ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Hyperspectral And Multispectral Image Fusion Using Fully Constrained Nonlinear Coupled Nonnegative Matrix Factorization


Affiliations
1 Department of Information Technology, Kannur University, India
     

   Subscribe/Renew Journal


Hyperspectral images (HSI) have a wide range of spectral information compared to conventional images. This rich spectral information leads to store more information about the image. Even though the hyperspectral images have multiple spectrum bands that makes narrow division of each spectral band in the image. This narrow band division reduces the spatial quality of HSI and hence it necessitates the improvement of the spatial quality of the hyperspectral image. One of the most emerging methods to improve or enhance the hyperspectral image quality is the HS-MS image fusion. Most of the existing image fusion methods neglects the nonlinear data associated with the image. To overcome this limitation, we proposed a nonlinear unmixing-based fusion model, namely Fully Constrained Nonlinear-CNMF (FCNCNMF) by consider the nonlinearity data associated with the image. To improve the performance of our nonlinear unmixing-based fusion method, we imposed certain constraints on both spectral and spatial data. The constraints include minimum volume simplex with spectral data and total variance and sparsity with spatial data to enhance the quality of the image. We applied all these constraints to both hyperspectral and multispectral images and then fused these data to obtain the final high-quality image. The fused image’s quality is measured using five standard quality measures on four benchmark datasets and found that the proposed method shows superiority over all baseline methods.

Keywords

Hyperspectral Image, Nonlinearity, Spectral Unmixing, Spectral Image Fusion
Subscription Login to verify subscription
User
Notifications
Font Size

  • Ting Xu, Ting Zhu Huang, Liang Jian Deng, XiLe Zhao and Jie Huang, “Hyperspectral Image Superresolution using Unidirectional Total Variation with Tucker Decomposition”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 13, pp. 4381-4398, 2020.

  • Renwei Dian, Shutao Li, Leyuan Fang and Qi Wei. “Multispectral and Hyperspectral Image Fusion with Spatial-Spectral Sparse Representation”, Information Fusion, Vol. 49, pp. 262-270, 2019.

  • Naoto Yokoya, Claas Grohnfeldt and Jocelyn Chanussot. “Hyperspectral and Multispectral Data Fusion: A Comparative Review of the Recent Literature”, IEEE Geoscience and Remote Sensing Magazine, Vol. 5, No. 2, pp. 29-56, 2017.

  • Renwei Dian, Shutao Li, Leyuan Fang, Ting Lu and Jose M. Bioucas-Dias, “Nonlocal Sparse Tensor Factorization for Semiblind Hyperspectral and Multispectral Image Fusion”, IEEE Transactions on Cybernetics, Vol. 50, No. 10, pp. 4469-4480, 2019.

  • Xuelong Li, Yue Yuan and Qi Wang, “Hyperspectral and Multispectral Image Fusion via Nonlocal Low-Rank Tensor Approximation and Sparse Representation”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 59, No. 1, pp. 550-562, 2020.

  • Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot and Xiao Xiang Zhu, “An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing”, IEEE Transactions on Image Processing, Vol. 28, No. 4, pp. 1923-1938, 2019.

  • Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot and Xiao Xiang Zhu, “Learning a Low Coherence Dictionary to Address Spectral Variability for Hyperspectral Unmixing”, Proceedings of IEEE International Conference on Image Processing, pp. 1-13, 2017.

  • Xinyu Zhou, Ye Zhang, Junping Zhang and Shaoqi Shi, “Alternating Direction Iterative Nonnegative Matrix Factorization Unmixing for Multispectral and Hyperspectral Data Fusion”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 13, pp. 52235232, 2020.

  • N. Yokoya, T. Yairi and A. Iwasaki, “Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 2, pp. 528537, 2012.

  • M. Simoes, J. Bioucas Dias, L.B. Almeida and J. Chanussot, “A Convex Formulation for Hyperspectral Image Superresolution via Subspacebased Regularization”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, No. 6, pp. 3373-3380, 2015.

  • C.H. Lin, F. Ma, C.Y. Chi and C.H. Hsieh, “A Convex Optimization-Based Coupled Nonnegative Matrix Factorization Algorithm for Hyperspectral and Multispectral Data Fusion”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 3, pp. 1652-1667, 2018.

