航空影像去运动模糊研究

分析了航空影像梯度分布特征,介绍了一种改进的模糊核估计方法和BRL（Bilateral Richardson-Lucy）反卷积算法,并提出了一种同时具有模糊核估计和BRL反卷积功能的单幅航空影像去除运动模糊方法,最后用运动模糊航空影像进行了实验验证和分析。结果表明,该方法可有效去除像移,改善模糊航空影像视觉效果,特别是可以保护图像中重要边缘信息。     

基于稀疏表示的单帧运动图像盲复原

提出一种基于稀疏表示的单帧运动盲复原方法,它充分利用自然图像中存在的各种先验知识进行求解。该方法分为模糊核估计和图像修复两个阶段。在估计模糊核时,它运用shock滤波器从模糊图像中预测出清晰边缘,以此指导全局图像的复原,并运用多尺度策略来解决大模糊核问题。在图像修复阶段,运用稀疏表示理论对复原图像进行降噪和重建,最终提高图像复原质量。实验结果表明,在不同噪声和模糊核条件下,该算法能有效消除运动模糊。     

单幅图象去运动模糊的新方法

由相机抖动引起的图象退化是一种常见现象,由于退化函数和隐藏图象均未知所以对单幅模糊图象进行恢复具有很大难度。介绍了一种新的模糊核估计方法和贝叶斯最小均方误差采样反卷积算法,提出了一种同时具有该模糊核估计和贝叶斯最小均方误差采样算法功能的单幅图象去运动模糊方法,并使用由相机抖动引起的运动模糊图象进行了实验验证和分析,实验结果表明,该方法恢复结果中保留了图象重要边缘信息,振铃失真很少,视觉效果较好。     

Blind motion image deblurring using an effective blur kernel prior

Multimedia Tools and Applications - Blind image deblurring, i.e., reconstructing a sharp version of a blurred image, is generally an ill-posed problem, as both the blur kernel and the sharp image...     

Linearized proximal alternating minimization algorithm for motion deblurring by nonlocal regularization

Non-blind motion deblurring problems are highly ill-posed and so it is quite difficult to find the original sharp and clean image. To handle ill-posedness of the motion deblurring problem, we use nonlocal total variation (abbreviated as TV) regularization approaches. Nonlocal TV can restore periodic textures and local geometric information better than local TV. But, since nonlocal TV requires weighted difference between pixels in the whole image, it demands much more computational resources than local TV. By using the linearization of the fidelity term and the proximal function, our proposed algorithm does not require any inversion of blurring operator and nonlocal operator. Therefore, the proposed algorithm is very efficient for motion deblurring problems. We compare the numerical performance of our proposed algorithm with that of several state-of-the-art algorithms for deblurring problems. Our numerical results show that the proposed method is faster and more robust than state-of-the-art algorithms on motion deblurring problems.     

一个基于运动的视频检索系统

给出了一种基于运动在空间 时间域上体现的运动特征的设计方案 ,主要涉及两个模块 ,即 :运动检测模块 (Detec tionModule)和任何检索系统都必需的匹配模块 (MatchingModule)。初步试验表明 ,检测的结果基本和我们的直觉相符合。     

Motion-based mesh segmentation using augmented silhouettes

Motion-based segmentation, the problem of detecting rigid parts of an articulated three-dimensional shape, is an open challenge that has several applications in mesh animation, compression, and interpolation. We present a novel approach that uses the visual perception of the shape and its motion to distinguish the rigid from the deformable parts of the object. Using two-dimensional projections of the different shape poses with respect to a number of different view points, we derive a set of one-dimensional curves, which form a superset of the mesh silhouettes. Analysing these augmented silhouettes, we identify the vertices of the mesh that correspond to the deformable parts, and a subsequent clustering approach, which is based on the diffusion distance, yields a motion-based segmentation of the shape.     

