基于子空间自适应学习的粒子滤波跟踪算法

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3526-3530.

基于子空间自适应学习的粒子滤波跟踪算法

吴桐¹,²,王玲¹,何凡²

1. 湖南大学电气与信息工程学院,长沙 410082
2. 中国洛阳电子装备试验中心,河南洛阳 471000

收稿日期:2014-06-11 修回日期:2014-08-11 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 吴桐
作者简介:吴桐(1987-),男,江苏如东人,助理工程师,硕士研究生, 主要研究方向:计算机视觉、机器学习；王玲(1962-),女,湖南长沙人,教授,博士生导师,博士,主要研究方向:计算机视觉、机器学习；何凡(1987-),男,安徽合肥人,助理工程师,主要研究方向:机器学习、电子对抗效能评估。

Particle filter tracking algorithm based on adaptive subspace learning

WU Tong¹,²,WANG Ling¹,HE Fan²

1. College of Electrical and Information Engineering, Hunan University, Changsha Hunan 410082, China
2. Luoyang Electronic Equipment Examination Center of China, Luoyang Henan 471003, China;

Received:2014-06-11 Revised:2014-08-11 Online:2014-12-01 Published:2014-12-31
Contact: WU Tong

摘要/Abstract

摘要：

为了提高目标外观迅速变化时视觉跟踪算法的鲁棒性,提出了一种基于自适应子空间学习的粒子滤波跟踪算法。在粒子滤波构架下,建立状态判决机制,根据判决结果并结合主成分分析(PCA)子空间与正交子空间的特点,选择合适的学习方法。这样既能准确、稳定地学习到目标的低维子空间,又能迅速地学习到目标外观变化的趋势。同时,加入鲁棒估计技术处理遮挡问题,避免了对目标状态估计的影响。实验结果表明,该算法在光照变化、姿态变化、遮挡的情况下,均具有较强的鲁棒性。

Abstract:

In order to improve the robustness of visual tracking algorithm when the target appearance changes rapidly, a particle filter tracking algorithm based on adaptive subspace learning was presented in this paper. In the particle filter framework, this paper established a state decision mechanism, chose the appropriate learning method by combining the verdict and the characteristics of the Principal Component Analysis (PCA) subspace and orthogonal subspace. It not only can accurately, stably learn target in low dimensional subspace, but also can quickly learn the change trend of the target appearance. For the occlusion problem, robust estimation techniques were added to avoid the impact of the target state estimation. The experimental results show that the algorithm has strong robustness in the case of illumination change, posture change, and occlusion.

中图分类号:

TP391

吴桐王玲何凡. 基于子空间自适应学习的粒子滤波跟踪算法[J]. 计算机应用, 2014, 34(12): 3526-3530.

WU Tong WANG Ling HE Fan. Particle filter tracking algorithm based on adaptive subspace learning[J]. Journal of Computer Applications, 2014, 34(12): 3526-3530.

