Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered ...Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered by the loss of shallow texture information during feature extraction.To address this limitation,we propose a 3D Convolutional Enhanced Residual Video Super-Resolution Network(3D-ERVSNet).This network employs a forward and backward bidirectional propagation module(FBBPM)that aligns features across frames using explicit optical flow through lightweight SPyNet.By incorporating an enhanced residual structure(ERS)with skip connections,shallow and deep features are effectively integrated,enhancing texture restoration capabilities.Furthermore,3D convolution module(3DCM)is applied after the backward propagation module to implicitly capture spatio-temporal dependencies.The architecture synergizes these components where FBBPM extracts aligned features,ERS fuses hierarchical representations,and 3DCM refines temporal coherence.Finally,a deep feature aggregation module(DFAM)fuses the processed features,and a pixel-upsampling module(PUM)reconstructs the high-resolution(HR)video frames.Comprehensive evaluations on REDS,Vid4,UDM10,and Vim4 benchmarks demonstrate well performance including 30.95 dB PSNR/0.8822 SSIM on REDS and 32.78 dB/0.8987 on Vim4.3D-ERVSNet achieves significant gains over baselines while maintaining high efficiency with only 6.3M parameters and 77ms/frame runtime(i.e.,20×faster than RBPN).The network’s effectiveness stems from its task-specific asymmetric design that balances explicit alignment and implicit fusion.展开更多
Frequency modulated continuous wave(FMCW)radar is an advantageous sensor scheme for target estimation and environmental perception.However,existing algorithms based on discrete Fourier transform(DFT),multiple signal c...Frequency modulated continuous wave(FMCW)radar is an advantageous sensor scheme for target estimation and environmental perception.However,existing algorithms based on discrete Fourier transform(DFT),multiple signal classification(MUSIC)and compressed sensing,etc.,cannot achieve both low complexity and high resolution simultaneously.This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar.Firstly,we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy.Secondly,we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data,which improves the efficiency of continuous target tracking.These two approaches have improved the algorithm efficiency by nearly 2-4 orders of magnitude without losing accuracy and resolution.Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.展开更多
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...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.展开更多
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 su...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.展开更多
Passive millimeter wave （PMMW） images inherently have the problem of poor resolution owing to limited aperture dimension. Thus, efficient post-processing is necessary to achieve resolution improvement. An adaptive p...Passive millimeter wave （PMMW） images inherently have the problem of poor resolution owing to limited aperture dimension. Thus, efficient post-processing is necessary to achieve resolution improvement. An adaptive projected Landweber （APL） super-resolution algorithm using a spectral correction procedure, which attempts to combine the strong points of all of the projected Landweber （PL） iteration and the adaptive relaxation parameter adjustment and the spectral correction method, is proposed. In the algorithm, the PL iterations are implemented as the main image restoration scheme and a spectral correction method is included in which the calculated spectrum within the passband is replaced by the known low frequency component. Then, the algorithm updates the relaxation parameter adaptively at each iteration. A qualitative evaluation of this algorithm is performed with simulated data as well as actual radiometer image captured by 91.5 GHz mechanically scanned radiometer. From experiments, it is found that the super-resolution algorithm obtains better results and enhances the resolution and has lower mean square error （MSE）. These constraints and adaptive character and spectral correction procedures speed up the convergence of the Landweber algorithm and reduce the ringing effects that are caused by regularizing the image restoration problem.展开更多
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...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.展开更多
Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead t...Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.展开更多
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 combini...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.展开更多
With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.He...With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.Hence,designing an efficient short video recommendation method has become important for major network platforms to attract users and satisfy their requirements.Nevertheless,the explosive growth of data leads to the low efficiency of the algorithm,which fails to distill users’points of interest on one hand effectively.On the other hand,integrating user preferences and the content of items urgently intensify the requirements for platform recommendation.In this paper,we propose a collaborative filtering algorithm,integrating time context information and user context,which pours attention into expanding and discovering user interest.In the first place,we introduce the temporal context information into the typical collaborative filtering algorithm,and leverage the popularity penalty function to weight the similarity between recommended short videos and the historical short videos.There remains one more point.We also introduce the user situation into the traditional collaborative filtering recommendation algorithm,considering the context information of users in the generation recommendation stage,and weight the recommended short-formvideos of candidates.At last,a diverse approach is used to generate a Top-K recommendation list for users.And through a case study,we illustrate the accuracy and diversity of the proposed method.展开更多
