摘要: Pan-tilt-zoom (PTZ) cameras are frequently used in surveillance applications as they can observe a much larger region ofthe environment than a fixed-lens camera while still providing high-resolution imagery. The pan, tilt, and zoo... 展开 Pan-tilt-zoom (PTZ) cameras are frequently used in surveillance applications as they can observe a much larger region ofthe environment than a fixed-lens camera while still providing high-resolution imagery. The pan, tilt, and zoomparameters of a single camera may be simultaneously controlled by online users as well as automated surveillanceapplications. To accurately register autonomously tracked objects to a world model, the surveillance system requiresaccurate knowledge of camera parameters. Due to imprecision in the PTZ mechanism, these parameters cannot beobtained from PTZ control commands but must be calculated directly from camera imagery. This paper describes theefforts undertaken to implement a real-time calibration system for a stationary PTZ camera. The approach continuouslytracks distinctive image feature points from frame to frame, and from these correspondences, robustly calculates thehomography transformation between frames. Camera internal parameters are then calculated from these homographies.The calculations are performed by a self contained program that continually monitors images collected by the camera asit performs pan, tilt, and zoom operations. The accuracy of the calculated calibration parameters are compared to groundtruth data. Problems encountered include inaccuracies in large orientation changes and long algorithm execution time. 收起