您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (5): 14-19.doi: 10.6040/j.issn.1672-3961.0.2014.090

• 控制科学与工程 • 上一篇    下一篇

基于局部敏感直方图的稀疏表达跟踪算法

葛凯蓉, 常发亮, 董文会   

  1. 山东大学控制科学与工程学院, 山东 济南 250061
  • 收稿日期:2014-03-27 修回日期:2014-09-24 发布日期:2014-03-27
  • 通讯作者: 常发亮(1965-), 男, 山东潍坊人, 博士, 教授, 博士生导师, 主要研究方向为机器视觉和模式识别.E-mail:flchang@sdu.edu.cn E-mail:flchang@sdu.edu.cn
  • 作者简介:葛凯蓉(1988-), 女, 山东烟台人, 硕士研究生, 主要研究方向为机器视觉及运动目标跟踪.E-mail:gekairong303@163.com
  • 基金资助:
    国家自然科学基金项目(61273277);高等学校博士学科点专项科研基金资助课题(2013013111003);教育部留学回国人员科研启动基金资助项目(20101174);山东省自然科学基金(ZR2011FM032)

Sparse representation tracking method based on locality sensitive histogram

GE Kairong, CHANG Faliang, DONG Wenhui   

  1. School of Control Science and Engineering, Shandong University, Jinan 250061, China
  • Received:2014-03-27 Revised:2014-09-24 Published:2014-03-27

PDF (PC)

949

摘要： 为解决目标跟踪过程中光照变化、姿态变化等问题,提出了一种基于局部敏感直方图特征的稀疏表达跟踪方法。对粒子滤波获取的多个候选目标提取局部敏感直方图特征,并根据模板字典,采用改进的L1范数模型求取每个候选目标的稀疏表示系数;然后计算每个候选目标的权重,选取权重最大的候选目标作为跟踪结果。实验结果表明,本算法能很好实现对目标的跟踪,在解决光照变化、姿态变化等问题方面有较好的效果。

关键词: 局部敏感直方图, 稀疏表达, 粒子滤波, 目标跟踪, 鲁棒性

Abstract: In order to solve the problems of illumination and pose change during target tracking, a sparse representation tracking method based on local sensitive histogram was proposed. Local sensitive histogram features of multiple candidate targets were extracted, and sparse representation coefficient of each candidate target was calculated based on template dictionary by using modified L1 norm model. Then, the weight of each candidate target was calculated. The candidate target which had the largest weight was selected as tracking result. Experimental results demonstrated that the method can track the target accurately and effectively and has advantage in illumination and pose change.

Key words: local sensitive histogram, particle filter, target tracking, robust, sparse representation

中图分类号: 

