基于K2结构学习算法的多光谱影像贝叶斯网络分类器     

陶建斌  舒宁  沈照庆 《地理空间信息》2009,7(2):15-18

用基于启发式搜索的结构学习算法，学习得到多光谱影像的贝叶斯网络结构，分析了TM的波段（特征）间条件独立性假设的合理性，给出了贝叶斯推理中后验概率计算的公式，并通过和最大似然法对比试验分析了简单贝叶斯网络应用于多光谱影像分类的优势。  相似文献   

基于面向对象的重大工程土地利用变化信息提取——以国家体育场(鸟巢)建设工程为例   总被引：2，自引：0，他引：2  

刘浩  胡卓玮  赵文慧 《国土资源遥感》2009,(4):86-89,95

以国家体育场（鸟巢）工程建设为例,研究基于面向对象的重大工程土地利用变化信息提取技术,以及建设工程对周边环境土地利用类型变化的影响。选取鸟巢2001年（动工之前）和2005年（建设中期）两期高分辨率遥感图像,运用多尺度影像分割和面向对象分类方法,进行土地利用信息提取及其变化对比分析。结果表明：利用面向对象方法取得了理想的土地利用分类结果,两期影像的分类精度分别达到93.23%和94.55%,Kappa系数分别为0.9158和0.9332;鸟巢的建设对周边土地利用类型影响较大,尤其是植被、道路和耕地的变化显著,草地和道路明显增加,耕地明显减少。  相似文献   

基于RS和GIS土地利用现状调查     

王丽丽  余代俊  白铁勇 《地理空间信息》2009,7(6):94-97

以甘孜州炉霍县为例,采用2007年LandsatTM影像为数据源,通过对不同分类方法所得的分类结果进行比较,最终选用分区监督分类与目视解译相结合的方法对地物进行解译和分类提取。在GIS技术的支持下,对自动分类结果进行人工修整、完善,并计算、统计各类用地的面积,绘制相应的土地利用现状图。  相似文献   

基于Brovey融合与HSV锐化的ASTER影像绿地信息提取分析   总被引：1，自引：1，他引：0  

秦鹏  陈健飞 《地球信息科学学报》2009,11(3):400-404

为了突出图像的边缘、线状目标或某些亮度变化率大的部分,生成边缘图像,运用Brovey融合和HSV锐化方法,对广州市部分地区的ASTER遥感影像进行处理,然后,对两种方法分别处理后的图像,采用平行六面体法监督分类,提取城市用地信息,并对分类后的图像进行对比试验,着重对城市绿地信息的提取进行分析,探究ASTER遥感数据的两种影像处理方法对城市绿地信息的提取效果,及其空间分布为城市生态评价和景观生态建设提供必要的基础数据。通过对比试验,结果显示:Brovey方法较好地显示城市绿地的分布状况,可作为城市绿地动态监测的判别方法之一;融合后的影像能够清晰地显示研究区城市绿地的分布结构及毗邻关系;通过采用区域放大、勾画不同地类边缘轮廓、配合人工解译等工作,能够增加城市绿地与其他用地类型的差异,突显城市绿地的分布、结构、生态学特征。  相似文献   

多时相影像的典型区农作物识别分类方法对比研究   总被引：8，自引：0，他引：8  

彭光雄  宫阿都  崔伟宏  明涛  陈锋锐 《地球信息科学学报》2009,11(2):225-230

基于甘蔗和玉米的物候特征差异,对多时相影像典型分类方法处理的适宜性和准确性进行了比较研究。并以目视解译结果作为参考数据,利用全样本检验法,对自动分类的结果进行了精度检验。试验结果表明:面向对象法的分类精度最高,总体Kappa系数为0.655,是最适宜的方法;其次是BP神经网络法和光谱角制图法,总体Kappa系数分别为0.635和0.631;而最大似然法和分类后比较法则是不适宜采纳的分类方法,总体Kappa系数分别为0.601和0.577。上述分析可见,它们对遥感分类处理多时相影像识别算法的适用性选取有一定参考意义。  相似文献   

Classification of Grove Mountains meteorites and its significance     

缪秉魁  王道德 《极地研究(英文版)》2009,20(2):97-109

Meteorites are the extraterrestrial rocks, which provide insights into the origin and evolution of the solar system. During the past half century, a great number of meteorites has been discovered on the Antarctic Ice Sheet, confirming that the Antarctica is the most important meteorite concentration area on the earth. Since the first four Antarctic meteorites were found in Grove Mountains in 1998, a total of 9834 meteorites have been collected by four subsequent expeditions. It opens a new field of meteorite study in China, and also accumulates a great deal of scientific samples for China. Recently, classification of Grove Mountains meteorites has been carried out for 6 years, and made following progresses: (1) 2433 meteorites, which include many special meteorites, e.g. Martian meteorites, ureilites and carbonaceous chondrites, have been classified. (2) the Antarctic meteorite curation and the sample sharing system are set up preliminarily. (3) the classification procedure, the management of meteorite samples, and the application procedure for the Antarctic meteorites are completed after the systematic classification during these years. (4) young generation researchers on meteorite are trained through the cooperation of many universities and institutes on meteorite classification.  相似文献   

Performance assessment of a GCM land surface scheme using a fine‐scale calibrated hydrological model: an evaluation of MOSES for the Nile Basin     

