Multi-sensor image super-resolution with fuzzy cluster by using multi-scale and multi-view sparse coding for infrared image

Super-resolution (SR) methods are effective for generating a high-resolution image from a single low-resolution image. However, four problems are observed in existing SR methods. (1) They cannot reconstruct many details from a low-resolution infrared image because infrared images always lack detailed information. (2) They cannot extract the desired information from images because they do not consider that images naturally come at different scales in many cases. (3) They fail to reveal different physical structures of low-resolution patch because they extract features from a single view. (4) They fail to extract all the different patterns because they use only one dictionary to represent all patterns. To overcome these problems, we propose a novel SR method for infrared images. First, we combine the information of high-resolution visible light images and low-resolution infrared images to improve the resolution of infrared images. Second, we use multiscale patches instead of fixed-size patches to represent infrared images more accurately. Third, we use different feature vectors rather than a single feature to represent infrared images. Finally, we divide training patches into several clusters, and multiple dictionaries are learned for each cluster to provide each patch with a more accurate dictionary. In the proposed method, clustering information for low-resolution patches is learnt by using fuzzy clustering theory. Experiments validate that the proposed method yields better results in terms of quantization and visual perception than the state-of-the-art algorithms.     

高光谱图像超分辨率重建技术研究进展

不同于传统图像（如灰度图像、RGB图像等）专注于保存目标场景的空间信息,高光谱图像蕴含丰富的空—谱信息,不仅可以保存目标的空间信息,还可以保存具有高可辨性的光谱信息。因此高光谱图像广泛应用于多种计算机视觉和遥感图像任务中,如目标检测、场景分类和目标追踪等。然而,在高光谱图像获取以及重建过程中仍然存在许多问题与瓶颈。如传统高光谱成像仪器在成像过程中通常会引入噪声,且获得的图像往往具有较低的空间分辨率,极大地影响了高光谱图像的质量,对后续数据分析任务造成了极大的困难。近年来,高光谱图像超分辨率重建技术研究得到了极大的发展,现有超分辨率重建方法可以大致分为两类,一类为空间超分辨率重建方法,可以通过直接提升高光谱图像的空间分辨率来获得高质量高光谱图像;另一类为光谱超分辨率重建方法,可以通过提升高空间分辨率图像的光谱分辨率来生成高质量高光谱图像。本文从高光谱图像超分辨率重建领域的新设计、新方法和应用场景出发,通过综合国内外前沿文献来梳理该领域的主要发展,重点论述高光谱图像超分辨率重建领域的发展现状、前沿动态、热点问题及趋势。     

Progressive spatial-angular feature enhancement network for light field image super-resolution

The intensity and direction of the light field (LF) can be recorded simultaneously by using LF cameras. However, since LF cameras sacrifice spatial resolution for higher angular resolution, the images acquired by LF cameras tend to have low spatial resolution. Therefore, LF image super-resolution (SR) has become an integral part of LF studies. Many existing LF image SR methods fail to fully utilize angular and spatial information due to only using partial sub-aperture images (SAIs). In this paper, we propose a progressive spatial-angular feature enhancement network (PSAFENet) to deal with the problem of missing information in LF image SR. Specifically, we first extract the spatial features of SAIs, the spatial and angular features contained in the macro-pixel images (MacPIs) by three different feature extraction modules. Then, these features are fed into a spatial-angular feature enhancement (SAFE) module to perform enhancement of spatial-angular information on the SAIs. To improve the reconstruction accuracy, we also use the information multi-distillation block (IMDB) to remove the redundant information before upsampling. Our network can well merge the angular and spatial information into each SAI, which facilitates the reconstruction of the LF images. Experimental results on five public datasets show that the proposed PSAFENet method outperforms existing methods in both qualitative and quantitative comparisons.     

