基于SLIC和主动学习的高光谱遥感图像分类方法

在主动学习的基础上,提出一种基于SLIC的高光谱遥感图像主动分类方法。首先提取图像纹理特征并与光谱特征融合,使用PCA对新数据进行降维,取前三个主成分构成假彩色图像,然后使用SLIC处理该图像获得超像素;接着随机抽取定量超像素作为初始训练样本,样本光谱信息为超像素样本中所有像素点的光谱信息均值,样本标签为超像素中出现次数最多的类别;然后通过主动学习得到SVM分类器;最后使用分类器对超像素分类得到其类别,并将超像素类别赋予其包含的像素点,从而达到高光谱遥感图像分类的目的。实验表明：该方法明显降低了主动学习过程的时间消耗,有效地提高了分类效果,其OA,AA和Kappa值显著优于未使用SLIC的主动学习方法。     

结合超像元和子空间投影支持向量机的高光谱图像分类

目的 高光谱图像包含了丰富的空间、光谱和辐射信息,能够用于精细的地物分类,但是要达到较高的分类精度,需要解决高维数据与有限样本之间存在矛盾的问题,并且降低因噪声和混合像元引起的同物异谱的影响。为有效解决上述问题,提出结合超像元和子空间投影支持向量机的高光谱图像分类方法。方法 首先采用简单线性迭代聚类算法将高光谱图像分割成许多无重叠的同质性区域,将每一个区域作为一个超像元,以超像元作为图像分类的最小单元,利用子空间投影算法对超像元构成的图像进行降维处理,在低维特征空间中执行支持向量机分类。本文高光谱图像空谱综合分类模型,对几何特征空间下的超像元分割与光谱特征空间下的子空间投影支持向量机（SVMsub）,采用分割后进行特征融合的处理方式,将像元级别转换为面向对象的超像元级别,实现高光谱图像空谱综合分类。结果 在AVIRIS（airbone visible/infrared imaging spectrometer）获取的Indian Pines数据和Reflective ROSIS（optics system spectrographic imaging system）传感器获取的University of Pavia数据实验中,子空间投影算法比对应的非子空间投影算法的分类精度高,特别是在样本数较少的情况下,分类效果提升明显;利用马尔可夫随机场或超像元融合空间信息的算法比对应的没有融合空间信息的算法的分类精度高;在两组数据均使用少于1%的训练样本情况下,同时融合了超像元和子空间投影的支持向量机算法在两组实验中分类精度均为最高,整体分类精度高出其他相关算法4%左右。结论 利用超像元处理可以有效融合空间信息,降低同物异谱对分类结果的不利影响;采用子空间投影能够将高光谱数据变换到低维空间中,实现有限训练样本条件下的高精度分类;结合超像元和子空间投影支持向量机的算法能够得到较高的高光谱图像分类精度。     

图像分割中的超像素方法研究综述

目的 超像素(superpixel)是近年来快速发展的一种图像预处理技术,它将图像快速分割为一定数量的具有语义意义的子区域,相比于传统处理方法中的基本单元——像素,超像素更有利于局部特征的提取与结构信息的表达,并且能够大幅度降低后续处理的计算复杂度,在计算机视觉领域尤其是图像分割中得到了广泛的应用,为使国内外研究者对超像素理论及其在图像分割中的应用有一个比较全面的认识,对其进行系统综述.方法 以图像分割为应用背景,在广泛调研文献特别是超像素最新发展成果的基础上,结合对比实验,对每种方法的基本思想、方法特点进行总结,并对超像素分割目前存在的局限性进行说明,对未来可能发展方向进行展望.结果 不同的超像素分割算法在分割思想、性能特点上各不相同.当前的超像素方法普遍在超像素数量、紧密度与分割质量、算法实用性之间存在相互制约,同时对于某些特殊目标的分割也难以取得较好的结果.结论 超像素作为一种有效的图像预处理手段具有较高的研究价值,但针对目前超像素存在的一些局限性还需要进行深入的研究.     

