On-line control of active camera networks for computer vision tasks

Large networks of cameras have been increasingly employed to capture dynamic events for tasks such as surveillance and training. When using active cameras to capture events distributed throughout a large area, human control becomes impractical and unreliable. This has led to the development of automated approaches for on-line camera control. We introduce a new automated camera control approach that consists of a stochastic performance metric and a constrained optimization method. The metric quantifies the uncertainty in the state of multiple points on each target. It uses state-space methods with stochastic models of the target dynamics and camera measurements. It can account for static and dynamic occlusions, accommodate requirements specific to the algorithm used to process the images, and incorporate other factors that can affect its results. The optimization explores the space of camera configurations over time under constraints associated with the cameras, the predicted target trajectories, and the image processing algorithm. The approach can be applied to conventional surveillance tasks (e.g., tracking or face recognition), as well as tasks employing more complex computer vision methods (e.g., markerless motion capture or 3D reconstruction).