Superresolution mapping based on hybrid interpolation by parallel paths

摘要

Superresolution mapping (SRM) is a technology to handle mixed pixels in remote sensing image. In this letter, a novel hybrid interpolation-based SRM by parallel paths (HISRM-PP) is proposed. Firstly, the two different high resolution fractional images for each class are respectively derived by parallel paths. Then the two kinds of high resolution fractional images are integrated to produce the higher resolution fractional images by the appropriate weighting parameter. Finally, the higher resolution fractional images are utilized to obtain SRM result by class allocation. Due to the parallel paths in HISRM-PP, the more spatial-spectral information of the original image is utilized to improve the accuracy of SRM result. Experimental results on the two real remote sensing data show that HISRM-PP produces the better SRM result than the existing hybrid interpolation-based SRM (HISRM).