SUBPIXEL MAPPING OF HYPERSPECTRAL IMAGES BASED ON COLLABORATIVE REPRESENTATION

Subpixel mapping with a low resolution hyperspectral image as the only input is widely applicable due to the fact that auxiliary image with high spatial resolution is not always available in practice. In this paper, to extract spatial information without auxiliary image, the upscaled low resolution hyperspectral image is classified using collaborative representation-based classifier. Another subpixel scale classification map is available by the combination of collaborative representation-based classification, spectral unmixing and subpixel spatial attraction model. To achieve better classification performance, decision fusion is employed to elect approximate class label from these two initial classification maps for each subpixel by the voting of the neighboring subpixels. Experimental results illustrate that the proposed approach is more promising in extracting and utilizing spatial information compared with some state-of-the-art subpixel mapping approaches.