scholarly journals SUPER-RESOLUTION OF MULTISPECTRAL SATELLITE IMAGES USING CONVOLUTIONAL NEURAL NETWORKS

2020 ◽  
Vol V-1-2020 ◽  
pp. 33-40
Author(s):  
M. U. Müller ◽  
N. Ekhtiari ◽  
R. M. Almeida ◽  
C. Rieke
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Spatial Resolution ◽  
Satellite Images ◽  
State Of The Art ◽  
Super Resolution ◽  
Image Resolution ◽  
The Other ◽  
Multispectral Satellite Images

Abstract. Super-resolution aims at increasing image resolution by algorithmic means and has progressed over the recent years due to advances in the fields of computer vision and deep learning. Convolutional Neural Networks based on a variety of architectures have been applied to the problem, e.g. autoencoders and residual networks. While most research focuses on the processing of photographs consisting only of RGB color channels, little work can be found concentrating on multi-band, analytic satellite imagery. Satellite images often include a panchromatic band, which has higher spatial resolution but lower spectral resolution than the other bands. In the field of remote sensing, there is a long tradition of applying pan-sharpening to satellite images, i.e. bringing the multispectral bands to the higher spatial resolution by merging them with the panchromatic band. To our knowledge there are so far no approaches to super-resolution which take advantage of the panchromatic band. In this paper we propose a method to train state-of-the-art CNNs using pairs of lower-resolution multispectral and high-resolution pan-sharpened image tiles in order to create super-resolved analytic images. The derived quality metrics show that the method improves information content of the processed images. We compare the results created by four CNN architectures, with RedNet30 performing best.

scholarly journals Remote Sensing Single-Image Resolution Improvement Using A Deep Gradient-Aware Network with Image-Specific Enhancement

2020 ◽  
Vol 12 (5) ◽  
pp. 758 ◽  
Author(s):  
Mengjiao Qin ◽  
Sébastien Mavromatis ◽  
Linshu Hu ◽  
Feng Zhang ◽  
Renyi Liu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Spatial Resolution ◽  
Super Resolution ◽  
Image Resolution ◽  
Single Image ◽  
Remote Sensing Images ◽  
Practical Applications ◽  
Specific Enhancement ◽  
Urban Monitoring ◽  
High Resolution Images

Super-resolution (SR) is able to improve the spatial resolution of remote sensing images, which is critical for many practical applications such as fine urban monitoring. In this paper, a new single-image SR method, deep gradient-aware network with image-specific enhancement (DGANet-ISE) was proposed to improve the spatial resolution of remote sensing images. First, DGANet was proposed to model the complex relationship between low- and high-resolution images. A new gradient-aware loss was designed in the training phase to preserve more gradient details in super-resolved remote sensing images. Then, the ISE approach was proposed in the testing phase to further improve the SR performance. By using the specific features of each test image, ISE can further boost the generalization capability and adaptability of our method on inexperienced datasets. Finally, three datasets were used to verify the effectiveness of our method. The results indicate that DGANet-ISE outperforms the other 14 methods in the remote sensing image SR, and the cross-database test results demonstrate that our method exhibits satisfactory generalization performance in adapting to new data.

scholarly journals SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS

2016 ◽  
Vol XLI-B3 ◽  
pp. 883-890 ◽  
Author(s):  
L. Liebel ◽  
M. Körner
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Spatial Resolution ◽  
Super Resolution ◽  
Remote Sensing Data ◽  
Single Image ◽  
Sensing Data ◽  
Multispectral Remote Sensing ◽  
Image Super Resolution ◽  
Single Image Super Resolution

In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for <i>single-image super resolution</i> are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations—e.g., segmentation or feature extraction—can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of <i>deep learning</i> techniques, such as <i>convolutional neural networks</i> (CNN), can successfully be applied to remote sensing data. With a huge amount of training data available, <i>end-to-end learning</i> is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. <br><br> We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

scholarly journals Convolutional Neural Networks for High Spatial Resolution Remote Sensing Image Classification

2021 ◽  
Author(s):  
Rajagopal T K P ◽  
Sakthi G ◽  
Prakash J
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Remote Sensing Data ◽  
Remote Sensing Image ◽  
Sensing Data

Abstract Hyperspectral remote sensing based image classification is found to be a very widely used method employed for scene analysis that is from a remote sensing data which is of a high spatial resolution. Classification is a critical task in the processing of remote sensing. On the basis of the fact that there are different materials with reflections in a particular spectral band, all the traditional pixel-wise classifiers both identify and also classify all materials on the basis of their spectral curves (or pixels). Owing to the dimensionality of the remote sensing data of high spatial resolution along with a limited number of labelled samples, a remote sensing image of a high spatial resolution tends to suffer from something known as the Hughes phenomenon which can pose a serious problem. In order to overcome such a small-sample problem, there are several methods of learning like the Support Vector Machine (SVM) along with the other methods that are kernel based and these were introduced recently for a remote sensing classification of the image and this has shown a good performance. For the purpose of this work, an SVM along with Radial Basis Function (RBF) method was proposed. But, a feature learning approach for the classification of the hyperspectral image is based on the Convolutional Neural Networks (CNNs). The results of the experiment that were based on various image datasets that were hyperspectral which implies that the method proposed will be able to achieve a better performance of classification compared to other traditional methods like the SVM and the RBF kernel and also all conventional methods based on deep learning (CNN).

scholarly journals Deep Distillation Recursive Network for Remote Sensing Imagery Super-Resolution

