28 January 2013, h.15:00 - Sala 201 DEI/A
Localization and optimization problems for camera networks
Politecnico di Torino, Italy
In the framework of networked control systems, we focus on networks of autonomous PTZ cameras. A large set of cameras communicating each other through a network is a widely used architecture in application areas like video surveillance, tracking and motion. First, we consider relative localization in sensor networks, and we tackle the issue of orientation calibration. The aim is to propose distributed algorithms that, from noisy relative measurements, make the cameras complete the calibration task autonomously. We focus on the planar case, formulating an optimization problem over the manifold SO(2). We propose synchronous deterministic and distributed algorithms that calibrate planar networks exploiting the cycle structure of the underlying communication graph. Performance analysis and numerical experiments are shown. Second, we propose a gossip-like randomized calibration algorithm, whose probabilistic convergence and numerical studies are provided. Third and finally, we design surveillance trajectories for a network of calibrated autonomous cameras to detect intruders in an environment, through a continuous graph partitioning problem.
Domenica Borra is a Ph.D. student in Mathematics for Engineering Sciences at Politecnico di Torino, Italy. She received her B.S. and M.S. degree in Mathematics in 2007 and 2009 at the University of Turin. Her research interests are in distributed optimization and estimation algorithms, dynamical systems over networks, opinion dynamics.