采用核相关滤波器的长期目标跟踪

杨德东; 蔡玉柱; 毛宁; 杨福才

doi:10.3788/OPE.20162408.2037

您当前的位置：

首页 >

文章列表页 >

采用核相关滤波器的长期目标跟踪

信息科学 | 更新时间：2020-07-07

- 采用核相关滤波器的长期目标跟踪
- Long-term object tracking based on kernelized correlation filters
- Editorial Office of Optics and Precision Engineeri 2016年24卷第8期页码：2037-2049
- 作者机构：
  
  河北工业大学控制科学与工程学院, 天津 300130
- 作者简介：
  
  蔡玉柱(1990-)，男，山东日照人，硕士研究生，2013年于天津职业技术师范大学获得学士学位，主要从事目标检测、目标跟踪方面的研究。E-mail：caiyuzhu001@sina.com E-mail:caiyuzhu001@sina.com
- 基金信息：
  
  国家自然科学基金资助项目(No.61203076);天津市自然科学基金资助项目(No.13JCQNJC03500)
- DOI：10.3788/OPE.20162408.2037
  中图分类号： TP391
- 收稿日期：2016-04-18，
  
  录用日期：2016-6-22，
  
  纸质出版日期：2016-08-25
- 稿件说明：
移动端阅览
杨德东, 蔡玉柱, 毛宁, 等. 采用核相关滤波器的长期目标跟踪[J]. Editorial Office of Optics and Precision Engineeri, 2016,24(8):2037-2049.

De-dong YANG, Yu-zhu* CAI, Ning MAO, et al. Long-term object tracking based on kernelized correlation filters[J]. Optics and precision engineering, 2016, 24(8): 2037-2049.
杨德东, 蔡玉柱, 毛宁, 等. 采用核相关滤波器的长期目标跟踪[J]. Editorial Office of Optics and Precision Engineeri, 2016,24(8):2037-2049. DOI： 10.3788/OPE.20162408.2037.

De-dong YANG, Yu-zhu* CAI, Ning MAO, et al. Long-term object tracking based on kernelized correlation filters[J]. Optics and precision engineering, 2016, 24(8): 2037-2049. DOI： 10.3788/OPE.20162408.2037.

摘要

针对核相关滤波器(KCF)跟踪算法在目标跟踪中存在尺度变化、严重遮挡、相似目标干扰和出视野情况下跟踪失败等问题，提出了一种基于KCF的长期目标跟踪算法。该算法在分类器学习中加入空间正则化，利用基于样本区域空间位置信息的空间权重函数调节分类器系数，使分类器学习到更多负样本和未破坏的正样本，从而增强学习模型的判别力。然后，在检测区域利用Newton方法完成迭代处理，求取分类器最大响应位置及其目标尺度信息。最后，对最大响应位置的目标进行置信度比较，训练在线支持向量机(SVM)分类器，以便在跟踪失败的情况下，重新检测到目标而实现长期跟踪。采用OTB-2013评估基准50组视频序列验证了本文算法的有效性，并与30种其他跟踪方法进行了对比。结果表明：本文提出的算法跟踪精度为0.813，成功率为0.629，排名第一，相比传统KCF算法分别提高了9.86%和22.3%。在目标发生显著尺度变化、严重遮挡、相似目标干扰和出视野等复杂情况下，本文方法均具有较强的鲁棒性。

Abstract

As Kernelized Correlation Filters (KCF) tracking algorithm has poor performance in handling scale-variant

heavy occlusion

similar target interfere and out of view

this paper proposes a long-term tracking approach based on the KCF. Firstly

a spatial regularization component was introduced in the learning of a classifier

the classifier coefficients were penalized depending on the weight function of spatial location information in sample locations. By which the classifier could learn significantly larger set of negative training samples and uncorrupted positive samples

so that the discriminative power of learned model was increased. Then

the Newton method was used to complete the iteration and obtain the maximizing response location and target score of the classifier in the detection area. Finally

to re-detect the target in the case of tracking failure and achieve a long-term tracking

the confidence of the target with the maximum response score was compared and an online Support Vector Machine (SVM) classifier was trained. To verify the feasibility of the proposed algorithm

fifty groups of OTB-2013 benchmark video sequences were tested and the obtained results were compared with thirty kinds of other tracking algorithms. Experimental results indicate that the precision and success rate from the proposed method are respectively 0.813 and 0.629

ranking first. Compared with traditional KCF tracking algorithm

the proposed approach respectively improves by 9.86% and 22.3% in the precision and the success rate. Moreover

it is robust to significant scale changing

heavy occlusion

interfere with similar target

out of view and other complex scenes.

