A method of calibrating a pan, tilt, zoom (PTZ) camera with a fixed camera utilizing an overview image of a scene captured by the fixed camera, and an image of the scene captured by the PTZ camera when directed in a first direction. By matching features in the overview image and the PTZ camera image, a first calibration is carried out by correlating the first direction to matching features in the overview image. A mapping between the PTZ camera image and the overview image is defined based on the matching features. The mapping is used to map an object from the PTZ camera image to the overview image. Based on an appearance of the mapped object, a quality of the mapping is calculated. If the quality is not good enough, the PTZ camera is redirected to a second direction, and a further calibration is carried out by again.