Automatic image parameter optimization Based on Levenberg-Marquardt algorithm

In automatic image mosaic, the problem of solving and optimizing the modeled image parameters is usually a least square problem. In this paper an approach to solve the image parameterization based on the Levenberg-Marquardt algorithm is introduced. An appropriate camera parameterization model is firstly established, and the problem of optimization against the parameters is turned into a least square problem of the projection error between images, which solves registering all the images. Finally the images are rendered with their parameters to a spherical surface, where the linear blending and bi-linear interpolation are employed to render the images. The spherical surface is unfolded into a planar surface which gives the final mosaic result.