共查询到20条相似文献,搜索用时 62 毫秒
1.
联合估计混叠度,运动参数和高分辨率图像的JEMAP算法 总被引:1,自引:0,他引:1
本文提出一种空域联合估计混叠度,运动参数和高分辨率图像的JEMAP算法,以提高超分辨率处理的适应性,在地面上稳定地获得高于实测卫星图像中所用CCD设备成像精度的高清晰图像。算法根据星戡CCD设备的成像机理,定义卫星图像的混叠度,确定超分辨率处理模型,通过空域迭代联合估计混叠度,运动参数和高分辨率图像。实际卫星图像处理表明JEMAP算法具有很好的适应性和稳定性,包含先验约束能力较强,可以解开欠采样低分辨率输入图像的混叠,重构清晰卫星图像。 相似文献
2.
3.
如何获取高质量的干涉图是INSAR技术的核心问题之一.首先概述了干涉图中存在的噪声,并对干涉图中频谱混叠现象的成因及其影响进行了重点分析.针对SAR影像距离向和方位向频谱的特性,通过增加影像频谱中空白带的带宽对影像进行过采样,从而成功消除了干涉图中的频谱混叠现象.针对过采样后干涉图数据量激增的问题,利用干涉图频谱的理论权函数推导了欠采样函数.最后,利用ERS数据验证了文中的过采样方法能有效消除干涉图中的频谱混叠现象,显著提高干涉图质量.同时,利用文中推导的欠采样函数可以使干涉图在恢复原始大小的同时,使噪声得到进一步抑制. 相似文献
4.
5.
预估计混叠度的MAP超分辨率处理算法 总被引:15,自引:1,他引:15
提出一种预估计混叠度的PEMAP(pre-estimated MAP(maximum a posteriori)算法,用于卫星图像的地面超分辨率处理.它通过频域分析确定卫星图像的混叠度,将其作为先验信息在空域控制MAP估计的循环迭代,联合估计帧间位移和高分辨率图像.该算法克服了最大后验概率MAP算法的盲目性和不稳定性,使其适应性更好.实际的卫星图像处理显示了较好的处理效果. 相似文献
6.
针对目前基于插值的红外图像超分辨率重建算法主要把重心置于原始图像的像素上的问题,提出了一种将原始图像像素和插值像素相结合的红外图像超分辨率重建算法。该算法在最近邻插值算法的基础上,将其与自适应高斯滤波相结合,采用边插值边滤波的方式对红外图像进行超分辨率重建处理。由红外数据集的大量对比试验结果可知,该算法能够在不以时间消耗为代价的前提下使重建结果得到有效提升。具体表现为其重建结果的客观评价指标与经典的图像插值算法相比提高了约2.8%~3.2%,并且能够有效减少噪声、锯齿和模糊现象。该算法有助于推动红外图像超分辨率重建在军事、医疗等领域的发展。 相似文献
7.
8.
9.
磁共振成像(MRI)因其无创伤和较高的软组织对比度而被广泛地用于复杂疾病诊断。目前多通过在k空间高倍欠采样磁共振(MR)信号解决MRI速度较慢的问题,然而代表性算法重建高倍欠采样的MR图像时往往存在细节模糊的问题。因此,提出一种基于残差图卷积神经网络(RGCNET)的高倍欠采样MR图像重建算法。首先,使用自编码技术与图卷积神经网络(GCN)构建生成器;其次,将欠采样图像输入特征提取(编码)网络中从底层提取特征;接着,通过GCN块提取MR图像的高层特征;然后,通过解码网络生成初始的重建图像;最后,经过生成器和鉴别器的动态博弈得到最终的高分辨率重建图像。在FastMRI数据集上的测试结果表明,与基于空间正交注意力机制的MRI重建算法SOGAN(Spatial Orthogonal attention Generative Adversarial Network)相比,在10%、20%、30%、40%和50%的采样率下,所提算法在标准均方根误差(NRMSE)指标上分别下降了3.5%、26.6%、23.9%、13.3%和14.3%,在峰值信噪比(PSNR)指标上分别提升了1.2%、8.7%、6... 相似文献
10.