结合区域协方差分析的图像显著性检测

目的 图像显著性检测的目的是为了获得高质量的能够反映图像不同区域显著性程度的显著图,利用图像显著图可以快速有效地处理图像中的视觉显著区域。图像的区域协方差分析将图像块的多维特征信息表述为一个协方差矩阵,并用协方差距离来度量两个图像块特征信息的差异大小。结合区域协方差分析,提出一种新的图像显著性检测方法。方法 该方法首先将输入的图像进行超像素分割预处理;然后基于像素块的区域协方差距离计算像素块的显著度;最后对像素块进行上采样用以计算图像像素点的显著度。结果 利用本文显著性检测方法对THUS10000数据集上随机选取的200幅图像进行了显著性检测并与4种不同方法进行了对比,本文方法估计得到的显著性检测结果更接近人工标定效果,尤其是对具有复杂背景的图像以及前背景颜色接近的图像均能达到较好的检测效果。结论 本文方法将图像像素点信息和像素块信息相结合,避免了单个噪声像素点引起图像显著性检测的不准确性,提高了检测精确度;同时,利用协方差矩阵来表示图像特征信息,避免了特征点的数量、顺序、光照等对显著性检测的影响。该方法可以很好地应用到显著目标提取和图像分割应用中。     

Very high resolution remote sensing image classification with SEEDS-CNN and scale effect analysis for superpixel CNN classification

Pixel-based convolutional neural network (CNN) has demonstrated good performance in the classification of very high resolution images (VHRI) from which abstract deep features are extracted. However, conventional pixel-based CNN demands large resources in terms of processing time and disk space. Therefore, superpixel CNN classification has recently become a focus of attention. We therefore propose a CNN based deep learning method combining superpixels extracted via energy-driven sampling (SEEDS) for VHRI classification. The approach consists of three main steps. First, based on the concept of geographic object-based image analysis (GEOBIA), the image is segmented into homogeneous superpixels using the SEEDS based superpixel segmentation method thereby decreasing the number of processing units. Second, the training data and testing data are extracted from the image and concatenated on a superpixel level at a variety of scales for CNN. Third, the training data are input to train the parameters of CNN and abstract deep features are extracted from the VHRI. Using these extracted deep features, we classify two VHRI data sets at single scales and multiple scales. To verify the effectiveness of SEEDS based CNN classification, the performance of SEEDS and three others superpixel segmentation algorithms are compared, and the superpixel extraction via SEEDS method was found to be the optimal superpixel segmentation approach for CNN classification. The scale effect on CNN classification accuracy was investigated by comparing the four superpixel segmentation methods. We found that (1) There is no strong evidence that using scales combinations is better than a single scale in some specific situations; (2) Natural objects with low complexity are not as sensitive to scale as artificial objects; (3) For a simple VHRI that contains clear artificial objects and simple texture, the classification result with multiple scales performs better a the single scale; (4) In contrast, for the complex VHRI containing a large number of complex objects, the classification result with a single small-scale best.     

基于图像分割的森林火灾早期烟检测算法研究

针对森林这样的大空间、复杂场景下的火灾检测,提出一种在单帧视频序列图像中的烟检测方法,并研究一种新的超像素合并算法,改进现有的天地线检测算法。该方法对图像进行SLIC（Simple Linear Iterative Clustering）超像素分割,并用一种新的超像素合并算法解决过分割问题;通过改进的天地线分割算法,排除天空中云对于烟检测的干扰;根据光谱特征,运用支持向量机（SVM）对超像素块进行分类。实验结果表明,超像素合并算法高效简洁,易于编程实现,基于图像分割的烟检测技术能排除云雾等噪声对烟雾检测的干扰,在森林场景下的烟雾检测正确率为77%,可以作为人工森林火灾监测的辅助手段。     

Semantic superpixel extraction via a discriminative sparse representation

The superpixel extraction algorithm is becoming increasingly significant for pattern recognition applications. Different superpixel generation methods have different properties and lead to various over-segmentation results. In this paper, we treat the over-segmentation as an image decomposition problem, and propose a novel discriminative sparse coding (DSC) algorithm to effectively extract the semantic superpixels. Specifically, the DSC algorithm incorporates a new discriminative regularization term in the traditional sparse representation model. Then the new regularization term is combined with the reconstruction error and sparse constraint to form a unified objective function. The extracted superpixels not only respect the local image boundaries, but also are dissimilar between each other. Meanwhile, the quantity of segments is sparse. These properties benefit for the semantic superpixel extraction. The final refined superpixels are generated based on an effective Bayesian-classification criterion in a post-processing step. Experimental results show that the over-segmentation quality of DSC algorithm outperforms the state of the art methods.     

