基于网格运动统计的改进快速鲁棒特征图像匹配算法

doi:10.16451/j.cnki.issn1003-6059.201912009

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1960 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract To solve the problems of long operation time and low matching accuracy in the local invariant feature descriptor of speeded up robust features(SURF) algorithm, a image matching algorithm combining improved SURF algorithm with grid-based motion statistics(GMS) is proposed. Firstly, determinant of Hessian is utilized to determine the feature points of the image, and the main direction extraction method in SURF algorithm is improved by gradient direction to increase the accuracy of the main direction of the feature points. The binary feature descriptor rotation-aware binary robust independent elementary feature(rBRIEF) is employed to describe the feature points. Then, the feature points are roughly matched by Hamming distance. Finally, GMS is adopted to eliminate the mismatches. Experiment on Oxford VGG standard dataset indicates that the proposed algorithm achieves higher matching accuracy and efficiency with image changes in scale, illumination and rotation.

Key words： Feature Matching Feature Extraction Gradient Direction Grid-Based Motion Statistics(GMS)

Received: 18 July 2019

ZTFLH:

TP 391

Fund:Supported by National Natural Science Foundation of China(No.51905405), Research Project of Engineering Science and Technology Talent Cultivation of Ministry of Education（No.18JDGC029）, Natural Science Foundation Research Program of Shanxi Province(No.2019JQ-855), Natural Science Project of Shanxi Provincial Department of Education(No.19JK0375)

Corresponding Authors: WANG Xiaohua, Ph.D., professor. Her research interests include intelligent robot and pattern recognition.

About author:: FANG Qi, master student. His research interests include intelligent robot and pattern recognition.WANG Wenjie, Ph.D., associate profe-ssor. His research interests include robotics.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Xiaohua
	FANG Qi
	WANG Wenjie

Cite this article:

WANG Xiaohua,FANG Qi,WANG Wenjie. Image Matching Algorithm Combining Improved SURF Algorithm with Grid-Based Motion Statistics[J]. , 2019, 32(12): 1133-1140.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201912009 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I12/1133

[1] 徐浩楠,余雷,费树岷.基于半直接法SLAM的大场景稠密三维重建系统.模式识别与人工智能, 2018, 31(5): 477-484.
(XU H N, YU L, FEI S M. Large Scene Dense 3D Reconstruction System Based on Semi-direct SLAM Method. Pattern Recognition and Artificial Intelligence, 2018, 31(5): 477-484.)
[2] 钟华民,王伟,张慧华.结合ORB特征和色彩模型的视觉跟踪算法.模式识别与人工智能, 2015, 28(1): 90-96.
(ZHONG H M, WANG W, ZHANG H H. Visual Tracking Algorithm Combining ORB Feature and Color Model. Pattern Recognition and Artificial Intelligence, 2015, 28(1): 90-96.)
[3] 彭天博,王恒升,曾斌.增强室内视觉里程计实用性的方法.模式识别与人工智能, 2017, 30(3): 260-268.
(PENG T B, WANG H S, ZENG B. Method of Improving Practicability of Indoor Visual Odometer. Pattern Recognition and Artificial Intelligence, 2017, 30(3): 260-268.)
[4] 李玉峰,李广泽,谷绍湖,等.基于区域分块与尺度不变特征变换的图像拼接算法.光学精密工程, 2016, 24(5): 1197-1205.
(LI Y F, LI G Z, GU S H, et al. Image Mosaic Algorithm Based on Area Blocking and SIFT. Optics and Precision Engineering, 2016, 24(5): 1197-1205.)
[5] LOWE D G. Object Recognition from Local Scale-Invariant Features // Proc of the 7th IEEE International Conference on Computer Vision. Washington, USA: IEEE, 1999, II: 1150-1157.
[6] BAY H, ESS A, TUYTELAARS T, et al. Speeded-up Robust Features(S-URF). Computer Vision and Image Understanding, 2008, 110(3): 346-359.
[7] LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK: Binary Robust Invariant Scalable Keypoints // Proc of the International Conference on Computer Vision. Berlin, Germany: Springer, 2011: 2548-2555.
[8] ALCANTARILLA P F, BARTOLI A, DAVISON A J. KAZE Features // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2012: 214-227.
[9] 张立亭,黄晓浪,鹿琳琳,等.基于灰度差分与模板的Harris角点检测快速算法.仪器仪表学报, 2018, 39(2): 218-224.
(ZHANG L T, HUANG X L, LU L L, et al. Fast Harris Corner Detection Based on Gray Difference and Template. Chinese Journal of Scientific Instrument, 2018, 39(2): 218-224.)
[10] SMITH S M, BRADY J M. SUSAN: A New Approach to Low Le-vel Image Processing. International Journal of Computer Vision, 1997, 23(1): 45-78.
[11] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: An Efficient Alternative to SIFT or SURF // Proc of the International Conference on Computer Vision. Washington, USA: IEEE, 2011: 2564-2571.
[12] ALAHI A, ORTIZ R, VANDERGHEYNST P. FREAK: Fast Retina Keypoint // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 510-517.
[13] 曾庆化,陈艳,王云舒,等.一种基于ORB的快速大视角图像匹配算法.控制与决策, 2017, 32(12): 2233-2239.
(ZENG Q H, CHEN Y, WANG Y S, et al. A Fast Matching Method for Large Viewpoint Changes Images Based on ORB Algorithm. Control and Decision, 2017, 32(12): 2233-2239.)
[14] 董强,刘晶红,王超,等.基于改进BRISK的图像拼接算法.电子与信息学报, 2017, 39(2): 444-450.
(DONG Q, LIU J H, WANG C, et al. Image Mosaic Algorithm Based on Improved BRISK. Journal of Electronics and Information Technology, 2017, 39(2): 444-450.)
[15] MURARTAL R, MONTIEL J M M, TARDOS J D. ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, 2015, 31(5): 1147-1163.
[16] ZHU W Q, SUN W J, WANG Y X, et al. An Improved RANSAC Algorithm Based on Similar Structure Constraints // Proc of the International Conference on Robots and Intelligent System. Washington, USA: IEEE, 2016: 94-98.
[17] 李小红,谢成明,贾易臻,等.基于ORB特征的快速目标检测算法.电子测量与仪器学报, 2013, 27(5): 455-460.
(LI X H, XIE C M, JIA Y Z, et al. Rapid Moving Object Detection Algorithm Based on ORB Features. Journal of Electronic Mea-surement and Instrumentation, 2013, 27(5): 455-460.)
[18] MYATT D R, TORR P H S, NASUTO S J, et al. NAPSAC: High Noise, High Dimensional Robust Estimation // Proc of the British Machine Vision Conference. Berlin, Germany: Springer, 2002: 458-467.
[19] BIAN J W, LIN W Y, MATSUSHITA Y, et al. GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2017: 2828-2837.
[20] TAREEN S A K, SALEEM Z. A Comparative Analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK // Proc of the International Conference on Computing, Mathematics and Engineering Technologies. Berlin, Germany: Springer, 2018. DOI: 10.1109/ICOMET.2018.8346440.
[21] 董傲霜,宋宏亮.基于SIFT特征和颜色融合的图像检索方法.吉林大学学报(工学版), 2013, 43(S): 440-444.
(DONG A S, SONG H L. Image Retrieval Technology Based on SIFT Feature and Color Fusion. Journal of Jilin University(Engineering and Technology Edition), 2013, 43(S): 440-444.)