该文提出了一种基于多帧的NEDI超分辨率图像重建算法。该算法先利用POCS方法将多帧序列的运动估计补偿到低分辨率图像中,然后再利用NEDI方法对补偿后的图像进行超分辨率图像重建,通过实验仿真证明该算法是有效的。 相似文献
11.
基于聚类的单帧图像超分辨率重建方法 总被引:1,自引:0,他引:1
为解决单幅图像的超分辨重建问题,提出一种基于聚类的单帧图像超分辨率重建方法.从高分辨率样本图像中学习一个结构聚类型的高分辨率字典,利用迭代收缩算法优化目标方程,求得高分辨率图像的表示系数,使用学习到的高分辨率字典对低分辨率图像进行重构.实验结果表明,与总变分方法、软切割方法和稀疏表示方法相比,该方法的单帧图像超分辨率重建效果较好. 相似文献
12.
摄屏类图像重构算法 总被引:1,自引:1,他引:0
目前摄影摄像设备所采集图像的分辨率远远高于屏幕分辨率,因此摄屏类图像经缩放后往往有大量摩尔纹产生.针对该类图像摩尔纹干扰以及内存过大、图像短焦距畸等现象,本文首次提出了摄屏类图像重构算法.首先,通过长度自适应的线型滤波算法分离网状高频信号.再通过快速Greedy算法和贝努利随机游走提取图像的高频信息,根据液晶点结构的先验知识,构建完整的液晶排布模型并数学拟合,分离出被拍摄屏幕画面信息和液晶点网状纹路.最后对图像矩阵空间重构,以及颜色通道的插值恢复.重构算法在矩阵空间上与原始图像一致,实验样本与原图的直方图相似度达到80%以上,远高于摄屏图像与原图38.7%的相似度.算法保留了图像信息,舍去高频网状噪声,恢复原始矩阵空间,使图像更符合实际需求. 相似文献
13.
In this paper, we study the problem of reconstructing a high-resolution image from several blurred low-resolution image frames. The image frames consist of decimated, blurred and noisy versions of the high-resolution image. The high-resolution image is modeled as a Markov random field (MRF), and a maximum a posteriori (MAP) estimation technique is used for the restoration. We show that with the periodic boundary condition, the high-resolution image can be restored efficiently by using fast Fourier transforms. We also apply the preconditioned conjugate gradient method to restore the high-resolution image. Computer simulations are given to illustrate the effectiveness of the proposed method.Research supported in part by Hong Kong Research Grants Council Grant Nos. HKU 7130/02P, 7046/03P, 7035/04P and HKU CRCG Grant No. 10205775.Michael K. Ng is a Professor of the Mathematics Department, Hong Kong Baptist University, and is Adjunct Research Fellow in the E-Business Technology Institute at the University of Hong Kong. Michael was a Research Fellow (1995–1997) of Computer Sciences Laboratory, Australian National University, and an Assistant/Associate Professor (1997–2005) of the Mathematics Department, the University of Hong Kong before joining Hong Kong Baptist University in 2005. Michael was one of the finalists and honourable mention of Householder Award IX, in 1996 at Switzerland, and he obtained an excellent young researcher’s presentation at Nanjing International Conference on Optimization and Numerical Algebra, 1999. In 2001, he has been selected as one of the recipients of the Outstanding Young Researcher Award of the University of Hong Kong. Michael has published and edited several books, and published extensively in international journals and conferences, and has organized and served in many international conferences. Now he serves on the editorial boards of SIAM Journal on Scientific Computing, Numerical Linear Algebra with Applications, Multidimensional Systems and Signal Processing, International Journal of Computational Science and Engineering, Numerical Mathematics, A journal of Chinese Universities (English Series), and several special issues of the international journals.Andy C. Yau received the undergraduate (1998–2001) from the Chinese University of Hong Kong, and the M.Phil degree (2002–2004) from the University of Hong Kong. He is a PhD student of the University of Hong Kong. His research area is image processing and scientific computing. 相似文献
14.
