共查询到19条相似文献,搜索用时 140 毫秒
1.
基于面向对象的无监督分类的遥感影像自动分类方法 总被引:3,自引:0,他引:3
为了实现无任何先验知识的高分辨率遥感数据的自动分类,并进一步提高自动分类精度和效率,提出了一种基于面向对象的无监督分类方法(Object Oriented Unsupervised Classification).具体步骤如下:首先对遥感影像进行分割,得到一系列空间上相邻、同质性较好的分割单元,然后对分割单元进行特征提取,得到分割单元的对象特征(光谱特征、纹理特征等多特征信息),进而对分割单元进行基于对象特征马氏距离聚类.最后,通过分类后处理(类别合并、错分类别调整等)得到最终的分类结果.通过实验表明:本文提出的方法不仅能够利用影像中更多的特征信息进行聚类而且还可以有效地减少聚类对象的个数,从而使自动分类的精度和效率都得到较大的提升. 相似文献
2.
3.
测井储层分类方法多样,每种方法的原理、计算步骤及所需资料各不相同,且各方法的适用性及应用效果均存在很大差异,本文通过文献调研,将测井储层分类方法归纳为四大类:(1)基于交会图版法的半定量储层分类方法,此方法操作简单、应用范围广但适用性不强;(2)基于流动单元概念的测井储层分类方法,此方法基于岩心物性数据可以迅速达到储层分类的目的 ,具有明确的地质意义,但结果依赖于取心数据;(3)基于多元统计法及机器学习算法的测井储层分类方法,此类方法可以有效地避免人为因素的干扰,速度快、方法多样,可以实现储层的定量分类评价,是未来发展的趋势,但分类结果意义不明确;(4)基于测井新技术新方法的储层分类方法,该方法携带了大量的地质信息,与其他分类方法结合可以更有效、更准确地评价储层.最后比较了四种分类方法的优缺点并给出了相应的选择建议,该研究对测井储层分类方法的优选具有一定的参考意义. 相似文献
4.
当强震台站场地资料不完整时,所收集到的强震数据因缺乏准确的场地类别信息而难以有效利用。为解决这一问题,本文提出一种基于离散Fréchet距离的强震台站场地分类方法。将获取到的664个KiK-net台站场地按照《建筑抗震设计规范(GB 50011—2010)》进行分类,并构建2个数据集。利用数据集1得到Ⅰ、Ⅱ、Ⅲ类场地标准谱比曲线,并结合离散Fréchet距离对数据集2中的台站进行场地分类,统计分类成功率与误判率。统计结果表明,本文方法能较准确地对场地进行分类,且误判率在可接受范围内。将本文方法分类统计结果与斯皮尔曼秩相关系数法分类的成功率与误判率进行对比,结合本文方法分类后得到的平均谱比曲线,均可表明应用本文方法进行强震台站场地分类具有合理性。 相似文献
5.
6.
孔隙结构评价和储层类型划分对致密储层的勘探和开发具有重要意义.本文利用核磁共振测井对沙溪庙组致密气储层孔隙结构进行评价和分类.首先根据核磁共振T2分布形态利用模糊聚类的方法将致密砂岩储层孔隙结构分为Ⅰ、Ⅱ和Ⅲ类,随后结合压汞实验数据,利用变刻度幂函数法建立不同类型孔隙结构岩石T2分布转化毛管压力曲线的模型.根据建立的模型,我们将研究区实际核磁共振测井T2分布转化为毛管压力曲线,并计算储层孔隙结构参数,实现研究区致密气储层分类,通过岩心压汞实验数据和试油数据验证了储层分类结果的准确性.该方法可以扩展应用于其他地区致密储层的孔隙结构评价和分类. 相似文献
7.
8.
针对B区块S油层含泥含钙中低孔特低渗储层渗透率计算精度低的难题,分析岩性、物性、孔隙结构对储层渗透率的影响,明确了孔隙度、泥质含量、钙质含量、孔隙结构是影响B区块S油层特低渗储层渗透率的主要因素,其中,孔隙结构是影响特低渗储层渗透率的关键因素.综合运用压汞曲线、孔喉半径分布特征以及流动单元指数反映特低渗储层孔隙结构变化,将特低渗储层按不同孔隙结构划分成3种类型,建立了特低渗储层类型的判别标准.利用中子测井、密度测井、声波测井、微球形聚焦测井、深浅侧向电阻率测井差值的绝对值等5个储层类型识别的敏感测井响应及参数,使用决策树法、最邻近结点法、BP神经网络法和支持向量机法建立了4种基于机器学习的储层判别方法,储层类型判别准确率依次提高,其中,基于支持向量机的储层类型判别方法判别准确率最高92.2%,且对3种类储层判别效果均很好.针对3类储层分别建立了渗透率计算公式.实际井解释结果表明,基于机器学习储层分类的渗透率模型计算B区块S油层特低渗储层渗透率精度明显高于储层分类前渗透率计算精度,其中,基于支持向量机储层分类计算的渗透率精度最高. 相似文献
9.
10.
11.
12.
