Sub-pixel Mapping of Remote Sensing Image Based on MAP model

Mixed pixel is a common problem in Remotely Sensed classification. Even though the composition of these pixels for different classes can be estimated with pixel un-mixing model, the output provides no indication of how such classes are distributed spatially within these pixels. Sub-pixel mapping is a technique designed to obtain the spatial distribution of these classes in these pixels with information contained in mixed pixels. In this paper, the work introduces a sub- pixel mapping algorithm exploiting spatial dependence. The spatial arrangement of the different class fractions in surrounding pixels is used to find the location of the sub-pixels inside the central pixel. The sub-pixel mapping algorithm is intended to be applied to fraction images of a high spatial resolution, a regularized super-resolution image reconstruction method can be proposed to solve the problem called the Maximum A Posteriori (MAP) formulation, which based on the assumption of spatial dependence and the application of the soft classification result. With the upscale factor the proposed algorithm was tested on both artificial text image and real TM image, the result shows that it is a simple and efficient method to solve the sub-pixel mapping problem.