结合快速鲁棒性特征改进ORB的特征点匹配算法

doi:10.11772/j.issn.1001-9081.2016.07.1923

计算机应用 ›› 2016, Vol. 36 ›› Issue (7): 1923-1926.DOI: 10.11772/j.issn.1001-9081.2016.07.1923

结合快速鲁棒性特征改进ORB的特征点匹配算法

白雪冰^1,2, 车进^1,2, 牟晓凯^1,2, 张英^1,2

1. 宁夏大学物理电气信息学院, 银川 750021;
2. 宁夏沙漠信息智能感知重点实验室(宁夏大学), 银川 750021

收稿日期:2015-12-10 修回日期:2016-03-18 出版日期:2016-07-10 发布日期:2016-07-14
通讯作者: 车进
作者简介:白雪冰(1991-),男,河南焦作人,硕士研究生,主要研究方向:信号和图像处理、模式识别;车进(1973-),男,陕西合阳人,教授,博士,主要研究方向:图像处理、智能视频;牟晓凯(1990-),男,山东潍坊人,硕士研究生,主要研究方向:模式识别、图像处理;张英(1989-),女,重庆潼南人,硕士研究生,主要研究方向:信号和图像处理、模式识别。
基金资助:
国家自然科学基金资助项目（61162020）。

Improved feature points matching algorithm based on speed-up robust feature and oriented fast and rotated brief

BAI Xuebing^1,2, CHE Jin^1,2, MU Xiaokai^1,2, ZHANG Ying^1,2

1. School of Physics & Electrical Information Engineering, Ningxia University, Yinchuan Ningxia 750021, China;
2. Ningxia Key Laboratory of Intelligent Sensing for Desert Information (Ningxia University), Yinchuan Ningxia 750021, China

Received:2015-12-10 Revised:2016-03-18 Online:2016-07-10 Published:2016-07-14
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61162020).

摘要/Abstract

摘要： 针对定向二进制简单描述符（ORB）算法不具备尺度不变性的问题，提出一种结合快速鲁棒性特征（SURF）算法和ORB的改进算法。首先，利用Hessian矩阵检测特征点的方法，使得提取出的特征点具有尺度不变性；然后，用ORB生成特征描述子；接着采用K-近邻算法进行粗匹配；最后，通过比率测试、对称测试、最小平方中值（LMedS）定理进行提纯。尺度变化时，该算法比ORB的匹配精度提高了74.3个百分点，比SURF的匹配精度提高了4.8个百分点；旋转变化时，该算法比ORB的匹配精度提高了6.6个百分点；匹配时间高于SURF低于ORB。实验结果表明，改进算法不仅保持了ORB的旋转不变性，而且具备了尺度不变性，在不失速度的前提下，匹配精度得到较大提高。

关键词: 特征点匹配, 尺度不变性, 旋转不变性, 比率测试, 对称测试, 最小平方中值定理

Abstract: Focusing on the issue that the Oriented fast and Rotated Brief (ORB) algorithm does not have scale invariance, an improved algorithm based on Speed-Up Robust Feature (SURF) and ORB was proposed. First, the feature points were detected by Hessian matrix, which made the extracted feature points have scale invariance. Second, the feature descriptors were generated by the ORB. Then the K-nearest neighbor algorithm was used for rough matching. Finally, the ratio test, symmetry test, the Least Median Squares (LMedS) theorem was used for purification. When the scale changed, the proposed algorithm's matching precision was improved by 74.3 percentage points than the ORB and matching precision was improved by 4.8 percentage points than the SURF. When the rotation changed, the proposed algorithm's matching precision was improved by 6.6 percentage points than the ORB. The proposed algorithm's matching time was above the SURF, below the ORB. The experimental results show that the improved algorithm not only keeps the rotation invariance of ORB, but also has the scale invariance, and the matching accuracy is improved greatly without decreasing the speed.

Key words: feature point matching, scale invariance, rotation invariance, ratio test, symmetry test, Least Median Squares (LMedS) theorem

中图分类号:

TP391.9

白雪冰, 车进, 牟晓凯, 张英. 结合快速鲁棒性特征改进ORB的特征点匹配算法[J]. 计算机应用, 2016, 36(7): 1923-1926.

BAI Xuebing, CHE Jin, MU Xiaokai, ZHANG Ying. Improved feature points matching algorithm based on speed-up robust feature and oriented fast and rotated brief[J]. Journal of Computer Applications, 2016, 36(7): 1923-1926.