Statistical facies classification from multiple seismic attributes: comparison between Bayesian classification and expectation–maximization method and application in petrophysical inversion 下载免费PDF全文
We present here a comparison between two statistical methods for facies classifications: Bayesian classification and expectation–maximization method. The classification can be performed using multiple seismic attributes and can be extended from well logs to three‐dimensional volumes. In this work, we propose, for both methods, a sensitivity study to investigate the impact of the choice of seismic attributes used to condition the classification. In the second part, we integrate the facies classification in a Bayesian inversion setting for the estimation of continuous rock properties, such as porosity and lithological fractions, from the same set of seismic attributes. The advantage of the expectation–maximization method is that this algorithm does not require a training dataset, which is instead required in a traditional Bayesian classifier and still provides similar results. We show the application, comparison, and analysis of these methods in a real case study in the North Sea, where eight sedimentological facies have been defined. The facies classification is computed at the well location and compared with the sedimentological profile and then extended to the 3D reservoir model using up to 14 seismic attributes. 相似文献
13.
储层岩相分布信息是油藏表征的重要参数,基于地震资料开展储层岩相识别通常具有较强的不确定性.传统方法仅获取唯一确定的岩相分布信息,无法解析反演结果的不确定性,增加了油藏评价的风险.本文引入基于概率统计的多步骤反演方法开展地震岩相识别,通过在其各个环节建立输入与输出参量的统计关系,然后融合各环节概率统计信息构建地震数据与储层岩相的条件概率关系以反演岩相分布概率信息.与传统方法相比,文中方法通过概率统计关系表征了地震岩相识别各个环节中地球物理响应关系的不确定性,并通过融合各环节概率信息实现了不确定性传递的数值模拟,最终反演的岩相概率信息能够客观准确地反映地震岩相识别结果的不确定性,为油藏评价及储层建模提供了重要参考信息.模型数据和实际资料应用验证了方法的有效性. 相似文献
14.
《地震研究进展(英文)》2021,1(4):100069
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. 相似文献
15.
基于空间-光谱特征和稀疏表达的高光谱图像分类算法(英文) 总被引:1,自引:0,他引:1
针对传统的高光谱数据分类方法分类精度不高、没有充分地利用空间信息等缺陷,提出一种基于Gabor空间纹理特征(Gabor spatial texture features)及无参数加权光谱特征(Nonparametric weighted spectral features)和稀疏表达分类(Sparse representation classification)的高光谱图像分类算法,可以简写为Gabor-NW SF和SRC,即GNWSF-SRC。所提出的GNWSF-SRC分类方法首先通过融合高光谱的Gabor空间特征和无参数加权光谱特征来更好地描述高光谱图像,然后通过其进行稀疏表达,最终通过对比其重构误差获得分类结果。在训练集比例不同的情况下,用所提出的方法对两组典型的高光谱数据进行处理,理论研究和仿真结果表明:与传统的分类方法相比,所提出算法能够提高分类精度、Kappa系数等,取得了较好的分类效果。 相似文献
16.
Self-organizing feature map neural network classification of the ASTER data based on wavelet fusion 总被引:3,自引:0,他引:3
HASI Bagan MA Jianwen LI Qiqing HAN Xiuzhen & LIU Zhili Laboratory of Remote Sensing Information Science Institute of Remote Sensing Applications Chinese Academy of Sciences Beijing China 《中国科学D辑(英文版)》2004,47(7):651-658
Remote sensing classification methods can be classified as supervised and unsupervised catalogs. The maximum likelihood method (MLH) is a super-vised classification method,which is widely used in the remote sensing data classification and produces good results[1]. In the MLH, the parameters are esti-mated, assuming that the samples are normally dis-tributed in spectral space, to determine the mean vec-tor and covariance matrix of all classes. In most cases, however, the samples are not norma… 相似文献
17.
Cladistics is a systematic method of classification that groups entities on the basis of sharing similar characteristics in
the most parsimonious manner. Here cladistics is applied to the classification of volcanoes using a dataset of 59 Quaternary
volcanoes and 129 volcanic edifices of the Tohoku region, Northeast Japan. Volcano and edifice characteristics recorded in
the database include attributes of volcano size, chemical composition, dominant eruptive products, volcano morphology, dominant
landforms, volcano age and eruptive history. Without characteristics related to time the volcanic edifices divide into two
groups, with characters related to volcano size, dominant composition and edifice morphology being the most diagnostic. Analysis
including time based characteristics yields four groups with a good correlation between these groups and the two groups from
the analysis without time for 108 out of 129 volcanic edifices. Thus when characters are slightly changed the volcanoes still
form similar groupings. Analysis of the volcanoes both with and without time yields three groups based on compositional, eruptive
products and morphological characters. Spatial clusters of volcanic centres have been recognised in the Tohoku region by Tamura
et al. (Earth Planet Sci Lett 197:105–106, 2002). The groups identified by cladistic analysis are distributed unevenly between the clusters, indicating
a tendency for individual clusters to form similar kinds of volcanoes with distinctive but coherent styles of volcanism. Uneven
distribution of volcano types between clusters can be explained by variations in dominant magma compositions through time,
which are reflected in eruption products and volcanic landforms. Cladistic analysis can be a useful tool for elucidating dynamic
igneous processes that could be applied to other regions and globally. Our exploratory study indicates that cladistics has
promise as a method for classifying volcanoes and potentially elucidating dynamic and evolutionary volcanic processes. Cladistics
may also have utility in hazards assessment where spatial distributions and robust definitions of a volcano are important,
as in locating sensitive facilities such as nuclear reactors and repositories. 相似文献
18.
19.
Land cover classification of remote sensing imagery based on interval-valued data fuzzy c-means algorithm 总被引:1,自引:0,他引:1
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. 相似文献