Filters








13 Hits in 7.0 sec

UMAG-Net: A New Unsupervised Multiattention-Guided Network for Hyperspectral and Multispectral Image Fusion

Shuaiqi Liu, Siyu Miao, Jian Su, Bing Li, Weiming Hu, Yu-Dong Zhang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Deep learning has been widely applied in the field of HSI-MSI fusion, which is limited with hardware.  ...  UMAG-Net first extracts deep multiscale features of MSI by using a multiattention encoding network.  ...  In this method, each tensor constructed by MSI can be sparsely coded based on its neighbor tensor and the joint sparse coding assumption was constructed on bands.  ... 
doi:10.1109/jstars.2021.3097178 fatcat:kxoiq4fyc5c4bjhhjceig4xdpq

Pansharpening Based on Low Rank Fuzzy Fusion and Detail Supplement

Yong Yang, Chenxu Wan, Shuying Huang, Hangyuan Lu, Weiguo Wan
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Because some details of the PAN image are replaced with those of the MS image, using them directly as injection details may result in redundant information or spatial distortion.  ...  Pansharpening is a technique used to reconstruct a high-resolution (HR) multispectral (MS) image by combining an HR panchromatic (PAN) image with a low-resolution MS image.  ...  Recently, the pansharpening method of deep neural networks (DNNs) has been gradually developing [30] .  ... 
doi:10.1109/jstars.2020.3022857 fatcat:osrkwagpunawppyurrix4b335q

Table of Contents

2020 2020 IEEE International Conference on Image Processing (ICIP)  
: CORNET: COMPOSITE-REGULARIZED NEURAL NETWORK FOR ......................................................... 818 CONVOLUTIONAL SPARSE CODING 'KUXY -DZDOL 3UDYHHQ .XPDU 3RNDOD &KDQGUD 6HNKDU 6HHODPDQWXOD  ...  MUTUAL INFORMATION FOR ............................................. 1751 LIGHT-WEIGHT CONVOLUTIONAL NEURAL NETWORKS 0LQ .  ...  CODED-APERTURE FOR UNSUPERVISED CLASSIFICATION OF HYPERSEPCTRAL IMAGERY -LDQFKHQ =KX 7RQJ =KDQJ 6KHQJMLH =KDR 7RQJML 8QLYHUVLW\ &KLQD IMT-02.4: ADMM-INSPIRED RECONSTRUCTION NETWORK FOR COMPRESSIVE  ... 
doi:10.1109/icip40778.2020.9191006 fatcat:3fkxl2sjmre2jkryewwo5mlahi

Fast and High-Quality Blind Multi-Spectral Image Pansharpening [article]

Lantao Yu, Dehong Liu, Hassan Mansour, Petros T. Boufounos
2021 arXiv   pre-print
Blind pansharpening addresses the problem of generating a high spatial-resolution multi-spectral (HRMS) image given a low spatial-resolution multi-spectral (LRMS) image with the guidance of its associated  ...  spatially misaligned high spatial-resolution panchromatic (PAN) image without parametric side information.  ...  Comparison with a Deep Learning-based Approach We also compare F-BMP with a deep learning-based algorithm in the task of pansharpening by a factor of 2 with small spatial misalignment.  ... 
arXiv:2103.09943v3 fatcat:n6xall5u2zdjvp7sfaw4ovzete

How can big data and machine learning benefit environment and water management: A survey of methods, applications, and future directions

Alexander Y. Sun, Bridget R Scanlon
2019 Environmental Research Letters  
Acknowledgments The authors were partially supported by funding from Jackson School of Geosciences, the University of Texas at Austin.  ...  The authors are grateful to Dr Michael Fienen and an anonymous reviewer for their constructive comments on the original manuscript.  ...  sparse coding, joint sparse representation, sparse autoencoder (SAE), and discrete wavelet transform) [106] [107] [108] [109] .  ... 
doi:10.1088/1748-9326/ab1b7d fatcat:vx4thuy45vhlnmhu7bk2hwh2g4

2021 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 14

2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, JSTARS 2021 12287-12299 Convolutional codes Single Satellite Imagery Superresolution Based on Hybrid Nonlocal Similarity Constrained Convolution Sparse Coding.  ... 
doi:10.1109/jstars.2022.3143012 fatcat:dnetkulbyvdyne7zxlblmek2qy

