Detecting Plumes In Lwir Using Robust Nonnegative Matrix Factorization With Graph-Based Initialization

We consider the problem of identifying chemical plumes in hyperspectral imaging data, which is challenging due to the diffusivity of plumes and the presence of excessive noise. We propose a robust nonnegative matrix factorization (RNMF) method to segment hyperspectral images considering the low-rank structure of the noise-free data and sparsity of the noise. Because the optimization objective is highly non-convex, nonnegative matrix factorization is very sensitive to initialization. We address the issue by using the fast Nystrom method and label propagation algorithm (LPA). Using the alternating direction method of multipliers (ADMM), RNMF provides high quality clustering results effectively. Experimental results on real single frame and multiframe hyperspectral data with chemical plumes show that the proposed approach is promising in terms of clustering quality and detection accuracy.