  • Feixia Yang, Fei Ma, Ziliang Ping and Guixian Xu, “Total Variation and Signature-Based Regularizations on Coupled Nonnegative Matrix Factorization for Data Fusion”, IEEE Access, Vol. 7, pp. 1-13, 2019.

  • Ricardo Augusto Borsoi, Tales Imbiriba and Jose Carlos Moreira Bermudez, “Super-Resolution for Hyperspectral and Multispectral Image Fusion Accounting for Seasonal Spectral Variability”, IEEE Transactions on Image Processing, Vol. 19, pp. 116-127, 2019.

  • Feixia Yang, Ziliang Ping, Fei Ma and Yanwei Wang, “Fusion of Hyperspectral and Multispectral Images With Sparse and Proximal Regularization”, IEEE Access, Vol. 7, pp. 891-899, 2019.

  • Cedric Fevotte and Nicolas Dobigeon, “Nonlinear Hyperspectral Unmixing with Robust Nonnegative Matrix Factorization”, IEEE Transactions on Image Processing, Vol. 24, No. 12, pp. 1-16, 2015.

  • Fei Ma, Feixia Yang, Ziliang Ping and Wenqin Wang, “Joint Spatial-Spectral Smoothing in a Minimum-Volume Simplex for Hyperspectral Image Super-Resolution”, Applied Sciences, Vol. 10, No. 1, pp. 237-256, 2019.

  • D. Hong, N. Yokoya, J. Chanussot and X. Zhu, “An Augmented Linear Mixing Model to Address Spectral Varialbilty for Hyperspectral Unmixing, Geography”, IEEE Transactions on Image Processing, Vol. 54, No. 3, pp. 1-17, 2018.

  • Naoto Yokoya, Takehisa Yairi and Akira Iwasaki, “Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 2, pp. 528-537, 2012.

  • Li Sun, Kang Zhao and Ziwen Liu, “Enhancing Hyperspectral Unmixing With Two-Stage Multiplicative Update Nonnegative Matrix Factorization”, IEEE Access, Vol. 7, pp. 171023-171031, 2019.

  • K. Priya and K.K. Rajkumar, “Multiplicative Iterative Nonlinear Constrained Coupled Non-negative Matrix Factorization (MINC-CNMF) for Hyperspectral and Multispectral Image Fusion”, International Journal of Advanced Computer Science and Applications, Vol. 9, No. 1, pp. 1-23, 2021.

  • Dataset for Classification, Available at http://lesun.weebly.com/hyperspectral-data-set.html, Accessed at 2021.


Abstract Views: 246

PDF Views: 0




  • Hyperspectral And Multispectral Image Fusion Using Fully Constrained Nonlinear Coupled Nonnegative Matrix Factorization

Abstract Views: 246  |  PDF Views: 0

Authors

K. Priya
Department of Information Technology, Kannur University, India
K.K. Rajkumar
Department of Information Technology, Kannur University, India

Abstract


Hyperspectral images (HSI) have a wide range of spectral information compared to conventional images. This rich spectral information leads to store more information about the image. Even though the hyperspectral images have multiple spectrum bands that makes narrow division of each spectral band in the image. This narrow band division reduces the spatial quality of HSI and hence it necessitates the improvement of the spatial quality of the hyperspectral image. One of the most emerging methods to improve or enhance the hyperspectral image quality is the HS-MS image fusion. Most of the existing image fusion methods neglects the nonlinear data associated with the image. To overcome this limitation, we proposed a nonlinear unmixing-based fusion model, namely Fully Constrained Nonlinear-CNMF (FCNCNMF) by consider the nonlinearity data associated with the image. To improve the performance of our nonlinear unmixing-based fusion method, we imposed certain constraints on both spectral and spatial data. The constraints include minimum volume simplex with spectral data and total variance and sparsity with spatial data to enhance the quality of the image. We applied all these constraints to both hyperspectral and multispectral images and then fused these data to obtain the final high-quality image. The fused image’s quality is measured using five standard quality measures on four benchmark datasets and found that the proposed method shows superiority over all baseline methods.

Keywords


Hyperspectral Image, Nonlinearity, Spectral Unmixing, Spectral Image Fusion

References