一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法

doi:10.3969/j.issn.0372-2112.2017.09.002

电子学报 ›› 2017, Vol. 45 ›› Issue (9): 2065-2070.DOI: 10.3969/j.issn.0372-2112.2017.09.002

一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法

王延江, 李蕙, 齐玉娟

中国石油大学(华东)信息与控制工程学院, 山东青岛 266580

收稿日期:2016-03-31 修回日期:2016-09-21 出版日期:2017-09-25
- 通讯作者:
- 齐玉娟
- 作者简介:
- 王延江,男,1966出生,山东海阳人,博士,教授,博士生导师,研究方向为智能信息处理与认知计算建模;李蕙,女,1986出生,山东淄博人,博士研究生,主要研究方向为计算机视觉、模式识别.
- 基金资助:
- 国家自然科学基金项目 (No.61271407，No.61402535，No.61671480）; 山东省自然科学基金项目 (No.ZR2013FQ015）

Robust Moving Object Tracking Method Inspired by the Mechanism of Human Brain Three-Stage Memory Model

WANG Yan-jiang, LI Hui, QI Yu-juan

College of Information and Control Engineering, China University of Petroleum, Qingdao, Shandong 266580, China

Received:2016-03-31 Revised:2016-09-21 Online:2017-09-25 Published:2017-09-25

摘要/Abstract

摘要： 目前大多数运动目标跟踪算法在目标姿态发生突变或目标被严重遮挡后会产生目标丢失现象，为解决此类问题，受人脑三阶段记忆信息处理机制的启发，本文提出一种三层旋转圆记忆模型（Spinning Tri-Layer-Circle Memory Modeling，STLC-MM）用于在目标跟踪过程中对目标模板进行更新.模型定义了三个旋转圆记忆空间用于存储和处理跟踪过程中用过的目标模板.三个圆记忆空间旋转时，记忆空间中的模板也随之以相同的速度旋转，同时模型通过模拟一些人类的认知行为，如，记忆、提取、遗忘等对模板进行更新.最后，为了验证所提方法有效性，本文将STLC-MM嵌入到粒子滤波目标跟踪框架进行目标跟踪实验.实验结果表明所提方法在目标姿态突变以及严重遮挡等方面具有较强的鲁棒性.

关键词: 人脑记忆模型, 三层圆旋转模型, 粒子滤波, 运动目标跟踪

Abstract: Most of the current object tracking algorithms will fail when sudden appearance changes and serious occlusions occur.Inspired by the mechanism of human brain three-stage memory model,this paper develops a spinning tri-layer-circle memory model(STLC-MM) and applies it for template updating during object tracking.Three memory spaces are defined to store and process the object templates used during tracking.With three circle memory spaces spinning,templates in the three memory spaces are updated by imitating the cognitive process of memorization,recall,and forgetting.Finally,in order to verify the effect of the proposed model,STLC-MM is incorporated into a particle filter (PF) framework.Experimental results show that the proposed method is more robust to sudden appearance changes and serious occlusions.

Key words: human brain memory modeling, spinning tri-layer-circle memory model, particle filters, moving object tracking

中图分类号:

TP391

王延江, 李蕙, 齐玉娟. 一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法[J]. 电子学报, 2017, 45(9): 2065-2070.

WANG Yan-jiang, LI Hui, QI Yu-juan. Robust Moving Object Tracking Method Inspired by the Mechanism of Human Brain Three-Stage Memory Model[J]. Acta Electronica Sinica, 2017, 45(9): 2065-2070.

