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 Image Reconstruction Based on an Improved Maximum a Posteriori Algorithm

A maximum a posteriori（ MAP） algorithm is proposed to improve the accuracy of super resolution（ SR） reconstruction in traditional methods. The algorithm applies both joints image registration and SR reconstruction in the framework,but separates them in the process of iteratiion. Firstly,we estimate the shifting parameters through two lowresolution（ LR） images and use the parameters to reconstruct initial HR images. Then,we update the shifting parameters using HR images. The aforementioned steps are repeated until the ideal HR images are obtained. The metrics such as PSNR and SSIM are used to fully evaluate the quality of the reconstructed image. Experimental results indicate that the proposed method can enhance image resolution efficiently.

Deep Learned Singular Residual Network for Super Resolution Reconstruction

Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.

Super resolution reconstruction of moving objects from low resolution surveillance video

Construction of high resolution images from low resolution sequences having rigid or semi-rigid ob-jects with unified motions is often important in surveillance and other applications.In this paper a novelobject-based super resolution reconstruction scheme was proposed,in which a six-parameter affine model-based object tracking and registration method was first used to segment and match objects among a se-quence of low resolution frames.The motion model was then further extended to the traditional maximuma posterior(MAP)super resolution algorithm.The proposed object tracking and registration method wasevaluated by both simulated and real acquired sequences.The results have demonstrated the high accura-cy of the proposed object based method and the enhanced reconstruction performance of the extended ap-proach.

Multi-channel fast super-resolution image reconstruction based on matrix observation model

A multi-channel fast super-resolution image reconstruction algorithm based on matrix observation model is proposed in the paper,which consists of three steps to avoid the computational complexity: a single image SR reconstruction step,a registration step and a wavelet-based image fusion. This algorithm decomposes two large matrixes to the tensor product of two little matrixes and uses the natural isomorphism between matrix space and vector space to transform cost function based on matrix-vector products model to matrix form. Furthermore,we prove that the regularization part can be transformed to the matrix formed. The conjugate-gradient method is used to solve this new model. Finally,the wavelet fusion is used to integrate all the registered highresolution images obtained from the single image SR reconstruction step. The proposed algorithm reduces the storage requirement and the calculating complexity,and can be applied to large-dimension low-resolution images.

Super-resolution image reconstruction based on three-step-training neural networks

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.

OBJECT-BASED SUPER RESOLUTION FOR INTELLIGENT VISUAL SURVEILLANCE VIDEO

Construction of high resolution images from low resolution sequences is often im- portant in surveillance applications. In this letter, an affine based multi-scale block-matching image registration algorithm is first proposed. The images to be registered are divided into overlapped blocks of different size according to its motions. The Least Square (LS) image reg- istration algorithm is extended to match the blocks. Then an object based Super Resolution (SR) scheme is designed, the Maximum A Priori (MAP) super resolution algorithm is extended to enhance the resolution of the interest objects. Experimental results show that the proposed multi-scale registration method provides more accurate registration between frames. Further more, the object based super resolution scheme shows an enhanced performance compared with the traditional MAP method.

Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation

Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.

A WAVELET TRANSFORM BASED POCS SUPERRESOLUTION ALGORITHM

Research interest in multi-frame Superresolution has risen substantially in recent years. This paper presents a modified Projection Onto Convex Set （POCS） superresolution method based on wavelet transform. The method analyzes the image formation model from wavelet multiresolution analysis point of view and defines an closed convex set and its corresponding projection based on wavelet transform. An iterative procedure is utilized to reduce the estimated errors of the result image, and this guarantees the estimated image to lay in the intersection of different convex sets, thus produces a high resolution image with a reduced error. The effectiveness of the algorithm is demonstrated bv experimental results.

