Abstract
Accuracy and speed are the essential metrics for the template matching algorithms in solving object tracking problems. Since the method based on Best Buddies Similarity (BBS) has achieved the state-of-the-art performance in terms of accuracy, matching speed becomes the shortest piece of wood of the bucket. In this paper, we propose a fast template matching method based on our deformable BBS measure. The deformable BBS measure enables matching to be performed between the patches in varying sizes, and hence leads to even higher accuracy than the original BBS-based methods. More important, we develop a fast potential-area discovery algorithm based on proposal generation and selection. It significantly reduces the numbers of useless attempts on calculating and comparing similarities of impossible image patches. The experimental results show that, with the deformable BBS measure and the fast potential-area discovery, our template matching method outperforms the state-of-the-art methods in terms of accuracy, speed and robustness.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-018-6722-x/MediaObjects/11042_2018_6722_Fig11_HTML.png)
Similar content being viewed by others
Notes
TB-50 Sequences are available at: http://cvlab.hanyang.ac.kr/tracker_benchmark/benchmark_v10.html
2 VOT2016 benchmark is available at: http://www.votchallenge.net/vot2016/dataset.html
References
Amiri et al (2010) A novel rotation/scale invariant template matching algorithm using weighted adaptive lifting scheme transform. Pattern Recogn 43(7):2485–2496
Arbeláez P, Pont-Tuset J, Barron JT et al (2014) Multiscale combinatorial grouping. IEEE Conf Comput Vis Patt Recog:328–335
Assari SM, Idrees H, Shah M (2016) Human reidentification in crowd videos using personal, social and environmental constraints. Euro Conf Comput Vis:119–136
Chen YS, Huang YP, Fuh CS (2001) A fast block matching algorithm based on the winner-update strategy. IEEE Trans Image Process 10(8):1212–1222
Choi MS, Kim WY (2002) A novel two stage template matching method for rotation and illumination invariance. Pattern Recogn 35(1):119–129
Dekel T et al (2015) Best-buddies similarity for robust template matching. 2015 IEEE Conf Comput Vis Patt Recog (CVPR) IEEE:2021–2029
Dollár P, Lawrence Zitnick C (2013) Structured forests for fast edge detection. IEEE Int Conf Comput Vis:1841–1848
Everingham M et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Fuh CS, Maragos P (1991) Motion displacement estimation using an affine model for image matching. Opt Eng 30(7):881–887
Hong Z, Chen Z, Wang C, Mei X, Prokhorov D, Tao D (2015) Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking. IEEE Conf Comput Vis Patt Recog (CVPR):749–758
Hosang J, Benenson R, Dollár P et al (2016) What makes for effective detection proposals? IEEE Trans Pattern Anal Mach Intell 38(4):814–830
Jain AK, Zhong Y, Dubuisson-Jolly MP (1998) Deformable template models: a review. Signal Process 71(2):109–129
Jin Z, Lou Z, Yang J et al (2007) Face detection using template matching and skin-color information. Neurocomputing 70(4):794–800
Kim HS, Kang WS, Shin JI et al (2000) Face detection using template matching and ellipse fitting. IEICE Trans Inform Syst 83(11):2008–2011
Korman S, Reichman D, Tsur G et al (2013) Fast-match: fast affine template matching. IEEE Conf Comput Vis Patt Recog:2331–2338
Lee C-H, Chen L-H (1997) A fast motion estimation algorithm based on the block sum pyramid. IEEE Trans Image Process 6(11):1587–1591
Lee Y, Hara T, Fujita H et al (2001) Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique. IEEE Trans Med Imaging 20(7):595–604
Lee H, Kwon H, Robinson RM et al (2016) DTM: deformable template matching. IEEE Int Conf Acoust Speech Signal Proc (ICASSP):1966–1970
Lin H et al (2008) Template matching using the parametric template vector with translation, rotation and scale invariance. Pattern Recogn 41(7):2413–2421
Pereira S, Pun T (2000) Robust template matching for affine resistant image watermarks. IEEE Trans Image Process 9(6):1123–1129
Swain MJ, Ballard DH (1992) Indexing via color histograms. In: Active perception and robot vision [M]. Springer, Berlin, pp 261–273
Talmi I, Mechrez R, Zelnik-Manor L (2017) Template matching with deformable diversity similarity. IEEE Conf Comput Vis Patt Recog:1311–1319
Tian Y, Narasimhan SG (2012) Globally optimal estimation of nonrigid image distortion. Int J Comput Vis 98(3):279–302
Wei SD, Lai SH (2008) Fast template matching based on normalized cross correlation with adaptive multilevel winner update. IEEE Trans Image Process 17(11):2227–2235
Wong RY, Hall EL (1978) Sequential hierarchical scene matching. IEEE Trans Comput 27:359–366
Yi W, Lim J, Yang M-H (2013) Online object tracking: a benchmark. IEEE Conf Comput Vis Patt Recog (CVPR):2411–2418
Zitnick CL, Dollár P (2014) Edge boxes: locating object proposals from edges. Euro Conf Comput Vis:391–405
Acknowledgements
This work is supported by the National Natural Science Foundation of China (No.61762014), the Opening Project of Guangxi Colleges and Universities Key Laboratory of robot & welding (Guilin University of Aerospace Technology), the Opening Project of Shaanxi Key Laboratory of Complex Control System and Intelligent Information Processing, and the Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security (MIMS15-05), and and the Research Fund of Guangxi Key Lab of intelligent integrated automation. This work is also partly supported by the National Natural Science Foundation of China (No.61762012 and No.61462026).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xia, H., Zhao, W., Jiang, F. et al. Fast template matching based on deformable best-buddies similarity measure. Multimed Tools Appl 78, 11905–11925 (2019). https://doi.org/10.1007/s11042-018-6722-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6722-x