检索结果-南通市图书馆

Semi-Supervised Classification based on Gaussian Mixture Model for remote imagery

在线全文

学校读者我要写书评

暂无评论

Science china(Technological Sciences) 2010年第S1期53卷 85-90页

作者： XIONG Biao1,ZHANG XiaoJun1 & JIANG WanShou1,2 1 State Key Laboratory of Information Engineering in Surveying,Mapping and remote sensing,Wuhan University,Wuhan 43.079,china 2 State Key Laboratory of remote sensing Science,beijing,china State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China State Key Laboratory of remote sensing Science Beijing China

Semi-Supervised Classification (SSC),which makes use of both labeled and unlabeled data to determine classification borders in feature space,has great advantages in extracting classification information from mass *** this paper,a novel SSC method based on Gaussian Mixture Model (GMM) is proposed,in which each class’s feature space is described by one *** show the proposed method can achieve high classification accuracy with small amount of labeled ***,for the same accuracy,supervised classification methods such as Support Vector Machine,Object Oriented Classification,*** be provided with much more labeled data.

关键词： remote sensing image classification Semi-Supervised Classification Gaussian Mixture Model EM algorithms

The definition of effective emissivity of land surface at the scale of remote sensing pixels

在线全文

学校读者我要写书评

暂无评论

Chinese Science Bulletin 1999年第23期44卷 2154-2158页

作者： LI Xiaowen and WANG Jindi Research Center for remote sensing and GIS, beijing Normal Unirersity, Keying 100875,{3. Center for remote sensing, Boston Univ. , MA02215, USA Research Center for remote sensing and CIS Beijing Normal University Beijing China Center for remote sensing Boston Univ. USA

remote sensing (RS) of land surface temperature (LST) is a very challenging problem at the present development stage of RS science. Tremendous efforts have been devoted to atmosphere correction and temperature emissivity separation (TES) of new LST product algorithms. However, the mechanism of directionality of thermal emission from land surface remains unknown, and even worse, there are confusions on the definition of the effective emissivity of land surface at the scale of RS pixels. The mechanism of directionality of thermal emission

关键词： non-isothermal pixel effective emissivity. directionality of thermal emission.

Principle and application of three-band gradient difference vegetation index

在线全文

学校读者我要写书评

暂无评论

Science china Earth Sciences 2005年第2期48卷 241-249页

作者： TANG Shihao, ZHU Qijiang, WANG Jindi, ZHOU Yuyu & ZHAO Feng Research Center for remote sensing and GIS, Department of Geography, beijing Normal University, beijing 100875, china National Satellite Meteorological Center, china Meteorological Administration, beijing 100081, china Research Center for remote sensing and GIS Department of Geography Beijing Normal University Beijing China National Satellite Meteorological Center China Meteorological Administration Beijing China

Vegetation index is a simple, effective and experiential measurement of terrestrial vegetation activity, and plays a very important role in qualitative and quantitative remote sensing. Aiming at shortages of current vegetation indices, and starting from the analysis of vegetation spectral characteristics, we put forward a new vegetation index, the three-band gradient difference vegetation index (TGDVI), and established algorithms to inverse crown cover fraction and leaf area index (LAI) from it. Theoretical analysis and model simulation show that TGDVI has high saturation point and the ability to remove the influence of background to some degree, and the explicit functional relation with crown cover fraction and LAI can be established. Moreover, study shows that TGDVI also has the ability to partly remove the influence of thin cloud. Experiment in the Shunyi District, beijing,{3. shows that reasonable result can be reached using the vegetation index to retrieve LAI. We also theoretically analyzed the reason why the normalized difference vegetation index (NDVI) owns the low saturation point, and show that it is determined by the definition of NDVI and the characteristic of vegetation spectra, and is unavoidable to some degree. Meanwhile, through model simulation, we also indicate that the relationship between simple ratio vegetation index (SR) and LAI closes to a piecewise linear one instead of a linear one, which is mainly caused by the influence of background and different change rates of reflectance in red and infrared bands with LAI increasing.

关键词： vegetation index, remote sensing, LAI, crown cover fraction, remote sensing inversion.