2018 ◽  
Vol 10 (11) ◽  
pp. 1700 ◽  
Author(s):  
Kui Jiang ◽  
Zhongyuan Wang ◽  
Peng Yi ◽  
Junjun Jiang ◽  
Jing Xiao ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Video Processing ◽  
Satellite Images ◽  
State Of The Art ◽  
Satellite Image ◽  
Super Resolution ◽  
Poor Performance ◽  
Feature Maps ◽  
Deep Convolutional Neural Networks ◽  
Frequency Components

Deep convolutional neural networks (CNNs) have been widely used and achieved state-of-the-art performance in many image or video processing and analysis tasks. In particular, for image super-resolution (SR) processing, previous CNN-based methods have led to significant improvements, when compared with shallow learning-based methods. However, previous CNN-based algorithms with simple direct or skip connections are of poor performance when applied to remote sensing satellite images SR. In this study, a simple but effective CNN framework, namely deep distillation recursive network (DDRN), is presented for video satellite image SR. DDRN includes a group of ultra-dense residual blocks (UDB), a multi-scale purification unit (MSPU), and a reconstruction module. In particular, through the addition of rich interactive links in and between multiple-path units in each UDB, features extracted from multiple parallel convolution layers can be shared effectively. Compared with classical dense-connection-based models, DDRN possesses the following main properties. (1) DDRN contains more linking nodes with the same convolution layers. (2) A distillation and compensation mechanism, which performs feature distillation and compensation in different stages of the network, is also constructed. In particular, the high-frequency components lost during information propagation can be compensated in MSPU. (3) The final SR image can benefit from the feature maps extracted from UDB and the compensated components obtained from MSPU. Experiments on Kaggle Open Source Dataset and Jilin-1 video satellite images illustrate that DDRN outperforms the conventional CNN-based baselines and some state-of-the-art feature extraction approaches.

scholarly journals PlanetScope Radiometric Normalization and Sentinel-2 Super-Resolution (2.5 m): A Straightforward Spectral-Spatial Fusion of Multi-Satellite Multi-Sensor Images Using Residual Convolutional Neural Networks

2020 ◽  
Vol 12 (15) ◽  
pp. 2366
Author(s):  
Nicolas Latte ◽  
Philippe Lejeune
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
State Of The Art ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
Research Areas ◽  
Novel Method ◽  
Spatial Fusion ◽  
Sentinel 2

Sentinel-2 (S2) imagery is used in many research areas and for diverse applications. Its spectral resolution and quality are high but its spatial resolutions, of at most 10 m, is not sufficient for fine scale analysis. A novel method was thus proposed to super-resolve S2 imagery to 2.5 m. For a given S2 tile, the 10 S2 bands (four at 10 m and six at 20 m) were fused with additional images acquired at higher spatial resolution by the PlanetScope (PS) constellation. The radiometric inconsistencies between PS microsatellites were normalized. Radiometric normalization and super-resolution were achieved simultaneously using state-of–the-art super-resolution residual convolutional neural networks adapted to the particularities of S2 and PS imageries (including masks of clouds and shadows). The method is described in detail, from image selection and downloading to neural network architecture, training, and prediction. The quality was thoroughly assessed visually (photointerpretation) and quantitatively, confirming that the proposed method is highly spatially and spectrally accurate. The method is also robust and can be applied to S2 images acquired worldwide at any date.

scholarly journals SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS

2016 ◽  
Vol XLI-B3 ◽  
pp. 883-890 ◽  
Author(s):  
L. Liebel ◽  
M. Körner
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Spatial Resolution ◽  
Super Resolution ◽  
Remote Sensing Data ◽  
Single Image ◽  
Sensing Data ◽  
Multispectral Remote Sensing ◽  
Image Super Resolution ◽  
Single Image Super Resolution

In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for <i>single-image super resolution</i> are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations—e.g., segmentation or feature extraction—can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of <i>deep learning</i> techniques, such as <i>convolutional neural networks</i> (CNN), can successfully be applied to remote sensing data. With a huge amount of training data available, <i>end-to-end learning</i> is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. <br><br> We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

scholarly journals Residual Compensation Networks for Heterogeneous Face Recognition

2019 ◽  
Vol 33 ◽  
pp. 8239-8246 ◽  
Author(s):  
Zhongying Deng ◽  
Xiaojiang Peng ◽  
Yu Qiao
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Learning Strategies ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
State Of The Art ◽  
The Other ◽  
Training Images ◽  
Heterogeneous Face Recognition ◽  
Cosine Distance

Heterogeneous Face Recognition (HFR) is a challenging task due to large modality discrepancy as well as insufficient training images in certain modalities. In this paper, we propose a new two-branch network architecture, termed as Residual Compensation Networks (RCN), to learn separated features for different modalities in HFR. The RCN incorporates a residual compensation (RC) module and a modality discrepancy loss (MD loss) into traditional convolutional neural networks. The RC module reduces modal discrepancy by adding compensation to one of the modalities so that its representation can be close to the other modality. The MD loss alleviates modal discrepancy by minimizing the cosine distance between different modalities. In addition, we explore different architectures and positions for the RC module, and evaluate different transfer learning strategies for HFR. Extensive experiments on IIIT-D Viewed Sketch, Forensic Sketch, CASIA NIR-VIS 2.0 and CUHK NIR-VIS show that our RCN outperforms other state-of-the-art methods significantly.

Sign in / Sign up

Export Citation Format

Share Document