参考文献

[1] Yilmaz A,Javed O.Object tracking:a survey[J].ACM Computing Surveys,2006,38(4):1-45.
[2] 常发亮,马丽,刘增晓,乔谊正.复杂环境下基于自适应粒子滤波器的目标跟踪[J].电子学报,2006,34(12):2150-2153. Chang Fa-liang,Ma Li,Liu Zeng-xiao,Qiao Yi-zheng.Target tracking based on adaptive particle filter under complex background[J].Acta Electronica Sinica,2006,34(12):2150-2153.(in Chinese)
[3] 张凯,单甘霖,等.基于姿态角辅助非线性滤波算法的机动目标跟踪[J].电子学报,2012,40(8):1670-1675. Zhang Kai,Shan Gan-lin,et al.Maneuvering targets tracking based on pose-aided nonlinear filter algorithm[J].Acta Electronica Sinica,2012,40(8):1670-1675.(in Chinese)
[4] Wang Y X,Chiew V.On the cognitive process of human problem solving[J].Cognitive Systems Research,2010,11(1):81-92.
[5] Wang Y X.Formal description of the cognitive process of memorization[A].Lecture Notes in Computer Science[C].Heidelberg:Springer Verlag,2009.81-98.
[6] Lin J H.A Theory for memory-based learning[J].Machine Learning,1994,17(2):143-167.
[7] Putze F,Schultz T.Cognitive memory modeling for interactive systems in dynamic environments[A].1st International Workshop on Spoken Dialog Systems[C].Kloster Irsee,Germany:IWSDS,2009.
[8] Dinerstein J,Egbert P K,Garis H,Dinerstein N.Fast and learnable behavioral and cognitive modeling for virtual character animation[J].Computer Animation and Virtual Worlds,2004,15(2):95-108.
[9] Yang Z,Fan Y,Zhang B,Cheng X.A computation memory model with human memory features for autonomous virtual humans[A].Proceedings of International Conference on Computer Application and System Modeling[C].Piscataway:IEEE Computer Society,2010.3246-3250.
[10] Ai D M,Ban X J,Zhang S J.Cognitive modeling of artificial fish learning and memory[A].Proceedings of the 12th International Symposium on Artificial Life and Robotics[C].United Kingdom:AROB,2007.280-283.
[11] Ho W C,Dautenhahn K,Lim M Y,Casse K D.Modeling human memory in robotic companions for personalization and long-term adaptation in HRI[A].Proceedings of the First Annual meeting of the Biologically Inspired Cognitive Architecture Society[C].Amsterdam:IOS Press,2010.64-71.
[12] Gnjatovi'c M,Janev M,Deli'c V.Focus tree:modeling attentional information in task-oriented human-machine interaction[J].Applied Intelligence,2012,37(3):305-320.
[13] Huang S,Sadek Adel W.A novel forecasting approach inspired by human memory:The example of short-term traffic volume forecasting[J].Transportation Research Part C:Emerging Technologies,2009,17(5):510-525.
[14] 齐玉娟,王延江,李永平.基于记忆的混合高斯背景建模[J].自动化学报,2010,36(11):1520-1526. Qi Yu-juan,Wang Yan-jiang,Li Yong-ping.Memory-based Gaussian mixture background modeling[J].Acta Automatica Sinica,2010,36(11):1520-1526.(in Chinese)
[15] Wang Y J,Qi Y J.Memory-based cognitive modeling for robust object extraction and tracking[J].Applied Intelligence,2013,39(1):614-629.
[16] Atkinson R C,Shiffrin R M.Human memory:A proposed system and its control processes[J].The Psychology of Learning and Motivation:Advances In Research and Theory,1968,2:89-195.
[17] Atkinson R C,Shiffrin R M.Mathematical models for memory and learning[R].Stanford,California:Institute for Mathematical Studies in the Social Sciences,Stanford University,1965.
[18] Birchfield S.Elliptical head tracking using intensity gradients and color histograms[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Los Alamitos:IEEE Computer Society,1998.232-237.

一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法

Robust Moving Object Tracking Method Inspired by the Mechanism of Human Brain Three-Stage Memory Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	奚畅, 蔡志明, 袁骏. 被动声纳粒子滤波检测前跟踪的检测门限设置方法[J]. 电子学报, 2022, 50(7): 1722-1734.
[2]	刘晓燕, 陈亮, 焦振航, 卢祥晨. 单基站DTMB信号约束的PDR运动参数修正[J]. 电子学报, 2022, 50(4): 860-868.
[3]	蒋林, 向超, 朱建阳, 刘奇. 加载语义似然估计的粒子滤波重定位[J]. 电子学报, 2021, 49(2): 306-314.
[4]	夏楠, 王珏, 李博. 基于粒子滤波和交互多模型的移动定位方法[J]. 电子学报, 2019, 47(1): 197-203.
[5]	陈志敏, 吴盘龙, 薄煜明, 田梦楚, 岳聪, 顾福飞. 基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法[J]. 电子学报, 2018, 46(4): 886-894.
[6]	范舜奕, 管桦, 侯志强, 余旺盛, 戴铂. 基于多表观特征子模型更新的鲁棒视觉跟踪[J]. 电子学报, 2018, 46(2): 440-446.
[7]	卢锦, 王鑫, 章为川. 基于代价参考粒子滤波的存在概率检测算法[J]. 电子学报, 2017, 45(6): 1498-1505.
[8]	刘龙, 樊波阳, 刘金星, 杨乐超. 面向运动目标检测的粒子滤波视觉注意力模型[J]. 电子学报, 2016, 44(9): 2235-2241.
[9]	吴昊, 孙晓燕, 郭玉堂, 刘路路, 沈晶. 保持粒子多样性的非退化粒子滤波方法研究[J]. 电子学报, 2016, 44(7): 1734-1741.
[10]	薛模根, 朱虹, 袁广林. 在线鲁棒判别式字典学习视觉跟踪[J]. 电子学报, 2016, 44(4): 838-845.
[11]	王伟, 余玉揆, 郝燕玲. 一种新型混合并行粒子滤波频率估计方法[J]. 电子学报, 2016, 44(3): 740-746.
[12]	张宏欣, 周穗华, 冯士民. 基于径向基-Galerkin解的反馈粒子滤波器[J]. 电子学报, 2016, 44(1): 95-100.
[13]	叶有时, 刘淑芬, 孙强, 刘鸿瑾, 刘波, 杨桦, 吴一帆. 改进粒子滤波算法在深空红外小目标跟踪中的应用[J]. 电子学报, 2015, 43(8): 1506-1512.
[14]	张玲霞, 刘志仓, 王辉, 齐会云, 胡旦. 非线性系统故障诊断的粒子滤波方法[J]. 电子学报, 2015, 43(3): 615-619.
[15]	於俊, 汪增福, 李睿. 一种同步人脸运动跟踪与表情识别算法[J]. 电子学报, 2015, 43(2): 371-376.