Fast multisensor infrared image super-resolution scheme with multiple regression models

High resolution (HR) infrared (IR) images play an important role in many areas. However, it is difficult to obtain images at a desired resolution level because of the limitation of hardware and image environment. Therefore, improving the spatial resolution of infrared images has become more and more urgent. Methods based on sparse coding have been successfully used in single-image super-resolution (SR) reconstruction. However, the existing sparse representation-based SR method for infrared (IR) images usually encounter three problems. First, IR images always lack detailed information, which leads to unsatisfying IR image reconstruction results with conventional method. Second, the existing dictionary learning methods in SR aim at learning a universal and over-complete dictionary to represent various image structures. A large number of different structural patterns exist in an image, whereas one dictionary is not capable of capturing all of the different structures. Finally, the optimization for dictionary learning and image reconstruction requires a highly intensive computation, which restricts the practical application in real-time systems. To overcome these problems, we propose a fast IR image SR scheme. Firstly, we integrate the information from visible (VI) images and IR images to improve the resolution of IR images because images acquired by different sensors provide complementary information for the same scene. Second, we divide the training patches into several clusters, then the multiple dictionaries are learned for each cluster in order to provide each patch with a more accurate dictionary. Finally, we propose an method of Soft-assignment based Multiple Regression (SMR). SMR reconstructs the high resolution (HR) patch by the dictionaries corresponding to its K nearest training patch clusters. The method has a low level of computational complexity and may be readily suitable for real-time processing applications. Numerous experiments validate that this scheme brings better results in terms of quantization and visual perception than many state-of-the-art methods, while at the same time maintains a relatively low level of time complexity. Since the main computation of this scheme is matrix multiplication, it will be easily implemented in FPGA system.     

Learning graph-constrained cascade regressors for single image super-resolution

Learning cascade regression has been shown an effective strategy to further enhance the perceptual quality of resulted high-resolution (HR) images. However, previous cascade regression-based SR methods have two obvious weaknesses: (1)edge structures cannot be preserved well when applying texture features to represent low-resolution (LR) images, and (2)the local manifold structures spanned by the LR-HR feature spaces cannot be revealed by the learned local linear mappings. To alleviate the aforementioned problems, a novel example regression-based super-resolution (SR) approach called learning graph-constrained cascade regressors (LGCCR) is presented, which learns a group of multi-round residual regressors in a unique way. Specifically, we improve the edge preservation capability by synthesizing the whole HR image rather than local image patches, which facilitates to extract the edge features to represent LR images. Moreover, we utilize a graph-constrained regression model to build the local linear regressors, where each local linear regressor responds to an anchored atom in the learned over-complete dictionary. Both quantitative and qualitative quality evaluations on seven benchmark databases indicate the superiority of the proposed LGCCR-based SR approach in comparing with other state-of-the-art SR predecessors.

     

递归式多阶特征融合图像超分辨率算法

目的 近年来,卷积神经网络在解决图像超分辨率的问题上取得了巨大成功,不同结构的网络模型相继被提出。通过学习,这些网络模型对输入图像的特征进行抽象、组合,进而建立了从低分辨率的输入图像到高分辨率的目标图像的有效非线性映射。在该过程中,无论是图像的低阶像素级特征,还是高阶各层抽象特征,都对像素间相关性的挖掘起了重要作用,影响着目标高分辨图像的性能。而目前典型的超分辨率网络模型,如SRCNN（super-resolution convolutional neural network）、VDSR（very deep convolutional networks for super-resolution）、LapSRN（Laplacian pyramid super-resolution networks）等,都未充分利用这些多层次的特征。方法 提出一种充分融合网络多阶特征的图像超分辨率算法：该模型基于递归神经网络,由相同的单元串联构成,单元间参数共享;在每个单元内部,从低阶到高阶的逐级特征被级联、融合,以获得更丰富的信息来强化网络的学习能力;在训练中,采用基于残差的策略,单元内使用局部残差学习,整体网络使用全局残差学习,以加快训练速度。结果 所提出的网络模型在通用4个测试集上,针对分辨率放大2倍、3倍、4倍的情况,与深层超分辨率网络VDSR相比,平均分别能够获得0.24 dB、0.23 dB、0.19 dB的增益。结论 实验结果表明,所提出的递归式多阶特征融合图像超分辨率算法,有效提升了性能,特别是在细节非常丰富的Urban100数据集上,该算法对细节的处理效果尤为明显,图像的客观质量与主观质量都得到显著改善。     