Salient object detection method using random graph

In this paper, a bottom-up salient object detection method is proposed by modeling image as a random graph. The proposed method starts with portioning input image into superpixels and extracting color and spatial features for each superpixel. Then, a complete graph is constructed by employing superpixels as nodes. A high edge weight is assigned into a pair of superpixels if they have high similarity. Next, a random walk prior on nodes is assumed to generate the probability distribution on edges. On the other hand, a complete directed graph is created that each edge weight represents the probability for transmitting random walker from current node to next node. By considering a threshold and eliminating edges with higher probability than the threshold, a random graph is created to model input image. The inbound degree vector of a random graph is computed to determine the most salient nodes (regions). Finally, a propagation technique is used to form saliency map. Experimental results on two challenging datasets: MSRA10K and SED2 demonstrate the efficiency of the proposed unsupervised RG method in comparison with the state-of-the-art unsupervised methods.     

基于超像素形状特征的图像复制粘贴篡改检测算法

针对传统图像复制粘贴篡改检测方法中划分子块的数目过大导致算法时间复杂度过高且抵抗几何变换能力较弱的问题,提出一种基于超像素形状特征的图像复制粘贴篡改检测算法.首先提出基于小波对比度自适应划分超像素的方法分割图像并提取稳定的特征点;然后提出新颖的形状编码方式提取超像素形状特征,并与特征点融合,估计可疑伪造区域;最后对可疑伪造区域进行二次超像素分割和匹配,精确定位篡改区域.实验结果表明,提出的算法具有抵抗几何变换、噪声、模糊和JPEG压缩的能力.     

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Superpixel segmentation is a popular image pre‐processing technique in many computer vision applications. In this paper, we present a novel superpixel generation algorithm by agglomerative clustering with quadratic error minimization. We use a quadratic error metric (QEM) to measure the difference of spatial compactness and colour homogeneity between superpixels. Based on the quadratic function, we propose a bottom‐up greedy clustering algorithm to obtain higher quality superpixel segmentation. There are two steps in our algorithm: merging and swapping. First, we calculate the merging cost of two superpixels and iteratively merge the pair with the minimum cost until the termination condition is satisfied. Then, we optimize the boundary of superpixels by swapping pixels according to their swapping cost to improve the compactness. Due to the quadratic nature of the energy function, each of these atomic operations has only O(1) time complexity. We compare the new method with other state‐of‐the‐art superpixel generation algorithms on two datasets, and our algorithm demonstrates superior performance.     

Pathological brain detection in MRI scanning via Hu moment invariants and machine learning

Abstract

Background: We proposed a new automatic and rapid computer-aided diagnosis system to detect pathological brain images obtained in the scans of magnetic resonance imaging (MRI). Methods: For simplification, we transformed the problem to a binary classification task (pathological or normal). It consisted of two steps: first, Hu moment invariants (HMI) were extracted from a specific MR brain image; then, seven HMI features were fed into two classifiers: twin support vector machine (TSVM) and generalised eigenvalue proximal SVM (GEPSVM). Results: Then, a 5 × 5-fold cross validation on a data set containing 90 MR brain images, demonstrated that the proposed methods “HMI + GEPSVM” and “HMI + TSVM” achieved classification accuracy of 98.89%, higher than eight state-of-the-art methods: “DWT + PCA + BP-NN”, “DWT + PCA + RBF-NN”, “DWT + PCA + PSO-KSVM”, “WE + BP-NN”, “WE + KSVM”, “DWT + PCA + GA-KSVM”, “WE + PSO-KSVM” and “WE + BBO-KSVM”. Conclusion: The proposed methods are superior to other methods on pathological brain detection (p < 0.05).     

