Detection algorithms for hyperspectral Imaging applications

Hyperspectral imaging (HSI) sensors in the reflective region of the spectrum acquire digital images in many contiguous and very narrow spectral bands that typically span the visible, near-infrared, and mid-infrared portions. This enables the construction of an essentially continuous radiance spectrum for every pixel in the scene. Irrespective of the design approach, however, performance evaluation of any detector should be done using statistical criteria. This paper focuses on the design and evaluation of detection algorithms using statistically hypothesis testing techniques.