基于Real-ESRGAN和改进YOLOv8n的输电线路绝缘子故障检测

为解决无人机在输电线路巡检时遇到的绝缘子故障难以检测的问题,提出一种绝缘子故障检测新方法。该方法结合了真实世界增强超分辨率生成对抗网络(Real-ESRGAN)和改进的YOLOv8n。首先,利用Real-ESRGAN对数据集进行超分辨率重构,优化数据集质量,有效减少复杂背景的干扰;然后利用高效视觉变压器框架替换YOLOv8的主干,加强模型的特征提取能力,同时使模型在推理阶段有更快的处理速度;再对YOLOv8的检测头进行轻量化处理,进一步加速模型推理。试验结果显示,该方法的均值平均精度达86.7%,证明了其在复杂背景下的卓越目标检测性能。通过分析热力图,展示了该算法与传统YOLOv8在关注区域上的差异,从而揭示了模型的内部工作机理。

基于ESRGCNN的单帧红外图像超分辨率重建算法

红外图像的超分辨率重建算法研究是近年来图像处理算法领域的研究重点,现有的具有较强学习能力的卷积神经网络(Convolutional Neural Networks,CNNs)在改善图像超分辨率重建效果的同时会增加计算成本,而后续提出的具有浅层结构的增强组卷积神经网络超分辨率重建方法(Enhanced Super-Resolution Group Convolutional Neural Network,ESRGCNN)在可见光图像的超分辨率重建中不仅节省成本且效率高。所以针对红外图像分辨率差、对比度低等不足,将经过预处理的红外图片通过高频纹理细节提取、重建等操作后得到的高分辨率纹理细节图与经过ESRGCNN网络得到红外图像的高频细节层、基层分别进行权重构建、CLAHE处理后进行加权融合得到最终的超分辨率红外图像。通过在红外数据集CVC-14进行大量对比实验,表明所提出的优化算法在三种倍率重建图像的PSNR优于经典算法约13.7%~32.4%,其重建效果的SSIM优于经典算法约13.9%~32.4%。

A lateral super-resolution imaging method using structured illumination without phase shift

Structured illumination microscopy has been a useful method for achieving lateral super-resolution,but it typically requires at least three precise phase shifts per orientation.In this paper,we propose a super-resolution method that utilizes structured illumination without phase shift.The reconstruction process requires only a conventionally illuminated image and an image with structured illumination.This method achieves the same effect as the traditional phase shift method,and more than doubles the resolution by synthesizing a few reconstructions at different illumination frequencies.We verify the resolution improvement process using a combination of theoretical derivations and diagrams,and demonstrate its effectiveness with numerical simulations.

基于SRCNN网络的喷墨印刷图像处理方法

为了应对采集环境或采集系统影响导致的喷墨印刷图像模糊、不显著等问题,本文提出了一种利用灰度图像处理,根据图像灰度值设置三维地形图和灰度等高线图的方法,以确定印刷图像中墨滴的中心位置和边缘,从而更好地区分重叠墨滴和单个墨滴。此外,还提出了一种基于SRCNN(Super-Resolution Convolutional Neural Network)的喷墨印刷图像处理方法,以提高低分辨率喷墨印刷图像的清晰度。通过在特征提取层加入普通卷积层以提取更丰富的图像特征,该方法在标准数据集上得到了验证。喷墨印刷图像的结果显示,改进后的SRCNN模型比未改进的SRCNN模型峰值信噪比提高了0.014dB,证明了改进模型的有效性,并在重建图像中取得了更好的视觉效果。

基于金字塔可形变卷积的多分支视频超分模型

为利用帧间的空时相关性特点,提升红外视频超分辨率重建效果,提出了一种改进BasicVSR的超分辨率重建方法。首先,使用金字塔可形变对齐代替BasicVSR中使用的光流法进行帧对齐,将参考帧和相邻帧当作输入,使用可形变卷积对帧间的偏移量进行测量,使不同帧进行信息上的叠加,最大限度得到图像中的细节特征。其次,在上采样时,将参考图像与经过融合后的图像进行级联,通过浅层特征与深层特征的融合,增强特征表达能力。文章设计的模型具有轻量、运行时间短、重建图像主观视觉效果好等优点,且峰值信噪比(PSNR)与结构相似度(SSIM)以及模型运行时间等客观评价指标得到了改进。本文所提模型EbasicVSR比相关模型运行时间平均提升了19 s,信噪比提升了0.14 dB以上,结构相似度提升了2.9%以上,实验结果表明,相比于原BasicVSR模型,本文提出的模型取得了更好的重建效果。

基于改进YOLOv4及SR-GAN的绝缘子缺陷辨识研究

为了精准地识别无人机巡检图形中的小目标绝缘子及缺陷,本文提出了一种基于改进的深度学习目标检测网络(YOLOv4)的输电线路绝缘子缺陷检测方法。首先,通过无人机航拍及数据增强获得足够的绝缘子图像,构造绝缘子数据集。其次,利用绝缘子图像数据集训练YOLOv4网络,在训练过程中采用多阶段迁移学习策略和余弦退火学习率衰减法提高网络的训练速度和整体性能。最后,在测试过程中,对存在小目标的图像采用超分辨率生成网络,生成高质量的图像后再进行测试,以提高识别小目标的能力。实验结果表明,与Faster R-CNN和YOLOv3相比,所提算法在平均分类精度和每帧检测速率方面均有较大提升,性能表现优异。