一种改进的快速SLIC分割算法

近年来,超像素算法被应用到计算机视觉的各个领域。超像素捕获图像冗余信息,降低图像后续处理的复杂度。超像素分割作为图像的预处理过程需要满足图像处理的实时性和准确性。在SLIC算法的框架下,所提算法的主要目的是提高超像素分割的效率;通过原图像降尺度过程,提取原图像中少量像素,生成降尺度图像;利用SLIC算法对降尺度图像进行超像素分割;初次超像素分割之后,根据降尺度图像的分割结果对原图像中像素进行K近邻分类,实现原图像的超像素最终分割结果。实验表明,对于同一处理对象,在准确度相近的状态下,本算法处理速度高于SLIC算法。     

Plant disease leaf image segmentation based on superpixel clustering and EM algorithm

Plant disease leaf image segmentation plays an important role in the plant disease detection through leaf symptoms. A novel segmentation method of plant disease leaf image is proposed based on a hybrid clustering. The whole color leaf image is firstly divided into a number of compact and nearly uniform superpixels by superpixel clustering, which can provide useful clustering cues to guide image segmentation to accelerate the convergence speed of the expectation maximization (EM) algorithm, and then, the lesion pixels are quickly and accurately segmented from each superpixel by EM algorithm. The experimental results and the comparison results with similar approaches demonstrate that the proposed method is effective and has high practical value for plant disease detection.

     

Spectral segmentation via minimum barrier distance

Constructing a reliable affinity matrix is crucial for spectral segmentation. In this paper, we define a technique to create a reliable affinity matrix for the application to spectral segmentation. We propose an affinity model based on the minimum barrier distance (MBD). First, the image is over-segmented into superpixels; then the subset of the pixels, located in the center of these superpixels, is used to compute the MBD-based affinities of the original image, with particular care taken to avoid a strong boundary, as described in the classical model. To deal with images with faint object and random or “clutter” background, we present gradient data that are integrated with the MBD data. To capture different perceptual grouping cues, the completed affinity model includes MBD, color, and spatial cues of the image. Finally, spectral segmentation is implemented at the superpixel level to provide an image segmentation result with pixel granularity. Experiments using the Berkeley image segmentation database validate the effectiveness of the proposed method. Covering, PRI, VOI, and the F-measure are used to evaluate the results relative to several state-of-the-art algorithms.     

Energy-based cloud detection in multispectral images based on the SVM technique

In this paper, the energy characteristics of Gabor texture are used for cloud detection in high-resolution multispectral images. First, the satellite remote-sensing image is divided into superpixels using simple linear iterative clustering (SLIC), and then, the energy characteristics of Gabor texture and spectral characteristics are computed by extracting the texture features of the superpixels. The features of the cloud superpixels are used as the learning sample of the support vector machine (SVM) classifier, and a classification model is obtained by training the SVM classifier. Finally, a cloud-detection experiment is conducted for various sensor images with three visible bands and one near-infrared band. The experimental results showed that the proposed method provides an excellent average overall accuracy for thick and thin clouds in a complex background of forests, harbours, snow and mountains. The characteristic parameters of this paper are not limited by the image parameters; thus, they provide good results and universality for various types of sensors.     

基于超像素的条件随机场图像分类

针对图模型在推导和参数估计中时间复杂度较高的问题,在条件随机场(CRF)中引入了超像素的概念,提出了一种基于超像素的CRF图像分类方法。该方法首先通过均值漂移算法将图像过分割成小的均匀区域（称为超像素）,然后以超像素为节点、空间相邻的节点以边连接建立图模型,给出了相应的CRF的定义,实现了模型的参数估计和推导。实验结果表明,基于超像素的CRF模型在得到较好分类结果的同时,极大地缩短了运行时间,提高了效率。     

