非监督SAR图像变化检测研究最新进展

SAR图像变化检测已经成为国内外研究热点,在多方面取得广泛应用。本文综述了SAR图像非监督变化检测技术研究的最新进展,从变化检测的基本流程出发,介绍了图像预处理、差异图提取、差异图分割的各类算法。本文的归纳总结,将进一步加深研究人员对SAR图像变化检测技术的认识,促进其在实际工作中的更好运用。     

综合边界和纹理信息的合成孔径雷达图像目标分割

目的 针对传统Grab Cut算法需要人工交互操作,无法实现合成孔径雷达（SAR）图像的自动分割,且方式单一（仅利用边界或纹理信息中的一种）的问题,提出一种综合利用边界和纹理信息的改进Grab Cut算法,实现对SAR图像目标的自动分割。方法 首先将其他格式的彩色或灰度SAR图像转化为24 bit的位图,采用图形理论对整幅SAR图像建模,根据最大流算法找到描述图的能量函数最小的割集,从而分割出目标区域;然后采用中值滤波抑制相干噪声;最后通过邻域生长算法滤除图像斑点和小目标的干扰,从而达到目标边界的连接,实现自动对SAR图像中的目标进行分割。结果 在64位Window 7环境下采用MATLAB R2014处理平台,对楼房、车库、大树、汽车群等4幅分辨率不同的SAR图像进行目标分割实验,特征目标被自动分割出来,耗时分别为1.69 s、1.58 s、1.84 s和3.09 s,相比Mean-shift和Otsu算法,平均计算效率分别提升150%和3%,并且图像中的背景杂波、目标阴影和干扰小目标均被有效去除。结论 综合利用边界和纹理信息能够有效抑制相干噪声,去除图像斑点和小目标的干扰,从而达到目标边界的连接,实现对SAR图像目标的自动分割。实验结果表明,本文算法可以满足工程化应用要求,自适应性强,分割精度高,且具有较好的鲁棒性。     

基于边缘强度特征和线性谱聚类的 SAR 图像超像素生成方法

面对高分辨合成孔径雷达(SAR)图像的海量数据,学界广泛通过基于超像素的方法 简化图像处理过程。一般适用于光学图像的超像素分割算法对存在斑噪的 SAR 图像分割性能均 不够理想。面向 SAR 图像改进现有超像素生成算法是目前的研究热点之一。在探讨了将边缘强 度特征引入超像素分割算法的可行性的基础上,结合边缘强度特征和线性谱聚类方法,提出了 一种新的 SAR 图像超像素生成方法(e-LSC)。通过仿真 SAR 图像和实测 SAR 图像的比较实验, 证实了 e-LSC 算法与其他几种典型超像素生成算法相比,生成的超像素在边缘贴合度和匀质区 域的规则化上都有所提高。     

区域GMM聚类的SAR图像分割

高斯混合模型(GMM)聚类算法近年来广泛应用于图像分割领域。但在SAR图像分割中,由于忽略了图像像素间的空间相关性,使其对相干斑噪声十分敏感。提出一种基于区域的GMM聚类算法,它将空间相关性引入聚类分类中,利用分水岭分割得到基本同质区域,计算区域的灰度均值作为GMM聚类算法的输入样本,将聚类特征从像素水平提升到区域水平,减少了噪声对分割结果的影响;并将自身反馈机制引入期望最大化(EM)算法中,进一步提高了GMM模型参数估计的精度。还对合成图像和真实SAR图像进行了分割实验,结果表明新算法可有效地提高分割的     

A level set method for oil slick segmentation in SAR images

Despite much effort and significant progress in recent years, image segmentation remains a challenging problem in image processing, especially for the low contrast, noisy synthetic aperture radar (SAR) images. This paper explores the segmentation of oil slicks using a partial differential equation (PDE)‐based level set method, which represents the slick surface as an implicit propagation interface. Starting from an initial estimation with priori information, the level set method creates a set of speed functions to detect the position of the propagation interface. Specifically, the image intensity gradient and the curvature flow are utilized together to determine the speed and direction of the propagation. This allows the front interface to propagate naturally with topological changes, significant protrusions and narrow regions, giving rise to stable and smooth boundaries that discriminate oil slicks from the surrounding water. As the speckles are removed concurrently while the front interface propagates, the pre‐filtering of noise is saved. The proposed method has been illustrated by experiments on oil slick segmentation using the ERS‐2 SAR images. Its advantages over the traditional image segmentation approaches have also been demonstrated.     

