Engineering Commons^™

Superpixel-Based Unsupervised Hyperspectral Unmixing, Jiarui Yi

Open Access Theses & Dissertations

Recently, superpixel-based approaches have been proposed for hyperspectral unmixing. The basic assumption of this approach is that the superpixel over-segmentation segments the image into small homogeneous areas. A low-dimensional (LD) image representation is obtained by using the average of the superpixels, which are then used in other image processing tasks up the processing chain. Due to superpixel-segmentation algorithm limitations, the region inside a superpixel may not be homogeneous. Therefore, the average may not be an adequate representation for the superpixel, leading to inaccuracies in the low dimensional representation resulting in errors in the image processing tasks or analysis. Here we …