A practical distortion correcting method from fisheye image to perspective projection image

摘要

Fisheye camera is finding increasing number of applications in robotic vision, visual surveillance, and other fields. But the use of super-wide angle fish-eye lenses causes strong distortions in the resulting images. A method for the correction of fisheye distortion using only single images and linearity of imaged objects is presented. Spherical projection is a simple and effective method to transform a fisheye image to a perspective projection image. To use this method, the optic center of the fisheye image and the radius of the projecting sphere must be known in advance. The proposed algorithm is based on ellipse fitting. It requires only the possibility of the extraction of distorted image points from straight lines in the 3D scene. The mathematical model is introduced for the transformation. The method for finding out the optic center and the radius of the projection sphere is discussed. Contrary to most former algorithms, the algorithm discussed here does not depend on information about the real world coordinates of matching points. The correctness and effectiveness of the proposed method are demonstrated with real image.