Mohamed Ezzat Elshamy  Howard S. Wheater 《水文研究》2009,23(11):1548-1564

Land surface schemes (LSSs) represent the interface between land surface and the atmosphere in general circulation models (GCMs). Errors in LSS‐simulated heat and moisture fluxes can result from inadequate representation of hydrological features and the derivation of effective surface parameters for large heterogeneous GCM gridboxes from small‐scale observations. Previous assessments of LSS performance have generally compared simulated heat and moisture fluxes to observations over a defined experimental domain for a limited period. A different approach has been evaluated in this study, which uses a fine‐resolution calibrated hydrological model of the study basin to provide a quasi‐observed runoff series for direct comparison with simulated runoff from a selected LSS at GCM scale. The approach is tested on two GCM gridboxes covering two contrasting regions within the Nile Basin. Performance is mixed; output from the LSS is generally compatible with that of the fine‐resolution model for one gridbox while it cannot reproduce the runoff dynamics for the other. The results also demonstrate the high sensitivity of runoff and evapotranspiration to radiation and precipitation inputs and show the importance of subtle issues such as temporal disaggregation of climatic inputs. We conclude that the use of a fine‐resolution calibrated model to evaluate a LSS has several advantages, can be generalized to other areas to improve the performance of global models and provides useful data that can be used to constrain LSS parameterizations. Copyright © 2009 John Wiley & Sons, Ltd.  相似文献   

遥感和GIS技术应用于伊拉克南部Basrah省土地利用/覆盖变化及城市扩张研究(英文)   总被引：2，自引：0，他引：2  

Hadeel A.S.  Mushtak T.Jabbar  陈晓玲 《地球空间信息科学学报》2009,12(2):135-141

In recent years, land use/cover dynamic change has become a key subject that needs to be dealt with in the study of global environmental change. In this paper, remote sensing and geographic information systems (GIS) are integrated to monitor, map, and quantify the land use/cover change in the southern part of Iraq (Basrah Province was taken as a case) by using a 1:250 000 mapping scale. Remote sensing and GIS software were used to classify Landsat TM in 1990 and Landsat ETM+ in 2003 imagery into five land use and land cover (LULC) classes: vegetation, sand, urban area, unused land, and water bodies. Supervised classification and normalized difference build-up index (NDBI) were used respectively to retrieve its urban boundary. An accuracy assessment was performed on the 2003 LULC map to determine the reliability of the map. Finally, GIS software was used to quantify and illustrate the various LULC conversions that took place over the 13-year span of time. Results showed that the urban area had increased by the rate of 1.2% per year, with area expansion from 3 299.1 km² in 1990 to 3 794.9 km² in 2003. Large vegetation area in the north and southeast were converted into urban construction land. The land use/cover changes of Basrah Province were mainly caused by rapid development of the urban economy and population immigration from the countryside. In addition, the former government policy of “returning farmland to transportation and huge expansion in military camps” was the major driving force for vegetation land change. The paper concludes that remote sensing and GIS can be used to create LULC maps. It also notes that the maps generated can be used to delineate the changes that take place over time. Supported by the Al-Basrah University, Iraq, the Geo-information Science and Technology Program (No. IRT 0438)China).  相似文献   

川西高原土地利用／土地覆盖分类方法   总被引：1，自引：0，他引：1  

潘倩  杨武年  邵怀勇 《地理空间信息》2009,7(4):82-84

针对川西高原地形地貌以及遥感图像特征等特点，以康定县为例，从影像的预处理到多光谱分类这一过程进行方法研究，引入DEM等辅助信息进行多分类器结合方法处理，分类效果有一定程度的提高，最后讨论了数据分类后处理的方法。  相似文献   

A Linking Test that investigates the feasibility of inverse modelling: application to a simple rainfall interception model for Mt Gambier,southeast South Australia     

J. A. P. Pollacco  R. Angulo‐Jaramilo 《水文研究》2009,23(14):2023-2032

Interception loss has an important influence on the water yield of forested areas. Nevertheless, in most studies stemflow is not measured, therefore the question of how to determine the feasibility of optimizing interception and stemflow parameters simultaneously by matching daily simulated throughfall to fortnightly measurements of cumulative throughfall is an important one. By applying a daily empirical interception model, a goodness fit of 2·2 mm/day is obtained between observed and simulated cumulative throughfall. However, by applying the simple but robust Linking Test, it was shown that the parameters are non‐unique and falsely linked, i.e. inter‐relationships between different vegetation parameter sets give similar throughfall but non‐unique net precipitation. The Linking Test investigates the causes of obtaining falsely linked parameters and shows that objective equifinality is not the source of the problem. Objective equifinality occurs when an inappropriate objective function is used. The Linking Test also shows that falsely linked parameters are not caused by measuring throughfall on a non‐daily basis (termed frequency sampling equifinality). By expanding the interception model to the second degree, it was found that the non‐uniqueness is due to the inherent nature of interception and stemflow functions that behave similarly and therefore can easily compensate each other (termed similarity equifinality). It is also shown that a simple daily empirical exponential interception model developed for conifers in the uplands of the United Kingdom is suitable to model interception in Pinus radiata plantations in the Mediterranean climate of southern Australia by using only daily gross precipitation data and two parameters. Copyright © 2009 John Wiley & Sons, Ltd.  相似文献