Monitoring Dynamic Change of Land Cover Based on SVM and Satellite Images in Hanoi,Vietnam

在线全文

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2010年第4期15卷 355-362页

作者： ZHAO Jinling1,2, LIU Chuang1, 3.1. Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, beijing 100101, china 2. Graduate University of Chinese Academy of Sciences, beijing 100049, china 3. College of Resources Science and Technology, beijing Normal University, beijing 100875, china Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China Graduate University of Chinese Academy of Sciences Beijing China College of Resources Science and Technology Beijing Normal University Beijing China

An integral method,combining support vector ma-chine (SVM) with remote-sensing analysis techniques,was ex-plored to monitor Hanoi’s dynamic change of land cover. The landsat thematic mapper (TM) image in 1993.the enhanced the-matic mapper plus (ETM+) image in 2000,and the image with the charge-coupled device camera (CCD) on the china-Brazil earth resources satellite (CBERS) in 2008 were used. Six land-cover types,including built-up areas,woodland,cropland,sand,water body and unused land,were identified. The detected results showed visually the rapid urban expansion as well as land-cover change of Hanoi from 1993.to 2008. There were 12 63..54 hm2 cropland de-creased between 1993.and 2000,and 8 227.6 hm2 cropland de-creased between 2000 and 2008. Compared with cropland,wood-land firstly decreased and then increased,and the other types did not change significantly. The results indicate that CBERS dataset has the application potential in world resources researches.

关键词： land cover the china-Brazil earth resources satellite (CBERS) support vector machine (SVM) change detection

A novel method of systematic error compensation for a position and orientation system

在线全文

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2008年第8期18卷 953-963页

作者： Xiuxiao Yuan* School of remote sensing and Information Engineering, Wuhan University, Wuhan 43.079, china School of remote sensing and Information Engineering Wuhan University Wuhan 430079 China

A novel method is introduced for self-calibration and elimination of systematic errors for a position and orientation system (POS). The method uses a combined bundle block adjustment with POS data (named the POS-supported bundle block adjustment) without a calibration field. On the basis of delivering strict observation equations for POS data, the specific scheme of compensating the translation and drift systematic errors in a POS is given, and a prototype system WuCAPS is developed. The effects of eliminating POS systematic errors using the POS-supported bundle block adjustment for different ground control conditions are tested using two sets of actual aerial photos. The first set was taken over a flat region in the suburbs of the city of Yingkou in china and tested at a scale of 1:2500. The second set was taken over a high mountainous region in the desert region of Xinjiang in china and tested at a scale of 1:3.,000. The empirical results verified that the POS systematic errors can be completely eliminated and the photo elements of exterior orientation obtained by the POS-supported bundle block adjustment can satisfy the requirements of aerial photogrammetric topographic mapping when four full ground control points (GCPs) are emplaced in the corners of the adjustment block for large-scale images of flat regions, but only one full GCP emplaced in the center of the adjustment block is needed for medium-small scale images of mountainous regions. This not only demonstrates the validity of the established mathematical model and the feasibility of the method proposed in this paper, but also avoids the use of a special calibration field. Therefore, it can simplify the existing POS operation rules and dramatically save on practical application costs, laying the theoretical foundation for widespread use of POS.

关键词： Position and orientation system (POS) Systematic error POS-supported bundle block adjustment Self-calibration Accuracy

Iterative implementation of the adaptive regularization yields optimality

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science china Mathematics 2005年第4期48卷 485-492页

作者： MA Qinghua & WANG Yanfei Department of Information Sciences, College of Arts and Science of beijing Union University, beijing 10003., china National Key Laboratory on {3. sensing Science, Institute of {3. sensing Applications, Chinese Academy of Sciences, beijing 100101, china Department of Mathematics, University of Central Florida, P. O. Box 1613.4, Orlando, FL 3.816-13.4, USA Department of Information Sciences College of Arts and Science of Beijing Union University Beijing China National Key Laboratory on remote sensing Science Institute of Remote Sensing Applications Chinese Academy of Sciences Beijing China

The adaptive regularization method is first proposed by Ryzhikov et al. for the deconvolution in elimination of multiples. This method is stronger than the Tikhonov regularization in the sense that itis adaptive, i.e. it eliminates the small eigenvalues of theadjoint operator when it is nearly singular. We will show in this paper that the adaptive regularization can be implemented iterately. Some properties of the proposed non-stationary iterated adaptive regularization method are analyzed. The rate of convergence for inexact data is proved. Therefore the iterative implementation of the adaptive regularization can yield optimality.