In order to improve the intelligence of video monitoring system of belt and make up the deficiency of higher failure rate and bad real-time performance in the traditional systems of measurement of belt speed, accordin...In order to improve the intelligence of video monitoring system of belt and make up the deficiency of higher failure rate and bad real-time performance in the traditional systems of measurement of belt speed, according to the fact that the light of coal mine is uneven, the strength of light changes greatly, the direction of belt movement is constant, and the position of camera was fixed, various algorithms of speed measurement by video were studied, and algorithm for template matching based on sum of absolute differences （SAD） and correlation coefficient was proposed and improved, besides, the tracking of feature regions was realized. Then, a camera calibration method using the invariance of the cross-ratio was adopted and the real-time measurement of belt speed by the hardware platform based on DM642 was realized. Finally, experiment results show that this method not only has advantages of high precision and strong anti-jamming capability but also can real-time reflect the changes of belt speed, so it has a comprehensive applicability.展开更多
A real-time electronic image stabilization motion estimation method based on fast sub- block gray projection algorithm is proposed. In the method, each image is divided into a number of sub-blocks, and sub-blocks are ...A real-time electronic image stabilization motion estimation method based on fast sub- block gray projection algorithm is proposed. In the method, each image is divided into a number of sub-blocks, and sub-blocks are sifted with their gray gradients. After removing sub-blocks whose gray gradients are lower than the given threshold, the calculation amount of projection is reduced and the motion estimation accuracy is improved. Then gray projection is done in each remained sub- block, and global motion vector of the image is calculated according to the local motion vectors of sub-blocks and the affine motion model. The drawbacks as the local motions reducing the global mo- tion estimation accuracy and traditional gray projection algorithm could not deal with rotation are re- solved well by this algorithm. The experiment results show that the algorithm is more accurate and efficient than the gray projection algorithm.展开更多
A new method of super-resolution image reconstruction is proposed, which uses a three-step-training error backpropagation neural network （BPNN） to realize the super-resolution reconstruction （SRR） of satellite ima...A new method of super-resolution image reconstruction is proposed, which uses a three-step-training error backpropagation neural network （BPNN） to realize the super-resolution reconstruction （SRR） of satellite image. The method is based on BPNN. First, three groups learning samples with different resolutions are obtained according to image observation model, and then vector mappings are respectively used to those three group learning samples to speed up the convergence of BPNN, at last, three times consecutive training are carried on the BPNN. Training samples used in each step are of higher resolution than those used in the previous steps, so the increasing weights store a great amount of information for SRR, and network performance and generalization ability are improved greatly. Simulation and generalization tests are carried on the well-trained three-step-training NN respectively, and the reconstruction results with higher resolution images verify the effectiveness and validity of this method.展开更多
Image scanning microscopy based on pixel reassignment can improve the confocal resolution limit without losing the image signal-to-noise ratio(SNR)greatly[C.J.R.Sheppard,"Super resolution in confocal imaging,&quo...Image scanning microscopy based on pixel reassignment can improve the confocal resolution limit without losing the image signal-to-noise ratio(SNR)greatly[C.J.R.Sheppard,"Super resolution in confocal imaging,"Optik 80(2)53-54(1988).C.B.Miller,E.Jorg,"Image scanning microscopy,"Phys.Reu.Lett.104(19)198101(2010).C.J.R.Sheppard,s.B.Mehta,R Heintzmann,"Superresolution by image scanning microscopy using pixel reassignment,"Opt.Lett.38(15)28892892(2013)].Here,we use a tailor-made optical fiber and 19 avalanche pho-todiodes(APDs)as parallel detectors to upgrade our existing confocal microscopy,termed as parallel-detection super resolution(PDSR)microscopy.In order to obtain the correct shift value,we use the normalized 2D cross correlation to calculate the shifting value of each image.We characterized our system performance by imaging fuorescence beads and applied this system to observing the 3D structure of biological specimen.展开更多
