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.
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.
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.
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.
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.
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.
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.