关键词

Keywords

references

SMEULDERS A W M, CHU D M, CUCCHIARA R, et al.. Visual tracking: An experimental survey [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1442-1468.

ROSS D A, LIM J, LIN R S, et al.. Incremental learning for robust visual tracking [J]. International Journal of Computer Vision, 2008, 77(1-3): 125-141.

KWON J, LEE K M. Visual tracking decomposition [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 1269-1276.

BABENKO B, YANG M H, BELONGINE S. Robust object tracking with online multiple instance learning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632.

HARE S, SAFFARI A, TORR P H S. Struck: Structured output tracking with kernels [C]. IEEE International Conference on Computer Vision (ICCV), 2011: 263-270.

KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422.

ZHANG K, ZHANG L, YANG M H. Real-time compressive tracking [C]. European Conference on Computer Vision (ECCV), 2012: 864-877. http://cn.bing.com/academic/profile?id=2165037244&encoded=0&v=paper_preview&mkt=zh-cn

陈东成, 朱明, 高文, 等. 在线加权多实例学习实时目标跟踪[J]. 光学精密工程, 2014, 22(6): 1661-1667.

CHEN D CH, ZHU M, GAO W, et al.. Real-time object tracking via online weighted multiple instance learning [J]. Opt. Precision Eng., 2014, 22(6): 1661-1667. (in Chinese)

程帅, 孙俊喜, 曹永刚, 等. 增量深度学习目标跟踪[J]. 光学精密工程, 2015, 23(4): 1161-1170.

CHEN SH, SUN J X, CAO Y G, et al.. Target tracking based on incremental deep learning [J]. Opt. Precision Eng., 2015, 23(4): 1161-1170. (in Chinese)

修春波, 魏世安. 显著性直方图模型的Camshift跟踪方法[J]. 光学精密工程, 2015, 23(6): 1750-1757.

XIU CH B, WEI SH AN. Camshift tracking with saliency histogram [J]. Opt. Precision Eng., 2015, 23(6): 1750-1757. (in Chinese)

郭敬明, 何昕, 魏仲慧. 基于在线支持向量机的Mean Shift彩色图像跟踪[J]. 液晶与显示, 2014, 29(1): 120-128.

GUO J M, H X, W ZH H. New mean shift tracking for color image based on online support vector machine [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(1): 120-128. (in Chinese)

李静宇, 王延杰. 基于子空间的目标跟踪算法研究[J]. 液晶与显示, 2014, 29(4): 617-622.

LI J Y, W Y J. Subspace based target tracking algorithm [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(4): 617-622. (in Chinese)

BOLME D S, BEVERIDGE J R, DRAPER B A, et al.. Visual object tracking using adaptive correlation filters [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 2544-2550.

HENRIQUES J F, CASEIRO R, MARTINS P, et al.. Exploiting the circulant structure of tracking-by-detection with kernels [C]. European Conference on Computer Vision (ECCV), 2012: 702-715.

DANELLJAN M, KHAN F, FELSBERG M, et al.. Adaptive color attributes for real-time visual tracking [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014: 1090-1097.

ZHANG K, ZHANG L, LIU Q, et al.. Fast visual tracking via dense spatio-temporal context learning [C]. European Conference on Computer Vision (ECCV), 2014: 127-141.

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.

LI Y, ZHU J. A scale adaptive kernel correlation filter tracker with feature integration [C]. European Conference on Computer Vision (ECCV), 2014: 254-265.

张雷, 王延杰, 孙宏海, 等. 采用核相关滤波器的自适应尺度目标跟踪[J]. 光学精密工程, 2016, 24(2): 448-459.

ZHANG L, WANG Y J, SUN H M, et al.. Adaptive scale object tracking with kernelized correlation filters [J]. Opt. Precision Eng., 2016, 24(2): 448-459. (in Chinese)

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.

YU L Y, FAN CH X, M Y. Improved target tracking algorithm based on kernelized correlation filter [J]. Journal of Computer Application, 2015, 35(12): 3550-3554. (in Chinese)

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), 2005: 886-893. http://cn.bing.com/academic/profile?id=2161969291&encoded=0&v=paper_preview&mkt=zh-cn

WU Y, LIM J, YANG M H. Online object tracking: A benchmark [C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), 2013: 2411-2418.

SCHOLKOPF B, SMOLA A J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond [M]. MIT press, 2002.

RIFKIN R, YEO G, POGGIO T. Regularized least-squares classification [J]. Nato Science Series Sub Series III Computer and Systems Sciences, 2003, 190: 131-154.

浏览量

662

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用最佳伙伴相似性的改进空间正则化判别相关滤波目标跟踪

采用核相关滤波器的自适应尺度目标跟踪

一种应用于人脸正面图像的眼睛自动定位算法