多区域SAR图像分割的改进水平集方法

由于合成孔径雷达（SAR）图像易受相干斑噪声的影响,光学图像的分割方法并不适用于SAR图像,更不能获得精确的分割结果对比,因此,首先基于GA^0统计模型定义能量映射函数以代替像素值进行后续处理,减小相干斑的影响;其次,使用水平集算法对处理后的图像进行分割处理,选用了一种形式更为简单的水平集函数,并可以较容易地推广到多区域SAR图像分割情况。实验结果表明,该方法可以减少相干斑噪声对SAR图像分割过程的不良影响,具有较好的准确性。     

面向对象的高分辨率SAR图像处理及应用

目的随着合成孔径雷达(SAR)技术和分辨率的不断提高,越来越多的空间细节呈现在高分辨率SAR影像上。与此同时,SAR图像的数据量越来越大,人们对其应用需求也越来越高,这使得传统的基于像素的SAR处理方法不再适用。面向对象分析技术以像元集合——"对象"为分析单元,为高分辨率遥感图像处理提供了有效的思路,并日渐成为遥感、摄影测量以及GIS等领域所关注的对象和研究热点之一。目前该技术在光学遥感中已经得到了广泛的应用,但在SAR图像处理中的应用还处于起步阶段。方法本文在简要阐述面向对象分析技术起源和特点的基础上,对SAR图像面向对象技术中常用的多尺度分割算法进行了分类分析,接着对面向对象技术在SAR遥感的应用方向进行全面介绍,最后对面向对象技术在SAR上的应用进行了总结与展望。结果面向对象分析技术在SAR图像处理中的应用主要分为以下五个方面:地物分类、城市信息提取、变化检测、海洋应用、森林应用。结论面向对象分析技术在解决高分辨率SAR图像尺度效应、抑制噪声等方面有着重要作用。目前,国外学者在基于SAR的面向对象分析技术研究上已经取得了一定的进展,但总体上该技术仍面临诸多问题,需要进一步的研究和完善。     

Water body segmentation of Synthetic Aperture Radar image using Deep Convolutional Neural Networks

Deep Convolutional Neural Networks are finding their way into modern machine learning tasks and proved themselves to become one of the best contenders for future development in the field. Several proposed methods in image segmentation and classification problems are giving us satisfactory results and could even perform better than humans in image recognition tasks. But also at the cost of their performance, they also require a huge amount of images for training and huge amount of computing power and time that makes them unrealistic in some situations where obtaining a large dataset is not feasible. In this work, an attempt is made for segmentation of Synthetic Aperture Radar (SAR) images which are not usually abundant enough for training, and are heavily affected by a kind of multiplicative noise called speckle noise. For the segmentation task, pre-defined filters are first applied to the images and are fed to hybrid CNN that is resulted from the concept of Inception and U-Net. The outcome of our proposed method has been examined for their effectiveness of application in a complete set of SAR images that are not used for training. The accuracy has also been compared with the manually annotated SAR images.     

基于边缘检测的SAR图像自适应区域分割

受相干斑噪声影响,合成孔径雷达（Synthetic Aperture Radar,SAR）图像成像质量低,目标判读困难。针对传统方法对SAR图像分割存在噪声敏感、细节缺失、过度分割等问题,提出一种基于边缘检测的SAR图像自适应区域分割方法。首先引入双边滤波构建级联滤波器,对SAR图像进行保边抑噪;然后建立基于纹理复杂度的阈值估算模型,实现阈值自适应目标SAR图像边缘检测;最后提出基于边缘特征的自适应区域生长分割方法,较好解决了传统区域生长算法对SAR图像分割时出现的过度生长和过度分割之间的矛盾问题。该方法综合利用了SAR图像二维熵、边缘灰度信息、区域灰度信息,实现了对单极化目标SAR图像的自动分割。实验表明,相较于其他传统分割方法,该方法保边抑噪能力更强,目标细节检测更准确,较好解决了SAR图像过分割问题。     

基于灰度共生矩阵纹理特征的SAR图像分割

同时考虑SAR图像局部灰度均值和方差及像素空间分布特征等统计量,在以灰度共生矩阵产生的纹理统计量为特征所生成的图像上,建立多分辨双Markov-GAR模型,采用多分辨MPM的参数估计方法及相应的无监督分割算法,对SAR图像进行纹理分割。该方法用于一些高分辨SAR图像,其分割精度及分割边缘的平滑度均优于基于灰度图像上的多分辨双Markov-GAR模型纹理分割。     

High-resolution SAR images segmentation using NSCT denoising and QIGA based parameters selection of PCNN model

