Efficient Vision-Based Calibration for Visual Surveillance Systems with Multiple PTZ Cameras

Surveillance systems with multiple cameras have become increasingly important. The space relationship between cameras offers useful information for surveillance applications, such as object tracking or 3- D positioning. In this paper, we propose a visionbased approach to infer the relative positioning and orientation among multiple PTZ cameras. The relationship between the tilt angle of a PTZ camera and the 3D-to-2D coordinate transformation is built first. Then, the tilt angles and the altitudes of PTZ cameras are estimated based on the observation of some simple objects lying on a horizontal plane, with known intrinsic parameters of these PTZ cameras. With the estimated tilt angles and altitudes, the calibration of multiple cameras can be accomplished by comparing the back-projected world coordinates of a common vector in the 3-D space. The whole procedure does not need a huge amount of data and the computational load is light. Experimental results over real images have demonstrated the efficiency and feasibility of this approach.