求取特征点所在曲线的法线作为主方向,以避免图像的旋转代价；计算特征点邻域像素点的B-LBP算子的加权分布直方图；然后搜索相同边缘上最近的特征点并计算相应的直方图信息；再对两个直方图进行级联,构造出512维的UB-LBP联合描述子,并将其归一化；最后采用最近邻算法实现特征点匹配。实验结果表明,这两种描述子在红外与可见光图像特征点匹配方面较SIFT算法具有较高的正确匹配率,能够实现两种图像的精确匹配。

关键词: 红外图像,可见光图像,CSS角点检测,局部二进制模式中图法分类号TP391文献标识码A

Abstract: A point matching algorithm based on edges of key points region was proposed to resolve the problem of IR and visible images matching．Firstly,the feature points were extracted by the CSS corner detector．Edges of key points region were reconstructed．Secondly,the normal direction of each feature point on the curve was adopted as the main direction of the point,making the point descriptor rotation invariant．Thirdly,through calculating the B-LBP weight histogram in interesting points’ neighborhood,the nearest feature point of each extracted one on the same edge was searched and the histograms of edge pixels of the two key points region were constructed．Then a 512-dimentional UB-LBP joint descriptor combining with two histograms was constructed and normalized．Finally,the feature matching was realized via the nearest neighbor algorithm．Experimental results show that the proposed algorithm can match the feature points in the IR and visible images more efficiently than the original SIFT.

Key words: Infrared image,Visual image,CSS corner detecting,Local binary patterns

朱英宏,李俊山,杨威,杨亚威,朱艺娟. 异源图像特征点边缘描述与匹配[J]. 计算机科学, 2013, 40(7): 277-279. https://doi.org/

ZHU Ying-hong,LI Jun-shan,YANG Wei,YANG Ya-wei and ZHU Yi-juan. Edges Description and Matching Algorithm for Different-source Images[J]. Computer Science, 2013, 40(7): 277-279. https://doi.org/

参考文献

[1] 王鲲鹏,徐一丹,于起峰．红外与可见光图像配准方法分类及现状[J]．红外技术,2009,31(5):270-275
[2] 田裕鹏．红外检测与诊断技术[M]．北京:化学工业出版社,2006:140-145
[3] Ojala T,Pietikainen M,Maenpaa T．Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987
[4] Nanni L,Lumini A,Brabnam S．Survey on LBP based texturedescriptors for image classification[J]．Expert Systems with Applications,2012(39):3634-3641
[5] Lee H,Chung Y,Kim J,et al．Face Image Retrieval UsingSparse Representation Classifier with Gabor-LBP Histogram[J]．Computer Science,2011,6513:273-280
[6] Yue Y,An Z,Wu H．Adaptive Targets-detecting Algorithmbased on LBP and Background Modeling under Complex Scenes[J]．Procedia Engineering,2011,15:2489-2494
[7] Arashloo S R,Kittler J．Energy Normalization for Pose-Invariant Face Recognition Based on MRF Model Image Matching[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(6):1274-1280
[8] Mokhtarian F,Suomela R．Robust image corner detection th-rough curvature scale space[J]．Proceedings of Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381
[9] Lowe D．Distinctive image features from scale-invariant key-points[J]．International Journal of Computer Vision,2004,60(2):91-110

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed