面向对象遥感分类方法在汶川地震震害提取中的应用

震后城市建筑物震害的自动识别与分类, 是遥感震害调查中的关键步骤, 其精度直接影响损失评估的结果. 而随着高分辨率遥感影像的发展, 传统基于像元的分类技术已不能满足需求, 引入面向对象的信息提取技术, 充分挖掘影像对象的纹理、形状和相互关系等信息, 能够有效的提高震害的分类精度. 该文阐述了面向对象的遥感震害提取思路和方法, 并应用汶川地震震后高分辨率航空遥感数据, 针对建筑物震害进行面向对象的快速提取与自动分类. 结果表明, 与基于像元分类比较, 面向对象的建筑物震害分类能够显著改善分类效果.     

基于面向对象分类的建筑物倒塌率计算方法研究

建筑物倒塌是造成地震人员伤亡的主要原因,对地震应急救援与决策具有重要的指导意义.遥感以其综合、宏观、快速、动态的特点,为地震灾害信息调查和震害快速评估提供了一种可靠的信息源.面向对象的分类方法是针对高分辨率影像的一种新的分类方法.本文在总结遥感影像建筑物震害信息提取方法进展的基础上,将建筑物分为基本完好和毁坏两个等级.选取唐山地震和汶川地震的震后航片,利用面向对象的分类方法来识别影像上基本完好的建筑物,计算评估区内的建筑物倒塌率.实验结果表明,面向对象的分类方法充分利用了图像上的光谱、形状、纹理等特征.在很大程度上克服了基于像元分类方法的局限性,并且基于对象的建筑物倒塌率计算也取得了较好的精度.     

基于遥感影像的农村建筑物分类

利用面向对象的遥感影像信息提取方法对建筑物进行分类研究,选取张家口不同地区5个中等规模农村建筑为研究对象,根据建筑物特征信息从遥感影像上进行提取,根据信息提取调整后的结果进行建筑物分类,并与调研结果进行对比,结果表明:建筑物分类准确率达到80%以上,满足对张家口地区农村建筑物分类的需求,可以用来辅助完成对建筑物结构类型的实地调研,能够有效提高调研效率,服务于建筑物抗震设防调研。     

基于自适应区间二型模糊聚类的遥感土地覆盖自动分类

遥感影像土地覆盖分类面临"类别密度差异显著"、"同谱异物"和"同物异谱"等不确定性问题,传统的分类方法(如FCM)因不能描述高阶模糊不确定性,无法完成准确建模,使分类误差较大,而二型模糊集恰是处理此类不确定性的有效工具.在引入二型模糊集新概念和自适应降型新方法的基础上,提出一种自适应二型模糊分类方法(A-IT2FCM):(1)基于样本集模糊距离度量构建面向分类的区间二型模糊集,以尽可能降低对先验知识和预设参数的依赖,从而满足自动分类的要求;(2)给出一种自适应探求等价一型代表(模糊)集合的高效降型方法,在此基础上进行自适应区间二型模糊聚类.实验数据为珠海横琴和北京颐和园的SPOT5影像数据,对比方法有A-IT2FCM、基于Karnik-Mendel算法降型和基于Tizhoosh提出的简易降型方法的区间二型模糊C均值聚类以及作者前期研究提出的区间值模糊C-均值算法(IV-FCM).实验结果表明,A-IT2FCM方法分类效果佳,在类别具有较大密度差异和多重模糊性时能得到比FCM及IV-FCM更精确的边界和更连贯的类别,适于处理遥感影像土地覆盖类别的深层不确定性;同时在"光谱混叠"现象严重时,可以获得比对比方法更稳健、精度更高的影像自动分类结果,且时间复杂度明显低于基于Karnik-Mendel方法.     

基于稀疏成分分析的遥感影像分类

遥感影像分类一直是遥感研究的重点、难点和热点之一.针对经典的主成分分析法在不同地物的光谱存在重叠相关时,分类效果欠佳的缺陷,提出一种基于稀疏成分分析的遥感影像分类法.该方法利用稀疏性提取源信号,不要求源成分之间互不相关.实验结果表明,与主成分分析方法相比,基于稀疏成分分析的分类结果更可靠、更准确.     

