Multimedia Laboratory

Projects / Camera Network

Camera network aims at generating useful information from multi-camera videos. Because visual surveillance systems collect a huge amount of video data from many different scenes, it is very important to collect and combine information from different sources together.

Our recent works based on multiple cameras include person re-identification and activity analysis.

Intelligent Multi-Camera Video Surveillance: A Review
Xiaogang Wang. Pattern Recognition Letters, Vol. 34, pp. 3-19, 2013.
PDF

Correspondence‐Free Activity Analysis and Scene Modeling in Multiple Camera Views
X. Wang, K. Tieu, and E. Grimson. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 32, pp. 56-71, 2010.
PDF

Incremental Activity Modelling in Multiple Disjoint Cameras
C. C. Loy, T. Xiang, and S. Gong. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 34, pp. 1799-1813, 2012.
PDF

Comparing Visual Feature Coding for Learning Disjoint Camera Dependencies
X. Zhu, S. Gong, and C. C. Loy. In Proceedings of British Machine Vision Conference (BMVC), 2012.
PDF

Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding
C. C. Loy, T. Xiang, and S. Gong. International Journal of Computer Vision (IJCV), Vol. 90, pp. 106-129, 2012.
PDF

Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
C. C. Loy, T. Xiang, and S. Gong. In Proceedings of International Conference on Computer Vision (ICCV, Oral), pp. 120-127, 2009.
PDF

Multi-Camera Activity Correlation Analysis
C. C. Loy, T. Xiang, and S. Gong. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR, Oral), pp. 1988-1995, 2009.
PDF


Back to Top

Share This Page

© 2013 Multimedia Laboratory

The Chinese University of Hong Kong 香港中文大学

Site Credits