Using GAN Neural Networks for Super-Resolution Reconstruction of Temperature Fields

A Generative Adversarial Neural(GAN)network is designed based on deep learning for the Super-Resolution(SR)reconstruction task of temperaturefields(comparable to downscaling in the meteorologicalfield),which is limited by the small number of ground stations and the sparse distribution of observations,resulting in a lack offineness of data.To improve the network’s generalization performance,the residual structure,and batch normalization are used.Applying the nearest interpolation method to avoid over-smoothing of the climate element values instead of the conventional Bicubic interpolation in the computer visionfield.Sub-pixel convolution is used instead of transposed convolution or interpolation methods for up-sampling to speed up network inference.The experimental dataset is the European Centre for Medium-Range Weather Forecasts Reanalysis v5(ERA5)with a bidirectional resolution of 0:1°×0:1°.On the other hand,the task aims to scale up the size by a factor of 8,which is rare compared to conventional methods.The comparison methods include traditional interpolation methods and a more widely used GAN-based network such as the SRGAN.Thefinal experimental results show that the proposed scheme advances the performance of Root Mean Square Error(RMSE)by 37.25%,the Peak Signal-to-noise Ratio(PNSR)by 14.4%,and the Structural Similarity(SSIM)by 10.3%compared to the Bicubic Interpolation.For the traditional SRGAN network,a relatively obvious performance improvement is observed by experimental demonstration.Meanwhile,the GAN network can converge stably and reach the approximate Nash equilibrium for various initialization parameters to empirically illustrate the effectiveness of the method in the temperature fields.

Single frame super-resolution reconstruction based on sparse representation

In order to effectively improve the quality of recovered images, a single frame super-resolution reconstruction method based on sparse representation is proposed. The combination method of local orientation estimation-based image patch clustering and principal component analysis is used to obtain a series of geometric dictionaries of different orientations in the dictionary learning process. Subsequently, the dictionary of the nearest orientation is adaptively assigned to each of the input patches that need to be represented in the sparse coding process. Moreover, the consistency of gradients is further incorporated into the basic framework to make more substantial progress in preserving more fine edges and producing sharper results. Two groups of experiments on different types of natural images indicate that the proposed method outperforms some state-of- the-art counterparts in terms of both numerical indicators and visual quality.

Image super-resolution reconstruction based on sparse representation and residual compensation

A super-resolution reconstruction algorithm is proposed. The algorithm is based on the idea of the sparse representation of signals, by using the fact that the sparsest representation of a sig- nal is unique as the constraint of the patched-based reconstruction, and compensating residual errors of the reconstruction results both locally and globally to solve the distortion problem in patch-based reconstruction algorithms. Three reconstruction algorithms are compared. The results show that the images reconstructed with the new algorithm have the best quality.

Super-resolution reconstruction based on CNN:A case study of Jilin-1 multispectral data

MS or MS+PAN is usually applied separately in convolutional neural network(CNN)resolution reconstruction to obtain high-resolution MS images,but the difference between the two datasets is rarely studied.This paper introduced a dual-channel network and took MS and MS+PAN of Jilin-1 spectrum satellites as two datasets to evaluate the performance of CNN resolution reconstruction,and analyzed the difference with bicubic and GS methods.The result of CNN reconstruction shows that MS+PAN dataset performed better than MS,with about 6%improvement in spatial and spectral components,and the overall quality of MS+PAN dataset was slightly higher than that of MS dataset,with QNR from 0.9559 to 0.9584.The bicubic performed best in spectral components with the quality value of 0.017,and GS performed best in spatial components with the quality values of 0.0443.CNN showed similar performance in spectral and spatial components with the two traditional methods and achieved the best overall quality with QNR value of 0.9584.

Super-resolution reconstruction for license plate images of moving vehicles

A novel reconstruction method to improve the recognition of license plate texts of moving vehicles in real traffic videos is proposed, which fuses complimentary information among low resolution （LR） images to yield a high resolution （HR） image. Based on the regularization super-resolution （SR） reconstruction schemes, this paper first introduces a residual gradient （RG） term as a new regularization term to improve the quality of the reconstructed image. Moreover, L1 norm is used to measure the residual data （RD） term and the RG term in order to improve the robustness of the proposed method. Finally, the steepest descent method is exploited to solve the energy functional. Simulated and real acquired video sequence experiments show the effectiveness and practicability of the proposed method and demonstrate its superiority over the bi-cubic interpolation and discontinuity adaptive Markov random field （DAMRF） SR method in both signal to noise ratios （SNR） and visual effects.

