基于多特征的双模板自适应更新跟踪算法

刘振涛, 王朝英, 刘卫群

刘振涛, 王朝英, 刘卫群. 基于多特征的双模板自适应更新跟踪算法[J]. 应用光学, 2012, 33(1): 78-84.
引用本文: 刘振涛, 王朝英, 刘卫群. 基于多特征的双模板自适应更新跟踪算法[J]. 应用光学, 2012, 33(1): 78-84.
shu
LIU Zhen-tao, WANG Zhao-ying, LIU Wei-qun. Tracking algorithm of dual template adaptive updating based on multiple features[J]. Journal of Applied Optics, 2012, 33(1): 78-84.
Citation: LIU Zhen-tao, WANG Zhao-ying, LIU Wei-qun. Tracking algorithm of dual template adaptive updating based on multiple features[J]. Journal of Applied Optics, 2012, 33(1): 78-84.
shu

基于多特征的双模板自适应更新跟踪算法

  • 1.

    空军工程大学 电讯工程学院,陕西 西安 710077;

  • 2.

    63751部队 技术室,陕西 西安 710028

详细信息
    通讯作者:

    刘振涛（1986-），男，辽宁抚顺人，硕士研究生，主要从事计算机视觉跟踪研究。

  • 中图分类号: TN911.73; TP391

Tracking algorithm of dual template adaptive updating based on multiple features

  • 1.

    Telecommunication Engineering Institute,Air Force Engineering University,Xi-an 710077,China;

  • 2.

    Technology Office,63751 Troops,Xi-an 710028,China

摘要

    摘要
  • 摘要: 针对均值漂移算法中采用单一颜色特征以及缺乏必要模板更新方法的缺陷，提出一种基于多特征的双模板自适应更新目标跟踪算法。引入像素点邻域灰度均值差和分层空间信息加强目标特征的鉴别性，再通过对目标与背景区域双模板相似度系数的综合分析，准确地判断跟踪干扰因素的来源，并以当前帧目标区域的相似度系数为权值对目标模板进行加权更新，使得模板更新速度与其目标特征变化相适应的同时抑制模板过更新，较好地解决了模板更新时机和更新速度等问题。仿真结果表明，所提算法在不同跟踪场景下均具有较强的鲁棒性。
    Abstract: To solve the problem of single color feature and the lack of necessary template updating method in mean shift algorithm, an adaptive tracking algorithm of dual template adaptive updating based on multiple features is proposed. The difference of gray mean in the neighborhood of pixel point and the layered space information are introduced to enhance feature differentiation. By analyzing the similarity coefficient of dual template in target and background region, the origin of disturbance factor is estimated truly, and the target template in target region of current frame is updated by similarity coefficient. The speed of template updating is adapted to the transformation of target feature, and at the same time excessive template updating is restrained, which solves the problem of the occasion and speed of template updating. The robustness of the proposed algorithm is demonstrated by simulations in different tracking scenarios.
    • HTML全文
    • 参考文献(1)
  • ［1］WANG Jun-qiu, YA Su-shi. Integrating shape and color features for adaptive real-time object tracking ［C］. Kunming, China: Proceedings of the 2006 IEEE International Conference on Robotics and Biomimetics,2006.
    ［2］YANG C, DURAISWAMI R, DAVIS L. Efficient mean-shift tracking via a new similarity measure［C］. Washington DC, USA: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2005.
    ［3］PORIKLI F, TUZEL O, MEER P. Covariance tracking using model update based on Lie algebra［C］. New York, USA: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006.
    ［4］惠宝聚,高雅,李良福.基于自适应非参数统计模型的彩色目标跟踪算法研究［J］.应用光学,2009,30(3):448-453.
    HUI Bao-ju, GAO Ya, LI Liang-fu. Visual tracking algorithm for color objects based on adaptive nonparametric statistical model［J］. Journal of Applied Optics, 2009,30(3):448-453.(in Chinese with an English abstract)
    ［5］PARK M, LIU Y X, COLLINS R T. Efficient mean shift belief propagation for vision tracking ［C］. Alaska, USA: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2008.
    ［6］HAN B, COMANICIU D, ZHU Y, et al. Sequential kernel density approximation and its application to real-time visual tracking ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(7):1186-1197.
    ［7］王欢,王江涛,任明武.一种鲁棒的多特征融合目标跟踪新算法［J］.中国图像图形学报,2009,14(3):489-498.
    WANG Huan, WANG Jiang-tao, REN Ming-wu. A new robust object tracking algorithm by fusing multi-features［J］. Journal of Image and Graphics, 2009,14(3):489-498.(in Chinese with an English abstract)
    ［8］胡铟,杨静宇.基于分块颜色直方图的Mean Shift跟踪算法［J］.系统仿真学报,2009,21(10):2396-2399.
    HU Yin, YANG Jing-yu. Tracking algorithm based on block color histogram and Mean Shift［J］. Journal of System Simulation, 2009,21(10):2396-2399. (in Chinese with an English abstract)
    ［9］ZHANG B, TIAN W F, JIN Z H. Joint tracking algorithm using particle filter and mean shift with target model updating ［J］. Chinese Optics Letters, 2006,4(10): 569-572.