Full-resolution quality assessment for pansharpening [article]

Giuseppe Scarpa, Matteo Ciotola
2022 arXiv   pre-print
A reliable quality assessment procedure for pansharpening methods is of critical importance for the development of the related solutions.  ...  On the other side, a new index of the spatial consistency between the pansharpened image and the panchromatic band at full resolution is also proposed.  ...  In pansharpening, the first method based on convolutional neural networks (CNN) was proposed by Masi et al.  ... 
arXiv:2108.06144v3 fatcat:2fq5fmpgkzfijghoc26zwt6z2i

Full-Resolution Quality Assessment for Pansharpening

Giuseppe Scarpa, Matteo Ciotola
2022 Remote Sensing  
A reliable quality assessment procedure for pansharpening methods is of critical importance for the development of the related solutions.  ...  On the other side, a new index of the spatial consistency between the pansharpened image and the panchromatic band at full resolution is also proposed.  ...  In pansharpening, the first method based on convolutional neural networks (CNN) was proposed by Masi et al.  ... 
doi:10.3390/rs14081808 fatcat:w54z6rqvubbe3dkpme5aooq4ui

Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing [article]

Danfeng Hong and Wei He and Naoto Yokoya and Jing Yao and Lianru Gao and Liangpei Zhang and Jocelyn Chanussot and Xiao Xiang Zhu
2021 arXiv   pre-print
However, with the ever-growing volume of data, the bulk of costs in manpower and material resources poses new challenges on reducing the burden of manual labor and improving efficiency.  ...  Machine learning (ML) tools with convex optimization have successfully undertaken the tasks of numerous artificial intelligence (AI)-related applications.  ...  The J-Play attempts to open the "black box" of deep networks in an explainable way by multi-layered linearized modeling.  ... 
arXiv:2103.01449v1 fatcat:jvo4pr5atvfb5kohpslvkhhmky

A Survey on Hyperspectral Image Restoration: From the View of Low-Rank Tensor Approximation [article]

Na Liu, Wei Li, Yinjian Wang, Rao Tao, Qian Du, Jocelyn Chanussot
2022 arXiv   pre-print
The ability of capturing fine spectral discriminative information enables hyperspectral images (HSIs) to observe, detect and identify objects with subtle spectral discrepancy.  ...  For each topic, the state-of-the-art restoration methods are compared by assessing their performance both quantitatively and visually.  ...  Foundation of China (Grant no. 61922013), and the Beijing Natural Science Foundation (Grant no.  ... 
arXiv:2205.08839v1 fatcat:34i56hcmvbbt7bs77tsghpuvoi

Dark side of UGC: A user-centric perspective on the impact of user-generated content [article]

Ankit Kariryaa, Universität Bremen, Johannes Schöning
2020
Finally, we present a deep learning-based approach for identifying individual trees at a large scale, with which we detect over 1.8 billion individual trees in 1.3 million sq. km area in Western Africa  ...  Through a user study, we find that our tool significantly limits the inclusion of personal information in passwords, thus limiting the negative impacts of UGC on online security.  ...  Johannes, I would always be grateful for the support you offered me in academic as well as personal matters, often going beyond what was required of you.  ... 
doi:10.26092/elib/331 fatcat:ypaovoi2bbah5j2imnhl5jmd6a

Dagstuhl Reports, Volume 7, Issue 10, October 2017, Complete Issue [article]

2018
We thank Schloss Dagstuhl for hosting us.  ...  Rather, we need to look at the information side of the network, and consider IoP mostly as a information-centric network.  ...  If trying replaces understanding, is this still in agreement with our understanding of science? 4. DL can potentially help for building up efficient dictionaries, e.g., for sparse reconstruction. 5.  ... 
doi:10.4230/dagrep.7.10 fatcat:l6tpayrw6veapbnmuxaxcrcxye

Efficient Algorithms for Large-Scale Image Analysis

Jan Wassenberg
2011
This work develops highly efficient algorithms for analyzing large images. Applications include object-based change detection and screening.  ...  To enable a side-by-side comparison, we display all images with this stretch mode enabled. The resulting screen captures are shown inFigures 5.3and 5.4.  ...  An analysis of convolution with an ideal line has demonstrated the flaws of commonly used ad-hoc point spread functions.  ... 
doi:10.5445/ir/1000025614 fatcat:freu7noy5vac5i3l73mrzmhbie