基于混合熵模型的遥感分类不确定性的多尺度评价方法研究

不确定性是影响遥感图像分类质量的最主要因素,针对在遥感图像分类过程中同时存在随机不确定性和模糊不确定性的特点,提出基于混合熵模型来综合测度这两种不确定性的方法,并建立起多尺度的评价指标.在分析混合熵模型基本原理的基础之上,提出利用特征空间的和模糊分类器的统计数据来建立信息熵、模糊熵以及混合熵的方法.同时,在像元和类别尺度上,分别建立像元混合熵和类别混合熵的指标对分类不确定性进行评价.最后,应用湖北省黄石市的遥感影像对上述评价方法进行验证分析,实验结果表明,混合熵模型能有效地反映分类过程中随机不确定性和模糊不确定性的综合影响,并从不同尺度反映出遥感影像分类的质量问题.     

双LSTM驱动的高分遥感影像地物目标空间关系语义描述

高分辨率遥感影像中的地物目标具有清晰的类别属性与空间关系语义。在人工智能技术支撑下,用计算机自动认知其空间关系具备了可行性。目前,遥感影像场景的语义理解主要依托图像描述任务(image caption),基于影像的全局特征生成描述语句。但是,这种粗粒度特征容易导致地物目标的类别属性在描述语句生成过程中被错误预测。事实上,以地物目标作为空间关系语义理解的基本单元,更符合人们认知地理空间的习惯。为得到更准确的描述语句,本文构建了基于地物目标的遥感影像语义理解数据集,并提出双LSTM驱动的地物目标空间关系语义理解方法。该方法用目标检测模型识别影像中的显著目标,将这些目标特征输入到语言模型,以缓解描述语句中类别被错误预测的问题。进而,为利用遥感影像场景信息,将影像全局特征与目标区域特征进行融合,并用双LSTM预测目标的注意力分布,提高描述语句生成质量。对比实验结果表明,该方法能生成更准确的图像描述。     

基于多维云空间的多光谱遥感影像边缘检测研究

在云模型的基础之上,提出一种基于多维云空间的遥感影像边缘检测算法。该方法依据矢量角相似性准则并结合邻域关系进行图像区域生长,在此基础之上根据影像不同波段的数据特征建立多维云空间映射模型,将数据从图像空间映射到云空间。通过多维云的逻辑运算生成边界云并进行向量综合。利用云的数字特征反推隶属度,构建边缘模糊特征平面,并通过最大模糊熵原则确定最优阈值,对图像模糊边界进行提取。试验结果表明,该算法在多光谱遥感影像中能取得较好检测效果。     

基于像斑空间关系的遥感图像分类

为充分挖掘遥感图像本身包含的空间关系信息,弥补基于光谱信息的传统图像分类方法的不足,提高分类精度,提出了一种基于像斑空间关系的遥感图像分类方法.通过图像分割获取像斑,利用最大似然法获取初始分类结果,引入马尔科夫随机场对像斑的空间关系予以描述,通过地物的类别邻接矩阵定量地描述各地物类别之间的空间关系,从而对图像的分类结果进行修正,最后采用条件迭代的方法获取最终的图像分类结果,精度较好.实验结果表明,该方法应用于高分辨率遥感图像可取得较好的分类效果.     

基于分辨率融合的多尺度遥感影像分类技术研究

影响遥感图像分类效果的主要因素之一是影像的空间分辨率。本文将Quickbird多光谱影像与高分辨率全色影像相融合,在保留了光谱信息的同时提高了影像分辨率。然后对融合后的影像进行多尺度分割,并运用地物的光谱统计特征、形状、纹理、类间关系等因素进行相关信息的提取。采用面向对象的模糊分类方法对试验区影像进行分类,最后对结果进行了精度评价。试验表明这种方法具有较高的精度。     

融合形状和光谱的高空间分辨率遥感影像分类

提出了一种像元形状指数及基于形状和光谱特征融合的高（空间）分辨率遥感影像分类方法。形状和光谱是遥感影像纹理的具体表现形式,尤其在高分辨率影像中地物细节得到充分表达,相邻像元的关系及其共同表征的形状特性成为分类的重要因素。本文用像元及其邻域的关系来描述其空间结构,同时为了更全面地利用影像特征,提出了基于支持向量机的形状和光谱融合分类方法。实验证明,该方法计算简便且能有效表达高分辨率影像的地物特征,提高分类精度。     

