[1]黄德天,顾培婷,柳培忠,等.改进的自适应核相关滤波目标跟踪[J].华侨大学学报(自然科学版),2017,38(5):693-698.[doi:10.11830/ISSN.1000-5013.201606062]
　HUANG Detian,GU Peiting,LIU Peizhong,et al.Improved Adaptive Target Tracking Based on Kernelized Correlation Filters[J].Journal of Huaqiao University(Natural Science),2017,38(5):693-698.[doi:10.11830/ISSN.1000-5013.201606062]
点击复制

改进的自适应核相关滤波目标跟踪()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第38卷
期数:
2017年第5期
页码:
693-698
栏目:
出版日期:
2017-09-20

文章信息/Info

Title:
Improved Adaptive Target Tracking Based on Kernelized Correlation Filters
文章编号:
1000-5013(2017)05-0693-06
作者:
黄德天1; 2;  顾培婷1;  柳培忠3;  黄炜钦1
1. 华侨大学 工学院, 福建 泉州 362021;2. 华侨大学 机电及自动化学院, 福建 厦门 361021;3. 厦门大学 信息与通信工程博士后流动站, 福建 厦门 361005
Author(s):
HUANG Detian1; 2;  GU Peiting1;  LIU Peizhong3;  HUANG Weiqin1
1. College of Engineering, Huaqiao University, Quanzhou 362021, China; 2. College of Mechanical Engineering and Automation, Huaqiao University, Xiamen 361021, China; 3. Postdoctoral Research Station of Information and Communication Engineering, Xiamen Uni
关键词:
目标跟踪;  核相关滤波器;  颜色属性;  局部线性嵌入
Keywords:
target tracking;  kernelized correlation filters;  color attribute;  local linear embedding
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201606062
文献标志码:
A
摘要:
利用核相关滤波器跟踪框架,提出一种改进的自适应颜色属性的目标跟踪方法.首先,构建循环样本矩阵,引进颜色属性作为特征描述目标;然后,采用流行学习局部线性嵌入(LLE)算法自适应地对特征向量进行降维,得到低维特征空间;最后,根据正则化最小二乘分类器获得目标位置.实验结果表明:文中算法的平均中心位置误差减少了21.29 px;在阈值为20 px时,平均距离精度提高了27.9%,平均跟踪速度为38 帧·s-1;与传统核相关滤波(KCF)算法相比,文中算法具有良好的光照不敏感性及更高的跟踪精度和鲁棒性.
Abstract:
An improved adaptive color attribute tracking algorithm is proposed based on the kernel correlation filter. Firstly, the cycle matrix is established, and color attribute is used to describe the target. Secondly, the local linear embedding(LLE)algorithm was applied to reduce the dimension of extracted feature to achieve a low-dimensional feature space. Finally, the position is obtained by learning the regularized least-squares classifiers. Experimental results demonstrate that the proposed algorithm reduces the median center location error by 21.29 px, the average distance precision is increased by 27.9% when the threshold is set 20 px, and the average tracking speed is 38 frames·s-1. Compared with the original kernelized correlation filters(KCF)algorithm, the proposed algorithm not only has well illumination insensitivity, but also has higher tracking accuracy and robustness.

参考文献/References:

[1] 李静宇,刘艳滢,田睿,等.视频监控系统中的概率模型单目标跟踪框架[J].光学精密工程,2015,23(7):2093-2099.
[2] YANG Fan,LU Huchuan,YANG M H.Robust superpixel tracking[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2014,23(4):1639-1651.
[3] KALAL Z,MIKOLAJCZYK K,MATAS J.Tracking-learning-detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1409-1422.
[4] ZHANG Kaihua,ZHANG Lei,YANG M H.Real-time compressive tracking[C]//Proceedings of the 12th European conference on Computer Vision.Florence:Springer-Verlag,2012:864-877.
[5] CHEN Zhe,HONG Zhibin,TAO Dacheng.An experimental survey on correlation filter-based tracking[J].Computer Science,2015,53(6025):68-83.
[6] HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//IEEE Conference on European Conference on Computer Vision.Berlin:Springer-verlag,2012:702-715.
[7] 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.
[8] 毕笃彦,库涛,查宇飞,等.基于颜色属性直方图的尺度目标跟踪算法研究[J].电子与信息学报,2016,38(5):1099-1106.
[9] BERLIN B,KAY P.Basic color terms: Their universality and evolution[M].Berkeley:UC Press,1969:11-25.
[10] ROWEIS S T,SAUL L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,2290(5500):2323-2326.
[11] 冯海亮,李见为,黄鸿.自组织LLE算法及其在人脸识别的应用[J].光学·精密工程,2008,16(9):1732-1737.
[12] WU Yi,LIM J,YANG M H.Online object tracking: A benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE Computer Society,2013:2411-2418.

相似文献/References:

[1]钟必能,潘胜男.选择性搜索和多深度学习模型融合的目标跟踪[J].华侨大学学报(自然科学版),2016,37(2):207.[doi:10.11830/ISSN.1000-5013.2016.02.0207]
　ZHONG Bineng,PAN Shengnan.Multi-Clue Fusion Target Tracking Algorithm Based on Selective Search and Deep Learning[J].Journal of Huaqiao University(Natural Science),2016,37(5):207.[doi:10.11830/ISSN.1000-5013.2016.02.0207]
[2]刘韶涛,姚灿荣.结合PSO的改进压缩跟踪方法[J].华侨大学学报(自然科学版),2017,38(1):121.[doi:10.11830/ISSN.1000-5013.201701024]
　LIU Shaotao,YAO Canrong.Improved Compress Tracking Algorithm Based on PSO[J].Journal of Huaqiao University(Natural Science),2017,38(5):121.[doi:10.11830/ISSN.1000-5013.201701024]
[3]顾培婷,黄德天,黄炜钦,等.抗遮挡的相关滤波目标跟踪算法[J].华侨大学学报(自然科学版),2018,39(4):611.[doi:10.11830/ISSN.1000-5013.201608031]
　GU Peiting,HUANG Detian,HUANG Weiqin,et al.Anti-Occlusion Object Tracking Algorithm Based on Kernelized Correlation Filters[J].Journal of Huaqiao University(Natural Science),2018,39(5):611.[doi:10.11830/ISSN.1000-5013.201608031]

备注/Memo

备注/Memo:
收稿日期: 2016-06-21
通信作者: 黄德天(1985-),男,讲师,博士,主要从事机器学习、图像处理的研究.E-mail:huangdetian@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(61203242); 福建省泉州市科技计划项目(2014Z113)
更新日期/Last Update: 2017-09-20