Comparison of target detection techniques for hyperspectral images

Target detection is a challenge to detect and classify objects in hyperspectral images. In this paper, a total of six algorithms broadly classified in type I and type II are used to detect targets such as metal, roof, and dirt. Type I algorithm differs from type II as in type II algorithm both target spectra and non-background spectra are used whereas in type I algorithm only target spectra is used as an external input. Vertex Component Analysis (VCA) is used to generate background spectra in type II algorithm. Two different hyperspectral data set such as Pavia and Urban are used for target detection. Detailed analysis of the output of the six methods shows that the wide range of output score plays an important role in the determination of threshold to detect any target. One of the type II method Orthogonal Subspace Projection (OSP) gives the best wide dynamic range compared to other techniques.