Об одном подходе к решению задачи ректификации стереоизображений по сцене без калибровки камер
This article is devoted to the method of initial image processing to use in stereovision systems. It is based on a modification of video stabilization approach . The method considers image rectification process as a sequence of transformations. Each transformation is found as a solution of optimization problem. The article describes mathematical model that fits main principles of video stabilization method, provides optimization techniques to find transformation parameters and describes statistical approach to solution refinement. The method provided does not require camera calibration and uses only scene images. This approach can be applied to create individual stereovision systems.