Target discrimination via optimal wavelength band selection with synthetic hyperspectral imagery

Hyperspectral imaging (HSI) tracking is an emerging area of research, employing HSI instruments and exploitation techniques with the goal to track moving objects within challenging environments and across frequent ambiguities. Dimensionality reduction through wavelength band selection can help resolve such ambiguities quickly and thereby improving the feature-aided tracking performance in realtime platforms. A novel band selection algorithm is proposed to determine the optimal subset of bands that contain important information for classification. A series of studies have been conducted to evaluate the band selection algorithm and to demonstrate the benefits of optimal wavelength band selection. Synthetic HSI data using the image simulation code DIRSIG has been a key enabler to this effort. A suite of end-to-end synthetic experiments have been conducted, which include high-fidelity moving-target urban vignettes, synthetic hyperspectral rendering, and full image-chain treatment of the various sensor models.