多尺度超像素分割和奇异谱分析的高光谱影像分类

目的 高光谱影像（hyperspectral image,HSI）中“同物异谱,异物同谱”的现象普遍存在,使分类结果存在严重的椒盐噪声问题。HSI中的空间地物结构复杂多样,单一尺度的空间特征提取方法无法有效地表达地物类间差异和区分地物边界。有效解决光谱混淆和空间尺度问题是提高分类精度的关键。方法 结合多尺度超像素和奇异谱分析,提出一种新的高光谱影像分类方法,从而充分挖掘地物的局部空间特征和光谱特征,解决空间尺度和光谱混淆的问题,提高分类精度。利用多尺度超像素对影像进行分割,获取不同尺度的分割影像,同时在分割区域内进行均值滤波,减少类内的光谱差异,增强类间的光谱差异;对每个区域计算平均光谱向量,并利用奇异谱分析方法获取光谱的主要鉴别特征,同时消除噪声的影响;利用支持向量机对不同尺度超像素分割影像进行分类,并进行决策融合,得到最终的分类结果。结果 实验选取了两个标准高光谱数据集和一个真实数据集,结果表明,利用本文算法提取的光谱—空间特征进行分类,比直接在原始数据上进行分类分别提高约26.8%、9.2%和13%的精度;与先进的深度学习SSRN （spectral-spatial residual network）算法相比,本文算法在精度上分别提升约5.2%、0.7%和4%,并且运行时间仅为前者的18.3%、45.4%和62.1%,处理效率更高。此外,在训练样本有限的情况下,两个标准数据集的样本分别为1%和0.2%时,本文算法均能取得87%以上的分类精度。结论 针对高光谱影像分类中的难题,提出一种新的融合光谱和多尺度空间特征的HSI分类方法。实验结果表明,本文方法优于对比方法,可以产生更精细的分类结果。     

具有纹理感知能力的超像素分割方法

目的 超像素分割是计算机视觉领域常用的一项预处理技术,目标是将相邻像素聚集成为具有一定语义的子区域,能够大幅度降低后续处理的计算复杂度,但是对包含强梯度纹理的图像分割效果不佳,为此提出一种具有纹理感知能力的超像素分割方法。方法 提出一种能够区分强梯度噪声和纹理像素的颜色距离,其中利用带方向的1/4圆形窗口均值滤波后的颜色信息,提升包含强梯度噪声和纹理图像的超像素分割性能。利用区间梯度幅值与Sobel梯度幅值相乘得到混合梯度幅值,具有纹理抑制、结构保持以及边缘线条细的优点,能够提升超像素的贴合边缘性能,增强超像素形状规则程度。最后,利用混合梯度的幅值计算具有结构回避能力的综合聚类距离,进一步防止超像素跨越物体的边界,增强超像素的贴边性能。结果 在BSDS500（Berkeley segmentation dataset 500）图像数据集和强纹理马赛克图像等不同类型图像上的测试结果显示,与目前主流的超像素分割方法相比,本文算法在UE （undersegmentation error）、ASA （achievable segmentation accuracy）和CM （compactness measure）等性能指标上分别提高了1.5%、0.2%和4.3%。从视觉效果上看,能够在排除纹理干扰的情况下生成结构边缘贴合程度更好的形状规则超像素。结论 本文算法在包含强梯度纹理图像上的超像素分割性能优于对比方法,在目标识别、目标追踪和显著性检测等易受强梯度干扰的技术领域具有较大应用潜力。     

Superpixel-based active contour model for unsupervised change detection from satellite images

This study proposes a superpixel-based active contour model (SACM) for unsupervised change detection from satellite images. The accuracy of change detection produced by the traditional active contour model suffers from the trade-off parameter. The SACM is designed to address this limitation through the incorporation of the spatial and statistical information of superpixels. The proposed method mainly consists of three steps. First, the difference image is created with change vector analysis method from two temporal satellite images. Second, statistical region merging method is applied on the difference image to produce a superpixel map. Finally, SACM is designed based on the superpixel map to detect changes from the difference image. The SACM incorporates spatial and statistical information and retains the accurate shapes and outlines of superpixels. Experiments were conducted on two data sets, namely Landsat-7 Enhanced Thematic Mapper Plus and SPOT 5, to validate the proposed method. Experimental results show that SACM reduces the effects of the trade-off parameter. The proposed method also increases the robustness of the traditional active contour model for input parameters and improves its effectiveness. In summary, SACM often outperforms some existing methods and provides an effective unsupervised change detection method.