Self-Paced Nonnegative Matrix Factorization for Hyperspectral Unmixing
- 10 June 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 59 (2), 1501-1515
- https://doi.org/10.1109/tgrs.2020.2996688
Abstract
The presence of mixed pixels in the hyperspectral data makes unmixing to be a key step for many applications. Unsupervised unmixing needs to estimate the number of endmembers, their spectral signatures, and their abundances at each pixel. Since both endmember and abundance matrices are unknown, unsupervised unmixing can be considered as a blind source separation problem and can be solved by nonnegative matrix factorization (NMF). However, most of the existing NMF unmixing methods use a least-squares objective function that is sensitive to the noise and outliers. To deal with different types of noises in hyperspectral data, such as the noise in different bands (band noise), the noise in different pixels (pixel noise), and the noise in different elements of hyperspectral data matrix (element noise), we propose three self-paced learning based NMF (SpNMF) unmixing models in this article. The SpNMF models replace the least-squares loss in the standard NMF model with weighted least-squares losses and adopt a self-paced learning (SPL) strategy to learn the weights adaptively. In each iteration of SPL, atoms (bands or pixels or elements) with weight zero are considered as complex atoms and are excluded, while atoms with nonzero weights are considered as easy atoms and are included in the current unmixing model. By gradually enlarging the size of the current model set, SpNMF can select atoms from easy to complex. Usually, noisy or outlying atoms are complex atoms that are excluded from the unmixing model. Thus, SpNMF models are robust to noise and outliers. Experimental results on the simulated and two real hyperspectral data sets demonstrate that our proposed SpNMF methods are more accurate and robust than the existing NMF methods, especially in the case of heavy noise.Keywords
Funding Information
- National Natural Science Foundation of China (61871177, 41971296, 11771130, 41671342)
- Science and Technology Development Fund, Macau SAR (189/2017/A3)
- University of Macau (MYRG2018-00136-FST)
- Zhejiang Provincial Natural Science Foundation of China (LR19D010001)
- Open Fund of State Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University (18R05)
This publication has 23 references indexed in Scilit:
- Robust Hyperspectral Unmixing With Correntropy-Based MetricIEEE Transactions on Image Processing, 2015
- Robust Nonnegative Matrix Factorization via Half-Quadratic MinimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based ApproachesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Robust nonnegative matrix factorization using L21-normPublished by Association for Computing Machinery (ACM) ,2011
- Hyperspectral Unmixing via $L_{1/2}$ Sparsity-Constrained Nonnegative Matrix FactorizationIEEE Transactions on Geoscience and Remote Sensing, 2011
- Constrained Nonnegative Matrix Factorization for Hyperspectral UnmixingIEEE Transactions on Geoscience and Remote Sensing, 2008
- Endmember Extraction From Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix FactorizationIEEE Transactions on Geoscience and Remote Sensing, 2007
- Vertex component analysis: a fast algorithm to unmix hyperspectral dataIEEE Transactions on Geoscience and Remote Sensing, 2005
- Non-negative sparse codingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral dataPublished by SPIE-Intl Soc Optical Eng ,1999