顾及形态特征和语义信息的双线道路识别方法     

张浩  武芳  张俊涛  李靖涵 《测绘科学技术学报》2016,(3)

双线道路识别与提取是城市路网综合的关键。提出了一种城市双线道路提取的方法。在构建好的道路网眼的基础上,综合考虑双线道路网眼形态特征以及构成网眼路段之间的语义相似度,设计了识别双线道路网眼的综合指标。通过判断网眼综合指标确定最终的双线道路网眼,最后根据识别出的双线道路网眼提取出双线道路。实验表明,该方法能有效提取出城市道路数据中的双线道路。  相似文献   

用雷达回波资料识别雹云的最新进展     

李祚泳  刘少侬  邓新民  张辉军 《成都信息工程学院学报》1993,(1)

本文评述了当前国内外利用雷达回波资料识别雹云的现状,着重介绍了笔者近年来利用雷达回波资料建立雹云识别模式的研究工作,并展望了雹云识别的未来发展前景。  相似文献   

冰雹云雷达回波自动识别系统   总被引：2，自引：0，他引：2  

段勇  贺敬安  谈曙青 《成都信息工程学院学报》2001,16(2):110-116

利用CAPPI资料对立体风暴进行识别，计算并提供出实用的风暴结构参数，采用矩心踊跃法和矩不变量法相结合对单体风暴和混合性风暴回波进行跟踪；最小二第线性外推预报；根据WSD－88D的冰雹算法，在风暴结构基础上本文建立了Windows98操作平台上冰雹识别系统，经单站1年11次强对流天气过程的资料检验，结果表明：雹云识别精度达82％。系统建立了大量人机对话框以方便用户，增加实用性及推广性。  相似文献   

Spatial pattern recognition by decomposition     

Yuwei Li 《Mathematical Geology》1984,16(3):217-236

The decomposition problem—the assignment of sample observations to component populations—is studied in a spatial context. The observations are spatially located and the assignment to component populations takes into account the value of each observation as well as the values of neighboring observations. Both parameter estimation and assignment rules use a new method that integrates a standard multivariate decomposition algorithm with nonlinear regression. The method is illustrated and tested with artificial data. The distribution of the trace component Cr₂O₃ in recent Lake Michigan sediments is, then, analyzed by the method. It yields a pattern of component populations that is correlated with the Lake's bottom structure and depositional environments. Study carried out as visiting scholar at the Department of Geological Sciences, Northwestern University, Evanston, Illinois U.S.A.  相似文献   

APPLICATION OF PATTERN RECOGNITION TO SPECIATION DATA OF HEAVY METALS IN SUSPENDED PARTICULATES OF URBAN AIR     

X.TOMAS  J.RIUS  J.OBIOLS  A.SOL 《地理学报(英文版)》1988,(Z1)

In order to get a better knowledge of the air pollution levels of the urban air of Barcelona,twelvesamples from three stations of the air-monitoring control network were analysed.Each control station isrepresentative of a different environmental situation.Thus the station at Plaa Molina responds to asimple domestic and urban traffic situation;the station at Poble Nou to the influence of medium andsmall industries,mainly metallurgical;and the station at Montcada to a zone in which there existimportant industries,a cement factory,two highways and railroads.The total content of unsedimentable particles,three inorganic anions(chlorides,sulphates andnitrates)and six heavy metals(Fe,Pb,Cu,Mn,Cr and Cd)were determined on all the samples obtainedduring the same period of time.The use of an analytical scheme of sequential extraction has alsopermitted the subdivision of the total content of each metal into the following four fractions:(1)solubleor exchangeable;(2)associated with carbonates and/or with iron and manganese oxides;(3)bound toorganic matter;and(4)residual.The use of principal component analysis applied to the data as a whole showed the associations andcorrelations between the various parameters as well as between the different above mentioned fractions.The predominant presence of Cd in the‘soluble or exchangeable’fraction is confirmed,while the othermetals are mainly associated with the‘carbonates and/or Fe and Mn oxides’and‘bound to organicmatter’fractions.Hierarchical cluster analysis applied to the twelve samples showed clearly the presence of threedifferent classes closely related to the origin(station)of the samples.Thus it becomes feasible to proposefor each station a possible profile of the content in terms of the different parameters considered.  相似文献   