联合多任务学习的人脸超分辨率重建

目的 人脸超分辨率重建是特定应用领域的超分辨率问题,为了充分利用面部先验知识,提出一种基于多任务联合学习的深度人脸超分辨率重建算法。方法 首先使用残差学习和对称式跨层连接网络提取低分辨率人脸的多层次特征,根据不同任务的学习难易程度设置损失权重和损失阈值,对网络进行多属性联合学习训练。然后使用感知损失函数衡量HR（high-resolution）图像与SR（super-resolution）图像在语义层面的差距,并论证感知损失在提高人脸语义信息重建效果方面的有效性。最后对人脸属性数据集进行增强,在此基础上进行联合多任务学习,以获得视觉感知效果更加真实的超分辨率结果。结果 使用峰值信噪比（PSNR）和结构相似度（SSIM）两个客观评价标准对实验结果进行评价,并与其他主流方法进行对比。实验结果显示,在人脸属性数据集（CelebA）上,在放大8倍时,与通用超分辨率MemNet（persistent memory network）算法和人脸超分辨率FSRNet（end-to-end learning face super-resolution network）算法相比,本文算法的PSNR分别提升约2.15 dB和1.2 dB。结论 实验数据与效果图表明本文算法可以更好地利用人脸先验知识,产生在视觉感知上更加真实和清晰的人脸边缘和纹理细节。     

A new framework for remote sensing image super-resolution: Sparse representation-based method by processing dictionaries with multi-type features

Remote sensing images play an important role in many practical applications, however, due to the physical limitations of remote sensing devices, it is difficult to obtain images at an expecting high resolution level. Acquiring high-resolution(HR) images from the original low-resolution(LR) ones with super-resolution(SR) methods has always been an attractive proposition in embedded systems including various kinds of tablet PC and smart phone. SR methods based on sparse representation have been successfully used in processing remote sensing images, however, they have two major problems in common. First, they use only one type of image features to represent the low resolution(LR) images. However, one single type of features cannot accurately represent an image due to the diverse structures of the image, as a result, artifacts would be produced simultaneously. Second, many dictionary learning methods try to build a universal dictionary with only one single type of features. However, apparently, a dictionary with a single type of features is not enough to capture the different structures of a remote sensing image, without any doubt, the resultant image would turn out to be a poor one. To overcome the problems above, we propose a new framework for remote sensing image super resolution: sparse representation-based SR method by processing dictionaries with multi-type features. First, in order to represent the remote sensing image more accurately, different types of features are extracted from images. Second, to achieve a better performance, various dictionaries with multi-type features are learned to capture the essential structures of the image. Then, it’s proposed to adaptively control the weights of the high resolution(HR) patches obtained by different dictionaries. Numerous experiments validate that this proposed framework brings better results in terms of both objective quantitation and visual perception than other compared algorithms.     

Image super resolution based on residual dense CNN and guided filters

Convolutional neural networks (CNNs) have recently made impressive results for image super-resolution (SR). Our goal is to introduce a new image SR framework rely on a CNN. In this paper, the input image is decomposed into luminance channel and chromatic channels. A designed network based on a residual dense network is introduced to extract the hierarchical features from luminance part. The bicubic interpolation is simply used to upscale low resolution (LR) chromatic channels. However, this step degrades the chromatic channels. To tackle this issue, the SR reconstructed luminance channel is applied as the reference image in guided filters to promote the interpolated chromatic channels. Guided filters technique has ability to retain sharp edges and fine details from the reference image and carry them to the target images. Extensive experiments on several commonly used image SR testing datasets demonstrate that our framework has the ability to extract features and outperforms existing well-known techniques for image SR by LR image into the high resolution (HR) image efficiently.

