Omni-directional image sparse reconstruction method based on omni-directional total variation

The invention discloses an omni-directional image sparse reconstruction method based on the omni-directional total variation. For reconstructing an omni-directional image fast and effectively from compressed sample data, a total variation model, namely, the omni-directional total variation combined with features of the omni-directional image is put forward, and when the omni-directional image is reconstructed on the basis of the TV norm, the omni-directional total variation is adopted as a target function to solve the model. According to the method, the adverse effect on calculation of the total variation from nonlinearity imaging distortion of the omni-directional image is taken into consideration, and therefore the omni-directional image sparse reconstruction quality is effectively improved.