搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

目标跟踪中目标模型更新问题的半监督学习算法研究

高文 汤洋 朱明

引用本文:
Citation:

目标跟踪中目标模型更新问题的半监督学习算法研究

高文, 汤洋, 朱明

Research on semi-supervising learning algorithm for target model updating in target tracking

Gao Wen, Tang Yang, Zhu Ming
PDF
导出引用
  • 本文针对长期稳定的目标跟踪中的目标形变、尺度缩放、旋转等问题, 提出一种步步为营的反馈式学习方法, 该方法通过正、负约束实现对于目标模型和分类器的判别能力和容错能力提高的同时, 使更新带来的误差尽量小, 并证明了其收敛性. 通过实验表明, 对于同一种跟踪算法使用本文提出的目标更新方法进行更新学习的比不更新学习的跟踪效果要稳定得多, 对于目标的尺度变化、形变、旋转、视角变化、模糊等都有较好的适应性, 并通过与现有的较流行的方法进行比较, 本文方法鲁棒性较好, 有很高的研究和应用价值.
    Target detection and tracking technique is one of the hot subjects in image processing and computer vision fields, which has significant research value not only in military areas such as imaging guidance and military target tracking, but also for civil use such as security and monitoring and the intelligent man-machine interaction. In this paper, for target deformation, scale changing, rotation, and other issues in the long-term stable target tracking, a bootstrapping feedback learning algorithm is proposed, which may improve the target model and the classifier discriminating capacity as well as the fault tolerance ability; and it also makes fewer errors during the updating, and then the proof of convergence of the algorithm is given. Experimental results show that among the same tracking algorithms, utilization of the learning method to update the target model and classifier is more stable and more adaptable than unusing it in the processes of target scale changing, deformation, rotation, perspective changing and fuzzy. And compared with the existing conventional method, this method has a better robustness, and a high value in practical application and research.
    • 基金项目: 中国科学院航空光学成像与测量重点实验室开放基金(批准号: Y2HC1SR121)资助的课题.
    • Funds: Project supported by the Key Laboratory of Airborne Optical Imaging and Measurement, Chinese Academy of Sciences (Grant No. Y2HC1SR121).
    [1]

    Li T W, Shi A G, He S H 2009 Acta Phys. Sin. 58 794 (in Chinese) [李天伟, 石爱国, 何四华 2009 物理学报 58 794]

    [2]

    Guo G R, Wang H Q, Jiang B 2006 Acta Phys. Sin. 55 3985

    [3]

    Wang M W, Zhai H C, Gao L J 2009 Acta Phys. Sin. 58 1662 (in Chinese) [王明伟, 翟宏琛, 高丽娟 2009 物理学报 58 1662]

    [4]

    Zhang J S, Zhang Z T 2010 Chinese Phys. B 19 104601

    [5]

    Sun J F, Wang Q, Wang L 2010 Chinese Phys. B 19 104203

    [6]

    Chen G Y, Guo Z X, Zhang C P 2003 Chin. Phys. Lett. 20 2161

    [7]

    Wang L J, Jia S M, Wang S, Li Z X 2013 Opt. Precision Eng. 21 2364 (in Chinese) [王丽佳, 贾松敏, 王爽, 李秀智 2013 光学精密工程 21 2364]

    [8]

    Zhu Q P, Yan J, Zhang H 2013 Opt. Precision Eng. 21 437 (in Chinese) [朱秋平, 颜佳, 张虎 2013 光学精密工程 21 437]

    [9]

    Chen D C, Zhu M, Gao W, Sun H H, Yang W B 2014 Opt. Precision Eng. 22 1661 (in Chinese) [陈东成, 朱明, 高文, 孙宏海, 杨文波 2014 光学精密工程 22 1661]

    [10]

    Ma Y, Lv Q B, Liu Y Y, Qian L L, Pei L L 2013 Acta Phys. Sin. 62 204202 (in Chinese) [马原, 吕群波, 刘扬阳, 钱路路, 裴琳琳 2013 物理学报 62 204202]

    [11]

    Duarte M F, Baraniuk R G 2012 IEEE Trans. Image Proc. 21 494

    [12]

    Sun X Y, Chang F L 2013 Opt. Precision Eng. 21 3191 (in Chinese) [孙晓燕, 常发亮 2013 光学精密工程 21 3191]

    [13]

    Song S, Zhang B, Yin C L 2014 Opt. Precision Eng. 22 1037 (in Chinese) [宋策, 张葆, 尹传历 2014 光学精密工程 22 1037]

    [14]

    Grabner H, Bischof H 2006 CVPR 2

    [15]

    Avidan S 2007 PAMI 29 261

    [16]

    Collins R, Liu Y, 2005 PAMI 27 1631

    [17]

    Lim J, Ross D, Lin R, Yang M 2005 NIPS 2 7

    [18]

    Yu Q, Dinh T, Medioni G 2008 ECCV 3 6

    [19]

