Hyperspectral Image Super-Resolution Using Deep Feature Matrix Factorization

Hyperspectral images (HSIs) can describe the subtle differences in the spectral signatures of materials. However, they have low spatial resolution due to various hardware limitations. Improving it via postprocess without an auxiliary high-resolution (HR) image still remains a challenging problem. In this paper, we address this problem and propose a new HSI super-resolution (SR) method. Our approach, called deep feature matrix factorization (DFMF), blends feature matrix extracted by a deep neural network (DNN) with nonnegative matrix factorization strategy for super-resolving real-scene HSI. The estimation of the HR HSI is formulated as a combination of latent spatial feature matrix and spectral feature matrix. In the DFMF model, the input low-resolution (LR) HSI is first partitioned into several subsets according to the correlation matrix, and the key band is selected from each subset. Then, the key band group is super-resolved by a DNN model, and the HR key band group is then used as a guide to carry out deep spatial feature matrix. Specifically, the input LR HSI with prototype reflectance spectral vectors of the scene will be preserved when super-resolving in a spatial domain. Thus, the nonnegative spectral and spatial feature matrices are extracted simultaneously from alternately factorizing the pair of LR HSI and the HR key band group. Finally, the HR HSI is obtained by the integration of the spectral and spatial feature matrices. Experiments have been conducted on real-scene remote sensing HSI. Comparative analyses validate that the proposed DFMF method presents a superior super-resolving performance, as it preserves spectral information better.

[1]  Hao Wu,et al.  Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification , 2018, IEEE Transactions on Image Processing.

[2]  Shree K. Nayar,et al.  Generalized Assorted Pixel Camera: Postcapture Control of Resolution, Dynamic Range, and Spectrum , 2010, IEEE Transactions on Image Processing.

[3]  Jianhua Lu,et al.  Bayesian Hyperspectral and Multispectral Image Fusions via Double Matrix Factorization , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[4]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[5]  Nicolas Gillis,et al.  Fast and Robust Recursive Algorithmsfor Separable Nonnegative Matrix Factorization , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yunsong Li,et al.  Hyperspectral image reconstruction by deep convolutional neural network for classification , 2017, Pattern Recognit..

[7]  Zhou Wang,et al.  No-reference perceptual quality assessment of JPEG compressed images , 2002, Proceedings. International Conference on Image Processing.

[8]  Xiangtao Zheng,et al.  Hyperspectral Image Superresolution by Transfer Learning , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Jocelyn Chanussot,et al.  Multimorphological Superpixel Model for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Yunsong Li,et al.  High-quality spectral-spatial reconstruction using saliency detection and deep feature enhancement , 2019, Pattern Recognit..

[11]  Songtao Lu,et al.  Inexact Block Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization , 2016, IEEE Transactions on Signal Processing.

[12]  Yunsong Li,et al.  Hyperspectral image super-resolution using deep convolutional neural network , 2017, Neurocomputing.

[13]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Yunsong Li,et al.  Hyperspectral Image Super-Resolution by Spectral Difference Learning and Spatial Error Correction , 2017, IEEE Geoscience and Remote Sensing Letters.

[17]  Johannes R. Sveinsson,et al.  Model-Based Fusion of Multi- and Hyperspectral Images Using PCA and Wavelets , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Kyoung Mu Lee,et al.  Deeply-Recursive Convolutional Network for Image Super-Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Lei Zhang,et al.  Exploiting Clustering Manifold Structure for Hyperspectral Imagery Super-Resolution , 2018, IEEE Transactions on Image Processing.

[20]  Andrew L. Maas Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[21]  S. Vavasis,et al.  M L ] 7 O ct 2 01 3 Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization ∗ , 2013 .

[22]  Feng Li,et al.  Super-Resolution for GaoFen-4 Remote Sensing Images , 2018, IEEE Geoscience and Remote Sensing Letters.

[23]  Guang-Zhong Yang,et al.  Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging , 2017, IEEE Transactions on Medical Imaging.

[24]  Yunsong Li,et al.  Trainable spectral difference learning with spatial starting for hyperspectral image denoising , 2018, Neural Networks.

[25]  Yuan Yuan,et al.  Hyperspectral Anomaly Detection by Graph Pixel Selection , 2016, IEEE Transactions on Cybernetics.

[26]  D. Foster,et al.  Frequency of metamerism in natural scenes , 2006 .

[27]  Ayan Chakrabarti,et al.  Statistics of real-world hyperspectral images , 2011, CVPR 2011.

[28]  Ajmal S. Mian,et al.  Sparse Spatio-spectral Representation for Hyperspectral Image Super-resolution , 2014, ECCV.

[29]  Qian Du,et al.  Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network , 2017, Remote. Sens..

[30]  Huchuan Lu,et al.  Learning Dual Convolutional Neural Networks for Low-Level Vision , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[31]  Narendra Ahuja,et al.  Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Naoto Yokoya,et al.  Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[33]  M. Körner,et al.  SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS , 2016 .

[34]  Yoichi Sato,et al.  Hyperspectral Image Super-Resolution With a Mosaic RGB Image , 2018, IEEE Transactions on Image Processing.

[35]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  John A. Richards,et al.  Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[38]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[39]  José M. Bioucas-Dias,et al.  Vertex component analysis: a fast algorithm to unmix hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Guangming Shi,et al.  Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation. , 2016, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[41]  Vincent Y. F. Tan,et al.  A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization , 2016, IEEE Transactions on Signal Processing.