With the widespread use of the internet,there is an increasing need to ensure the security and privacy of transmitted data.This has led to an intensified focus on the study of video steganography,which is a technique ...With the widespread use of the internet,there is an increasing need to ensure the security and privacy of transmitted data.This has led to an intensified focus on the study of video steganography,which is a technique that hides data within a video cover to avoid detection.The effectiveness of any steganography method depends on its ability to embed data without altering the original video’s quality while maintaining high efficiency.This paper proposes a new method to video steganography,which involves utilizing a Genetic Algorithm(GA)for identifying the Region of Interest(ROI)in the cover video.The ROI is the area in the video that is the most suitable for data embedding.The secret data is encrypted using the Advanced Encryption Standard(AES),which is a widely accepted encryption standard,before being embedded into the cover video,utilizing up to 10%of the cover video.This process ensures the security and confidentiality of the embedded data.The performance metrics for assessing the proposed method are the Peak Signalto-Noise Ratio(PSNR)and the encoding and decoding time.The results show that the proposed method has a high embedding capacity and efficiency,with a PSNR ranging between 64 and 75 dBs,which indicates that the embedded data is almost indistinguishable from the original video.Additionally,the method can encode and decode data quickly,making it efficient for real-time applications.展开更多
This paper presents a new kernel-based algorithm for video object tracking called rebound of region of interest (RROI). The novel algorithm uses a rectangle-shaped section as region of interest (ROI) to represent and ...This paper presents a new kernel-based algorithm for video object tracking called rebound of region of interest (RROI). The novel algorithm uses a rectangle-shaped section as region of interest (ROI) to represent and track specific objects in videos. The proposed algorithm is constituted by two stages. The first stage seeks to determine the direction of the object’s motion by analyzing the changing regions around the object being tracked between two consecutive frames. Once the direction of the object’s motion has been predicted, it is initialized an iterative process that seeks to minimize a function of dissimilarity in order to find the location of the object being tracked in the next frame. The main advantage of the proposed algorithm is that, unlike existing kernel-based methods, it is immune to highly cluttered conditions. The results obtained by the proposed algorithm show that the tracking process was successfully carried out for a set of color videos with different challenging conditions such as occlusion, illumination changes, cluttered conditions, and object scale changes.展开更多
In the realm of contemporary artificial intelligence,machine learning enables automation,allowing systems to naturally acquire and enhance their capabilities through learning.In this cycle,Video recommendation is fini...In the realm of contemporary artificial intelligence,machine learning enables automation,allowing systems to naturally acquire and enhance their capabilities through learning.In this cycle,Video recommendation is finished by utilizing machine learning strategies.A suggestion framework is an interaction of data sifting framework,which is utilized to foresee the“rating”or“inclination”given by the different clients.The expectation depends on past evaluations,history,interest,IMDB rating,and so on.This can be carried out by utilizing collective and substance-based separating approaches which utilize the data given by the different clients,examine them,and afterward suggest the video that suits the client at that specific time.The required datasets for the video are taken from Grouplens.This recommender framework is executed by utilizing Python Programming Language.For building this video recommender framework,two calculations are utilized,for example,K-implies Clustering and KNN grouping.K-implies is one of the unaided AI calculations and the fundamental goal is to bunch comparable sort of information focuses together and discover the examples.For that K-implies searches for a steady‘k'of bunches in a dataset.A group is an assortment of information focuses collected due to specific similitudes.K-Nearest Neighbor is an administered learning calculation utilized for characterization,with the given information;KNN can group new information by examination of the‘k'number of the closest information focuses.The last qualities acquired are through bunching qualities and root mean squared mistake,by using this algorithm we can recommend videos more appropriately based on user previous records and ratings.展开更多
Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic an...Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic and lightweight SR framework designed for arbitrary scaling factors.DDNet integrates a residual learning structure with an Adaptively fusion Feature Block(AFB)and a scale-aware upsampling module,effectively reducing parameter overhead while preserving reconstruction quality.Additionally,we introduce DDNetGAN,an enhanced variant that leverages a relativistic Generative Adversarial Network(GAN)to further improve texture realism.To validate the proposed models,we conduct extensive training using the DIV2K and Flickr2K datasets and evaluate performance across standard benchmarks including Set5,Set14,Urban100,Manga109,and BSD100.Our experiments cover both symmetric and asymmetric upscaling factors and incorporate ablation studies to assess key components.Results show that DDNet and DDNetGAN achieve competitive performance compared with mainstream SR algorithms,demonstrating a strong balance between accuracy,efficiency,and flexibility.These findings highlight the potential of our approach for practical real-world super-resolution applications.展开更多
基金supported in part by the Basic and Applied Basic Research Foundation of Guangdong Province[2025A1515011566]in part by the State Key Laboratory for Novel Software Technology,Nanjing University[KFKT2024B08]+1 种基金in part by Leading Talents in Gusu Innovation and Entrepreneurship[ZXL2023170]in part by the Basic Research Programs of Taicang 2024,[TC2024JC32].