基于多尺度超像素的高光谱图像分类研究

随着遥感技术的快速发展,高光谱遥感影像的分类方法研究受到普遍关注。现有高光谱遥感影像分类研究采用单一尺度下的超像素方法进行图像分割处理,无法确定最佳超像素个数,较易忽视图像细节信息,且单一核矩阵无法表征多特征信息导致分类精度降低。因此,本研究拟在多尺度下采用超像素分割方法对高光谱影像的第一主成分分量进行多尺度超像素分割处理,通过权值耦合多尺度空间光谱核与原始空间光谱核形成合成核来进行高光谱影像分类,并以Washington DC Mall高光谱影像为实验数据对本文方法进行测试与分析。实验结果显示,相较于对比方法,这一方法的有效分类精度最高提升6.93个百分点。结果证明该方法可以有效解决图像光谱无法自适应、光谱信息获取不全面的问题,能够显著提升高光谱影像分类精度。     

模糊Isodata聚类分析在遥感图像分类中的应用研究

针对模糊模式识别的原理，根据遥感图像的特征，提出了基于模糊Isodata聚类分析的遥感图像分类方法。研究结果表明：该方法具有简单、快速和有效的特点，从而拓宽了模糊模式识别的应用范围。     

利用OpenStreetMap数据进行高空间分辨率遥感影像分类

针对高分辨率遥感影像分类样本标注困难的问题，提出了一种利用OpenStreetMap （OSM）数据自动获取标注样本的方法。与现有的利用OSM数据进行分类的方法不同，该方法加入了空间特征以弥补单独使用光谱特征分类的不足。首先，基于OSM数据提供的地物类别和位置信息进行样本标注，为了降低OSM数据中少量错误信息对分类结果的影响，采用聚类分析的方法对样本进行提纯；其次，使用形态学轮廓来提取影像的结构特征，挖掘高分辨率遥感影像丰富的空间信息，与光谱特征相叠加并输入分类器进行分类。试验证明，本文提出的方法能够有效避免人工样本标注所需要的人力物力；同时，联合影像的光谱空间特征能够更好地描述地物特性，得到较高的分类精度。     

顾及结构特征的多层次马尔科夫随机场模型在影像分类中的应用

针对基于像素或基于区域的马尔科夫随机场(Markov random field,MRF)模型仅能描述单一层次影像数据特性的局限,提出了一种综合像素和区域特性的多层次MRF模型,以提高MRF模型表达遥感数据层次特性的能力。为利用高分辨率遥感影像几何结构信息来提高不同地物的可区分性,提出了一种描述地物结构特性的形状特征,用于区分光谱特性相似的不同地物。本文的分类算法包括两个过程:首先,基于像素和区域特征,采用多层次MRF模型进行初始分类;然后,基于形状特征采用SVM对第一步分类结果中易混淆的地物进行分类。根据不同地物采用合适特征量描述可在特征空间中增加可区分性的事实,采用形状特征对基于层次MRF模型的错分类别进行再分类可有效改善分类精度。同现有基于单一层次的方法相比,实验结果表明该算法的分类性能有了明显的改善。     

Combining the FCM Classifier with Various Kernels to Handle Non-linearity of Class Boundaries

This article presents the use of kernel functions in fuzzy classifiers for an efficient land use/land cover mapping. It focuses on handling mixed pixels obtained from a remote sensing image by considering non-linearity between class boundaries. It uses kernel functions combined with the conventional fuzzy c-means (FCM) classifier. Kernel-based fuzzy c-mean classifiers were applied to classify AWiFS and LISS-III images from Resourcesat-1 and Resourcesat-2 satellites. Optimal kernels were obtained from eight single kernel functions. Fractional images generated from high resolution LISS-IV image were used as reference data. Classification accuracy of the FCM classifier increased with 12.93%. Improvement in overall accuracy shows that non-linearity in the dataset was handled adequately. The inverse multiquadratic kernel and the Gaussian kernel with the Euclidean norm were identified as optimal kernels. The study showed that overall classification accuracy of the FCM classifier improved if kernel functions were included.     

基于灰度-基元共生矩阵的多光谱遥感影像分类

提出了基于灰度-基元共生矩阵的遥感影像纹理分析的方法,分析了提取的纹理特征,实现了利用模糊C-均值算法对多光谱影像和纹理特征影像进行分类,比较和讨论了各种不同的分类结果.     

Detecting shadows in multi-temporal aerial imagery to support near-real-time change detection

Multi-temporal aerial imagery captured via an approach called repeat station imaging (RSI) facilitates post-hazard assessment of damage to infrastructure. Spectral-radiometric (SR) variations caused by differences in shadowing may inhibit successful change detection based on image differencing. This study evaluates a novel approach to shadow classification based on bi-temporal imagery, which exploits SR change signatures associated with transient shadows. Changes in intensity (brightness from red–green–blue images) and intensity-normalized blue waveband values provide a basis for classifying transient shadows across a range of material types with unique reflectance properties, using thresholds that proved versatile for very different scenes. We derive classification thresholds for persistent shadows based on hue to intensity ratio (H/I) images, by exploiting statistics obtained from transient shadow areas. We assess shadow classification accuracy based on this procedure, and compare it to the more conventional approach of thresholding individual H/I images based on frequency distributions. Our efficient and semi-automated shadow classification procedure shows improved mean accuracy (93.3%) and versatility with different image sets over the conventional approach (84.7%). For proof-of-concept, we demonstrate that overlaying bi-temporal imagery also facilitates normalization of intensity values in transient shadow areas, as part of an integrated procedure to support near-real-time change detection.     