     

结合深度学习的单幅遥感图像超分辨率重建

目的 克服传统遥感图像超分辨率重建方法依赖同一场景多时相图像序列且需预先配准等缺点,解决学习法中训练效率低和过拟合问题,同时削弱插值操作后的块效应,增强单幅遥感图像超分辨率重建效果。方法 首先构造基于四层卷积的深度神经网络结构,并在结构中前三层卷积后添加参数修正线性单元层和局部响应归一化层进行优化,经过训练得到遥感图像超分辨率重建模型,其次,对多波段遥感图像的亮度空间进行双三次插值,然后使用该模型对插值结果进行重建,并在亮度空间重建结果指导下,使用联合双边滤波来提升其色度空间边缘细节。结果 应用该方法对实验遥感图像进行2倍、3倍、4倍重建时在无参考指标上均优于对比方法,平均清晰度提升约2.5个单位,同时取得了较好的全参考评价结果,在2倍重建时峰值信噪比较传统插值法提升了约2 dB,且平均训练效率较其他学习法提升3倍以上,所得遥感图像重建结果在目视效果上更加细致、自然。结论 实验结果表明,本文设计的网络抗过拟合能力强、训练效率高,重建时针对单幅遥感图像,无需依赖图像序列且不受波段影响,重建结果细节表现较好,具有较强的普适性。     

基于分组卷积和快照集成的图像隐写分析方法

现存的大多数隐写分析方法的泛化能力较弱,无法对未知隐写算法有效检测,使得其分类的准确性在实际运用过程中大幅度降低。针对这个问题,提出了一种基于分组卷积和快照集成的图像隐写分析方法(snapshot ensembling steganalysis network, SENet)。首先,残差卷积块和分组卷积块对图像的特征进行提取并利用;其次,在每个训练周期中得到性能最好的模型作为快照模型;最后将选定的快照模型进行集成后对图像进行分类。该方法应用分组卷积和快照集成的技术,避免了传统集成方法的高训练成本以及单一分类器泛化能力有限的问题。实验结果表明,该方法可以提升隐写分析模型的准确率,并且在训练集和测试集失配时,也能够有效地进行分类,具有较高的模型泛化能力。     

一种高效的多模型图像超分辨率框架

图像超分辨率(Super Resolution,SR)技术能够从低分辨率图像中恢复出高分辨率图像,已被广泛应用于遥感、医学影像、目标跟踪与识别等多个领域。随着深度学习研究的深入,该技术也被成功应用于 SR 相关研究中,但现有工作往往只关注输出图像的质量,而忽略了训练和重构效率。该文基于对图像特征和训练效率的观察,提出了一种基于多模型的 SR 框架——MMSR,能够根据不同的图像特征选择合适的网络模型,从而在不影响输出图像质量的情况下有效缩短训练时间。面向 DIV_2K 图像集的测试结果表明,该框架能够实现平均 66.7% 的性能提升,同时具有良好的可扩展性。     

自适应加权LBP的单样本人脸识别方法

在面对单训练样本的人脸识别问题时,传统人脸识别方法识别率会下降很多,有的方法甚至不能使用。针对单样本人脸识别问题,提出了一种自适应加权LBP方法。方法既提取了纹理信息又包含了分块拓扑信息,更重要的是可以把这些特征用合适的权重融合起来。划分图像并用LBP提取纹理信息;利用方差来完成对特征的自适应加权融合;用最近邻分类器识别结果。在ORL人脸数据库上的实验结果表明,该方法可以有效地提高识别率。     

Pose-and-illumination-invariant face representation via a triplet-loss trained deep reconstruction model

Face recognition under variable pose and illumination is a challenging problem in computer vision tasks. In this paper, we solve this problem by proposing a new residual based deep face reconstruction neural network to extract discriminative pose-and-illumination-invariant (PII) features. Our deep model can change arbitrary pose and illumination face images to the frontal view with standard illumination. We propose a new triplet-loss training method instead of Euclidean loss to optimize our model, which has two advantages: a) The training triplets can be easily augmented by freely choosing combinations of labeled face images, in this way, overfitting can be avoided; b) The triplet-loss training makes the PII features more discriminative even when training samples have similar appearance. By using our PII features, we achieve 83.8% average recognition accuracy on MultiPIE face dataset which is competitive to the state-of-the-art face recognition methods.     

