Camera Calibration Using Lengths of Corresponding Line Segments

Camera calibration using patterns is widely used in computer vision and industry. The accuracy of calibration depends on the accuracy of the pattern. A high accuracy pattern is usually difficult to manufacture in labs. In this paper, we propose to use two images of two identical industrial objects as natural calibration patterns. The corresponding line segments on the objects are used for a nonlinear calibration method, and only five intrinsic parameters of the camera are optimized in the procedure. The experiments show that the proposed method is both effective and practical.