一种改进的SRGAN红外图像超分辨率重建算法

针对红外图像分辨率偏低的问题,设计了一种改进的超分辨率生成对抗网络(Super-Resolution Using a Generative Adversarial Network,SRGAN)算法。在生成网络中,提出应用残差密集网络获取各网络层提取的图像特征以保留图像更多的高频信息,并采用渐进式上采样方式以提升大缩放因子下超分辨率重建效果。在损失函数方面采用更符合人类感官的感知损失,使生成图像在感官和内容上与真实高分辨率图像更加接近。实验结果表明:所提方法重建的超分辨率红外图像质量在主观及客观评价中均要优于当前具有代表性的方法。

基于偏微分方程的盲去模糊超分辨率重建算法及实验

提出一种基于偏微分方程的图像盲去模糊超分辨率重建算法,旨在未知模糊核的情况下,将含噪声的低分辨率模糊图像重建为清晰的高分辨率图像.首先,针对图像退化过程构建变分问题,并借助变分方法推导出偏微分方程模型.其次,结合交替方向法和数值差分方法,通过设计时空全离散数值格式求解未知的模糊核和清晰的图像.再次,通过一系列数值实验,分析参数选择对图像重建效果的影响,确定合适的参数设置.最后,针对若干遥感图像进行实验,实验结果证明了所给模型的有效性与可靠性.

基于灵活LBP纹理字典构造及多特征描述的改进SCSR算法

针对超分辨率重构字典对结构区分度不够、在最优匹配原子搜索中耗时太长的问题,提出了一种多特征联合的分级字典(MFJD).首先,分别用边缘块梯度特征和纹理块局部二值模式(LBP)特征来构建两种分类字典,用于逼近不同类型结构;其次,采用树结构来聚类原子,实现同一字典下的快速原子匹配;最后,引入双边总变分(BTV)正则项来约束重构结果.实验表明:与经典稀疏编码超分辨率重构(SCSR)算法相比,MFJD多特征联合的分级字典使重构图像的PSNR值提高了0.2424 d B,使平均结构相似度(MSSIM)和特征相似度(FSIM)分别提高了0.0043和0.0056;由于结构分类字典维数降低,重构时间降至SCSR算法的22.77%.

RAISR算法在遥感图像超分辨率重建中的可行性

针对遥感图像空间分辨率不足的问题,探讨了RAISR(rapid and accurate image super resolution)算法在单帧遥感图像超分辨率重建中的可行性。RAISR算法以处理自然图像为主,分为学习阶段和图像重建阶段。学习阶段是利用训练库图像生成滤波器,是算法的核心部分;图像重建阶段是利用滤波器重建图像。首先,在学习阶段,根据图像块的位置、角度、强度、相干性等特征对滤波器进行分类,并采用哈希列表存储;然后,针对遥感图像特点,优化了RAISR算法的滤波器尺寸,并采用USM(unsharp mask)方法增强边缘纹理特征,以达到最佳的重建效果;最后,用多组遥感图像进行了重建实验。结果表明:RAISR算法的重建质量与训练集图像的分辨率、数量、类别、所含地物类型有关;本文优化的RAISR算法重建后的遥感图像细节、边缘等信息都得到了改善。

基于SRCNN和SSD网络的小目标检测方法

针对实时目标检测SSD(Sing shot multibox detector)算法对小目标检测能力弱的问题,提出一种提高特征图分辨率的超分辨率重建SRCNN(Super Resolution Convolutional Neural Networks)设计策略。改进算法是在SSD基础网络VGG_16网络的conv4_3卷积层上进行的,把conv4_3卷积层产生的特征图通过SRCNN网络进行超分辨重建以提高conv4_3卷积层的特征图分辨率。然后再利用超分辨重建后的特征图和原特征图一起为小目标检测提供所需要的特征。实验表明上述设计方法相比于原经典SSD算法具有更高的检测精度和检测能力,以及在小目标检测上的效果更加明显。