遥感图象的马尔柯夫随机场模型的纹理识别方法     

吴士达  游思琼  杨立新  关忠仁 《成都信息工程学院学报》1992,(3)

本文讨论了马尔柯夫随机场图象模型及邻域选择方法,提出了8邻域5特征参数的马尔柯夫随机场图象模型以及一套完整而有效的特征参数的估计算法,将这些特征参数变成可视图象从而实现了视算。对8类不同纹理的标准图象进行分类试验,其识别(分类)的平均正确率达97.57％。  相似文献   

AN AUTOMATIC PROCEDURE FOR ESTIMATING SPRING SMALL GRAINS ACREAGE FROM LANDSAT DATA     

Robert R. J. Mohler  Wesley F. Palmer  Thomas C. Baker  Robert M. Bizzell 《The Professional geographer》1986,38(4):375-382

The development and testing of a computerized technique for utilizing multitemporal Landsat multispectral scanner data to estimate spring small grains acreage are described. The Kauth-Thomas green number transformation is applied to the data prior to application of the pixel-level standardized logic. Four years of data from the U.S. and Canada are used in testing. A comparison of the test results to those of the analyst-intensive procedures indicates a potential for increase in near-harvest estimation efficiency with little sacrifice in accuracy.  相似文献   

Automated Kerogen Classification in Microscope Images of Dispersed Kerogen Preparation     

L. I. Kuncheva  J. J. Charles  N. Miles  A. Collins  B. Wells  I. S. Lim 《Mathematical Geosciences》2008,40(6):639-652

We develop the classification part of a system that analyses transmitted light microscope images of dispersed kerogen preparation. The system automatically extracts kerogen pieces from the image and labels each piece as either inertinite or vitrinite. The image pre-processing analysis consists of background removal, identification of kerogen material, object segmentation, object extraction (individual images of pieces of kerogen) and feature calculation for each object. An expert palynologist was asked to label the objects into categories inertinite and vitrinite, which provided the ground truth for the classification experiment. Ten state-of-the-art classifiers and classifier ensembles were compared: Naïve Bayes, decision tree, nearest neighbour, the logistic classifier, multilayered perceptron (MLP), support vector machines (SVM), AdaBoost, Bagging, LogitBoost and Random Forest. The logistic classifier was singled out as the most accurate classifier, with an accuracy greater than 90. Using a 10 times 10-fold cross-validation provided within the Weka software, we found that the logistic classifier was significantly better than five classifiers (p<0.05) and indistinguishable from the other four classifiers. The initial set of 32 features was subsequently reduced to 6 features without compromising the classification accuracy. A further evaluation of the system alerted us to the possible sensitivity of the classification to the ground truth that might vary from one human expert to another. The analysis also revealed that the logistic classifier made most of the correct classifications with a high certainty.  相似文献   

颜色和形态学在交通标志识别中的应用研究     

姜雪宁  万幼川  何培培 《测绘与空间地理信息》2014,(12)

从自然场景中识别出交通标志是智能交通系统中的一个重要问题,本文提出了一种基于颜色和形态学的交通标志识别方法.该方法在HSV彩色空间进行颜色阈值分割,并采用形态学重构提取目标区域.再通过标记法检测目标区域形状,检测出交通标志.最后,利用SIFT算法进行模板匹配,识别出交通标志.实验证明,该方法在识别正确率和运行效率上具有明显优势.  相似文献   

地名识别与匹配的概率统计方法     

肖计划 《测绘科学技术学报》2014,(4)

建立了一个试验用地名库和地理语料库,在此基础上构建对地名用字可信度的统计分析模型。通过分析地名在中文文档中的使用习惯和规律,总结出经常与地名一起使用的且具有地名指示含义的辅助字或词,以此为基础建立地名识别辅助词词库和地名识别的规则库。对地名库和地理语料库的用字进行统计分析,通过设定地名用字可信度概率阈值和辅助词指示作用对文本中潜在地名进行初步的筛选形成候选地名;在粗筛选产生的候选地名基础上结合地名识别规则进一步确认,以提高地名识别的准确率。  相似文献