参考文献

[1] 朱琳,王莹,刘淑云,等.基于改进快速鲁棒特征的图像快速拼接算法[J].计算机应用,2014,34(10):2944-2947.(ZHU L, WANG Y, LIU S Y, et al. Fast image mosaic algorithm based on improved fast robust feature[J]. Journal of Computer Applications, 2014, 34(10):2944-2947.)
[2] 刘海燕,杨昌玉,刘春玲,等.基于梯度特征和颜色特征的运动目标跟踪算法[J].计算机应用,2012,32(5):1265-1268.(LIU H Y, YANG C Y, LIU C L, et al. Moving target tracking algorithm based on gradient feature and color feature[J]. Journal of Computer Applications, 2012, 32(5):1265-1268.)
[3] 侯毅,周石琳,雷琳,等.基于ORB的快速完全仿射不变图像匹配[J]. 计算机工程与科学,2014,36(2):303-310.(HOU Y, ZHOU S L, LEI L, et al. Fast fully affine invariant image matching based on ORB[J]. Computer Engineering & Science, 2014, 36(2):303-310.)
[4] 童宇,蔡自兴.基于特征匹配的全景图的生成[J].华中科技大学学报(自然科学版),2004,32(S1):77-79.(TONG Y, CAI Z X. Generation of panoramic image based on feature matching[J]. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2004, 32(S1):77-79.)
[5] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the 1999 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 1999:1150-1157.
[6] BAY H, ESS A, TUYTELAARS T, et al. SURF:speeded up robust feature[J]. Computer Vision and Image Understanding, 2008, 110(3):346-359.
[7] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2011:2564-2571.
[8] 刘铭.基于ORB算法的双目视觉测量与跟踪研究[D]. 哈尔滨:哈尔滨工业大学,2014:25.(LIU M. Binocular computer vision measurement and tracking research based on the ORB algorithm[D]. Harbin:Harbin Institute of Technology, 2014:25.)
[9] 孟凡清.基于背景差分法与ORB算法的运动目标检测与跟踪算法研究[D].北京:北京印刷学院,2014:30-33.(MENG F Q. Study on the moving object detection and tracking based on background subtraction and ORB algorithm[D]. Beijing:Beijing Printing Institute, 2014:30-33.)
[10] 佘建国,徐仁桐,陈宁.基于ORB和改进RANSAC算法的图像拼接技术[J].江苏科技大学学报(自然科学版),2015,29(2):164-169.(YU J G, XU R T, CHEN N. Image stitching technology based on ORB and improved RANSAC algorithm[J]. Journal of Jiangsu University of Science and Technology (Nature Science Edition), 2015, 29(2):164-169.)
[11] 张云生,邹峥嵘.基于改进ORB算法的遥感图像自动配准方法[J].国土资源遥感,2013,25(3):20-24.(ZHANG Y S, ZOU Z R. Automatic registration method for remote sensing images based on improved ORB algorithm[J]. Remote Sensing for Land and Resources, 2013, 25(3):20-24.)
[12] 许宏科,秦严严,陈会茹.基于改进ORB的图像特征点匹配[J].科学技术与工程,2014,14(18):105-109.(XU H K, QIN Y Y, CHEN H R. Feature points matching in images based on improved ORB[J]. Science Technology and Engineering, 2014, 14(18):105-109.)
[13] ROSTEN E, DRUMMOND T. Fusing points and lines for high performance tracking[C]//Proceedings of the 2005 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2005:1508-1515.
[14] ROSTEN E, DRUMMOND T. Machine learning for high speed corner detection[C]//ECCV'06:Proceedings of the 9th European Conference on Computer Vision. Berlin:Springer, 2006:430-443.
[15] CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF:binary robust independent elementary features[C]//ECCV'10:Proceedings of the 11th European Conference on Computer vision. Berlin:Springer, 2010:778-792.

结合快速鲁棒性特征改进ORB的特征点匹配算法

Improved feature points matching algorithm based on speed-up robust feature and oriented fast and rotated brief

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

[1]	刘望华, 刘光帅, 陈晓文, 李旭瑞. 结合微分特征和Haar小波分解的鲁棒纹理表达[J]. 计算机应用, 2020, 40(9): 2728-2736.
[2]	丁辉, 李丽宏, 原钢. 融合GMS与VCS+GC-RANSAC的图像配准算法[J]. 计算机应用, 2020, 40(4): 1138-1143.
[3]	朱成德, 李志伟, 王凯, 高燕, 郭亨长. 基于改进网格运动统计特征的图像匹配算法[J]. 计算机应用, 2019, 39(8): 2396-2401.
[4]	修春波, 马云菲, 潘肖楠. 基于距离融合的图像特征点匹配方法[J]. 计算机应用, 2019, 39(11): 3158-3162.
[5]	李卓, 刘洁瑜, 李辉, 周小刚, 李维鹏. 基于ORB-LATCH的特征检测与描述算法[J]. 计算机应用, 2017, 37(6): 1759-1762.
[6]	孙增友, 段玉帅, 李亚. 基于中心环绕滤波器检测的图像特征点匹配算法[J]. 计算机应用, 2017, 37(12): 3547-3553.
[7]	林陶, 黄国荣, 郝顺义, 沈飞. 尺度不变特征转换算法在图像特征提取中的应用[J]. 计算机应用, 2016, 36(6): 1688-1691.
[8]	于亚风, 刘光帅, 马子恒, 高攀. 用于纹理特征提取的改进的成对旋转不变共生局部二值模式算法[J]. 计算机应用, 2016, 36(12): 3389-3393.
[9]	陈彬彬, 邓新蒲, 杨俊刚. 基于U弦长曲率的抗旋转性广义Hough变换算法[J]. 计算机应用, 2015, 35(9): 2619-2623.
[10]	张恒, 刘大勇, 刘艳丽, 聂晨曦. 融合深度信息的BRISK改进算法[J]. 计算机应用, 2015, 35(8): 2285-2290.
[11]	连玮左军毅. 采用凹二次正则项的弹性点匹配算法[J]. 计算机应用, 2013, 33(08): 2320-2324.
[12]	刘晶王映辉何文娟. 基于图像特征点的数字水印算法[J]. 计算机应用, 2010, 30(3): 702-704.