  • TP391.4
[1] 王相海,方玲玲,丛志环.基于MSPF的实时监控多目标跟踪算法研究[J].自动化学报,2012,38(1):139-144.WANG Xianghai, FANG Lingling, CONG Zhihuan.Research on real-time multi-target tracking algorithm based on MSPF[J].Acta Automatica Sinica, 2012, 38(1):139-144.
[2] Joshi A S, James M R, Samples M E.Tracking on-road vehicles with sensors of different modalities: U.S.A, US20140032012 A1[P/OL].(2014-01-30)[2014-03-27].http://appft1.uspto.gov/netacgi/nph-Parser?Sect1=PTO1＆Sect2=HITOFF＆d=PG01＆p=1＆u=/netahtml/PTO/srchnum.html＆r=1＆f=G＆l=50＆s1=20140032012.PGNR.
[3] 王金川,黄雪梅,郝圆.一种改进的医学图像目标轮廓跟踪算法[J].现代制造工程, 2012(10):33-36.WANG Jinchuan, HUANG Xuemei, HAO Yuan.An improved algorithm on objects boundary tracking of medical image[J].Modern Manufacturing Engineering, 2012(10):33-36.
[4] Yilmaz A, Javed O, Shah M.Object tracking: A survey[J].ACM Computing Surveys, 2006, 38(4):13.
[5] 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.
[6] Jepson A D, Fleet D J, El-Maraghi T F.Robust online appearance models for visual tracking[J].Pattern Analysis and Machine Intelligence, 2003, 25(10):1296-1311.
[7] 孙晓燕,常发亮.梯度特征稀疏表示目标跟踪[J].光学精密工程, 2013, 21(12): 3191-3197.SUN X Y, CHANG F L.Object tracking based on sparse representation of gradient feature[J].Optics and Precision Engineering, 2013, 21(12):3191-3197.
[8] 杨大为,丛杨,唐延东.基于粒子滤波与稀疏表达的目标跟踪方法[J].模式识别与人工智能, 2013, 26(7): 680-687.YANG Dawei, CONG Yang, TANG Yandong.Object Tracking method based on particle filter and sparse representation[J].Pattern Recognition and Artificial Intelligence, 2013, 26(7):680-687.
[9] He R, Hu B G, Zheng W S, et al.Two-stage sparse representation for robust recognition on large-scale database[C]//The Association for the Advancement of Artificial Intelligence Conference, Atlanta, USA:AAIC, 2010:1-10.
[10] 林哲,闫敬文,袁野.基于稀疏表示和PCNN的多模态图像融合[J].山东大学学报:工学版, 2013, 43(4):13-17.LIN Zhe, YAN Jingwen, Yuan Ye.Multi-modality image fusion based on sparse representation and PCNN[J].Journal of Shan Dong University:Engineering Science, 2013, 43(4):13-17.
[11] Mei X, Ling H.Robust visual tracking and vehicle classification via sparse representation[J].Pattern Analysis and Machine Intelligence, 2011, 33(11):2259-2272.
[12] Wu Y, Blasch E, Chen G, et al.Multiple source data fusion via sparse representation for robust visual tracking[C]//IEEE International Conference on Information Fusion, Chicago, USA:IEEE, 2011:1-8.
[13] Han Z, Jiao J, Zhang B, et al.Visual object tracking via sample-based Adaptive Sparse Representation[J].Pattern Recognition, 2011, 44(9):2170-2183.
[14] He S, Yang Q, Lau R W H, et al.Visual tracking via locality sensitive histograms[C]//IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA:IEEE, 2013:2427-2434.
[15] Wright J, Yang A Y, Ganesh A, et al.Robust face recognition via sparse representation[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2009, 31(2): 210-227.
[16] Mei X, Ling H.Robust visual tracking using L1 minimization[C]//IEEE International Conference on Computer Vision, Kyoto, Japan:IEEE, 2009: 1436-1443.
[17] Mei X, Ling H, Wu Y, et al.Minimum error bounded efficient l 1 tracker with occlusion detection[C]//IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, USA:IEEE, 2011:1257-1264.
[18] Doucet A, De Freitas N, Gordon N.Sequential Monte Carlo methods in practice[M].New York: Springer, 2001.
[19] 白笛,张冰,朱志宇.目标跟踪的自适应双重采样粒子滤波算法[J].计算机科学, 2013, 40(3):248-262.BAI Di, ZHANG Bing, ZHU Zhiyu.Adaptive double-resampling particle filter algorithm for target tracking[J].Computer Science, 2013, 40(3):248-262.
[20] Centir M, Fragneto P, Denaro D, et al.A combined color-correlation visual model for object tracking using particle filters[C]//International symposia on Image and Signal Processing and Analysis, Trieste, Italy:[s.n.], 2013:153-158.
[21] Bao C, Wu Y, Ling H, et al.Real time robust l1 tracker using accelerated proximal gradient approach[C]//The IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, USA:IEEE, 2012:1830-1837.
[1] 马帅依凡,赵子健. 基于人工标记的手术导航仪[J]. 山东大学学报(工学版), 2017, 47(3): 63-68.
[2] 侯明冬,王印松,田杰. 积分时滞对象的一种内模PID鲁棒控制方法[J]. 山东大学学报(工学版), 2016, 46(5): 64-67.
[3] 王海军,葛红娟,张圣燕. 基于L1范数和最小软阈值均方的目标跟踪算法[J]. 山东大学学报(工学版), 2016, 46(3): 14-22.
[4] 张井岗, 马文廷, 赵志诚. 串级时滞过程的二自由度Smith预估控制[J]. 山东大学学报(工学版), 2015, 45(5): 43-50.
[5] 郭志波, 董健, 庞成. 多技术融合的Mean-Shift目标跟踪算法[J]. 山东大学学报(工学版), 2015, 45(2): 10-16.
[6] 邱晓欣1,2,张文强1,2*,秦晋贤1,2,杜正阳1,2,张德峰1,2. 恶劣环境下多目标实时跟踪算法研究[J]. 山东大学学报(工学版), 2014, 44(2): 21-27.
[7] 李武,侯志强*,魏国剑,余旺盛. 跟踪框自适应的尺度变化目标跟踪算法[J]. 山东大学学报(工学版), 2014, 44(2): 28-34.
[8] 谢志华. 一种新的血流建模方法及其在红外人脸识别中的应用[J]. 山东大学学报(工学版), 2013, 43(5): 1-5.
[9] 赵占山1,2, 张静3, 孙连坤1, 丁刚1. 有限时间收敛的滑模自适应控制器设计[J]. 山东大学学报(工学版), 2012, 42(4): 74-78.
[10] 周长辉1, 胡永健2,余绍鹏1. 鲁棒的源扫描仪辨识算法设计[J]. 山东大学学报(工学版), 2011, 41(2): 62-65.
[11] 黄斌. 基于离散趋近律的变结构系统控制[J]. 山东大学学报(工学版), 2011, 41(1): 45-48.
[12] 李岳阳,王士同. 基于鲁棒性神经模糊网络的脉冲噪声滤波算法[J]. 山东大学学报(工学版), 2010, 40(5): 164-170.
[13] 方 挺,杨 忠,沈春林 . 无人机编队视频序列中的多目标精确跟踪[J]. 山东大学学报(工学版), 2008, 38(4): 22-26 .
[14] 赵永国,贾磊,蔡文剑 . 一种积分过程PID自整定方法[J]. 山东大学学报(工学版), 2008, 38(1): 48-51 .
[15] 解淑英,张承进 . 一种输入饱和受限系统的自适应逆控制[J]. 山东大学学报(工学版), 2006, 36(6): 62-66 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发