The high-resolution synthetic aperture radar (SAR) images usually contain inhomogeneous coherent speckle noises. For the high-resolution SAR image segmentation with such noises, the conventional methods based on pulse coupled neural networks (PCNN) have to face heavy parameters with a low efficiency. In order to solve the problems, this paper proposes a novel SAR image segmentation algorithm based on non-subsampling Contourlet transform (NSCT) denoising and quantum immune genetic algorithm (QIGA) improved PCNN models. The proposed method first denoising the SAR images for a pre-processing based on NSCT. Then, by using the QIGA to select parameters for the PCNN models, such models self-adaptively select the suitable parameters for segmentation of SAR images with different scenes. This method decreases the number of parameters in the PCNN models and improves the efficiency of PCNN models. At last, by using the optimal threshold to binary the segmented SAR images, the small objects and large scales from the original SAR images will be segmented. To validate the feasibility and effectiveness of the proposed algorithm, four different comparable experiments are applied to validate the proposed algorithm. Experimental results have shown that NSCT pre-processing has a better performance for coherent speckle noises suppression, and QIGA-PCNN model based on denoised SAR images has an obvious segmentation performance improvement on region consistency and region contrast than state-of-the-arts methods. Besides, the segmentation efficiency is also improved than conventional PCNN model, and the level of time complexity meets the state-of-the-arts methods. Our proposed NSCT+QIGA-PCNN model can be used for small object segmentation and large scale segmentation in high-resolution SAR images. The segmented results will be further used for object classification and recognition, regions of interest extraction, and moving object detection and tracking.

     

空间约束层次加权Gamma混合模型的SAR图像分割

目的 合成孔径雷达（SAR）图像中像素强度统计分布呈现出复杂的特性,而传统混合模型难以建模非对称、重尾或多峰等特性的分布。为了准确建模SAR图像统计分布并得到高精度分割结果,本文提出一种利用空间约束层次加权Gamma混合模型（HWGaMM）的SAR图像分割算法。方法 采用Gamma分布的加权和定义混合组份;考虑到同质区域内像素强度的差异性和异质区域间像素强度的相似性,采用混合组份加权和定义HWGaMM结构。采用马尔可夫随机场（MRF）建模像素空间位置关系,利用中心像素及其邻域像素的后验概率定义混合权重以将像素邻域关系引入HWGaMM,构建空间约束HWGaMM,以降低SAR图像内固有斑点噪声的影响。提出算法结合M-H（Metropolis-Hastings）和期望最大化算法（EM）求解模型参数,以实现快速SAR图像分割。该求解方法避免了M-H算法效率低的缺陷,同时克服了EM算法难以求解Gamma分布中形状参数的问题。结果 采用3种传统混合模型分割算法作为对比算法进行分割实验。拟合直方图结果表明本文算法具有准确建模复杂统计分布的能力。在分割精度上,本文算法比基于高斯混合模型（GMM）、Gamma分布和Gamma混合模型（GaMM）分割算法分别提高33%,29%和9%。在分割时间上,本文算法虽然比GMM算法多64 s,但与基于Gamma分布和GaMM算法相比较分别快600 s和420 s。因此,本文算法比传统M-H算法的分割效率有很大的提高。结论 提出一种空间约束HWGaMM的SAR图像分割算法,实验结果表明提出的HWGaMM算法具有准确建模复杂统计分布的能力,且具有较高的精度和效率。     

深度学习下的医学影像分割算法综述

医学影像分割是计算机视觉在医学影像处理中的一个重要应用领域,其目标是从医学影像中分割出目标区域,为后续的疾病诊断和治疗提供有效的帮助。近年来深度学习技术在图像处理方面取得了巨大进展,基于深度学习的医学影像分割算法逐渐成为该领域研究的重点和热点。叙述了计算机视觉下的医学影像分割任务及其难点,重点综述了基于深度学习的医学影像分割算法,对当前具有代表性的相关方法进行了分类和总结,介绍了医学影像分割算法常用的评价指标和数据集。对该技术的发展进行了总结和展望。     

基于多尺度随机模型的SAR图像无监督分割

合成孔径雷达（synthetic aperture radar,SAR）是一种基于相干原理的成像系统,在SAR图像中存在严重影响图像质量的斑点噪声,使得SAR图像的可靠分割非常困难。〖BP）〗根据SAR图像的成像机理,利用两种多尺度随机模型,即多尺度自回归（Multiscale Autoregressive,MAR）模型和多尺度自回归滑动平均（Multiscale Aautoregressive Moving Average, MARMA）模型,分别来描述同一场景不同分辨率SAR图像像素间的统计相关性,并构造了相应的多分辨混合算法实现SAR图像的无监督分割。试验结果表明,提出的两种无监督分割方法是可行的,且MARMA模型比MAR模型能够更精确地捕捉SAR图像多尺度序列中不同类型地形的统计信息,使分割质量具有明显的改进。     