    ［10］覃剑,曾孝平,曾浩.均值漂移跟踪的双模板更新算法［J］. 计算机应用研究,2009,26(7):2771-2774.
    TAN Jian, ZENG Xiao-ping, ZENG Hao. Dual template algorithm for Mean-Shift template update［J］. Application Research of Computer, 2009,26(7):2771-2774. (in Chinese with an English abstract)
    ［11］张良春,夏利民.一种自适应特征选择的运动目标实时跟踪算法［J］.小型微型计算机系统,2008,7(7):1324-1328.
    ZHANG Liang-chun, XIA Li-min. An adaptive feature selecting real-time moving object tracking algorithm［J］. Journal of Chinese Computer Systems, 2008,7(7):1324-1328. (in Chinese with an English abstract)
    ［12］虞旦,韦巍,张远辉.基于多特征空间的均值漂移算法［J］.模式识别与人工智能,2009,22(4):666-672.
    YU Dan, WEI Wei, ZHANG Yuan-hui. Mean Shift tracking algorithm based on multi-feature space［J］. PR & AI,2009,22(4):666-672. (in Chinese with an English abstract)
    ［13］刘素珍,邓和林.一种基于特征融合的运动目标跟踪算法［J］.激光与红外,2008,38(8):837-840.
    LIU Su-zhen, DENG He-lin. A moving object tracking algorithm based on feature fusion［J］. Laser & Infrared,2008,38(8):837-840. (in Chinese with an English abstract)
    ［14］王书朋,姬红兵.利用子区域特征进行自适应目标跟踪［J］. 系统工程与电子技术,2008,30(5):785-788.
    WANG Shu-peng, JI Hong-bing. Adaptive object tracking based on the sub-regions features［J］. Systems Engineering and Electronics, 2008,30(5):785-788. (in Chinese with an English abstract)
    ［15］沈志熙,杨欣,黄席樾.均值漂移算法中的目标模型更新方法研究［J］.自动化学报,2009,35(5):478-483.
    SHEN Zhi-xi, YANG Xin, HUANG Xi-yue. Study on target model update method in Mean Shift algorithm［J］. Acta Automatica Sinica, 2009,35(5):478-483. (in Chinese with an English abstract)
    • 相关文章
    • 施引文献
    • 资源附件(0)
计量
  • 文章访问数:  3534
  • HTML全文浏览量:  130
  • PDF下载量:  615
  • 被引次数: 0
出版历程
  • 刊出日期:  2012-02-14

目录

摘要
HTML全文
    参考文献(1)
    相关文章
    施引文献
    资源附件(0)

    /

    返回文章
    返回

    相关数据库

    广告合作

    友情链接

    帮助中心

    扫描关注本刊微信平台

    您是第  2899627位访问者，欢迎！

    地址: 西安市电子三路西段9号 邮政编码: 710065 联系电话: 029-88288172

    版权所有 © 《应用光学》编辑部

    陕公网安备 61011302001501号       陕ICP备19002862号-1

    北京仁和汇智信息技术有限公司 开发  技术支持: info@rhhz.net   百度统计