2,892 Hits in 10.2 sec

Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks

Md Rifat Arefin, Vincent Michalski, Pierre-Luc St-Charles, Alfredo Kalaitzis, Sookyung Kim, Samira E. Kahou, Yoshua Bengio
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this work, we present a data-driven, multi-image super resolution approach to alleviate these problems.  ...  High-resolution satellite imagery is critical for various earth observation applications related to environment monitoring, geoscience, forecasting, and land use analysis.  ...  Acknowledgements We thank Ishaan Kumar, Zhichao Lin, Kris Sankaran, Julien Cornebise, Anthony Ortiz and Jason Jo for useful discussions.  ... 
doi:10.1109/cvprw50498.2020.00111 dblp:conf/cvpr/ArefinMSKKKB20 fatcat:eaobilz56bat3evwywwtywbnna


H. He, K. Gao, W. Tan, L. Wang, S. N. Fatholahi, N. Chen, M. A. Chapman, J. Li
2022 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In a variety of remote sensing applications, DL based super-resolution methods are widely used.  ...  In these cases, super-resolution, especially deep learning (DL)-based methods, can provide higher spatial resolution images given lower resolution images.  ...  As we mentioned above, single-image super-resolution were widely used in remote sensing images super-resolution.  ... 
doi:10.5194/isprs-archives-xliii-b1-2022-31-2022 fatcat:rjn7yubl4vbglng5ntwfy2dkve

Bidirectional 3D Quasi-Recurrent Neural Networkfor Hyperspectral Image Super-Resolution

Ying Fu, Zhiyuan Liang, Shaodi You
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this article, we design a bidirectional 3D quasi-recurrent neural network for HSI super-resolution with arbitrary number of bands.  ...  Recently, deep learning-based methods for HSI spatial super-resolution have been actively exploited.  ...  Thus, spatial super-resolution is essential for HSI, especially in remote sensing field [7] .  ... 
doi:10.1109/jstars.2021.3057936 fatcat:522lja4s65bbhhcm62lrelueby

Deep learning approaches for real-time image super-resolution

Pourya Shamsolmoali, M. Emre Celebi, Ruili Wang
2020 Neural computing & applications (Print)  
Generating a high-resolution (HR) image from its corresponding low-resolution (LR) input is referred to image super-resolution (SR).  ...  The paper entitled "Perceptual image quality using dual generative adversarial network" develops a variety of generative adversarial networks for image SR that contains two generators and two discriminators  ...  to further push the frontier of object detection for remote sensing images.  ... 
doi:10.1007/s00521-020-05176-z fatcat:gvmbzve6kvfmzfwumblipqzaji

Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks

Lize Zhang, Wen Lu, Yuanfei Huang, Xiaopeng Sun, Hongyi Zhang
2021 Remote Sensing  
As the high-resolution (HR) remote sensing images are difficult to collect with a limited imaging device, most of the existing remote sensing super-resolution methods try to down-sample the collected original  ...  In this paper, we propose a perceptually unpaired super-resolution method by constructing a multi-stage aggregation network (MSAN). The optimization of the network depends on consistency losses.  ...  For the unpaired remote sensing super-resolution task, the low-resolution remote sensing images still contain enough similar principal information by transmitting hardware devices.  ... 
doi:10.3390/rs13163167 fatcat:o34lbvuvfvgwnfo4z3ixsgpelu

Single satellite imagery simultaneous super-resolution and colorization using multi-task deep neural networks

Heng Liu, Zilin Fu, Jungong Han, Ling Shao, Hongshen Liu
2018 Journal of Visual Communication and Image Representation  
8 Satellite imagery is a kind of typical remote sensing data, which holds preponderance in large area imaging and strong macro integrity.  ...  In this work, unlike existing works which solve these two problems separately, we focus on achieving image super-resolution (SR) and image colorization synchronously.  ...  Single-image super resolution for multispectral 526 remote sensing data using convolutional neural networks.  ... 
doi:10.1016/j.jvcir.2018.02.016 fatcat:v5gmsy4r5nhp3og2itnfblkgvi

Spatial–Spectral Fusion in Different Swath Widths by a Recurrent Expanding Residual Convolutional Neural Network

He, Li, Yuan, Li, Shen
2019 Remote Sensing  
Remote sensing image fusion aims at overcoming the different constraints of remote sensing images, to achieve the purpose of combining the useful information in the different images.  ...  The quality of remotely sensed images is usually determined by their spatial resolution, spectral resolution, and coverage.  ...  Because of this advantage, many scholars have applied deep learning to image fusion and super-resolution tasks.  ... 
doi:10.3390/rs11192203 fatcat:mh466wuplzfavdinhinaq5gcgu

Pre‐training of gated convolution neural network for remote sensing image super‐resolution

Yali Peng, Xuning Wang, Junwei Zhang, Shigang Liu
2021 IET Image Processing  
Many very deep neural networks are proposed to obtain accurate super-resolution reconstruction of remote sensing images.  ...  To solve these problems, a novel single-image superresolution algorithm named pre-training of gated convolution neural network (PGCNN) is proposed for remote sensing images.  ...  [31] proposed a new single-image super-resolution algorithm named local-global combined networks for remote sensing images based on the deep CNNs.  ... 
doi:10.1049/ipr2.12096 fatcat:sr5bro5sw5gctp5twvw2lbtriq

