Remote sensing images are easily degraded because the imaging process is influenced by the camera itself link (CIL), such as optical systems, electronic systems, and image sensors. The invariant modulation transfer function (IMTF) of a remote sensing camera can represent the degeneration produced by the CIL. Thus, the IMTF compensation can remove the degeneration of the CIL to improve the image quality. However, conventional IMTF measurement methods using a single feature (e.g., edge or pulse) have low measurement accuracy due to the influence of noises, resulting in low image compensation quality. Here, we propose an efficient measurement method of the IMTF in conjunction with a learning approach to compensate for the imaging degeneration. The IMTF from the CIL is measured using multiple diffractive grids, which are generated by two 1-D gratings. A learning approach is proposed to estimate the IMTF from the diffractive grids, where diffractive grids are not directly used as a point spread function (PSF) because grids are easily affected by various noises and result in low reconstruction accuracy of the IMTF. We experimentally confirm that the proposed method is useful for the IMTF estimations and compensation for image quality degeneration of remote sensing cameras under noise conditions. The proposed methods can double the MTF reconstruction accuracy and yield higher image compensation quality compared with traditional methods.
Read full abstract