基于Agast-Adaboost的图像匹配算法

兰州理工大学学报 ›› 2020, Vol. 46 ›› Issue (4): 110-115.

• 自动化技术与计算机技术 • 上一篇下一篇

基于Agast-Adaboost的图像匹配算法

徐铸业¹, 赵小强^1,2,3

1.兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050;
2.兰州理工大学甘肃省工业过程先进控制重点实验室, 甘肃兰州 730050;
3.兰州理工大学国家级电气与控制工程实验教学中心, 甘肃兰州 730050

收稿日期:2019-04-03 出版日期:2020-08-28 发布日期:2020-11-10
作者简介:徐铸业(1992-),男,甘肃景泰人,博士生.
基金资助:
国家自然科学基金(61763029)

Image matching algorithm based on Agast-Adaboost

XU Zhu-ye¹, ZHAO Xiao-qiang^1,2,3

1. College of Electrical and Information Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China;
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou Univ. of Tech., Lanzhou 730050, China;
3. National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2019-04-03 Online:2020-08-28 Published:2020-11-10

摘要/Abstract

摘要： 针对传统浮点型特征描述算法误匹配率高、匹配率低的问题,提出了一种基于尺度空间金字塔与AGAST(adaptive and generic accelerated segment test)快速特征提取相融合的局部二进制特征匹配算法(Agast-Adaboost local binary feature matching algorithm,ALBFMA).该算法首先构建高斯尺度空间金字塔,将AGAST与尺度空间融合并提取特征点,然后用改进的Adaboost算法对特征点进行二值描述,生成特征向量,从而提高该算法的匹配速率和匹配精度.实验结果表明:与已有算法相比,该算法具有匹配精度高的优点,并且对光照、尺度及旋转有良好的鲁棒性.

关键词: 图像匹配, 尺度空间, Adaboost, 局部二进制特征

Abstract: In response to the problem of high mismatch rate and low match rate of traditional floating-point feature description algorithm,a algorithm of ALBFMA (Agast-Adaboost local binary feature matching algorithm, ALBFMA) based on AGAST and fast feature extraction is proposed in this paper. Firstly, this algorithm builds Gaussian scale space pyramid and integrates AGAST with scale space and extracts relevant feature points. Then it uses the improved Adaboost algorithm to conduct binary description for those feature points to generate the feature vector, thus providing a high matching rate and matching accuracy of the algorithm. Our experimental results show that compared with the existing algorithms, the proposed algorithm has advantages of high matching accuracy, and have good robustness for lighting, scale and rotation.

Key words: image matching, scale space, Adaboost, local binary feature

中图分类号:

TP751.1

徐铸业, 赵小强. 基于Agast-Adaboost的图像匹配算法[J]. 兰州理工大学学报, 2020, 46(4): 110-115.

XU Zhu-ye, ZHAO Xiao-qiang. Image matching algorithm based on Agast-Adaboost[J]. Journal of Lanzhou University of Technology, 2020, 46(4): 110-115.

参考文献

[1] WU H,BIE R F,GUO J Q,et al.CNN refinement based object recognition through optimized segmentation [J].Optik - International Journal for Light and Electron Optics,2017,150(Supplement C):76-82.
[2] PAN H L,GUAN T,LUO Y W,et al.Dense 3D reconstruction combining depth and RGB information [J].Neurocomputing,2016,175(PA):644-651.
[3] SHI X S,XING F Y,XU K D,et al.Supervised graph hashing for histopathology image retrieval and classification [J].Medical Image Analysis,2017,42(Supplement C):117-128.
[4] 曲怀敬,李健.基于混合统计建模的图像融合 [J].计算机辅助设计与图形学学报,2017,29(5):838-845.
[5] 张鹏,徐欣楠,王洪伟,等.基于深度学习的计算机辅助肺癌诊断方法 [J].计算机辅助设计与图形学学报,2018,30(1):90-99.
[6] LOWE D G.Distinctive image features from scale-invariant keypoints [J].International Journal of Computer Vision,2004,60(2):91-110.
[7] KE Y,SUKTHANKAR R.PCA-SIFT:a more distinctive representation for local image descriptors [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington:IEEE,2004:506-513.
[8] BAY H,TUYTELAARS T,GOOL L V.SURF:speeded up robust features [J].Computer Vision and Image Understanding,2006,110(3):404-417.
[9] MAIR E,HAGER G D,BURSCHKA D,et al.Adaptive and generic corner detection based on the accelerated segment test [C]//Proceedings of the Computer Vision - ECCV 2010.Berlin:Springer-Verlag,2010:183-196.
[10] 周莉莉,姜枫.基于FAST和BRIEF的图像匹配算法 [J].计算机工程与设计,2015,36(5):1269-1273.
[11] CALONDER M,LEPETIT V,OZUYSAL M,et al.BRIEF:computing a local binary descriptor very fast [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(7):1281-1298.
[12] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An efficient alternative to SIFT or SURF [C]//Proceedings of the IEEE International Conference on Computer Vision.[S.l.]:IEEE,2012:2564-2571.
[13] LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK:binary robust invariant scalable keypoints [C]//Proceedings of the International Conference on Computer Vision.[S.l.]:IEEE,2011:2548-2555.
[14] 刘冲,张均东,曾鸿,等.基于支持向量机的无穷维AdaBoost算法及其应用 [J].仪器仪表学报,2010,31(4):764-769.
[15] TRZCINSKIT T,CHRISTOUDIAS M,FUA P,et al.Boosting binary keypoint descriptors [C]//Proceedings of the Computer Vision and Pattern Recognition.[S.l.]:IEEE,2013:2874-2881.
[16] FREUND Y,SCHAPIRE R E.A decision-theoretic generalization of on-line learning and an application to boosting [C]// Proceedings of the II European Conference on Computational Learning Theory.Berlin,Heidelberg:Springer,1999:119-139.
[17] MIKOLAJCZYK K,SCHMID C.A performance evaluation of local descriptors [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2005,27(10):1615-1630.

基于Agast-Adaboost的图像匹配算法

Image matching algorithm based on Agast-Adaboost

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	王燕, 李国臣, 孙晓丽. 基于多分类器融合的高光谱图像分类研究[J]. 兰州理工大学学报, 2022, 48(1): 98-106.
[2]	朱昶胜,田慧星,冯文芳. 基于Adaboost算法结合DEGWO-SVM的财务困境预测[J]. 兰州理工大学学报, 2021, 47(6): 100-107.