基于SHALSTAB模型与面向对象遥感影像分析的地震滑坡信息快速检测

滑坡是最为常见的地震次生灾害之一,对其进行有效监测一直都是业界研究的热点。基于此,提出了一种高分遥感影像地震滑坡信息快速检测方法,该方法将SHALSTAB模型与面向对象影像分析相结合,首先对遥感影像进行多尺度分割,并根据稳定性模型赋权,然后根据深度学习机制对滑坡对象进行检测,最后对检测结果进行过滤,并将该方法应用于2013年芦山地震滑坡检测,与目视解译结果进行对比。结果表明:该方法能快速检测高分遥感影像上滑坡,滑坡检测正确率达85%以上。     

基于无人机影像的面向对象建筑物结构分级提取方法研究

为提高遥感影像建筑物结构识别精度,综合利用光谱、形状、空间、纹理和数字表面模型(DSM)建立了建筑物结构分级提取方法。基于研究区无人机高分辨率影像,采用面向对象的影像分析策略,首先进行多尺度分割,以最佳分割与合并指数提取影像中建筑物目标;然后分别采用规则、训练样本与DSM方法对建筑物结构进行分类;最后将3种分类方法进行融合,对比分析了单一方法和融合分类方法的建筑物结构分类精度。结果表明:基于规则+样本+DSM的半监督建筑物结构分类方法错分率、漏检率与Kappa系数最优。     

遥感影像震害信息提取技术研究

近年来,随着遥感影像分辨率的提高和遥感信息提取技术的发展,遥感技术逐渐成为快速获取地震灾情信息、震后应急和震害快速评估的有效手段。但以往的遥感震害信息提取结果精度较低、震害识别对象单一     

面向对象遥感分类方法在震害快速提取中的应用

以汶川地震后受灾严重的北川县城为研究区域,应用面向对象的遥感分类方法,对福卫二号卫星多光谱影像进行灾害提取与分析。提取过程中在传统分类运用的光谱信息中加入影像地物的几何结构和纹理信息,运用多尺度分割、多层次交叉的地物分类模式,模拟人类思维,快速准确的提取了灾害区域的宏观受灾范围,为震后快速评估提供依据。     

基于最优分割的高分辨率遥感影像震害建筑物识别技术

为了提高建筑物震害信息提取的效率与准确度,针对震后高分辨率遥感影像,根据震害建筑物在遥感影像上的特征,以2010年海地M_S7.0地震为例,通过尺度参数估计算法自动选择最优分割尺度对影像进行多尺度分割,并采用面向对象方法对海地高分辨率遥感影像进行建筑物震害信息提取,同时与基于像元的支持向量机、反向传播神经网络、基于分类回归算法的决策树分类方法进行比较。试验结果表明,面向对象的分类方法具有更好的目视效果和更高的分类精度,有利于地震后震害信息的准确提取和快速评估。      

A classification method of building structures based on multi-feature fusion of UAV remote sensing images

In order to improve the accuracy of building structure identification using remote sensing images, a building structure classification method based on multi-feature fusion of UAV remote sensing image is proposed in this paper. Three identification approaches of remote sensing images are integrated in this method: object-oriented, texture feature, and digital elevation based on DSM and DEM. So RGB threshold classification method is used to classify the identification results. The accuracy of building structure classification based on each feature and the multi-feature fusion are compared and analyzed. The results show that the building structure classification method is feasible and can accurately identify the structures in large-area remote sensing images.     

Improvement of dark object method in atmospheric correction of hyperspectral remotely sensed data

The existing methods in atmospheric correction of hyperspectral data usually focus on removing the effects of water vapor and other absorptive gases, while this paper mainly studies the method of re- moving the influence of the aerosol and the water vapor simultaneously. Because the hyperspectral data has a larger number of bands, the conventional dark object method cannot be applied to the at- mospheric correction of the hyperspectral data which can be improved, as described in this paper, by adequately making use of spectral characteristics of the hyperspectral data with an iterative correction during the whole process. The effects of the aerosol and water vapor are eliminated at the same time finally. The improved dark object method is used to do the atomospheric correction of the Hyperion data in Yanzhou, Shandong Province as an example. And the result indicates that it can correct the atmospheric influence of the hyperspectral data quickly and remarkably.     