A New Super Resolution Framework Based on Multi-Task Learning for Remote Sensing Images

Li Yan, Kun Chang
2021 Sensors  
Super-resolution (SR) algorithms based on deep learning have dominated in various tasks, including medical imaging, street view surveillance and face recognition.  ...  Inspired by multi-task learning strategy, we propose a multiple-blur-kernel super-resolution framework (MSF), in which a multiple-blur-kernel learning module (MLM) optimizes the parameters of the network  ...  Acknowledgments: The authors would like to thank Li K et al. for providing public remote sensing object detection dataset DIOR. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21051743 pmid:33802432 pmcid:PMC7959284 fatcat:hwegqyc7mrcd3hp4be7au6midm

Table of contents

2021 IEEE Transactions on Geoscience and Remote Sensing  
Zhang 2307 Hybrid 2-D-3-D Deep Residual Attentional Network With Structure Tensor Constraints for Spectral Super-Resolution of RGB Images ................................................... J. Li, C.  ...  Hu 2579 Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast ...............................................  ... 
doi:10.1109/tgrs.2021.3052119 fatcat:obk5h6sp2nh47ounq4jqlhukcu

An Unsupervised Remote Sensing Single-Image Super-Resolution Method Based on Generative Adversarial Network

Ning Zhang, Yongcheng Wang, Xin Zhang, Dongdong Xu, Xiaodong Wang
2020 IEEE Access  
Since we were not able to obtain the source code or SR images of deep generative network for unsupervised remote sensing single-image super resolution (UGN) [15] , the published numerical results were  ...  These challenges render highly difficult in the reconstruction of remote sensing images by using a deep neural network for supervised learning.  ... 
doi:10.1109/access.2020.2972300 fatcat:22xqsh6hdnhlrcrccoocdxhb5q

Super-Resolving Beyond Satellite Hardware Using Realistically Degraded Images [article]

Jack White, Alex Codoreanu, Ignacio Zuleta, Colm Lynch, Giovanni Marchisio, Stephen Petrie, Alan R. Duffy
2021 arXiv   pre-print
Modern deep Super-Resolution (SR) networks have established themselves as valuable techniques in image reconstruction and enhancement.  ...  In this paper, we test the feasibility of using deep SR in real remote sensing payloads by assessing SR performance in reconstructing realistically degraded satellite images.  ...  Support for the project has been provided by Swinburne University of Technology's Data Science Research Institute. The work in this paper made use of the OzSTAR national HPC facility.  ... 
arXiv:2103.06270v1 fatcat:2ul5f5kep5g2xibaqxethtv5sa

Table of contents

2018 IEEE Transactions on Image Processing  
Malik 3114 Interpolation, Super-Resolution, and Mosaicing Robust Single-Radar Imaging, Remote Sensing, and Geophysical Imaging Z. Han, Z. Liu, C.-M. Vong, Y.-S. Liu, S. Bu, J. Han, and C. L. P.  ...  Zeng 2635 Lossless Coding of Images and Video Camera-Aware Multi-Resolution Analysis for Raw Image Sensor Data Compression ...................................... .......................................  ... 
doi:10.1109/tip.2018.2826279 fatcat:g2phh6es3vhq5arrsk62bblzua

Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios [chapter]

Xiong Zhou, Saurabh Prasad
2020 Advances in Computer Vision and Pattern Recognition  
In recent years, there has been an emergence of deep learning algorithms being applied to hyperspectral and multispectral imagery for remote sensing and biomedicine tasks.  ...  Deep neural networks have proven to be very effective for computer vision tasks, such as image classification, object detection, and semantic segmentation -- these are primarily applied to color imagery  ...  In addition to making advances in algorithms and network architectures (e.g. networks for multi-scale, multi-sensor data analysis, data fusion, image super-resolution etc.), there is a need for addressing  ... 
doi:10.1007/978-3-030-38617-7_5 fatcat:23ibk4ojbvepbpikxgjxan4i6e

Two-Path Network with Feedback Connections for Pan-Sharpening in Remote Sensing

Shipeng Fu, Weihua Meng, Gwanggil Jeon, Abdellah Chehri, Rongzhu Zhang, Xiaomin Yang
2020 Remote Sensing  
High-resolution multi-spectral images are desired for applications in remote sensing. However, multi-spectral images can only be provided in low resolutions by optical remote sensing satellites.  ...  To make full use of the powerful deep features that have strong representation ability, we propose a two-path network with feedback connections, through which the deep features can be rerouted for refining  ...  Acknowledgments: We thank all the editors and reviewers in advance for their valuable comments that will improve the presentation of this paper.  ... 
doi:10.3390/rs12101674 fatcat:w4lepqr2hvbs3kivqak3bl2y7u
« Previous Showing results 1 — 15 out of 2,892 results