3-D Depth Reconstruction from a Single Still Image 总被引:4,自引:0,他引:4
Ashutosh Saxena Sung H. Chung Andrew Y. Ng 《International Journal of Computer Vision》2008,76(1):53-69
We consider the task of 3-d depth estimation from a single still image. We take a supervised learning approach to this problem,
in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which
include forests, sidewalks, trees, buildings, etc.) and their corresponding ground-truth depthmaps. Then, we apply supervised
learning to predict the value of the depthmap as a function of the image. Depth estimation is a challenging problem, since
local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image.
Our model uses a hierarchical, multiscale Markov Random Field (MRF) that incorporates multiscale local- and global-image features,
and models the depths and the relation between depths at different points in the image. We show that, even on unstructured
scenes, our algorithm is frequently able to recover fairly accurate depthmaps. We further propose a model that incorporates
both monocular cues and stereo (triangulation) cues, to obtain significantly more accurate depth estimates than is possible
using either monocular or stereo cues alone. 相似文献
15.
针对单幅含噪图像的超分辨率重建问题,基于图像在过完备字典下的稀疏表示建立了超分辨率重建模型.该模型中低分辨率字典采用K-SVD算法直接训练,高分辨率字典则由高分辨率图像块与低分辨率字典下的同构的表示系数进行逼近求得;近似的高分辨率图像块通过高分辨率字典乘以表示系数得到,为使重建结果对噪声具有鲁棒性,利用基于稀疏表示的噪声图像恢复的方法由重叠的近似高分辨率图像块求得最终结果.实验结果表明,文中模型无论是主观视觉还是客观评价指标均取得了较好的效果,并验证了模型及算法的有效性. 相似文献
16.
3D modeling of trees in real environments is a challenge in computer graphics and computer vision, since the geometric shape and topological structure of trees are more complex than conventional artificial objects. In this paper, we present a multi-process approach that is mainly performed in 2D space to faithfully construct a 3D model of the trunk and main branches of a real tree from a single range image. The range image is first segmented into patches by jump edge detection based on depth discontinuity. Coarse skeleton points and initial radii are then computed from the contour of each patch. Axis directions are estimated using cylinder fitting in the neighborhood of each coarse skeleton point. With the help of axis directions, skeleton nodes and corresponding radii are computed. Finally, these skeleton nodes are hierarchically connected, and improper radii are modified based on plant knowledge. 3D models generated from single range images of real trees demonstrate the effectiveness of our method. The main contributions of this paper are simple reconstruction by virtue of image storage order of single scan and skeleton computation based on axis directions. 相似文献
17.
传统的以彩色图像为指导的深度图像超分辨率(SR)重建方法,参考图像必须为高分
辨率彩色图像,彩色图像的分辨率决定了深度图像的放大上限。同时,实际应用中可能只存在低
分辨率彩色图像,此时上述方法也不再适用。为此,探讨使用任意分辨率彩色图像为指导的深度
图像SR 重建方法。首先,使用大量不同类别的图像SR 算法对输入彩色图像进行上采样,得到
高分辨率彩色图像并以此作为指导图像,然后采用基于二阶总广义变分方法,将由低分辨率彩色
图像重建得到的图像作为正则约束项,添加图像边缘信息,构建目标函数,将深度图像SR 重建
问题转化为最优化问题,再通过原-对偶方法求解,最终得到高分辨率深度图像。探讨了之前被
相关方法所忽略的情形,该方法可以适用于任意分辨率的彩色指导图像。并且通过相关实验发现
了令人惊异的现象,即通过使用低分辨率彩色图像放大后作为指导,可以得到与使用高分辨率彩
色指导图像相近甚至更好的结果,对相关问题的研究和应用具有一定参考意义。 相似文献
18.
传统的建模方式非常复杂,而日常生活中拍摄的多数照片本身包含着足够几何信息,于是文中提出了从单幅图像中直接生成具有三维动态效果的系列图片的设想。首先需要用户简化勾画出图像的遮挡关系,然后将图像按遮挡关系进行分层,针对每一个图层,根据提取出的特征边缘来识别出有意义的空间信息,最后从新的视角出发,重定景物间的关系和相对位置,进而生成具有三维浏览效果的图像。实验结果表明,该方法在用户简单参与下能得到良好效果。 相似文献
19.
20.