Sparse Superpixel Unmixing for Hyperspectral Image Analysis
- Created on Wednesday, 01 September 2010
Software was developed that automatically detects minerals that are present in each pixel of a hyperspectral image. An algorithm based on sparse spectral unmixing with Bayesian Positive Source Separation is used to produce mineral abundance maps from hyperspectral images. A “superpixel” segmentation strategy enables efficient unmixing in an interactive session.
Subwindow of Observation demonstrates superpixel segmentation. Left: original subimage. Center: coarse segmentation, minimum region size 100. Right: fine segmentation, minimum region size 20." class="caption" align="left">The algorithm computes statistically likely combinations of constituents based on a set of possible constituent minerals whose abundances are uncertain. A library of source spectra from laboratory experiments or previous remote observations is used. A superpixel segmentation strategy improves analysis time by orders of magnitude, permitting incorporation into an interactive user session (see figure).
Mineralogical search strategies can be categorized as “supervised” or “unsupervised.” Supervised methods use a detection function, developed on previous data by hand or statistical techniques, to identify one or more specific target signals. Purely unsupervised results are not always physically meaningful, and may ignore subtle or localized mineralogy since they aim to minimize reconstruction error over the entire image. This
algorithm offers advantages of both methods, providing meaningful physical interpretations and sensitivity to subtle or unexpected minerals.
The software used in this innovation is available for commercial licensing. Please contact Daniel Broderick of the California Institute of Technology at danielb@ caltech.edu. Refer to NPO-47038.