Constrained Nonnegative Matrix Factorization For Hyperspectral Change Detection

This paper presents an unmixing based change detection (UBCD) approach based on constrained nonnegative matrix factorization (NMF) for hyperspectral images. UBCD provides not only multi-output change detection, but also subpixel level information about the nature of the changes that occur in the scene. The proposed method utilizes constrained NMF with the sparsity constraint for the abundances and the minimum volume constraint for the endmembers, reducing the solution space for the matrix factorization and resulting in enhanced unmixing and change detection performance. The change detection output is obtained in terms of the temporal abundance matrix differences for each endmember. The proposed method is evaluated on synthetic and real multitemporal datasets.