Scale adaptive improvement of kernel correlation filter tracking algorithm

doi:10.11772/j.issn.1001-9081.2017.03.811

Abstract

Abstract: To solve the problem that Circulant Structure of tracking-by-detection with Kernels (CSK) is difficult to adapt to the target scale change, a multi-scale kernel correlation filter classifier was proposed to realize the scale adaptive target tracking. Firstly, the multi-scale image was used to construct the sample set, the multi-scale kernel correlation filtering classifier was trained by the sample set, for target size estimation to achieve the goal of the optimal scale detection, and then the samples collected on the optimal target scale were used to update the classifier on-line to achieve the scale-adaptive target tracking. The comparative experiments and analysis illustrate that the proposed algorithm can adapt to the scale change of the target in the tracking process, the error of the eccentricity is reduced to 1/5 to 1/3 that of CSK algorithm, which can meet the needs of long time tracking in complex scenes.

Key words: target tracking, multi-scale image, self-adaption, Kernel Correlation Filter (KCF)

摘要： 针对基于检测的核相关滤波跟踪（CSK）算法难以适应目标尺度变化的问题，提出多尺度核相关滤波分类器以实现尺度自适应目标跟踪。首先，采用多尺度图像构建样本集，训练多尺度核相关滤波分类器，通过分类器对目标的尺度估计实现目标的最佳尺度检测；然后，在最佳尺度下采集样本在线学习更新分类器，实现尺度自适应的目标跟踪。对比实验与分析表明，本文算法在目标跟踪过程中能够正确适应目标的尺度变化，相比CSK算法，偏心距误差减少至其1/5~1/3，能满足复杂场景长时间跟踪的需求。

关键词: 目标跟踪, 多尺度图像, 自适应, 核相关滤波

CLC Number:

TP391.41

QIAN Tanghui, LUO Zhiqing, LI Guojia, LI Yingyun, LI Xiankai. Scale adaptive improvement of kernel correlation filter tracking algorithm[J]. Journal of Computer Applications, 2017, 37(3): 811-816.

钱堂慧, 罗志清, 李果家, 李应芸, 李显凯. 核相关滤波跟踪算法的尺度自适应改进[J]. 计算机应用, 2017, 37(3): 811-816.

References

[1] 陈东成.基于机器学习的目标跟踪技术研究[D].北京:中国科学院大学,2015:6-7.(CHEN D C. Research of the techniques of object tracking based on machine learning[D]. Beijing:University of the Chinese Academy of Sciences, 2015:6-7.)
[2] CHENG Y H, WANG J. A motion image detection method based on the inter-frame difference method[J]. Applied Mechanics and Materials, 2014, 490:1283-1286.
[3] LAI H, ZHU Y, NONG Z. An improved background subtraction approach in target detection and tracking[C]//ICMV 2013:Proceedings of the 6th International Conference on Machine Vision. Bellingham, WA:SPIE, 2013, 9067:10-13.
[4] WEDEL A, POCK T, ZACH C, et al. An improved algorithm for TV-L¹ optical flow[M]//Statistical and Geometrical Approaches to Visual Motion Analysis, LNCS 5604. Berlin:Springer, 2008:23-45.
[5] GRABNER H, LEISTNER C, BISCHOF H. Semi-supervised on-line boosting for robust tracking[C]//ECCV'08:Proceedings of the 10th European Conference on Computer Vision. Berlin:Springer, 2008:234-247.
[6] BABENKO B, YANG M-H, BELONQIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8):1619-1632.
[7] AVIDAN S. Support vector tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8):1064-1072.
[8] SAFFARI A, LEISTNER C, SANTNER J, et al. On-line random forests[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Workshops. Piscataway, NJ:IEEE, 2009:1393-1400.
[9] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422.
[10] HENRIQUES J F, CAESIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//ECCV'12:Proceedings of the 12th European Conference on Computer Vision. Berlin:Springer, 2012:702-715.
[11] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):583-596.
[12] DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]//CVPR'14:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:1090-1097.
[13] 李英明,夏海宏.双二次B-样条插值图像缩放[J].中国图象图形学报,2011,16(10):1937-1943.(LI Y M, XIA H H. Double two B-spline interpolation image scaling[J]. Journal of Image and Graphics, 2011, 16(10):1937-1943.)
[14] 夏海宏.图像缩放及其GPU实现[D].杭州:浙江大学,2010:10-11.(XIA H H. Image scaling and its GPU implementation[D]. Hangzhou:Zhejiang University, 2010:10-11.)
[15] 阮秋琦.数字图像处理学[M].北京:电子工业出版社,2013:130-135.(RUAN Q Q. Digital Image Processing[M]. Beijing:Publishing House of Electronics Industry, 2013:130-135.)
[16] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//Proceedings of the 2010 Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2010:2544-2550.
[17] SCHÖLKOPF B, SMOLA A J. Learning with kernels:support vector machines, regularization, optimization, and beyond[M]. Cambridge, MA:MIT Press, 2001.
[18] ORON S, BAR-HILLEL A, LEVI D, et al. Locally orderless tracking[C]//CVPR'12:Proceedings of the 2012 IEEE Conference on Computer Vision an Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:1940-1947.
[19] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//CVPR'05:Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2005:886-893.
[20] VAPNIK V N. Statistical learning theory[J]. Encyclopedia of the Sciences of Learning, 2010, 41(4):3185-3185.