Parallel optimization of hyperspectral unmixing based on sparsity constrained nonnegative matrix factorization

Hyperspectral unmixing is a typical problem of blind source separation, which can be solved by nonnegative matrix factorization (NMF). Sparsity based NMF will increase the efficiency of unmixing, but its computational complexity limits the possibility of utilizing it in time-critical applications. In this paper, method of parallel hyperspectral unmixing based on sparsity constrained nonnegative matrix factorization on Graphics Processing Units (CSNMF-GPU) is investigated and compared in terms of both accuracy and speed. The realization of the proposed method using Compute Unified Device Architecture (CUDA) on GPU are described and evaluated. The experimental results comparing with the serial implementations based on both simulated and real hyperspectral data demonstrate the effectiveness of the proposed parallel optimization approach.