图像检索中一种有效的SVM相关反馈算法

提出受限随机选择方法.首先对图像进行相似性排序;然后使用一个阈值限定随机选择的范围;最后在该范围内进行划分,在子范围内通过随机选择来扩大训练样本,较好地解决了小样本问题.另外,动态计算多个SVM分类器的权值,融合分类结果,较好地解决了相关反馈过程中用户的不同喜好问题.实验结果表明了该方法的有效性.     

SR-AFU: super-resolution network using adaptive frequency component upsampling and multi-resolution features

Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.     

Densely connected deep random forest for hyperspectral imagery classification

In very recent years, deep learning based methods have been widely introduced for the classification of hyperspectral images (HSI). However, these deep models need lots of training samples to tune abundant parameters which induce a heavy computation burden. Therefore, most of these algorithms need to be accelerated with high-performance graphics processing units (GPU). In this paper, a new deep model–densely connected deep random forest (DCDRF) is proposed to classify the hyperspectral images. This model is composed of multiple forward connected random forests. The DCDRF has following merits: 1) It obtains satisfactory classification accuracy with a small number of training samples, 2) It can be run efficiently on the central processing unit (CPU), 3) Only a few parameters are involved during the training. Experimental results based on three hyperspectral images demonstrate that the proposed method can achieve better classification performance than the conventional deep learning based methods.     

脊柱MR图像自动分割方法的研究

脊柱磁共振（magnetic resonance,MR）图像精确分割是脊柱配准、三维重建等技术的前提。传统脊柱MR图像分割方法过程繁琐,精度低。为克服传统方法弊端,提出了一种基于深度学习的脊柱MR图像自动分割方法。该方法构建对称通道卷积神经网络提取多尺度图像特征,通过残差连接解决训练中网络退化问题,同时用跳跃连接层连接中间层特征减少信息丢失。在搭建的网络模型中加入卷积块注意力机制关注空间和通道中的有效特征。实验结果表明,该模型在测试集上的平均DSC系数为0.861?9,相比FCN、U-Net、DeeplabV3+和UNet++网络模型分别提高了15.34%、7.08%、5.79%、3.1%。该模型可应用于临床实践中提升脊柱MR图像的分割精度。     

基于随机森林的高光谱遥感图像分类

为了充分利用高光谱图像的光谱信息和空间结构信息,提出了一种新的基于随机森林的高光谱遥感图像分类方法,首先,利用主成分分析降低数据的维数,并对主成分进行独立成分分析提取其光谱特征,同时消除像元的空间相关性,再采用形态学分析提取像元的空间结构特征,然后,根据像元的谱域和空域特征分别构造随机森林,并引入空间连续性对像元点的预测结果进行约束修正,最后由投票机制决定最后的分类结果。在AVIRIS和ROSIS高光谱图像上的实验结果表明,所提方法的分类性能要优于传统的高光谱图像分类方法,且分类精度高于基于单一特征的方法。     

基于像素对比学习的图像超分辨率算法

目前, 深度卷积神经网络(Convolutional neural network, CNN)已主导了单图像超分辨率(Single image super-resolution, SISR)技术的研究, 并取得了很大进展. 但是, SISR仍是一个开放性问题, 重建的超分辨率(Super-resolution, SR)图像往往会出现模糊、纹理细节丢失和失真等问题. 提出一个新的逐像素对比损失, 在一个局部区域中, 使SR图像的像素尽可能靠近对应的原高分辨率(High-resolution, HR)图像的像素, 并远离局部区域中的其他像素, 可改进SR图像的保真度和视觉质量. 提出一个组合对比损失的渐进残差特征融合网络(Progressive residual feature fusion network, PRFFN). 主要贡献有: 1)提出一个通用的基于对比学习的逐像素损失函数, 能够改进SR图像的保真度和视觉质量; 2)提出一个轻量的多尺度残差通道注意力块(Multi-scale residual channel attention block, MRCAB), 可以更好地提取和利用多尺度特征信息; 3)提出一个空间注意力融合块(Spatial attention fuse block, SAFB), 可以更好地利用邻近空间特征的相关性. 实验结果表明, PRFFN显著优于其他代表性方法.