参考文献

［1］CRUZ-MOTA J, BIERLAIRE M, THIRAN J. Sample and pixel weighting strategies for robust incremental visual tracking［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(5): 898-911.
［2］LIWICKI S, ZAFEIRIOU S, TZIMIROPOULOS G. Efficient online subspace learning with an indefinite kernel for visual tracking and recognition［J］. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(10):1624-1636.
［3］LI X, DICK A, SHEN C, et al. Incremental Learning of 3D-DCT compact representations for robust visual tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 34(4):863-881.
［4］WEI B, LI K, CAO C. Target tracking algorithm based on particle filter and learning with local and global consistency［J］. Journal of Computer Applications, 2013, 33(10): 2914-2917.(卫保国,李克靖,曹慈卓.基于粒子滤波与局部全局一致性学习的目标跟踪算法［J］.计算机应用,2013,33(10): 2914-2917.)
［5］ROSS D, LIM J, LIN R S, et al. Incremental learning for robust visual tracking［J］. International Journal of Computer Vision, 2008, 77(1/2/3): 125-141.
［6］LIM J, ROSS D, LIN R S, et al. Incremental learning for visual tracking［C］// Advances in Neural Information Processing Systems. Vancouver: MIT Press, 2004: 793-800.
［7］LIN R S, ROSS D, LIM J, et al. Adaptive discriminative generative model and its applications［C］// Advances in Neural Information Processing Systems. Vancouver: MIT Press, 2004: 801-808.
［8］HO J, LEE K C, YANG M, et al. Visual tracking using learned linear subspaces［C］// Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2004: 782-789.
［9］YANG J, ZHANG D, FRANGI F, et al. Two dimensional PCA: a new approach to appearance based face representation and recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
［10］LI G, LIANG D, HUANG Q, et al. Object tracking using incremental 2D-LDA learning and Bayes inference［C］// Proceedings of the 15th IEEE International Conference on Image Processing. Piscataway: IEEE, 2008: 1568-1571.
［11］WEN J, LI J, GAO X. An adaptive object tracking algorithm combined with particle filter and tensor subspace［J］. Acta Photonica Sinica, 2010,39(6):1047-1050.(温静,李洁,高新波.一种结合粒子滤波和张量子空间的目标跟踪算法［J］.光子学报, 2010,39(6):1047-1050.)
［12］LI X, HU W, ZHANG Z, et al. Robust visual tracking based on incremental tensor subspace learning［C］// Proceedings of the 11th International Conference on Computer Vision. Piscataway: IEEE, 2007: 1-8.
［13］TONG X, ZHANG Y, YANG T. Robust object tracking based on adaptive and incremental subspace learning［J］. Acta Automatica Sinica, 2011,37(12):1483-1493.(仝小敏,张艳宁,杨涛.基于增量子空间自适应决策的目标跟踪［J］. 自动化学报,2011,37(12):1483-1493.)
［14］ZHANG H, ZHAO B. Visual tracking based on probabilistic PCA appearance model［J］. Systems Engineering and Electronics, 2009, 31(12): 2827-2829.(张辉,赵保军. 基于概率主成分分析表观模型的视觉跟踪［J］. 系统工程与电子技术,2009,31(12):2827-2829.)
［15］BIRCHFIELD S, RANGARAJAN S. Spatiograms versus histograms for region-based tracking［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005: 1158-1163.

[1]	吴军欧阳艾嘉张琳. 基于影响度的统计显著序列模式挖掘算法[J]. 计算机应用, 0, (): 0-0.
[2]	张璐方春祝铭. 基于Res2Net-YOLACT和融合特征的室内跌倒检测算法[J]. 计算机应用, 0, (): 0-0.
[3]	殷雨昌王洪元陈莉冯尊登肖宇. 基于单标注样本的多损失学习与联合度量视频行人重识别[J]. 计算机应用, 0, (): 0-0.
[4]	胡军许正康刘立钟福金张清华. 融合多粒度社区信息的网络嵌入方法[J]. 计算机应用, 0, (): 0-0.
[5]	李润泽孙雪姣. 基于时间条件提取序列的数据流偏好查询[J]. 计算机应用, 0, (): 0-0.
[6]	罗圣钦陈金怡李洪均. 基于注意力机制的多尺度残差UNet实现乳腺癌灶分割[J]. 计算机应用, 0, (): 0-0.
[7]	曹一珉蔡磊高敬阳. 基于生成对抗网络的基因数据生成方法[J]. 计算机应用, 0, (): 0-0.
[8]	陈冲闫珠赵继轩何为梁华庆. 基于集合经验模态分解和长短期记忆网络的催化裂化装置NOx排放预测[J]. 计算机应用, 0, (): 0-0.
[9]	徐光柱林文杰陈莎匡婉雷帮军周军. U-Net与自适应阈值脉冲耦合神经网络相结合的眼底血管分割方法[J]. 计算机应用, 0, (): 0-0.
[10]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[11]	李讷徐光柱雷帮军马国亮石勇涛. 交通道路行驶车辆车标识别算法[J]. 计算机应用, 0, (): 0-0.
[12]	孟杰王莉杨延杰廉飚. 基于多模态深度融合的虚假信息检测[J]. 计算机应用, 0, (): 0-0.
[13]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[14]	鲁永帅唐英杰马鑫然. 基于深度特征融合的无纺布低对比度浆丝缺陷检测方法[J]. 计算机应用, 0, (): 0-0.
[15]	王宇航周永霞吴良武. 基于高斯函数的池化算法[J]. 计算机应用, 0, (): 0-0.