结合纹理的SVM遥感影像分类研究

针对传统统计模式识别分类方法分类精度不高,分类时未加入像元灰度的空间分布和结构特征以及分类时样本不足等缺陷,采用一种结合纹理的支持向量机(SVM)遥感图像分类方法。该方法在对Landsat7 ETM遥感影像进行纹理特征提取的基础上,构建了结合纹理的SVM分类模型。以河南省汝阳县为试验区,利用此模型对该区域的土地利用类型进行分类研究,并将分类结果与最大似然法和单源数据(光谱)SVM分类结果进行定性和定量比较分析。研究结果表明:该方法能够有效地解决单数据源分类效果破碎、分类精度不高等问题;对高维输入向量具有较高的推广能力;总精度达到90%,比单源信息的SVM分类法提高了6%,而与最大似然法相比,总精度提高了近9%,取得了良好的效果。     

露天灰岩矿纹理特征分析及面向对象的分类

矿产资源过度开发造成了严重的环境污染,可持续发展面临严峻挑战,矿山治理迫在眉睫。遥感信息提取技术能够便捷地获取矿山开发信息,为矿山治理提供依据。然而,目前信息提取的精度和自动化程度仍有提升空间,并且就矿产类型而言,关于石灰岩矿开采信息提取的研究甚少。针对以上现状,本文以唐山市的一处灰岩矿山为例,以Landsat-8影像作为基础数据,通过计算不同地物的纹理信息,包括地物均值、方差、信息熵、偏离度和数据范围,构造了能够突出露天灰岩矿开采区域的纹理指数模型(texture variance index,简称TVI)。结合已有的光谱和空间特征,设定准确的阈值并建立决策树,以面向对象方法为依托,进行露天灰岩矿山开采边界的信息提取。结果表明,将纹理方差指数作为灰岩矿山开发信息提取的规则之一,总体精度、用户精度和Kappa系数与原有决策树相比皆有所提高。以文中灰岩矿开采范围提取结果为基础,根据高分辨率影像的纹理特征,进一步实现了新矿区与待复垦旧矿区的分类,总体精度约为0.916。     

一种基于纹理和光谱特征的高光谱影像信息向量机分类方法

针对高光谱影像中空间特征信息利用不足的问题,提出了一种基于纹理和光谱特征的高光谱影像信息向量机分类方法。该方法首先采用三维Gabor滤波器对高光谱影像数据立方体进行纹理特征提取,提取后的影像数据同时具有光谱和纹理特征,避免了传统纹理特征提取带来的高维特征和光谱不连续的问题;然后采用分类精度和效率都较高的信息向量机进行分类处理。通过AVIRIS高光谱影像实验,结果表明该方法不仅提高了影像的分类精度,而且还消除了分类结果图中的类别噪声现象。     

“数字城市”三维建模技术

三维虚拟现实技术作为"数字城市"的重要组成部分,其核心是通过三维建模等技术手段完整再现城市全貌。结合"数字城市"建模实例,探讨了通过3DS Max平台实现高效三维建模的方法。     

基于SketchUp的三维地貌建模技术

提出了三维地貌模型的逻辑结构,阐述了基于三维建模工具SketchUp的三维地貌建模流程,介绍了基于等高线和基于高程点的2种三维地貌建模技术;并以大连生态科技创新城核心区为例,详细介绍了2种建模技术的具体步骤。     

基于分区和纹理特征的伊犁河谷遥感影像土地利用分类

利用新疆伊犁河谷的伊宁县SPOT5遥感影像,在ERDAS IMAGINE 9.2软件平台下,通过二次变异分析算法和三次非对称分析算法提取纹理信息。基于图像的光谱特征和纹理特征进行监督分类,然后根据地物的空间分布进行"分区分类处理"。结果表明,伊宁县的总体分类精度提高了19.34%,Kappa系数提高了0.247。利用霍城县遥感图像进行分类方法验证,同样取得了较好的效果,表明该方法可在伊犁河谷土地利用分类中进行推广应用。     

An approach to extracting information of residential areas from Beijing-1 image based on Gabor texture segmentation

Abstract

According to the features of high-resolution panchromatic imagery of Beijing-1 small satellite, an approach to extracting information of residential areas is proposed in this paper based on Gabor texture segmentation. The algorithm extracts the features in different directions and different scales by building the Gabor filter, uses cluster analysis of multiple features to segment the image, and performs the fusion processing based on morphological scale space. It solves the problems in image processing resulting from low contrast between remote sensing objects and background, the blurring of image edges and high noise. It has the benefits of direction selection and frequency selection with strong self-adaptive ability. Our experiments prove the effectiveness of the approach for extracting information of residential areas from Beijing-1 high-resolution imagery.     