Super-resolution reconstruction of synthetic-aperture radar image using adaptive-threshold singular value decomposition technique

A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function （PSF） matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar （SAR） images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio （SNR）. Five versions of SVD algorithms, namely 1 ） using all singular values, 2） using the top 80% singular values, 3） using the top 50% singular values, 4） using the top 20% singular values and 5） using singular values s such that S2≥/max（s2）/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/（rinSNR）1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.

A Fast Super-Resolution Reconstruction from Image Sequence

Based on the mechanism of imagery, a novel method called the delaminating combining template method, used for the problem of super-resolution reconstruction from image sequence, is described in this paper. The combining template method contains two steps： a delaminating strategy and a combining template algorithm. The delaminating strategy divides the original problem into several sub-problems; each of them is only eonnected to one degrading factor. The combining template algorithm is suggested to resolve each sub-problem. In addition, to verify the valid of the method, a new index called oriental entropy is presented. The results from the theoretical analysis and experiments illustrate that this method to be promising and efficient.

Spatio-Temporal Adaptive Super-Resolution Reconstruction Model Based on Zemike Moment for Spatial Video Sequences

Video Super-Resolution （SR） reconstruction produces video sequences with High Resolution （HR） via the fusion of several Low-Resolution （LR） video frames. Traditional methods rely on the accurate estimation of subpixel motion, which constrains their applicability to video sequences with relatively simple motions such as global translation. We propose an efficient iterative spatio-temporal adaptive SR reconstruction model based on Zemike Moment （ZM）, which is effective for spatial video sequences with arbitrary motion. The model uses region correlation judgment and self-adaptive threshold strategies to improve the effect and time efficiency of the ZM-based SR method. This leads to better mining of non-local self-similarity and local structural regularity, and is robust to noise and rotation. An efficient iterative curvature-based interpolation scheme is introduced to obtain the initial HR estimation of each LR video frame. Experimental results both on spatial and standard video sequences demonstrate that the proposed method outperforms existing methods in terms of both subjective visual and objective quantitative evaluations, and greatly improves the time efficiency.

A NOVEL ALGORITHM OF SUPER-RESOLUTION RECONSTRUCTION FOR COMPRESSED VIDEO

Super-Resolution (SR) technique means to reconstruct High-Resolution (HR) images from a sequence of Low-Resolution (LR) observations,which has been a great focus for compressed video. Based on the theory of Projection Onto Convex Set (POCS),this paper constructs Quantization Constraint Set (QCS) using the quantization information extracted from the video bit stream. By combining the statistical properties of image and the Human Visual System (HVS),a novel Adaptive Quantization Constraint Set (AQCS) is proposed. Simulation results show that AQCS-based SR al-gorithm converges at a fast rate and obtains better performance in both objective and subjective quality,which is applicable for compressed video.

A NOVEL METHOD TO REALIZE COMPRESSED VIDEO SUPER-RESOLUTION RECONSTRUCTION

This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.

Anisotropic fourth-order diffusion regularization for multiframe super-resolution reconstruction

A novel rcgularization-based approach is presented for super-resolution reconstruction in order to achieve good tradeoff between noise removal and edge preservation. The method is developed by using L1 norm as data fidelity term and anisotropic fourth-order diffusion model as a regularization item to constrain the smoothness of the reconstructed images. To evaluate and prove the performance of the proposed method, series of experiments and comparisons with some existing methods including bi-cubic interpolation method and bilateral total variation method are carried out. Numerical results on synthetic data show that the PSNR improvement of the proposed method is approximately 1.0906 dB on average compared to bilateral total variation method, and the results on real videos indicate that the proposed algorithm is also effective in terms of removing visual artifacts and preserving edges in restored images.

Image Super-Resolution Reconstruction Based on Dual Residual Network

Research shows that deep learning algorithms can ffectivelyimprove a single image's super-resolution quality.However,if the algorithmis solely focused on increasing network depth and the desired result is not achieved,difficulties in the training process are more likely to arise.Simultaneously,the function space that can be transferred from a iow-resolution image to a high-resolution image is enormous,making finding a satisfactory solution difficult.In this paper,we propose a deep learning method for single image super-resolution.The MDRN network framework uses multi-scale residual blocks and dual learning to fully acquire features in low-resolution images.Finally,these features will be sent to the image reconstruction module torestore high-quality images.The function space is constrained by the closedloop formed by dual learning,which provides additional supervision forthe super-resolution reconstruction of the image.The up-sampling processincludes residual blocks with short-hop connections,so that the networkfocuses on learning high-frequency information,and strives to reconstructimages with richer feature details.The experimental results of ×4 and ×8 super-resolution reconstruction of the image show that the quality of thereconstructed image with this method is better than some existing experimental results of image super-resolution reconstruction in subjective visual ffectsand objective evaluation indicators.

