[1] Yang Biao, Lin Guoyu, Zhang Weigong,. Adaptive topology learning of camera networkacross non-overlapping views [J]. Journal of Southeast University (English Edition), 2015, 31 (1): 61-66. [doi:10.3969/j.issn.1003-7985.2015.01.011]

Copy

Adaptive topology learning of camera networkacross non-overlapping views()

无重叠视域摄像机网络拓扑自适应学习方法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

31

Issue:

2015 1

Page:

61-66

Research Field:

Computer Science and Engineering

Publishing date:

2015-03-30

Info

Title:

Adaptive topology learning of camera networkacross non-overlapping views

无重叠视域摄像机网络拓扑自适应学习方法

Author(s):

Yang Biao¹;  Lin Guoyu²;  Zhang Weigong²

¹Faculty of Information Science and Engineering, Changzhou University, Changzhou 213164, China
²School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China

杨彪¹;  林国余²;  张为公²

¹常州大学信息科学与工程学院, 常州 213164; ²东南大学仪器科学与工程学院, 南京 210096

Keywords:

non-overlapping views;  mutual information;  Gaussian mixture model;  adaptive topology learning;  cross-correlation function

无重叠视域;  交互信息;  混合高斯模型;  自适应拓扑学习;  互关联函数

PACS:

TP391

DOI:

10.3969/j.issn.1003-7985.2015.01.011

Abstract:

An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.

提出一种自适应拓扑学习方法来无监督地学习摄像机网络的拓扑.利用混合高斯算法建立节点模型, 并通过计算节点对的互关联函数得到该对节点的连通性以及连通节点对的转移时间分布.利用交互信息计算连通的节点对的转移概率.对学习到的拓扑结构, 提出虚假连接排除策略以及拓扑更新策略对其进行优化.为了测试所提出算法的有效性, 搭建了由5个不包含重叠视域的摄像机组成的监控系统进行试验.通过与已有算法的对比, 结果表明该算法可以更准确地学习监控网络的拓扑, 并对环境变化有一定的鲁棒性.

References:

[1] Javed O, Rasheed Z, Shafique K, et al. Tracking across multiple cameras with disjoint views [C]//Proceedings of the Ninth IEEE International Conference on Computer Vision. Nice, France, 2003: 952-957.
[2] Javed O, Shafique K, Shah M. Appearance modeling for tracking in multiple non-overlapping cameras [C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA, 2005: 26-33.
[3] Makris D, Ellis T, Black J. Bridging the gaps between cameras [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC, USA, 2004: 205-210.
[4] Niu C, Grimson E. Recovering non-overlapping network topology using far-field vehicle tracking data [C]//Proceedings of International Conference on Pattern Recognition. Hong Kong, China, 2006: 944-949.
[5] Center for Research in Intelligent Systems. Continuous learning of a multilayered network topology in a video camera network[R]. Berkeley, CA, USA: University of California at Berkeley, 2009.
[6] Nam Y Y, Ryu J H, Choi Y J, et al. Learning spatio-temporal topology of a multi-camera network by tracking multiple people[J]. International Journal of Computer, Information, Systems and Control Engineering, 2007, 6(1): 1523-1528.
[7] Piccardi M, Cheng E D. Tracking matching over disjoint camera views based on an incremental major color spectrum histogram [C]//IEEE Conference on Advanced Video and Signal Based Surveillance. Como, Italy, 2005: 147-152.
[8] Alahi A, Vandergheynst P, Bierlaire M, et al. Cascade of descriptors to detect and track objects across any network of cameras[J]. Computer Vision and Image Understanding, 2010, 114(6): 624-640.
[9] Zhao R, Ouyang W L, Wang X G. Unsupervised salience learning for person re-identification [C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA, 2013: 3586-3593.
[10] Viola P, Wells W M III. Alignment by maximization of mutual information[J]. International Journal of Computer Vision, 1997, 24(2): 137-154.
[11] Liu S H, Lai S M, Zhang M J. A min-cost flow based algorithm for objects association of multiple non-overlapping cameras[J]. ACAT Automatica Sinica, 2010, 36(10): 1484-1489.
[12] Exner D, Bruns E, Kurz D. Fast and robust CAMShift tracking [C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA, 2010: 9-16.

Memo

Memo:

Biography: Yang Biao(1987—), male, doctor, lecturer, yb6864171@126.com.
Foundation items: The National Natural Science Foundation of China(No. 60972001), the Science and Technology Plan of Suzhou City(No.SS201223).
Citation: Yang Biao, Lin Guoyu, Zhang Weigong. Adaptive topology learning of camera network across non-overlapping views[J].Journal of Southeast University(English Edition), 2015, 31(1):61-66.[doi:10.3969/j.issn.1003-7985.2015.01.011]

Common functions