Fisheye Image Correction Based on Straight-Line Detection and Preservation

Fisheye lenses are widely used when the users want to capture the image/video with wide field of view (FoV) which is particularly suited to surveillance monitoring and vehicle camera. However, no projection from the actual scene in wide FoV image can avoid the distortion. If this problem cannot be solved, the fisheye image will difficult be used for object detection or analysis due to the distorted shapes of the scene objects. To correct this problem and obtain the natural-looking image, a two-step correction approach is proposed. Firstly, adaptive latitude and longitude correction are presented and the Hough transform is used to detect and estimate the straight-line. Secondly, the straight-line preserving and orientation, consistency based optimization is examined to obtain the final correction result. To compare the effectiveness of the proposed method, some fisheye correction methods are discussed. The experimental results demonstrate that the proposed method can obtain the coherent natural-looking.