尺度自适应的核相关滤波跟踪器

doi:10.11772/j.issn.1001-9081.2016.12.3385

计算机应用 ›› 2016, Vol. 36 ›› Issue (12): 3385-3388.DOI: 10.11772/j.issn.1001-9081.2016.12.3385

尺度自适应的核相关滤波跟踪器

李麒骥¹, 李磊民², 黄玉清¹

1. 西南科技大学信息工程学院, 四川绵阳 621010;
2. 西南科技大学国防科技学院, 四川绵阳 621010

收稿日期:2016-05-11 修回日期:2016-07-18 出版日期:2016-12-10 发布日期:2016-12-08
通讯作者: 李磊民
作者简介:李麒骥(1988-),男,重庆合川人,硕士研究生,主要研究方向:目标跟踪、模式识别;李磊民(1960-),男,辽宁辽阳人,教授,主要研究方向:图像恢复、机器视觉;黄玉清(1962-),女,四川绵阳人,教授,硕士,主要研究方向:图像处理、智能控制。

Scale adaptive tracker based on kernelized correlation filtering

LI Qiji¹, LI Leimin², HUANG Yuqing¹

1. School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
2. School of National Defence Science and Technology, Southwest University of Science and Technology, Mianyang Sichuan 621010, China

Received:2016-05-11 Revised:2016-07-18 Online:2016-12-10 Published:2016-12-08

摘要/Abstract

摘要： 为了解决核相关滤波（KCF）跟踪器中目标尺度固定的问题，提出了一种尺度自适应的跟踪方法。首先利用Lucas-Kanade光流法跟踪相邻视频帧之间特征点的运动，引入前向后向跟踪方法保留可信特征点；其次将可信点用于尺度变化估计；然后将尺度估计应用到可调高斯窗上；最后运用前向后向跟踪算法来判断目标是否处于被遮挡状态，修改了模板更新策略。解决了核跟踪滤波器中目标尺度固定的限制，使得跟踪器更具鲁棒性与准确性。在目标跟踪视频集上测试算法效果。实验结果表明，所提算法在成功率图与精确度图排名上均优于原KCF、TLD、Struck算法。与原方法相比，改进后的方法能更好地适用于有尺度变化与遮挡的跟踪。

关键词: 视觉目标跟踪, 相关滤波器, 尺度自适应

Abstract: In order to solve the problem of fixed target size in Kernel Correlation Filtering (KCF) tracker, a scale adaptive tracking method was proposed. Firstly, the Lucas-Kanade optical flow method was used to track the movement of keypoints in the neighbor frames, and the reliable points were obtained by introducing the forward-backward method. Secondly, the reliable points were used to estimate the target changing in scale. Thirdly, the scale estimation was applied to the adjustable Gaussian window. Finally, the forward-backward tracking method was used to determine whether the target was occluded or not, the template updating strategy was revised. The fixed target size limitation in the KCF was solved, the tracker was more accurate and robust. The object tracking datasets were used to test the algorithm. The experimental results show that the proposed method ranks over the original KCF, Tracking-Learning-Detection (TLD), Structured output tracking with kernel (Struck) algorithms both in success plot and precision plot. Compared with the original method, the proposed tracker can be better applied in target tracking with scale variation and occlusion.

Key words: visual object tracking, correlation filter, scale adaptive

中图分类号:

TP391.4

李麒骥, 李磊民, 黄玉清. 尺度自适应的核相关滤波跟踪器[J]. 计算机应用, 2016, 36(12): 3385-3388.

LI Qiji, LI Leimin, HUANG Yuqing. Scale adaptive tracker based on kernelized correlation filtering[J]. Journal of Computer Applications, 2016, 36(12): 3385-3388.

参考文献

[1] HARE S, SAFFARI A, TORR P H S. Struck:structured output tracking with kernels[C]//ICCV 2011:Proceedings of the 2011 International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2011:263-270.
[2] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422.
[3] ZHANG K, ZHANG L, YANG M H.Real-time compressive tracking[C]//ECCV 2012:Proceedings of the 12th European Conference on Computer Vision, LNCS 7574. Berlin:Springer, 2012:864-877.
[4] BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8):1619-1632.
[5] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//CVPR 2010:Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2010:2544-2550.
[6] HENRIQUES J F, RUI C, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//ECCV 2012:Proceedings of 12th European Conference on Computer Vision, LNCS 7575. Berlin:Springer, 2012:702-715.
[7] HENRIQUES J F, RUI C, 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.
[8] DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:1090-1097.
[9] GRAY R M. Toeplitz and circulant matrices:a review[J]. Foundations and Trends in Communications and Information Theory, 2005, 2(3):155-239.
[10] SCHÖLKOPF B, SMOLA A. Learning with kernels:support vector machines, regularization, optimization, and beyond[J]. IEEE Transactions on Neural Networks, 2005, 16(3):781-781.
[11] RIFKIN R, YEO G, POGGIO T. Regularized least-squares classification[M]//Advances in Learning Theory:Methods, Models and Applications. Amsterdam:IOS Press, 2003:131-154.
[12] KALAL Z, MIKOLAJCZYK K, MATAS J. Forward-backward error:automatic detection of tracking failures[C]//Proceeding of the 2010 International Conference on Pattern Recognition. Washington, DC:IEEE Computer Society, 2010:23-26.
[13] LUCAS B D, KANADE T. An iterative image registration technique with an application to stereo vision[C]//IJCAI'81:Proceeding of the 7th International Joint Conference on Artificial Intelligence. San Francisco:Morgan Kaufmann Publishers, 1981, 2:674-679.
[14] WU Y, LIM J, YANG M H. Online object tracking:a benchmark[C]//CVPR 2013:Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington, DC:IEEE Computer Society, 2013:2411-2418.
[15] Visual Tracker Benchmark. The evaluation tool[EB/OL].[2016-03-11]. http://cvlab.hanyang.ac.kr/tracker_benchmark/.

尺度自适应的核相关滤波跟踪器

Scale adaptive tracker based on kernelized correlation filtering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

[1]	杨春德, 刘京, 瞿中. 分离窗口快速尺度自适应目标跟踪算法[J]. 计算机应用, 2019, 39(4): 1145-1149.
[2]	陈平, 龚勋. 基于尺度自适应与增量式学习的人脸对齐方法[J]. 计算机应用, 2018, 38(7): 2064-2069.
[3]	刘培强, 张加惠, 吴大伟, 安志勇. 基于自适应组合核的鲁棒视频目标跟踪算法[J]. 计算机应用, 2018, 38(12): 3372-3379.
[4]	余礼杨, 范春晓, 明悦. 改进的核相关滤波器目标跟踪算法[J]. 计算机应用, 2015, 35(12): 3550-3554.