    Kalal Z, Matas J, Mikolajczyk K 2010 Conference on Computer Vision and Pattern Recognition, CVPR, San Francisco, CA, USA

    [20]

    Zhang T, Oles F J 2000 Proceedings of 17th International Conference on Machine Learning. Stanford 2000 p1191

    [21]

    Nigam K, McCallum A, Thrun S, Mitchell T 2000 Machine Learning 39 103

    [22]

    Blum A, Mitchell T 1998 COLT 1 2

    [23]

    Xu Q, Hu D H, Xue H 2009 BMC Bioinformatics 10 S47

    [24]

    Viola P, Jones M, Snow D 2005 International Journal of Computer Vision 63 153

    [25]

    Breiman L 2001 Machine Learning 45 5

    [26]

    Lepetit V, Fua P 2006 IEEE Trans. Pattern Analysis and Machine Intelligence 28 1465

    [27]

    Grabner H, Leistner C, Bischof H 2008 European Conf. on Computer Vision

    [28]

    Babenko B, Yang M H, Belongie S 2009 IEEE Conf. on Computer Vision and Pattern Recognition, Washington, DC 2009 p983

    [29]

    Yu Q, Dinh T B, Medioni G 2008 European Conf. on Computer Vision 2008

  • [1]

    Li T W, Shi A G, He S H 2009 Acta Phys. Sin. 58 794 (in Chinese) [李天伟, 石爱国, 何四华 2009 物理学报 58 794]

    [2]

    Guo G R, Wang H Q, Jiang B 2006 Acta Phys. Sin. 55 3985

    [3]

    Wang M W, Zhai H C, Gao L J 2009 Acta Phys. Sin. 58 1662 (in Chinese) [王明伟, 翟宏琛, 高丽娟 2009 物理学报 58 1662]

    [4]

    Zhang J S, Zhang Z T 2010 Chinese Phys. B 19 104601

    [5]

    Sun J F, Wang Q, Wang L 2010 Chinese Phys. B 19 104203

    [6]

    Chen G Y, Guo Z X, Zhang C P 2003 Chin. Phys. Lett. 20 2161

    [7]

    Wang L J, Jia S M, Wang S, Li Z X 2013 Opt. Precision Eng. 21 2364 (in Chinese) [王丽佳, 贾松敏, 王爽, 李秀智 2013 光学精密工程 21 2364]

    [8]

    Zhu Q P, Yan J, Zhang H 2013 Opt. Precision Eng. 21 437 (in Chinese) [朱秋平, 颜佳, 张虎 2013 光学精密工程 21 437]

    [9]

    Chen D C, Zhu M, Gao W, Sun H H, Yang W B 2014 Opt. Precision Eng. 22 1661 (in Chinese) [陈东成, 朱明, 高文, 孙宏海, 杨文波 2014 光学精密工程 22 1661]

    [10]

    Ma Y, Lv Q B, Liu Y Y, Qian L L, Pei L L 2013 Acta Phys. Sin. 62 204202 (in Chinese) [马原, 吕群波, 刘扬阳, 钱路路, 裴琳琳 2013 物理学报 62 204202]

    [11]

    Duarte M F, Baraniuk R G 2012 IEEE Trans. Image Proc. 21 494

    [12]

    Sun X Y, Chang F L 2013 Opt. Precision Eng. 21 3191 (in Chinese) [孙晓燕, 常发亮 2013 光学精密工程 21 3191]

    [13]

    Song S, Zhang B, Yin C L 2014 Opt. Precision Eng. 22 1037 (in Chinese) [宋策, 张葆, 尹传历 2014 光学精密工程 22 1037]

    [14]

    Grabner H, Bischof H 2006 CVPR 2

    [15]

    Avidan S 2007 PAMI 29 261

    [16]

    Collins R, Liu Y, 2005 PAMI 27 1631

    [17]

    Lim J, Ross D, Lin R, Yang M 2005 NIPS 2 7

    [18]

    Yu Q, Dinh T, Medioni G 2008 ECCV 3 6

    [19]

    Kalal Z, Matas J, Mikolajczyk K 2010 Conference on Computer Vision and Pattern Recognition, CVPR, San Francisco, CA, USA

    [20]

    Zhang T, Oles F J 2000 Proceedings of 17th International Conference on Machine Learning. Stanford 2000 p1191

    [21]

    Nigam K, McCallum A, Thrun S, Mitchell T 2000 Machine Learning 39 103

    [22]

    Blum A, Mitchell T 1998 COLT 1 2

    [23]

    Xu Q, Hu D H, Xue H 2009 BMC Bioinformatics 10 S47

    [24]

    Viola P, Jones M, Snow D 2005 International Journal of Computer Vision 63 153

    [25]

    Breiman L 2001 Machine Learning 45 5

    [26]

    Lepetit V, Fua P 2006 IEEE Trans. Pattern Analysis and Machine Intelligence 28 1465

    [27]

    Grabner H, Leistner C, Bischof H 2008 European Conf. on Computer Vision

    [28]

