Please wait a minute...
J4  2011, Vol. 45 Issue (12): 2240-2246    DOI: 10.3785/j.issn.1008-973X.2011.12.026
计算机技术﹑电信技术     
适用于目标跟踪的加权增量子空间学习算法
钱诚, 张三元
浙江大学 计算机科学与技术学院,浙江 杭州 310027
Weighted incremental subspace learning algorithm
suitable for object tracking
QIAN Cheng, ZHANG San-yuan
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要:

为了克服目标物外观变化给跟踪造成的困难,提出一种基于加权增量子空间学习的目标跟踪算法.该算法构造了一个可在线更新的子空间作为视频中目标物的外观模型,根据概率转移模型预测得到一组图像样本作为目标物在当前帧中可能出现的图像区域;然后将图像样本投影到该低维子空间中估计每个图像样本为目标图像区域的似然度,以具有最高似然度的样本作为目标在当前帧中的图像区域,通过加权增量的方式调整子空间.实验结果表明:相比基于其他增量子空间学习的跟踪算法,该算法能够稳定、准确地对运动目标进行跟踪.

Abstract:

An object tracking method based on weighted incremental subspace learning was proposed to overcome the difficulty in object tracking resulting from variations in appearance. The method constructs a subspace updated online to depict the appearance of the object in the video. A set of image patches are predicted based on probabilistic transformation model as candidate image regions of the object in the current frame, then these image patches are projected onto the low-dimensional subspace, and the likelihood of each image patch as the image region of the object is evaluated. The image patch with maximal likelihood is regarded as the object image region. Finally, the subspace is updated incrementally with temporal weights. Experimental results show that the method accomplishes object tracking more steadily and accurately, compared with other incremental subspace learning based object tracking methods.

出版日期: 2011-12-01
:  TP 391.41  
基金资助:

国家“973”重点基础研究发展规划资助项目(2009CB320804);省部产学研资助项目(2011B090400546).

通讯作者: 钱诚(1981—),男,博士生,从事视频图像处理研究.E-mail: qc_hz@163.com     E-mail: syzhang@zju.edu.cn
作者简介: 钱诚(1981—),男,博士生,从事视频图像处理研究.E-mail: qc_hz@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

钱诚, 张三元. 适用于目标跟踪的加权增量子空间学习算法[J]. J4, 2011, 45(12): 2240-2246.

QIAN Cheng, ZHANG San-yuan. Weighted incremental subspace learning algorithm
suitable for object tracking. J4, 2011, 45(12): 2240-2246.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.12.026        https://www.zjujournals.com/eng/CN/Y2011/V45/I12/2240

[1] DORIN C, VISVANATHAN R, PETER M. Kernelbased object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.
[2] HANZI W, DAVID S, KONRAD S, et al. Adaptive object tracking based on an effective appearance filter [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(9): 1661-1667.
[3] ZHOU H, YUAN Y, ZHANG Y, et al. Nonrigid object tracking in complex scenes [J]. Pattern Recognition Letters, 2009, 30(2): 98-102.
[4] 袁广林,薛模根,谢恺,等.基于核函数粒子滤波和多特征自适应融合的目标跟踪[J].计算机辅助设计与图形学学报,2009,21(12): 1774-1784.
YUAN Guanglin, XUE Mogen, XIE Kai, et al. Kernelbased particle filter for target tracking with adaptive multiple feature fusion [J]. Journal of ComputerAided Design and Computer Graphics, 2009, 21(12): 1774-1784.
[5] 王震宇,张可黛,吴毅,等.基于SVM和Adaboost的红外目标跟踪[J].中国图象图形学报,2007,12(11): 2052-2057.
WANG Zhenyu, ZHANG Kedai, WU Yi. Target tracking in infrared image sequences by combining SVM and Adaboost [J]. Journal of Image and Graphics, 2007, 12(11): 2052-2057.
[6] ROBERT T C, LIU Y, MARIUS L. Online selection of discriminative tracking features [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643.
[7] LI Y. On incremental and robust subspace learning [J]. Pattern Recognition, 2004, 37(7): 1509-1518.
[8] MICHAEL J B, ALLAN D J. EigenTracking: robust matching and tracking of articulated object using a viewbased representation [J]. International Journal of Computer Vision, 1998, 26(1): 63-84.
[9] LEVY A, LINEDENBAUM M. Sequential karhunenloeve basis extraction and its application to images [J]. IEEE Transactions on Image Processing, 2000, 9(8): 1371-1374.
[10] DANIJEL S, ALES L. Incremental and robust learning of subspace representations [J]. Image and Vision Computing, 2008, 26(1): 27-38.
[11] HO J, LEE K, YANG M, et al. Visual tracking using learned linear subspace [C] ∥Proceedings of 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE, 2004: 782-789.
[12] DAVID A R, LIM J, LIN R, et al. Incremental learning for robust visual tracking [J]. International Journal of Computer Vision, 2008, 77(1): 125-141.

[1] 杨玉婷, 史玉回, 夏顺仁. 基于讨论机制的头脑风暴优化算法[J]. J4, 2013, 47(10): 1705-1711.
[2] 朱晓恩, 郝欣, 夏顺仁. 基于Levy flight的特征选择算法[J]. J4, 2013, 47(4): 638-643.
[3] 孙创日,甄帅,夏顺仁. 基于吸引区域的多模态脑磁共振图像仿射配准[J]. J4, 2012, 46(9): 1722-1728.
[4] 谢迪, 童若锋, 唐敏, 冯阳. 具有高区分度的视频火焰检测方法[J]. J4, 2012, 46(4): 698-704.
[5] 李启雷, 金文光, 耿卫东. 基于无线惯性传感器的人体动作捕获方法[J]. J4, 2012, 46(2): 280-285.
[6] 戴渊明, 韦巍, 林亦宁. 基于颜色纹理特征的均值漂移目标跟踪算法[J]. J4, 2012, 46(2): 212-217.
[7] 刘晨彬,潘颖,张海石,黄峰平,夏顺仁. 基于磁共振图像的脑瘤MGMT表达状况检测算法[J]. J4, 2012, 46(1): 170-176.
[8] 曹颖, 郝欣, 朱晓恩, 夏顺仁. 基于自动随机游走的乳腺肿块分割算法[J]. J4, 2011, 45(10): 1753-1760.
[9] 吕谷来, 李建平, 李锵, 俞利兴, 朱松明, 楼建忠, 袁祎琳. 基于机器视觉的砧木定位识别方法[J]. J4, 2011, 45(10): 1766-1770.
[10] 赖小波,朱世强. 基于互相关信息的非参数变换立体匹配算法[J]. J4, 2011, 45(9): 1636-1642.
[11] 刘建明, 鲁东明, 葛蓉. 基于全局优化的图像修复及其在GPU上实现[J]. J4, 2011, 45(2): 247-252.
[12] 王金德, 寿黎但, 李晓燕, 陈刚. 基于多重分割捆绑特征的目标图像检索[J]. J4, 2011, 45(2): 259-266.
[13] 战江涛,刘强,柴春雷. 基于三维模型与Gabor小波的人脸特征点跟踪方法[J]. J4, 2011, 45(1): 30-36.
[14] 梁文锋,项志宇. 鲁棒的PTZ摄像机目标跟踪算法[J]. J4, 2011, 45(1): 59-63.
[15] 宋坤坡, 夏顺仁, 徐清. 考虑小波系数相关性的超声图像降噪算法[J]. J4, 2010, 44(11): 2203-2208.