视觉传感网络分布式在线数据关联

刘莉; 万九卿

doi:10.3724/SP.J.1004.2014.00117

视觉传感网络分布式在线数据关联

doi: 10.3724/SP.J.1004.2014.00117 cstr: 32138.14.SP.J.1004.2014.00117

刘莉,
万九卿

1.
北京航空航天大学自动化科学与电气工程学院北京 100191

基金项目:

国家自然科学基金（61174020）;北京市自然科学基金（4113072）资助

详细信息

作者简介:
刘莉北京航空航天大学自动化科学与电气工程学院硕士研究生. 主要研究方向为数字图像处理和目标跟踪.E-mail：liulizi123@sina.com

计量
- 文章访问数: 1547
- HTML全文浏览量: 113
- PDF下载量: 825
- 被引次数: 0
出版历程
- 收稿日期: 2012-08-15
- 修回日期: 2013-01-11
- 刊出日期: 2014-01-20

Distributed Online Data Association in Visual Sensor Networks

1.
School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191

Funds:

Supported by National Natural Science Foundation of China (61174020), Natural Science Foundation of Beijing (4113072)

摘要

摘要: 数据关联是视觉传感网络监控系统的基本问题之一. 本文针对无重叠视域视觉监控网络的多目标跟踪问题提出一种基于多外观模型的视觉传感网络在线分布式数据关联方法，将同一目标在不同摄像机节点上的外观用不同的高斯模型描述，由分布式推理算法综合利用外观与时空观测计算关联变量的后验概率，同时通过近似最大似然估计算法对各传感节点上的外观模型参数进行在线估计. 实验结果表明了所提方法的有效性.
- 视觉传感网络 /
- 数据关联 /
- 分布式在线推理 /
- 极大似然估计 /
- 多模型
Abstract: One of the fundamental requirements for visual surveillance with smart camera networks is the correct association of camera's observations. In this paper, we present a distributed online approach based on multiple appearance models for multi-object tracking with distributed non-overlapping cameras. Firstly, we use multiple Gaussian models to describe each object's appearances under different camera nodes. Secondly, we develop a novel distributed online framework, in which the posterior margins of association variables are calculated using appearance and spatio-temporal information by a distributed inference algorithm, and the model parameters are updated online on each camera by approximate maximum likelihood estimation. Experimental results show the validity of the proposed method.
- Smart camera networks /
- data association /
- online distributed inference /
- maximum likelihood estimation /
- multiple models

HTML全文

参考文献(18)

[1]	Gilbert A, Bowden R. Tracking objects across cameras by incrementally learning inter-camera colour calibration and patterns of activity. In: Proceedings of the 9th European Conference on Computer Vision. Berlin, Heidelberg: Springer-Verlag, 2006. 125-136
[2]	Javed O, Shafique K, Rasheed Z, Shah M. Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views. Computer Vision and Image Understanding, 2008, 109(2): 146-162
[3]	Kuo C H, Huang C, Nevatia R. Inter-camera association of multi-target tracks by on-line learned appearance affinity models. In: Proceedings of the 11th European Conference on Computer Vision. Berlin, Heidelberg: Springer-Verlag, 2010. 383-396
[4]	Song B, Roy-Chowdhury A K. Robust tracking in a camera network: a multi-objective optimization framework. IEEE Journal of Selected Topics in Signal Processing, 2008, 2(4): 582-596
[5]	Liu Shao-Hua, Lai Shi-Ming, Zhang Mao-Jun. A min-cost flow based algorithm for objects association of multiple non-overlapping cameras. Acta Automatica Sinica, 2010, 36(10): 1484-1489(刘少华, 赖世铭, 张茂军. 基于最小费用流模型的无重叠视域多摄像机目标关联算法. 自动化学报, 2010, 36(10): 1484-1489)
[6]	Zajdel W, Klöse B J A. A sequential Bayesian algorithm for surveillance with nonoverlapping cameras. International Journal of Pattern Recognition and Artificial Intelligence, 2005, 19(8): 977-996
[7]	Zajdel W. Bayesian Visual Surveillance: from Object Detection to Distributed Cameras[Ph.D. dissertation], University of Amsterdam, Amsterdam, 2006
[8]	Wan Jiu-Qing, Liu Qing-Yun. Data association in visual sensor networks based on high-order spatio-temporal model. Acta Automatica Sinica, 2012, 38(2): 236-247(万九卿, 刘青云. 基于高阶时空模型的视觉传感网络数据关联方法. 自动化学报, 2012, 38(2): 236-247)
[9]	Rinner B, Wolf W. A bright future for distributed smart cameras. Proceedings of the IEEE, 2008, 96(10): 1562-1564
[10]	Mensink T, Zajdel W, Krose B. Distributed EM learning for appearance based multi-camera tracking. In: Proceedings of the 1st ACM/IEEE International Conference on Distributed Smart Cameras. Vienna, Austria: IEEE, 2007. 178-185
[11]	Nowak R D. Distributed EM algorithms for density estimation and clustering in sensor networks. IEEE Transactions on Signal Processing, 2003, 51(8): 2245-2253
[12]	Dimakis A G, Kar S, Mouraand J F. Gossip algorithms for distributed signal processing. Proceedings of the IEEE, 2010, 98(11): 1847-1864
[13]	Gu D B. Distributed EM algorithm for Gaussian mixtures in sensor networks. IEEE Transactions on Neural Networks, 2008, 19(7): 1154-1166
[14]	Saul L K, Weiss Y, Bottou L. Advances in Neural Information Processing Systems Vol.17. Cambridge: The MIT Press, 2005. 713-720
[15]	Olfati-Saber R, Shamma J S. Consensus filters for sensor networks and distributed sensor fusion. In: Proceedings of the 44th IEEE Conference on Decision Control. Seville, Spain: IEEE, 2005. 6698-6703
[16]	Wan J Q, Liu Q Y. Distributed data association in smart camera networks. In: Proceedings of the 5th ACM/IEEE International Conference on Distributed Smart Cameras. Ghent, Belgium: IEEE, 2011. 1-8
[17]	Morral G, Bianchi P, Jakubowicz J. On-line Gossip-based distributed expectation maximization algorithm. In: Proceedings of the 20th IEEE Statistical Signal Processing Workshop. Wisconsin, USA: IEEE, 2012. 305-308
[18]	Jepson A D, Fleet D J, El-Maraghi T F. Robust online appearance models for visual tracking. In: Proceedings of the 2001 IEEE Conference on Computer Vision and Pattern Recognition. Kauai, Hawaii, USA: IEEE, 2001. 415-422