Active Camera Calibration

Robert T. Collins, Robotics Institute, Carnegie Mellon University

We have developed a parametric camera model and calibration procedures for an outdoor active camera system with pan, tilt and zoom control. Unlike traditional methods, active camera motion plays a key role in the calibration process, and no special laboratory setups are required. Intrinsic parameters are estimated automatically by fitting parametric models to the optic flow induced by rotating and zooming. No knowledge of 3D scene structure is needed. Extrinsic parameters are calculated by actively rotating the camera to sight a sparse set of surveyed landmarks over a virtual hemispherical field of view, yielding a well-conditioned pose estimation problem.
To get the paper
  R.Collins and Y.Tsin, "Calibration of an Outdoor Active Camera
  System," IEEE Computer Vision and Pattern Recognition (CVPR'99),
  Ft.Collins, CO, June 23-25, 1999.

CMU Landmark-Based Pose Dataset

As part of the process of calibrating a network of outdoor active sensors mounted on campus, I have put together a test dataset for landmark-based pose algorithms. Also included is source code for extrinsic camera calibration, as described in the CVPR'99 paper. Follow this link to get the dataset:

CMU Landmark-Based Pose Dataset.