Fuzzy Logic System for Road Identification Using Ikonos Images

Research into both extraction of man-made objects and automatic change detection from aerial and satellite images has made significant progress in recent years. This paper presents an approach, based on a fuzzy logic system, for the identification of suburban roads in Ikonos images. The linguistic variables are the mean and standard deviation (SD) of different objects with Gaussian membership function. After the roads have been identified provisionally and their skeleton extracted, the skeleton can be vectorised and then used as direct input to a GIS for further analysis. The method was tested on an Ikonos "Geo" image covering Bilesavar in north-western Iran. For the suburban area of Bilesavar, the results showed that grey scale values ranged from 20 to 190 for non-roads and 226 to 228 for roads, the optimum width of the Gaussian kernel function was 3 and the SD was 0.4. It was also found that about 91% of main roads with a width of 6 to 12 pixels could be extracted from high resolution satellite imagery by the algorithm. The computer program for this study has been developed in visual C++ based on Windows 98     

基于支持向量机的航空影像纹理分类研究

提出一种用SVM解决航空影像纹理分类的方法。在利用一些常用的纹理特征的基础上，将SVM用于航空影像纹理分类，有效地解决了特征选择难和高维数问题。试验表明，这种方法可以取得较好的结果。     

线阵推扫影像的核线模型研究

通过对线阵CCD推扫式影像和框幅式中心投影影像的核线理论的对比研究，建立了线阵CCD推扫式影像的核线理论，并探讨了它的基本特性，从而为核线在线阵CCD推扫式影像中的应用提供了理论基础。     

A comparison of alternative criteria for defining fuzzy boundaries on fuzzy categorical maps

1　ＩｎｔｒｏｄｕｃｔｉｏｎＣａｔｅｇｏｒｉｃａｌｍａｐｓｒｅｐｒｅｓｅｎｔａｎｉｍｐｏｒｔａｎｔｔｙｐｅｏｆｄａｔａｉｎｃｏｒｐｏｒａｔｅｄｉｎＧＩＳｓ,ｗｈｉｃｈｄｅｐｉｃｔｓｐａｔｉａｌｄｉｓ ｔｒｉｂｕｔｉｏｎｓｉｎｆｏｒｍｏｆｅｘｈａｕｓｔｉｖｅ,ｎｏｎ＿ｏｖｅｒｌａｐｐｉｎｇａｒｅａｌｕｎｉｔｓｓｅｐａｒａｔｅｄｂｙｂｏｕｎｄａｒｙｌｉｎｅｓ.Ａｎａｓｓｕｍｐ ｔｉｏｎｕｎｄｅｒｌｙｉｎｇｃｏｎｖｅｎｔｉｏｎａｌｃａｔｅｇｏｒｉｃａｌｍａｐｐｉｎｇｉｓｔｈｅｏｂｊｅｃｔ＿ｂａｓｅｄｖｉｅｗ…     

航空影像分割的最小二乘支持向量机方法

将最小支持向量机LS-SVM用于航空影像的分割,讨论了不同核函数对分割结果的影响和稀疏化处理对决策函数的影响。试验表明了LS-SVM方法用于航空影像分割的可行性。     

A support vector machine classifier based on a new kernel function model for hyperspectral data

The kernel function is a key factor to determine the performance of a support vector machine (SVM) classifier. Choosing and constructing appropriate kernel function models has been a hot topic in SVM studies. But so far, its implementation can only rely on the experience and the specific sample characteristics without a unified pattern. Thus, this article explored the related theories and research findings of kernel functions, analyzed the classification characteristics of EO-1 Hyperion hyperspectral imagery, and combined a polynomial kernel function with a radial basis kernel function to form a new kernel function model (PRBF). Then, a hyperspectral remote sensing imagery classifier was constructed based on the PRBF model, and a genetic algorithm (GA) was used to optimize the SVM parameters. On the basis of theoretical analysis, this article completed object classification experiments on the Hyperion hyperspectral imagery of experimental areas and verified the high classification accuracy of the model. The experimental results show that the effect of hyperspectral image classification based on this PRBF model is apparently better than the model established by a single global or local kernel function and thus can greatly improve the accuracy of object identification and classification. The highest overall classification accuracy and kappa coefficient reached 93.246% and 0.907, respectively, in all experiments.