Mapping groundwater‐dependent ecosystems using remote sensing measures of vegetation and moisture dynamics

Protection of groundwater‐dependent ecosystems (GDEs) is an important criterion in sustainable groundwater management, particularly when human water consumption is in competition with environmental water demands; however, the delineation of GDEs is commonly a challenging task. The Groundwater‐dependent Ecosystem Mapping (GEM) method proposed here is based on interpretation of the land surface response to the drying process derived from combined changes in two multispectral indices, the Normalised Difference Vegetation Index and the Normalised Difference Wetness Index, both derived from Landsat imagery. The GEM method predicts three land cover classes used for delineation of potential GDEs: vegetation with permanent access to groundwater; vegetation with diminishing access to groundwater; and water bodies that can persist through a prolonged dry period. The method was applied to a study site in the Ellen Brook region of Western Australia, where a number of GDEs associated with localised groundwater, diffuse discharge zones, and riparian vegetation were known. The estimated accuracy of the method indicated a good agreement between the predicted and known GDEs; Producer's accuracy was calculated as up to 91% for some areas. The method is most applicable for mapping GDEs in regions with a distinct drying period. Copyright © 2012 John Wiley & Sons, Ltd.     

Land cover classification of remote sensing imagery based on interval-valued data fuzzy c-means algorithm

There is a certain degree of ambiguity associated with remote sensing as a means of performing earth observations.Using interval-valued data to describe clustering prototype features may be more suitable for handling the fuzzy nature of remote sensing data,which is caused by the uncertainty and heterogeneity in the surface spectral reflectance of ground objects.After constructing a multi-spectral interval-valued model of source data and defining a distance measure to achieve the maximum dissimilarity between intervals,an interval-valued fuzzy c-means(FCM)clustering algorithm that considers both the functional characteristics of fuzzy clustering algorithms and the interregional features of ground object spectral reflectance was applied in this study.Such a process can significantly improve the clustering effect;specifically,the process can reduce the synonym spectrum phenomenon and the misclassification caused by the overlap of spectral features between classes of clustering results.Clustering analysis experiments aimed at land cover classification using remote sensing imagery from the SPOT-5 satellite sensor for the Pearl River Delta region,China,and the TM sensor for Yushu,Qinghai,China,were conducted,as well as experiments involving the conventional FCM algorithm,the results of which were used for comparative analysis.Next,a supervised classification method was used to validate the clustering results.The final results indicate that the proposed interval-valued FCM clustering is more effective than the conventional FCM clustering method for land cover classification using multi-spectral remote sensing imagery.     

地震前后景观格局的变化研究——以四川都江堰地区为例

景观是保护生态环境的关键所在,考虑地震灾害对景观格局的破坏影响,模拟景观格局在地震作用后的变化情况,对于找到景观设计脆弱点意义重大。提出地震前后景观格局的变化研究,以四川都江堰地区为研究对象,基于遥感图像、ArcGIS软件和Fragstats景观计算软件,以景观单元特征指数、景观格局指数作为指标,分析该地区在2007—2008年地震发生前后景观格局的变化,为该地区的震后重建以及未来的景观规划提供参考。     

基于Lasso函数的分层混合模糊-神经网络及其在遥感影像分类中的应用

本文提出一种新的分层混合模糊-神经网络(HHFNN)算法.在模糊系统中使用Takagi-Sugeno模型和三角波隶属函数.同时,为降低离散输入变量中可能存在的强交互作用,采用了系数收缩机制中的Lasso函数.最后,以福建的漳平洛阳—安溪潘田地区LANDSAT ETM+遥感影像数据地物分类为例,应用本文的改进算法与其他神经网络算法进行分析比较,得到了较高的分类精度,验证了采用基于Lasso函数的T-S型分层混合模糊-神经网络的可行性和有效性,可作为一种新的遥感影像地物分类方法.     

基于聚类分析方法的砾岩油藏储层类型划分

砾岩油藏由于近物源、多水系和快速多变的沉积环境导致储层岩性复杂多变以及非均质性严重等特点,储层类型的精细划分成为该类油藏二次调整开发的重点和难点.本文以克拉玛依油田六中区克下组砾岩油藏为研究对象,选取密闭取心井岩心分析的物性参数、压汞驱替参数以及微观孔隙结构参数共计12项作为砾岩油藏储层类型划分的参数组合,对比研究了基于划分、基于层次、基于模型和基于密度的4种聚类算法建立的储层划分标准,结果表明基于划分的k-means算法建立的聚类标准最符合实际油藏的地质特征和储层类型的划分精度,内部度量的紧凑性、有效性和分辨性都优于其他三种算法,并且分析了Ⅴ类储层与岩性的对应关系,发现砾岩油藏储层类型受岩性控制的机制非常复杂,岩性相同的储层类型可能呈现出不同的物性和渗流性,而岩性不同的储层类型又可能表现为相同的物性和渗流性,其根本原因是储层非均质性造成的.储层类型与砾岩岩性的有效结合为该区精细开发方案的设计和水淹层的定量评价提供了技术支持.