Local motion deblurring using an effective image prior based on both the first- and second-order gradients

Local motion deblurring is a highly challenging problem as both the blurred region and the blur kernel are unknown. Most existing methods for local deblurring require a specialized hardware, an alpha matte, or user annotation of the blurred region. In this paper, an automatic method is proposed for local motion deblurring in which a segmentation step is performed to extract the blurred region. Then, for blind deblurring, i.e., simultaneously estimating both the blur kernel and the latent image, an optimization problem in the form of maximum-a-posteriori (MAP) is introduced. An effective image prior is used in the MAP based on both the first- and second-order gradients of the image. This prior assists to well reconstruct salient edges, providing reliable edge information for kernel estimation, in the intermediate latent image. We examined the proposed method for both global and local deblurring. The efficiency of the proposed method for global deblurring is demonstrated by performing several quantitative and qualitative comparisons with the state-of-the-art methods, on both a benchmark image dataset and real-world motion blurred images. In addition, in order to demonstrate the efficiency in local motion deblurring, the proposed method is examined to deblur some real-world locally linear motion blurred images. The qualitative results show the efficiency of the proposed method for local deblurring at various blur levels.     

Motion-based segmentation of objects using overlapping temporal windows

Motion segmentation refers to the problem of separating the objects in a video sequence according to their motion. It is a fundamental problem of computer vision, since various systems focusing on the analysis of dynamic scenes include motion segmentation algorithms. In this paper we present a novel approach, where a video shot is temporally divided in successive and overlapping windows and motion segmentation is performed on each window respectively. This attribute renders the algorithm suitable even for long video sequences. In the last stage of the algorithm the segmentation results for every window are aggregated into a final segmentation. The presented algorithm can handle effectively asynchronous trajectories on each window even when they have no temporal intersection. The evaluation of the proposed algorithm on the Berkeley motion segmentation benchmark demonstrates its scalability and accuracy compared to the state of the art.     

图像去模糊研究综述

图像模糊是指在图像捕捉或传输过程中,由于镜头或相机运动、光照条件等因素导致图像失去清晰度和细节,从而影响图像的质量和可用性。为了消除这种影响,图像去模糊技术应运而生。其目的在于通过构建计算机数学模型来衡量图像的模糊信息,从而自动预测去模糊后的清晰图像。图像去模糊算法的研究发展不仅为计算机视觉领域的其他任务提供了便利,同时也为生活领域提供了便捷和保障,如安全监控等。1）回顾了整个图像去模糊领域的发展历程,对盲图像去模糊和非盲图像去模糊中具有影响力的算法进行论述和分析。2）讨论了图像模糊的常见原因以及去模糊图像的质量评价方法。3）全面阐述了传统方法和基于深度学习方法的基本思想,并针对图像非盲去模糊和图像盲去模糊两方面的一些文献进行了综述。其中,基于深度学习的方法包括基于卷积神经网络、基于循环神经网络、基于生成式对抗网络和基于Transformer的方法等。4）简要介绍了图像去模糊领域的常用数据集并比较分析了一些代表性图像去模糊算法的性能。5）探讨了图像去模糊领域所面临的挑战,并对未来的研究方法进行了展望。     

基于图像运动的三维重建及虚拟化应用

提出了一种稳定、快速地获取摄像机视频运动图像的三维重建方法,并对该运动图像做适当的虚拟化处理以展示重建效果。采用基于尺度不变特征点匹配的摄像机标定进行三维重建。尺度不变特征对于视频图像中的特征具有优秀敏锐的匹配能力,极大地放宽了摄像机标定对于设备上的限制,拓宽了实时三维重建的适用范围。通过对系统的一系列优化,不但提升了三维重建的精度,减少了错误匹配对摄像机标定的影响,而且进一步提升了处理速度。通过在三维重建的基础之上进行虚拟化处理,展示了本系统的三维重建效果。实验结果表明,该系统适用范围广,处理速度较快,重建精度高,实现了基于视频运动图像的三维重建。     