文摘Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered by the loss of shallow texture information during feature extraction.To address this limitation,we propose a 3D Convolutional Enhanced Residual Video Super-Resolution Network(3D-ERVSNet).This network employs a forward and backward bidirectional propagation module(FBBPM)that aligns features across frames using explicit optical flow through lightweight SPyNet.By incorporating an enhanced residual structure(ERS)with skip connections,shallow and deep features are effectively integrated,enhancing texture restoration capabilities.Furthermore,3D convolution module(3DCM)is applied after the backward propagation module to implicitly capture spatio-temporal dependencies.The architecture synergizes these components where FBBPM extracts aligned features,ERS fuses hierarchical representations,and 3DCM refines temporal coherence.Finally,a deep feature aggregation module(DFAM)fuses the processed features,and a pixel-upsampling module(PUM)reconstructs the high-resolution(HR)video frames.Comprehensive evaluations on REDS,Vid4,UDM10,and Vim4 benchmarks demonstrate well performance including 30.95 dB PSNR/0.8822 SSIM on REDS and 32.78 dB/0.8987 on Vim4.3D-ERVSNet achieves significant gains over baselines while maintaining high efficiency with only 6.3M parameters and 77ms/frame runtime(i.e.,20×faster than RBPN).The network’s effectiveness stems from its task-specific asymmetric design that balances explicit alignment and implicit fusion.
基金funded by the National Natural Science Foundation of China,grant number 42074176,U1939204。
文摘Frequency modulated continuous wave(FMCW)radar is an advantageous sensor scheme for target estimation and environmental perception.However,existing algorithms based on discrete Fourier transform(DFT),multiple signal classification(MUSIC)and compressed sensing,etc.,cannot achieve both low complexity and high resolution simultaneously.This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar.Firstly,we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy.Secondly,we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data,which improves the efficiency of continuous target tracking.These two approaches have improved the algorithm efficiency by nearly 2-4 orders of magnitude without losing accuracy and resolution.Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.
基金the Natural Science Foundation of Jiangsu Province (No.BK2004151).
文摘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.
基金the National Basic Research Program of China (973 Program) under Grant No.2012CB821200，the National Natural Science Foundation of China under Grants No.91024001,No.61070142，the Beijing Natural Science Foundation under Grant No.4111002
文摘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.
基金the National Natural Science Foundation of China (60632020).
文摘Passive millimeter wave （PMMW） images inherently have the problem of poor resolution owing to limited aperture dimension. Thus, efficient post-processing is necessary to achieve resolution improvement. An adaptive projected Landweber （APL） super-resolution algorithm using a spectral correction procedure, which attempts to combine the strong points of all of the projected Landweber （PL） iteration and the adaptive relaxation parameter adjustment and the spectral correction method, is proposed. In the algorithm, the PL iterations are implemented as the main image restoration scheme and a spectral correction method is included in which the calculated spectrum within the passband is replaced by the known low frequency component. Then, the algorithm updates the relaxation parameter adaptively at each iteration. A qualitative evaluation of this algorithm is performed with simulated data as well as actual radiometer image captured by 91.5 GHz mechanically scanned radiometer. From experiments, it is found that the super-resolution algorithm obtains better results and enhances the resolution and has lower mean square error （MSE）. These constraints and adaptive character and spectral correction procedures speed up the convergence of the Landweber algorithm and reduce the ringing effects that are caused by regularizing the image restoration problem.
基金Supported by the Natural Science Foundation of Jiangsu Province (No. BK2004151).
文摘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.
基金Supported by Open Project of the Ministry of Industry and Information Technology Key Laboratory of Performance and Reliability Testing and Evaluation for Basic Software and Hardware。
文摘Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.
文摘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.