    Babenko B, Yang M H, Belongie S 2009 IEEE Conf. on Computer Vision and Pattern Recognition, Washington, DC 2009 p983

    [29]

    Yu Q, Dinh T B, Medioni G 2008 European Conf. on Computer Vision 2008

  • [1] 段磊, 徐润亲, 宋云波, 谭姝丹, 梁成斌, 徐帆江, 刘朝晖. 基于目标反射回光对高功率光纤激光器影响的理论模型和数值研究. 物理学报, 2023, 72(10): 104203. doi: 10.7498/aps.72.20222464
    [2] 黄志伟, 杨宏宇, 翟峰, 陆肖励, 卢军强, 吴健. 非监督学习高维多体波函数矢量轨迹所在低维子空间. 物理学报, 2021, 70(24): 247101. doi: 10.7498/aps.70.20210697
    [3] 雷波, 何兆阳, 张瑞. 基于迁移学习的水下目标定位方法仿真研究. 物理学报, 2021, 70(22): 224302. doi: 10.7498/aps.70.20210277
    [4] 张文杰, 王世元, 冯亚丽, 冯久超. 基于Huber的高阶容积卡尔曼跟踪算法. 物理学报, 2016, 65(8): 088401. doi: 10.7498/aps.65.088401
    [5] 陈典兵, 朱明, 高文, 王慧利, 杨航. 基于残差矩阵估计的稀疏表示目标跟踪算法. 物理学报, 2016, 65(19): 194201. doi: 10.7498/aps.65.194201
    [6] 马鸽, 胡跃明, 高红霞, 李致富, 郭琪伟. 基于物理总能量目标函数的稀疏重建模型. 物理学报, 2015, 64(20): 204202. doi: 10.7498/aps.64.204202
    [7] 吴昊, 陈树新, 杨宾峰, 陈坤. 基于广义M估计的鲁棒容积卡尔曼滤波目标跟踪算法. 物理学报, 2015, 64(21): 218401. doi: 10.7498/aps.64.218401
    [8] 逯志宇, 王大鸣, 王建辉, 王跃. 基于时频差的正交容积卡尔曼滤波跟踪算法. 物理学报, 2015, 64(15): 150502. doi: 10.7498/aps.64.150502
    [9] 陈涵瀛, 高璞珍, 谭思超, 付学宽. 自然循环流动不稳定性的多目标优化极限学习机预测方法. 物理学报, 2014, 63(20): 200505. doi: 10.7498/aps.63.200505
    [10] 王燕, 邹男, 付进, 梁国龙. 基于倒谱分析的单水听器目标运动参数估计. 物理学报, 2014, 63(3): 034302. doi: 10.7498/aps.63.034302
    [11] 杨立学, 陈克安, 张冰瑞, 梁雍. 基于不相似度评价的水下声目标分类与听觉特征辨识. 物理学报, 2014, 63(13): 134304. doi: 10.7498/aps.63.134304
    [12] 王保宪, 赵保军, 唐林波, 王水根, 吴京辉. 基于双向稀疏表示的鲁棒目标跟踪算法. 物理学报, 2014, 63(23): 234201. doi: 10.7498/aps.63.234201
    [13] 高文, 汤洋, 朱明. 复杂背景下目标检测的级联分类器算法研究. 物理学报, 2014, 63(9): 094204. doi: 10.7498/aps.63.094204
    [14] 于文英, 安里千. 锥柱复合目标激光距离多普勒像分析模型. 物理学报, 2012, 61(21): 218703. doi: 10.7498/aps.61.218703
    [15] 刘辉, 杨俊安, 王一. 基于流形学习的声目标特征提取方法研究. 物理学报, 2011, 60(7): 074302. doi: 10.7498/aps.60.074302
    [16] 王娜, 陈克安. 水下噪声音色属性回归模型及其在目标识别中的应用. 物理学报, 2010, 59(4): 2873-2881. doi: 10.7498/aps.59.2873
    [17] 朱樟明, 万达经, 杨银堂. 一种基于多目标约束的互连线宽和线间距优化模型. 物理学报, 2010, 59(7): 4837-4842. doi: 10.7498/aps.59.4837
    [18] 余赟, 惠俊英, 陈阳, 孙国仓, 滕超. 浅海低频声场中目标深度分类方法研究. 物理学报, 2009, 58(9): 6335-6343. doi: 10.7498/aps.58.6335
    [19] 窦春霞, 张淑清. 基于观测器的模型不确定的耦合时空混沌H∞跟踪控制. 物理学报, 2004, 53(12): 4120-4125. doi: 10.7498/aps.53.4120
    [20] 申金媛, 刘, 常胜江, 贾 佳, 张文伟, 张延, 母国光. 基于径向基函数的多目标旋转不变分类及其光电实现. 物理学报, 1998, 47(12): 1968-1975. doi: 10.7498/aps.47.1968
计量
  • 文章访问数:  5152
  • PDF下载量:  678
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-04-17
  • 修回日期:  2014-05-19
  • 刊出日期:  2015-01-05

/

返回文章
返回