关键词： ill-posed problems, non-stationary iterated adaptive regularization, optimality.

A common sense geographic knowledge base for GIR

在线全文

学校读者我要写书评

暂无评论

Science china(Technological Sciences) 2008年第S1期51卷 26-37页

作者： ZHANG Yi,GAO Yong,XUE LuLu,SHEN Si & CHEN KaiChen Institute of remote sensing and Geographic Information System,Peking University,beijing 100871,{3. Institute of remote sensing and Geographic Information System Peking University

As background knowledge of geographic information retrieval (GIR),the gazetteers have their limitations. In this paper we propose to develop and implement a com-mon sense geographic knowledge base (CSGKB) instead of the gazetteers. We define that CSGKB is concerned with the representation of geographic knowledge in human brain and the simulation of geographic reasoning in daily life. Traditional geographic information system (GIS) is based on the model of map with its data based on geographic coordinates and its computation based on geometry. However,CSGKB,which is made up of geographic features and relationships and is based on qualitative spatio-temporal reasoning,can be viewed as the direct model of geographic world. This paper also discusses the characters of CSGKB and pre-sents its structure which is composed of knowledge base,inference engine,geo-graphic ontology and learner. The applications using CSGKB include geographic information retrieval (GIR),natural language processing (NLP),named entity rec-ognition (NER),Semantic Web,etc. At present,our work focuses on the design of geographic ontology and the implementation of the CSGKB knowledge base. In this paper we describe the CSGKB ontology structure,top ontology,geographic loca-tion ontology,spatial relationship ontology,and domain ontologies. Finally,we in-troduce the current state of implementation of CSGKB and give an outlook on our future researches.

关键词： geographic information retrieval common sense geographic knowledge base geographic ontology

Architecture and key technologies of grid geographic information system

在线全文

学校读者我要写书评

暂无评论

Science china(Technological Sciences) 2008年第S1期51卷 102-113页

作者： FANG Yu,HUANG Zhou,CHEN Bin,WU Lun & YIN DaFei Institute of remote sensing and Geographic Information System,Peking University,beijing 100871,{3. Institute of remote sensing and Geographic Information System Peking University

The highly efficient and stable collaborative computation platform for geospatial information can be constructed on the basis of Grid computing technology,com-bined with Peer-to-Peer (P2P) computing technology and geospatial database technology. This paper proposed the architecture and key technologies of the Grid GIS (Geographic Information System) incorporated with P2P structure,and corre-spondingly a Grid GIS prototype named Nebula was designed and then imple-mented. Nebula is a suite of middleware for geospatial Grid computing,which could be deployed onto various service nodes in network. Based on Grid protocols and infrastructure,Nebula provides invocation interfaces to users in form of Grid services. By using P2P message based communication mechanism,complex geospatial computation tasks could be accomplished by Nebula in a collaborative way. This paper introduced Nebula's architecture and key modules,and according to experimental data,we discussed the Grid GIS's advantages,application scenar-ios and future directions.

关键词： Grid GIS distributed geospatial computing Peer-to-Peer computing

Knowledge-Based Classification in Automated Soil Mapping

在线全文

学校读者我要写书评

暂无评论

Pedosphere 2003年第3期13卷 209-218页

作者： ZHOU BIN and WANG RENCHAOInstitute of Agricultural remote sensing and Information Technology Application, Zhejiang University, Hangzhou 3.0029 (china) Institute of Agricultural remote sensing and Information Technology Application Zhejiang University Hangzhou 310029

A machine-learning approach was developed for automated building of knowledgebases for soil resources mapping by using a classification tree to generate knowledge from trainingdata. With this method, building a knowledge base for automated soil mapping was easier than usingthe conventional knowledge acquisition approach. The knowledge base built by classification tree wasused by the knowledge classifier to perform the soil type classification of Longyou County,Zhejiang Province, china using Landsat TM bi-temporal images and CIS data. To evaluate theperformance of the resultant knowledge bases, the classification results were compared to existingsoil map based on a field survey. The accuracy assessment and analysis of the resultant soil mapssuggested that the knowledge bases built by the machine-learning method was of good quality formapping distribution model of soil classes over the study area.

关键词： classification classification tree knowledge-based rule extracting soilmapping