Quantitative geophysical pore‐type characterization and its geological implication in carbonate reservoirs

This paper discusses and addresses two questions in carbonate reservoir characterization: how to characterize pore‐type distribution quantitatively from well observations and seismic data based on geologic understanding of the reservoir and what geological implications stand behind the pore‐type distribution in carbonate reservoirs. To answer these questions, three geophysical pore types (reference pores, stiff pores and cracks) are defined to represent the average elastic effective properties of complex pore structures. The variability of elastic properties in carbonates can be quantified using a rock physics scheme associated with different volume fractions of geophysical pore types. We also explore the likely geological processes in carbonates based on the proposed rock physics template. The pore‐type inversion result from well log data fits well with the pore geometry revealed by a FMI log and core information. Furthermore, the S‐wave prediction based on the pore‐type inversion result also shows better agreement than the Greensberg‐Castagna relationship, suggesting the potential of this rock physics scheme to characterize the porosity heterogeneity in carbonate reservoirs. We also apply an inversion technique to quantitatively map the geophysical pore‐type distribution from a 2D seismic data set in a carbonate reservoir offshore Brazil. The spatial distributions of the geophysical pore type contain clues about the geological history that overprinted these rocks. Therefore, we analyse how the likely geological processes redistribute pore space of the reservoir rock from the initial depositional porosity and in turn how they impact the reservoir quality.     

Magmatic Processes of Ashi Volcano,Western Kunlun Mountains,China

The Ashikule volcanic cluster(AVC) in western Kunlun Mountains is located in a graben region at the convergence of the Altun and Kangxiwa fault zones, and consists of more than 10 main volcanoes and dozens of volcanelloes. The Ashi volcano lies in the central part of the volcanic cluster. The lithology, chemical composition and texture of Ashi volcanic rocks were studied in detail, and their implication in magmatic processes was discussed. The phenocrysts in Ashi volcanic rocks consist mainly of plagioclase and pyroxene, and the statistical results of phenocryst contents show that the rocks can be subdivided into two groups. In group A, the content of pyroxene phenocrysts is generally higher than that of plagioclase phenocrysts, but an inverse relation occurs in group B. In TAS diagram, the compositions of both groups fall into the trachyandensite field, but they are obviously concentrated into two clusters. The two clusters exist also in the oxide diagrams. The pyroxene phenocrysts comprise augite, bronzite and hypersthene, and their Mg# histogram shows two peaks. Plagioclase phenocrysts with reaction rim are observed in rocks of both groups. The An values of the core are generally 30–40, and those of the rim are 44–48, which are closer to those of euhedral plagioclases. The bronzites are in equilibrium with the melt, and two sets of magma depths, i.e., 18–25 km and 13–18 km, can be estimated by using thermobarometer proposed by Putirka. The hypersthenes are not in equilibrium with the melt, and can be assigned to xenocrysts. The crystal size distribution(CSD) curves of plagioclase appear as kinked lines indicative of magma mixing. The above analyses show that two magma pockets might exist beneath the Ashi volcano. It is likely that they are connected with each other. The one has more evolved and contains more acidic magma, and the other is a trachyandensite magma pocket characterized by layering. The magma from the upper part of the trachyandensite magma pocket might mix with more acidic magma, resulting in a magma that is more acidic than the magma from the lower part.     

江苏姜堰孔隙承压地下水资源评价三维数值模拟

通过建立符合该地区承压地下水赋存条件和渗流特征的地下水三维数值模型,并在模型识别、验证的基础上,根据各承压含水层的水位控制要求,调整现有地下水的开采布局,以乡镇为单位,确定出各含水层的地下水可开采资源量及最优开采布局,并预测2011—2020年底逐年地下水水位动态变化情况。