文摘With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.Hence,designing an efficient short video recommendation method has become important for major network platforms to attract users and satisfy their requirements.Nevertheless,the explosive growth of data leads to the low efficiency of the algorithm,which fails to distill users’points of interest on one hand effectively.On the other hand,integrating user preferences and the content of items urgently intensify the requirements for platform recommendation.In this paper,we propose a collaborative filtering algorithm,integrating time context information and user context,which pours attention into expanding and discovering user interest.In the first place,we introduce the temporal context information into the typical collaborative filtering algorithm,and leverage the popularity penalty function to weight the similarity between recommended short videos and the historical short videos.There remains one more point.We also introduce the user situation into the traditional collaborative filtering recommendation algorithm,considering the context information of users in the generation recommendation stage,and weight the recommended short-formvideos of candidates.At last,a diverse approach is used to generate a Top-K recommendation list for users.And through a case study,we illustrate the accuracy and diversity of the proposed method.
文摘In order to improve the intelligence of video monitoring system of belt and make up the deficiency of higher failure rate and bad real-time performance in the traditional systems of measurement of belt speed, according to the fact that the light of coal mine is uneven, the strength of light changes greatly, the direction of belt movement is constant, and the position of camera was fixed, various algorithms of speed measurement by video were studied, and algorithm for template matching based on sum of absolute differences （SAD） and correlation coefficient was proposed and improved, besides, the tracking of feature regions was realized. Then, a camera calibration method using the invariance of the cross-ratio was adopted and the real-time measurement of belt speed by the hardware platform based on DM642 was realized. Finally, experiment results show that this method not only has advantages of high precision and strong anti-jamming capability but also can real-time reflect the changes of belt speed, so it has a comprehensive applicability.
基金Supported by the National Defense Scientific Research Project （ B2220132013 ）
文摘A real-time electronic image stabilization motion estimation method based on fast sub- block gray projection algorithm is proposed. In the method, each image is divided into a number of sub-blocks, and sub-blocks are sifted with their gray gradients. After removing sub-blocks whose gray gradients are lower than the given threshold, the calculation amount of projection is reduced and the motion estimation accuracy is improved. Then gray projection is done in each remained sub- block, and global motion vector of the image is calculated according to the local motion vectors of sub-blocks and the affine motion model. The drawbacks as the local motions reducing the global mo- tion estimation accuracy and traditional gray projection algorithm could not deal with rotation are re- solved well by this algorithm. The experiment results show that the algorithm is more accurate and efficient than the gray projection algorithm.
文摘A new method of super-resolution image reconstruction is proposed, which uses a three-step-training error backpropagation neural network （BPNN） to realize the super-resolution reconstruction （SRR） of satellite image. The method is based on BPNN. First, three groups learning samples with different resolutions are obtained according to image observation model, and then vector mappings are respectively used to those three group learning samples to speed up the convergence of BPNN, at last, three times consecutive training are carried on the BPNN. Training samples used in each step are of higher resolution than those used in the previous steps, so the increasing weights store a great amount of information for SRR, and network performance and generalization ability are improved greatly. Simulation and generalization tests are carried on the well-trained three-step-training NN respectively, and the reconstruction results with higher resolution images verify the effectiveness and validity of this method.
基金sponsored by National Natural Science Foundation of China(61827825 and 61735017)Fundamental Research Funds for the Central Universities(2019XZZX003-06)+1 种基金Natural Science Foundation of Zhejiang province(LR16F050001)Zhejiang Lab(2018EB0ZX01).
文摘Image scanning microscopy based on pixel reassignment can improve the confocal resolution limit without losing the image signal-to-noise ratio(SNR)greatly[C.J.R.Sheppard,"Super resolution in confocal imaging,"Optik 80(2)53-54(1988).C.B.Miller,E.Jorg,"Image scanning microscopy,"Phys.Reu.Lett.104(19)198101(2010).C.J.R.Sheppard,s.B.Mehta,R Heintzmann,"Superresolution by image scanning microscopy using pixel reassignment,"Opt.Lett.38(15)28892892(2013)].Here,we use a tailor-made optical fiber and 19 avalanche pho-todiodes(APDs)as parallel detectors to upgrade our existing confocal microscopy,termed as parallel-detection super resolution(PDSR)microscopy.In order to obtain the correct shift value,we use the normalized 2D cross correlation to calculate the shifting value of each image.We characterized our system performance by imaging fuorescence beads and applied this system to observing the 3D structure of biological specimen.
