Localizing surveillance cameras

Branislav Micusik
Austrian Institute of Technology, Vienna, Austria

We present new approaches for camera localization with non-overlapping camera views, particularly relevant for video surveillance systems. The aim is to localize the surveillance cameras given observations of a walking person across camera field of views. First, we present a novel method for automatic single camera calibration and foot-head homology estimation by observing persons standing at several positions in the camera field of view. We demonstrate that human body can be considered as a calibration target thus avoiding special calibration objects or manually established fiducial points. By assuming roughly parallel human poses we derive a new constraint which allows to formulate the calibration of internal and external camera parameters as a Quadratic Eigenvalue Problem. Second, we show how to localize multiple non-overlapping cameras by exploiting observations of a walking person given either output from the presented single camera calibration method or camera rotations yielding Second Order Cone Program.