Hyperspectral demixing using foveated compressive projections
The present disclosure generally relates to systems and methods for spectral demixing. An example technique includes obtaining empirical spectroscopic data representing a plurality of frequencies of electromagnetic energy that has interacted with a specimen, accessing a computer readable representation of a hierarchal spectral cluster tree representing a spectral library, demixing, with data on each of a plurality of levels of the hierarchal spectral cluster tree, foveated spectroscopic data derived from the empirical spectroscopic data, identifying at least one node in the hierarchal spectral cluster tree as corresponding to the empirical spectroscopic data, and outputting an endmember abundance assessment of the specimen corresponding to at least the at least one node.
1. A method for spectral demixing, the method comprising:
obtaining empirical spectroscopic data produced by a spectroscopic sensor and representing a plurality of frequencies of electromagnetic energy that has interacted with a specimen;
accessing a computer readable representation of a hierarchal spectral cluster tree representing a spectral library;
demixing, with data on each of a plurality of levels of the hierarchal spectral cluster tree, foveated spectroscopic data derived from the empirical spectroscopic data;
identifying at least one node in the hierarchal spectral cluster tree as corresponding to the empirical spectroscopic data; and
outputting an endmember abundance assessment of the specimen corresponding to at least the at least one node.
2. The method of claim 1 , wherein the empirical spectroscopic data represents a plurality of frequencies of electromagnetic energy reflected off of the specimen.
3. The method of claim 1 , wherein the empirical spectroscopic data represents a pixel.
4. The method of claim 1 , wherein the hierarchal spectral cluster tree comprises a plurality of levels comprising at least one terminal level comprising nodes representing individual endmembers.
5. The method of claim 1 , wherein the hierarchal spectral cluster tree comprises a plurality of prototype nodes, wherein a respective prototype node represents a plurality of endmembers.
6. The method of claim 1 , further comprising hierarchical clustering the spectral library.
7. The method of claim 1 , wherein the demixing foveated spectroscopic data comprises performing foveated compressive projection.
8. The method of claim 1 , wherein the demixing foveated spectroscopic data comprises sparse reconstruction.
9. The method of claim 1 , further comprising using the endmember abundance assessment for at least one of geospatial analysis, target recognition, surveillance, chemical identification, remote sensing, and combinations thereof.
10. The method of claim 1 , wherein the outputting comprises causing a display in a human readable format.
11. A system for spectral demixing, the system comprising:
an interface configured to obtain empirical spectroscopic data produced by a spectroscopic sensor and representing a plurality of frequencies of electromagnetic energy that has interacted with a specimen;
at least one electronic processor communicatively coupled to a computer readable representation of a hierarchal spectral cluster tree representing a spectral library;
at least one electronic processor configured to demix, with data on each of a plurality of levels of the hierarchal spectral cluster tree, foveated spectroscopic data derived from the empirical spectroscopic data;
at least one electronic processor configured to identify at least one node in the hierarchal spectral cluster tree as corresponding to the empirical spectroscopic data; and
at least one electronic processor configured to output an endmember abundance assessment of the specimen corresponding to at least the at least one node.
12. The system of claim 11 , wherein the empirical spectroscopic data represents a plurality of frequencies of electromagnetic energy reflected off of the specimen.
13. The system of claim 11 , wherein the empirical spectroscopic data represents a pixel.
14. The system of claim 11 , wherein the hierarchal spectral cluster tree comprises a plurality of levels comprising at least one terminal level comprising nodes representing individual endmembers.
15. The system of claim 11 , wherein the hierarchal spectral cluster tree comprises a plurality of prototype nodes, wherein a respective prototype node represents a plurality of endmembers.
16. The system of claim 11 , further comprising at least one electronic processor configured to hierarchically cluster the spectral library.
17. The system of claim 11 , wherein the at least one electronic processor configured to demix foveated spectroscopic data is further configured to perform foveated compressive projection.
18. The system of claim 11 , wherein the at least one electronic processor configured to demix foveated spectroscopic data is further configured to perform sparse reconstruction.
19. The system of claim 11 , further comprising at least one electronic processor configured to provide the endmember abundance assessment for at least one of geospatial analysis, target recognition, surveillance, chemical identification, remote sensing, and combinations thereof.
20. The system of claim 11 , wherein the at least one electronic processor configured to output is further configured to cause a display in a human readable format.