强边缘导向的盲去模糊算法

目的 在图像的获取过程中,成像设备与拍摄场景发生了相对位移,导致获取的实际图像存在信息丢失、模糊退化的现象,这极大地影响了图像的质量和人们的视觉体验,也影响了图像的后续处理。盲去卷积旨在从观测图像中估计模糊核并获得清晰图像,为此提出了一种基于强边缘的运动图像盲去模糊算法。方法 结合图像梯度稀疏性,采用自适应l₀范数约束待估计图像梯度的强边缘;针对模糊核稀疏性和连续性,以l₀-l₂范数分别约束模糊核的像素和梯度,同时把模糊核归一化先验作为正则项引入模型中,以强边缘指导模糊核估计。在去模糊阶段,结合全变分与超拉普拉斯正则化方法的优点,将两种方法复原的图像取平均,以减轻复原图像中的振铃效应,同时保留更多的图像细节。结果 为了检验本文算法的有效性,对Levin测试集和实际拍摄的模糊图像分别进行仿真,并同现有算法进行比较。Levin测试集上的实验结果表明,提出的盲反卷积成功率为100%且在对比算法中具有最高PSNR;实际彩色图像的盲反卷积实验表明,相比于其他算法,本文算法获得的模糊核具有更准确的支撑和较少的噪点,获得的清晰图像具有较优的视觉效果。结论 该方法从定量和定性比较上都体现了较好的去运动模糊能力,可适用于遥感、医学等领域。     

Motion-based prediction is sufficient to solve the aperture problem

In low-level sensory systems, it is still unclear how the noisy information collected locally by neurons may give rise to a coherent global percept. This is well demonstrated for the detection of motion in the aperture problem: as luminance of an elongated line is symmetrical along its axis, tangential velocity is ambiguous when measured locally. Here, we develop the hypothesis that motion-based predictive coding is sufficient to infer global motion. Our implementation is based on a context-dependent diffusion of a probabilistic representation of motion. We observe in simulations a progressive solution to the aperture problem similar to physio-logy and behavior. We demonstrate that this solution is the result of two underlying mechanisms. First, we demonstrate the formation of a tracking behavior favoring temporally coherent features independent of their texture. Second, we observe that incoherent features are explained away, while coherent information diffuses progressively to the global scale. Most previous models included ad hoc mechanisms such as end-stopped cells or a selection layer to track specific luminance-based features as necessary conditions to solve the aperture problem. Here, we have proved that motion-based predictive coding, as it is implemented in this functional model, is sufficient to solve the aperture problem. This solution may give insights into the role of prediction underlying a large class of sensory computations.     

Motion-based method for estimating time required to attach self-adhesive insulators

A self-adhesive insulator is a component of a home appliance that is used to suppress vibration or prevent humidity affecting the internal parts of the appliance. There is a wide range of types and designs available, allowing them to be applied to areas having different shapes. At the design stage, once an insulator design has been developed sufficiently to identify its dimensions and features, the attaching time and baseline cost must be estimated with reasonable accuracy to enable a comparison of vendor quotes. However, the current estimation method is not sufficiently accurate in terms of the baseline cost. This paper presents a motion-based time-estimating scheme with which the time required for the attachment of such insulators can be calculated more accurately. The scheme has been developed by analyzing the motions needed to attach 350 insulators and then designating representative motions and their time values. For this purpose, a modular arrangement of predetermined time standards (MODAPTS) is adopted. Motion-based time-estimation method is useful in terms of simplicity and accuracy. It enables design engineers to estimate the time required for the attachment based only on a drawing of the insulator and a few MODAPTS rules. Estimates made with this method should vary from the actual value by no more than 9.5%.     

