Sub-pixel Mapping with Multiple Shifted Remotely Sensed Images Based on Attraction Model

摘要

Sub-pixel mapping is a technique designed to obtain the spatial distribution of different classes in mixed pixels at the sub-pixel scale by transforming fraction images to classification map. However, sub-pixel mapping is an ill-posed problem as information in single low resolution image is not enough to obtain a high resolution land cover map. Accuracy can be improved by incorporating auxiliary datasets to provide more land-cover information. In this paper, the traditional attraction model is used to utilize multiple shifted remotely sensed images which have complementary information to each other at the sub-pixel scale. The proposed algorithm was tested on the synthetic and degraded real imagery and experimental results demonstrate that the proposed approach outperform traditional single image based sub-pixel mapping algorithm, and hence provide an effective option for improving the accuracy of sub-pixel mapping of remote sensing imagery.