Transformer and GAN-Based Super-Resolution Reconstruction Network for Medical Images

Super-resolution reconstruction in medical imaging has become more demanding due to the necessity of obtaining high-quality images with minimal radiation dose,such as in low-field magnetic resonance imaging(MRI).However,image super-resolution reconstruction remains a difficult task because of the complexity and high textual requirements for diagnosis purpose.In this paper,we offer a deep learning based strategy for reconstructing medical images from low resolutions utilizing Transformer and generative adversarial networks(T-GANs).The integrated system can extract more precise texture information and focus more on important locations through global image matching after successfully inserting Transformer into the generative adversarial network for picture reconstruction.Furthermore,we weighted the combination of content loss,adversarial loss,and adversarial feature loss as the final multi-task loss function during the training of our proposed model T-GAN.In comparison to established measures like peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM),our suggested T-GAN achieves optimal performance and recovers more texture features in super-resolution reconstruction of MRI scanned images of the knees and belly.

IMAGE SUPER-RESOLUTION RECONSTRUCTION BY HUBER REGULARIZATION AND TAILORED FINITE POINT METHOD

In this paper,we propose using the tailored finite point method(TFPM)to solve the resulting parabolic or elliptic equations when minimizing the Huber regularization based image super-resolution model using the augmented Lagrangian method(ALM).The Hu-ber regularization based image super-resolution model can ameliorate the staircase for restored images.TFPM employs the method of weighted residuals with collocation tech-nique,which helps get more accurate approximate solutions to the equations and reserve more details in restored images.We compare the new schemes with the Marquina-Osher model,the image super-resolution convolutional neural network(SRCNN)and the classical interpolation methods:bilinear interpolation,nearest-neighbor interpolation and bicubic interpolation.Numerical experiments are presented to demonstrate that with the new schemes the quality of the super-resolution images has been improved.Besides these,the existence of the minimizer of the Huber regularization based image super-resolution model and the convergence of the proposed algorithm are also established in this paper.

Combination of super-resolution reconstruction and SGA-Net for marsh vegetation mapping using multi-resolution multispectral and hyperspectral images

Vegetation is crucial for wetland ecosystems.Human activities and climate changes are increasingly threatening wetland ecosystems.Combining satellite images and deep learning for classifying marsh vegetation communities has faced great challenges because of its coarse spatial resolution and limited spectral bands.This study aimed to propose a method to classify marsh vegetation using multi-resolution multispectral and hyperspectral images,combining super-resolution techniques and a novel self-constructing graph attention neural network(SGA-Net)algorithm.The SGA-Net algorithm includes a decoding layer(SCE-Net)to preciselyfine marsh vegetation classification in Honghe National Nature Reserve,Northeast China.The results indicated that the hyperspectral reconstruction images based on the super-resolution convolutional neural network(SRCNN)obtained higher accuracy with a peak signal-to-noise ratio(PSNR)of 28.87 and structural similarity(SSIM)of 0.76 in spatial quality and root mean squared error(RMSE)of 0.11 and R^(2) of 0.63 in spectral quality.The improvement of classification accuracy(MIoU)by enhanced super-resolution generative adversarial network(ESRGAN)(6.19%)was greater than that of SRCNN(4.33%)and super-resolution generative adversarial network(SRGAN)(3.64%).In most classification schemes,the SGA-Net outperformed DeepLabV3+and SegFormer algorithms for marsh vegetation and achieved the highest F1-score(78.47%).This study demonstrated that collaborative use of super-resolution reconstruction and deep learning is an effective approach for marsh vegetation mapping.

Deep learning method for super-resolution reconstruction of the spatio-temporal flow field

The high-resolution(HR)spatio-temporal flow field plays a decisive role in describing the details of the flow field.In the acquisition of the HR flow field,traditional direct numerical simulation(DNS)and other methods face a seriously high computational burden.To address this deficiency,we propose a novel multi-scale temporal path UNet(MST-UNet)model to reconstruct temporal and spatial HR flow fields from low-resolu-tion(LR)flow field data.Different from the previous super-resolution(SR)model,which only takes advantage of LR flow field data at instantaneous(SLR)or in a time-series(MTLR),MST-UNet introduces multi-scale information in both time and space.MST-UNet takes the LR data at the current frame and the predicted HR result at the previous moment as the model input to complete the spatial SR reconstruction.On this basis,a temporal model is introduced as the inbetweening model to obtain HR flow field data in space and time to complete spatio-temporal SR reconstruction.Finally,the proposed model is validated by the spatio-temporal SR task of the flow field around two-dimen-sional cylinders.Experimental results show that the outcome of the MST-UNet model in spatial SR tasks is much better than those of SLR and MTLR,which can greatly improve prediction accuracy.In addition,for the spatio-temporal SR task,the spatio-temporal HR flow field predicted by the MST-UNet model has higher accuracy either.