文摘With the widespread use of the internet,there is an increasing need to ensure the security and privacy of transmitted data.This has led to an intensified focus on the study of video steganography,which is a technique that hides data within a video cover to avoid detection.The effectiveness of any steganography method depends on its ability to embed data without altering the original video’s quality while maintaining high efficiency.This paper proposes a new method to video steganography,which involves utilizing a Genetic Algorithm(GA)for identifying the Region of Interest(ROI)in the cover video.The ROI is the area in the video that is the most suitable for data embedding.The secret data is encrypted using the Advanced Encryption Standard(AES),which is a widely accepted encryption standard,before being embedded into the cover video,utilizing up to 10%of the cover video.This process ensures the security and confidentiality of the embedded data.The performance metrics for assessing the proposed method are the Peak Signalto-Noise Ratio(PSNR)and the encoding and decoding time.The results show that the proposed method has a high embedding capacity and efficiency,with a PSNR ranging between 64 and 75 dBs,which indicates that the embedded data is almost indistinguishable from the original video.Additionally,the method can encode and decode data quickly,making it efficient for real-time applications.
文摘This paper presents a new kernel-based algorithm for video object tracking called rebound of region of interest (RROI). The novel algorithm uses a rectangle-shaped section as region of interest (ROI) to represent and track specific objects in videos. The proposed algorithm is constituted by two stages. The first stage seeks to determine the direction of the object’s motion by analyzing the changing regions around the object being tracked between two consecutive frames. Once the direction of the object’s motion has been predicted, it is initialized an iterative process that seeks to minimize a function of dissimilarity in order to find the location of the object being tracked in the next frame. The main advantage of the proposed algorithm is that, unlike existing kernel-based methods, it is immune to highly cluttered conditions. The results obtained by the proposed algorithm show that the tracking process was successfully carried out for a set of color videos with different challenging conditions such as occlusion, illumination changes, cluttered conditions, and object scale changes.
文摘In the realm of contemporary artificial intelligence,machine learning enables automation,allowing systems to naturally acquire and enhance their capabilities through learning.In this cycle,Video recommendation is finished by utilizing machine learning strategies.A suggestion framework is an interaction of data sifting framework,which is utilized to foresee the“rating”or“inclination”given by the different clients.The expectation depends on past evaluations,history,interest,IMDB rating,and so on.This can be carried out by utilizing collective and substance-based separating approaches which utilize the data given by the different clients,examine them,and afterward suggest the video that suits the client at that specific time.The required datasets for the video are taken from Grouplens.This recommender framework is executed by utilizing Python Programming Language.For building this video recommender framework,two calculations are utilized,for example,K-implies Clustering and KNN grouping.K-implies is one of the unaided AI calculations and the fundamental goal is to bunch comparable sort of information focuses together and discover the examples.For that K-implies searches for a steady‘k'of bunches in a dataset.A group is an assortment of information focuses collected due to specific similitudes.K-Nearest Neighbor is an administered learning calculation utilized for characterization,with the given information;KNN can group new information by examination of the‘k'number of the closest information focuses.The last qualities acquired are through bunching qualities and root mean squared mistake,by using this algorithm we can recommend videos more appropriately based on user previous records and ratings.
基金supported by Sichuan Science and Technology Program[2023YFSY0026,2023YFH0004].
文摘Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic and lightweight SR framework designed for arbitrary scaling factors.DDNet integrates a residual learning structure with an Adaptively fusion Feature Block(AFB)and a scale-aware upsampling module,effectively reducing parameter overhead while preserving reconstruction quality.Additionally,we introduce DDNetGAN,an enhanced variant that leverages a relativistic Generative Adversarial Network(GAN)to further improve texture realism.To validate the proposed models,we conduct extensive training using the DIV2K and Flickr2K datasets and evaluate performance across standard benchmarks including Set5,Set14,Urban100,Manga109,and BSD100.Our experiments cover both symmetric and asymmetric upscaling factors and incorporate ablation studies to assess key components.Results show that DDNet and DDNetGAN achieve competitive performance compared with mainstream SR algorithms,demonstrating a strong balance between accuracy,efficiency,and flexibility.These findings highlight the potential of our approach for practical real-world super-resolution applications.
