A revisit to target-constrained interference-minimized filter (TCIMF)

The Orthogonal Subspace Projection (OSP) and Constrained Energy Minimization (CEM) have been used in hyperspectral target detection and classification. A target-constrained interference-minimized filter (TCIMF) was recently proposed to extend the CEM to improve signal detectability by annihilating undesired target signal sources as the way carried out in the OSP. In this paper, we revisit the TCIMF from a signal processing viewpoint where signals can be characterized by three types of information sources, desired target sources and undesired target sources, both of which are provided a priori, and interferers which are unknown interfering sources. By virtue of such signal decomposition, we can show that the TCIMF is actually a generalization of the OSP and CEM. In particular, we investigate assumptions made for the OSP and CEM in terms of these three types of signal sources and exploit insights into their filter design. As will be shown in this paper, the OSP and the CEM perform the same tasks by operating different levels of information and both can be viewed as special cases of the TCIMF.