FPGA-based position reconstruction method for neutron beam flux spatial distribution measurement in BNCT

A new measurement method for the spatial distribution of neutron beam flux in boron neutron capture therapy(BNCT)is being developed based on the two-dimensional Micromegas detector.To address the issue of long processing times in traditional offline position reconstruction methods,this paper proposes a field programmable gate array based online position reconstruction method utilizing the micro-time projection chamber principle.This method encapsulates key technical aspects:a self-adaptive serial link technique built upon the dynamical adjustment of the delay chain length,fast sorting,a coordinate-matching technique based on the mapping between signal timestamps and random access memory(RAM)addresses,and a precise start point-merging technique utilizing a circular combined RAM.The performance test of the selfadaptive serial link shows that the bit error rate of the link is better than 10-12 at a confidence level of 99%,ensuring reliable data transmission.The experiment utilizing the readout electronics and Micromegas detector shows a spatial resolution of approximately 1.4 mm,surpassing the current method’s resolution level of 5 mm.The beam experiment confirms that the readout electronics system can obtain the flux spatial distribution of neutron beams online,thus validating the feasibility of the position reconstruction method.The online position reconstruction method avoids traditional methods,such as bubble sorting and traversal searching,simplifies the design of the logic firmware,and reduces the time complexity from O(n2)to O(n).This study contributes to the advancement in measuring neutron beam flux for BNCT.

Reactor field reconstruction from sparse and movable sensors using Voronoi tessellation-assisted convolutional neural networks

The aging of operational reactors leads to increased mechanical vibrations in the reactor interior.The vibration of the incore sensors near their nominal locations is a new problem for neutronic field reconstruction.Current field-reconstruction methods fail to handle spatially moving sensors.In this study,we propose a Voronoi tessellation technique in combination with convolutional neural networks to handle this challenge.Observations from movable in-core sensors were projected onto the same global field structure using Voronoi tessellation,holding the magnitude and location information of the sensors.General convolutional neural networks were used to learn maps from observations to the global field.The proposed method reconstructed multi-physics fields(including fast flux,thermal flux,and power rate)using observations from a single field(such as thermal flux).Numerical tests based on the IAEA benchmark demonstrated the potential of the proposed method in practical engineering applications,particularly within an amplitude of 5 cm around the nominal locations,which led to average relative errors below 5% and 10% in the L_(2) and L_(∞)norms,respectively.

Sparse Modal Decomposition Method Addressing Underdetermined Vortex-Induced Vibration Reconstruction Problem for Marine Risers

When investigating the vortex-induced vibration(VIV)of marine risers,extrapolating the dynamic response on the entire length based on limited sensor measurements is a crucial step in both laboratory experiments and fatigue monitoring of real risers.The problem is conventionally solved using the modal decomposition method,based on the principle that the response can be approximated by a weighted sum of limited vibration modes.However,the method is not valid when the problem is underdetermined,i.e.,the number of unknown mode weights is more than the number of known measurements.This study proposed a sparse modal decomposition method based on the compressed sensing theory and the Compressive Sampling Matching Pursuit(Co Sa MP)algorithm,exploiting the sparsity of VIV in the modal space.In the validation study based on high-order VIV experiment data,the proposed method successfully reconstructed the response using only seven acceleration measurements when the conventional methods failed.A primary advantage of the proposed method is that it offers a completely data-driven approach for the underdetermined VIV reconstruction problem,which is more favorable than existing model-dependent solutions for many practical applications such as riser structural health monitoring.

Estimation-free spatial-domain image reconstruction of structured illumination microscopy

Structured illumination microscopy(SIM)achieves super-resolution(SR)by modulating the high-frequency information of the sample into the passband of the optical system and subsequent image reconstruction.The traditional Wiener-filtering-based reconstruction algorithm operates in the Fourier domain,it requires prior knowledge of the sinusoidal illumination patterns which makes the time-consuming procedure of parameter estimation to raw datasets necessary,besides,the parameter estimation is sensitive to noise or aberration-induced pattern distortion which leads to reconstruction artifacts.Here,we propose a spatial-domain image reconstruction method that does not require parameter estimation but calculates patterns from raw datasets,and a reconstructed image can be obtained just by calculating the spatial covariance of differential calculated patterns and differential filtered datasets(the notch filtering operation is performed to the raw datasets for attenuating and compensating the optical transfer function(OTF)).Experiments on reconstructing raw datasets including nonbiological,biological,and simulated samples demonstrate that our method has SR capability,high reconstruction speed,and high robustness to aberration and noise.