Distributed camera networks for biometrics and surveillance

We investigate problems related to the use of distributed camera networks in urban surveillance applications. Typically, when camera networks are used for surveillance raw data captured by cameras is transferred over a network to a central processing unit where computer vision algorithms are used to process the data and identify events of interest. In this project we use embedded smart cameras that combine local processing, in-network collaboration and centralized processing thereby decreasing communication load, providing real time analysis, improving robustness and increasing system coverage.

We are working on the following projects related to distributed camera networks:

1. Fast, localized algorithms for coverage optimization in large scale camera networks

2. Distributed camera networks for robust, real-time human recognition

3. Real-time human activity recognition using wireless camera networks

4. Development of Hawk-eye, a smart camera testbed for surveillance

Related publications

o B. Lemon, V. Kulathumani, “Local reconfiguration algorithms for simultaneous coverage and tracking using a large scale wireless camera network”, IEEE HST 2011

o S. Parupati, R. Bakkannagiri, S. Sankar and V. Kulathumani, “Collaborative acquisition of multi-view face images for real-time face recognition using a wireless camera network”, ICDSC 2011

o S. Ramagiri, R. Kavi and V. Kulathumani, “Real-time multi-view action recognition using a wireless camera network”, ICDSC 2011

o V. Kulathumani, S. Parupati, A. Ross and R. Jillela, "Collaborative face recognition using a network of embedded cameras”, Distributed Video Sensor Networks (DVSN), Editors: B. Bhanu, C.Ravishankar, A. Choudhary, D. Terzopoulos and H. Aghajan, Springer-Verlag, 2011

---

Student members

Bryan Lemon [Ph.D. student]

Rahul Kavi [Ph.D. student]