分区域去运动模糊

去运动模糊一直是计算机视觉领域中面向画质增强的一个热点研究方向。模糊核的估算是去运动模糊中的关键问题。提出一种新的思路,即首先将模糊图像按照模糊核的相似度进行图像分割,再对分割后的图像应用空间不变去模糊算法。本文方法主要包含以下几个步骤:分离输入图像中的光照、颜色和纹理信息;分割图像;分区域估算模糊核,计算重叠区域模糊核,并根据计算出的模糊核进行分区域单核去模糊;利用重叠区域整合拼接去模糊结果并还原光照和颜色信息。实验结果表明本文方法比基于单核的去运动模糊算法效果要好。     

密集连接卷积网络图像去模糊

目的 非均匀盲去运动模糊是图像处理和计算机视觉中的基础课题之一。传统去模糊算法有处理模糊种类单一、耗费时间两大缺点,且一直未能有效解决。随着神经网络在图像生成领域的出色表现,本文把去运动模糊视为图像生成的一种特殊问题,提出一种基于神经网络的快速去模糊方法。方法 首先,将图像分类方向表现优异的密集连接卷积网络（dense connected convolutional network, DenseNets）应用到去模糊领域,该网络能充分利用中间层的有用信息。在损失函数方面,采用更符合去模糊目的的感知损失（perceptual loss）,保证生成图像和清晰图像在内容上的一致性。采用生成对抗网络（generative adversarial network,GAN）,使生成的图像在感官上与清晰图像更加接近。结果 通过测试生成图像相对于清晰图像的峰值信噪比 （peak signal to noise ratio,PSNR）,结构相似性 （structural similarity,SSIM）和复原时间来评价算法性能的优劣。相比DeblurGAN（blind motion deblurring using conditional adversarial networks）,本文算法在GOPRO测试集上的平均PSNR提高了0.91,复原时间缩短了0.32 s,能成功恢复出因运动模糊而丢失的细节信息。在Kohler数据集上的性能也优于当前主流算法,能够处理不同的模糊核,鲁棒性强。结论 本文算法网络结构简单,复原效果好,生成图像的速度也明显快于其他方法。同时,该算法鲁棒性强,适合处理各种因运动模糊而导致的图像退化问题。     

Preconditioned edge-preserving image deblurring and denoising

Preconditioned conjugate gradient (PCG) algorithms have been successfully used to significantly reduce the number of iterations in Tikhonov regularization techniques for image restoration. Nevertheless, in many cases Tikhonov regularization is inadequate, in that it produces images that are oversmoothed across intensity edges. Edge-preserving regularization can overcome this inconvenience but has a higher complexity, in that it involves non-convex optimization. In this paper, we show how the use of preconditioners can improve the computational performance of edge-preserving image restoration as well. In particular, we adopt an image model which explicitly accounts for a constrained binary line process, and a mixed-annealing algorithm that alternates steps of stochastic updating of the lines with steps of preconditioned conjugate gradient-based estimation of the intensity. The presence of the line process requires a specific preconditioning strategy to manage the particular structure of the matrix of the equivalent least squares problem. Experimental results are provided to show the satisfactory performance of the method, both with respect to the quality of the restored images and the computational saving.     

基于超拉普拉斯模型的运动去模糊算法*

通过分析自然图像梯度统计的长尾分布特性,提出一种基于超拉普拉斯模型的图像运动去模糊算法。该算法使用分步交替迭代最小化办法优化能量方程,并在优化过程中采用了查询表法快速求解图像反卷积。实验结果表明,该算法可以在数秒时间内处理完成一幅中等大小的图像,并获得较优的复原结果,其复原效果和对振铃现象的抑制均优于维纳滤波法和Richardson-Lucy复原法。     

图像插值模糊的非线性自适应消除

针对线性移不变图像插值方法造成的插值图像边缘模糊,提出采用具有高通特性的有理滤波器增强图像,重建锐变的图像边缘。对基本有理滤波算子进行改进,避免滤波信号峰值点和孤立点的失真。推广算子的二维形式并引入图像对比度约束,形成一种自适应图像插值模糊消除算法。实验结果表明,算法能够不失真地重建图像边缘的高频细节,提高图像的视觉分辨率,图像质量优于现有图像插值模糊消除算法。