基于联合条件随机场的移动机器人多目标跟踪

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1923 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
罗荣华, 闵华清, 林盛锋. 基于联合条件随机场的移动机器人多目标跟踪[J]. 机器人, 2011, 33(3): 279-286.. LUO Ronghua, MIN Huaqing, LIN Shengfeng. Joint Conditional Random Fields for Multi-object Tracking with a Mobile Robot. ROBOT, 2011, 33(3): 279-286..

摘要通过将目标与观测数据之间的数据关联抽象为标记序列，为移动机器人的多目标跟踪提出了一种具有多层次结构的联合条件随机场（joint conditional random field，JCRF）．JCRF包括联合数据关联和运动目标状态估计两层随机场，不仅在联合数据关联中可以融合目标的形状信息和运动信息以提高目标跟踪的稳定性，而且可以同时进行目标检测与目标跟踪．利用JCRF模型，对基于激光距离传感器的多目标跟踪进行了研究，通过从激光距离传感器信息中分割出候选目标区域，采用匹配树降低标记序列的状态空间．在移动机器人平台上进行实验，结果表明，基于JCRF的多目标跟踪具有良好的精度、稳定性和实时性．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	罗荣华
	闵华清
	林盛锋

关键词 ：条件随机场, 目标跟踪, 目标检测, 信息融合

Abstract：A novel joint conditional random field(JCRF)with hierarchical structure is proposed for multi-object tracking of mobile robots by abstracting the data association between objects and observed data to be a sequence of labels.JCRF include two layers of random fields,one for joint data association and the other for moving object state estimation.With JCRF,shape information and motion information can be fused for joint data association to improve the stability of object tracking,and moving object detection and object tracking can be performed simultaneously.In this paper,multi-object tracking based on laser range finder is studied using JCRF in which candidate regions of object are segmented out from laser range sensor data firstly and then the match tree is adopted to reduce the state space of label sequence.Experimental results on the mobile robot show that the multi-object tracking based on JCRF can run precisely and stably in real time.

Key words： conditional random field(CRF) object tracking object detection information fusion

收稿日期: 2010-06-02 录用日期: 2011-02-15

TP242.6

基金资助:国家自然科学基金资助项目（61005061，60873078）；中央高校基本科研业务费资助项目（2009ZM0123）

通讯作者: 罗荣华 E-mail: rhluo@scut.edu.cn

作者简介: 罗荣华（1975- ），男，博士，副教授．研究领域：智能机器人，机器人自主导航，机器人视觉．
闵华清（1956- ），男，教授，博士生导师．研究领域：智能软件系统，智能机器人．林盛锋（1983- ），男，硕士生．研究领域：智能机器人，感知信息处理．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2011/V33/I3/279

[1] 钱堃,马旭东,戴先中,等.同时机器人定位与人体跟踪的多源感知协作粒子滤波方法[J].机器人,2008,30(6):491-497.Qian K,Ma X D,Dai X Z,et al.Multisensor collaborative panicle filters for simultaneous robot localization and peopletracking[J].Robot,2008,30(6):491-497.
[2] Hue C,Le Cadre J P,Perez P.Tracking multiple objects with particle filtering[J].IEEE Transactions on Aerospace and Electronic Systems,2002,38(3):791-812.

[3] 李少军,王宏,柴天佑.基于t-分布粒子滤波器的目标跟踪[J].机器人,2006,28(6):598-604.Li S J,Wang H,Chai T Y.A t-distribution-based particle filter for target tracking[J].Robot,2006,28(6):598-604.
[4] Cox I J,Hingorani S L.An efficient implementation of Reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(2):138-150.

[5] Cox I J.A review of statistical data association techniques for motion correspondence[J].International Journal of Computer Vision,1993,10(1):53-66.

[6] Kluge B,Kohler C,Prassler E.Fast and robust tracking of multiple moving objects with a laser range finder[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2001:1683-1688.
[7] Glas D F,Miyashita T,Ishiguro H,et al.Laser tracking of human body motion using adaptive shape modeling[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,2007:602-608.
[8] Rebai K,Benabderrahmane A,Azouaoui O,et al.Moving obstacles detection and tracking with laser range finder[C]//International Conference on Advanced Robotics.Piscataway,NJ,USA:IEEE,2009:1-6.
[9] Arras K O,Grzonka S,Luber M,et al.Efficient people tracking in laser range data using a multi-hypothesis leg-tracker with adaptive occlusion probabilities[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2008:1710-1715.
[10] Schluz D,Burgard W,Fox D,et al.People tracking with mobile robots using sample-based joint probabilisric data association filters[J].International Journal of Robotics Research,2003,22(2):99-116.

[11] Luo R H,Min H Q.Hybrid conditional random fields for multiobject tracking with a mobile robot[C]//IEEE International Conference on Information and Automation.Piscataway,NJ,USA:IEEE,2010:391-396.
[12] Lafferty J,McCallum A,Pereira F C N.Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]//International Conference on Machine Learning.New York,USA:ACM,2001:282-289.
[13] Sarawagi S,Cohen W W.Semi-Markov conditional random fields for information extraction[C]//Advances in Neural Information Processing Systems.Cambridge,MA,USA:MIT Press,2005:1185-1192.
[14] Wang Y,Loe K F,Wu J K.A dynamic conditional random field model for foreground and shadow segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(2):279-289.

[15] Wang Y,Mori G.Max-margin hidden conditional random fields for human action recognition[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ,USA:IEEE,2009:872-879.
[16] Limketkai B,Fox D,Liao L.CRF-filters:Discriminative particle filters for sequential state estimation[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2007:3142-3147.
[17] Hess R,Fern A.Discriminatively trained particle filters for complex multi-object tracking[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ,USA:IEEE,2009:240-247.
[18] Taycher L,Demirdjian D,Darrell T,et al.Conditional random people:Tracking humans with CRFs and grid filters[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,vol.l.Piscataway,NJ,USA:IEEE,2006:222-229.
[19] Sutton C,McCallum A.Piecewise pseudolikelihood for efficient training of conditional random fields[C]//International Conference on Machine Learning.New York,NY,USA:ACM,2007:863-870.