一种适用于SAR图像的2维Otsu改进算法

Otsu法是图像阈值分割中的经典算法之一,在图像处理中得到广泛的应用。针对原始2维Otsu法直方图区域划分上的缺陷和运算速度慢的缺点,分析了适用于SAR图像相干斑乘性噪声的直方图区域划分方法,提出了一种更符合实际图像模型的阈值选取准则。实验结果表明,该改进算法的分割效果良好,运算速度也有很大提高。     

基于描述方法的SAR图像分割*

针对减少SAR图像分割中自由参数的问题,提出了基于最小描述长度的SAR图像分割方法。该方法经对数变换将SAR图像乘性噪声转换为加性噪声,对其建立描述模型,在描述长度最短意义上计算出重建图像,在假设SAR图像各区域实际地物后向散射特性对应的像素值恒定的前提下,该重建图像即为SAR图像的分割结果。该方法在分割的同时很好地抑制了SAR图像的相干斑噪声,保留了原始SAR图像的区域边界,并且不需要参数调节,整个分割过程自动完成,是一种非监督SAR图像分割方法。给出了该方法的具体实现步骤,实验结果验证了该方法的有效性。     

Multi-objective evolutionary for synthetic aperture radar image segmentation with non-local means denoising

Synthetic aperture radar (SAR) image segmentation is an important problem of the realm of image segmentation. In this study, a novel SAR image segmentation algorithm using a multi-objective evolutionary algorithm based on decomposition with non-local means denoising (MISD) is proposed. The novelty of MISD lies in the following issues: (1) an effective multi-objective method with decomposition to solve SAR image segmentation; (2) in order to denoise the SAR images and retain the details, we employ non-local means to remove the noise. The multi-objective decomposition method makes MISD have lower computational complexity. In order to evaluate the performance of the new method, we compared the results with three other popular segmentation approaches on four simulated and two real SAR images. In our experiments, the new method can always find better results, which means MISD is a promising SAR image segmentation method.     

基于模糊理论的SAR图像分割算法研究与实现

SAR图像存在强烈的相干斑噪声,传统方法不能很好对其分割。文章基于模糊理论,通过选择图像特征,构造模糊集,借助最大隶属度原则进行了SAR图像分割算法的设计,并借助SAR图像分别进行了参数调节和窗口选择的实验,获得了满意的分割结果。实验结果表明．该算法对于SAR图像分割可行有效。     

Multiscale SAR image segmentation by combining curvelet transform and GMTRJ algorithms

To integrate multiscale analysis within region-based segmentation framework, this paper presents multiscale SAR image segmentation method. First, curvelet transform is used to obtain a collection of the decomposed SAR images on multiple scales. Their domain is partitioned into a set of blocks by a regular tessellation, in which the number of blocks is assumed to be a random variable with Poisson distribution. On the partitioned domain, the Bayesian paradigm is followed to build the region- and multiscale-based image segmentation model with unknown number of classes. Further, a Generalized Multiple-Try Reversible Jump (GMTRJ) algorithm is designed to simulate the segmentation model. During the procedure of iterative simulation for the segmentation model, the segmentation result on the current scale is regarded as the initial segmentation on next scale. The segmented results corresponding to the finest scale is considered as the optimal image segmentation. The proposed method is validated using SAR images. The Kappa coefficient of the test simulated SAR image is up to 0.998, and the Kappa coefficients of the test real SAR images are up or equal to 0.903. From the test results of the quantitative and qualitative evaluation, it can be found that the proposed method can not only determine the number of classes, but also segment homogeneous regions well.     

中医舌象分割技术研究进展: 方法、性能与展望

中医舌诊的客观化、定量化研究是中医现代化发展中的重要课题. 数字化采集到的舌图像包括舌体及部分面部区域, 为了便于后续舌象自动分析, 需要首先将舌体部分从图像中分割出来, 分割效果将直接影响后续舌象特征分析的准确性. 基于传统方法的舌象分割技术虽然取得了很大进展, 但其性能仅能达到半自动分割, 对较难分割的图像往往需要借助人机交互来完成. 近年来, 深度学习技术在图像处理及计算机视觉等多个领域取得了突破, 其在图像语义分割任务中也取得了远超传统方法的进展. 基于深度学习的舌象分割技术已经基本实现了全自动的鲁棒分割. 本文首先从传统分割方法和基于深度学习的分割方法两方面对中医舌象分割技术发展中的主要方法进行综述; 其次, 采用我们收集的舌象数据库对典型的方法进行性能评估, 并对不同舌象分割方法的特点进行分析与讨论. 最后, 对中医舌图像分割方法潜在的发展方向进行了展望.