Remote sensing hyperspectral sensors collect large volumes of high
dimensional spectral and spatial data. However, due to spectral and spatial
redundancy the true hyperspectral signal lies on a subspace of much lower
dimension than the original data. The identification of the signal subspace is
a very important first step for most hyperspectral algorithms. In this paper we
investigate the important problem of identifying the hyperspectral signal
subspace by minimizing the mean squared error (MSE) between the true signal and
an estimate of the signal. Since the MSE is uncomputable in practice, due to
its dependency on the true signal, we propose a method based on the Stein's
unbiased risk estimator (SURE) that provides an unbiased estimate of the MSE.
The resulting method is simple and fully automatic and we evaluate it using
both simulated and real hyperspectral data sets. Experimental results shows
that our proposed method compares well to recent state-of-the-art subspace
identification methods.

本研究针对遥感高光谱数据采集过程中存在的信号子空间识别问题，通过优化均方误差提出了一种基于 Stein's 无偏风险估计的方法，该方法简单自动且在模拟和真实高光谱数据集中均表现良好。