Detecting subpixel targets in Hyperspectral images via knowledgeaided adaptive filtering

Hyperspectral imaging (HSI) sensors capture the spectral signature of targets and thus provide the capability of remotely identifying ground objects smaller than a full pixel in HSI images. Conventional methods for subpixel target detection rely on estimating a large-size covariance matrix of the background and using the matrix for target detection. To complete the estimation, a large set of target-free training pixels is needed, which makes the estimation impractical for a heterogeneous environment and also computationally expensive. In this paper, we propose to generate a parametric model, named knowledge-aided non-stationary autoregressive (KANS-AR) model, for target detection. Instead of estimating the large-size covariance matrix explicitly, the proposed parametric model can be estimated from a small-size training pixels and used directly in timeseries- based whitening. This advantage makes a KANS-AR based target detector work well in both homogenous and heterogeneous environments. Experimental results demonstrate the efficiency of the proposed method.