提出了一种基于多特征的遥感分类方法。
In this paper, a new method, namely the multi feature based method, was presented to classify remotely sensed imagery.
遥感分类图像是研究土地利用变化的基础。
The method used are remote image classification and model researches.
蚊媒孳生环境遥感分类和遥感信息提取研究。
RS image classification and information derivation of mosquito habitats.
对红树林群落进行遥感分类在实际应用中具有较大的意义。
Remote sensing can be used to obtain the information about mangrove wetlands, such as the monitoring of mangrove changes and classification of mangrove types.
组合方法在不同景观特征地区的遥感分类中具有相同的性能特征。
The method of combining multiple classifiers developed in this paper has the same performance in classification of remote sensing images which have different landscape characteristics.
介绍了干旱区土壤遥感分类识别推理决策器的设计原理与实现方法。
This paper presents design principle and realizable approach of Classification and Recognition Inference Decider for Soil Remote Sensing in arid land.
研究结论：该系统基本可以满足在国家尺度上的遥感分类应用要求。
The interpretation characters of every catalogue were also demonstrated. The system can satisfy national remote sensing classification applications.
介绍了干旱区土壤遥感分类识别推理决策器的设计原理与实现方法。
This paper presents design principle and realizable approach of Classification and Recognition Inference Decider for Soil Remote Sensing (CRID) in arid land.
提出了基于知识发现和决策规则基础的盐碱地GIS和遥感分类的方法。
This paper presents the classification of saline soil method, based on knowledge discovery and decision supporting rule base systems using remotely sensed data and GIS.
高维遥感数据的分类与识别与传统的多光谱遥感分类技术具有明显的区别。
Classification and pattern recognition of high dimensional remote sensing data are distinctly different from traditional multi-channel remote sensing classification techniques.
实验表明，该方法是一种由遥感分类图自动转换成g IS通用数据的高效方案。
Finally, the experiment demonstrates that the method is a highly efficient scheme to automatically convert classified raster map to general format GIS data.
遥感分类是主要的遥感数据分析方法，是遥感图像处理中的一个非常重要研究内容。
Remote sensing classification is the main method of the analysis of remote sensing data and very important research content in remote sensing image procession.
在地形复杂地区，采用传统的遥感分类方法进行土地利用遥感分类很难获得理想的精度。
The land use classification accuracy is usually unsatisfactory in the complicated terrain area when the traditional methods are used.
得出结论，面向对象分类法比基于像元的分类法精度更高，更适合于高分辨率遥感分类。
Concluded that the object-oriented classification than the pixel-based classification more precise, more suitable for high-resolution remote sensing classification.
另外，根据图像特征和经验对图像进行波段选择，也是改善高光谱遥感分类效果的有效途径。
In addition, the spectral selection based on the image's feature and experience is also an effective way to improve the classification of hyper-spectral remote sensing images.
计算机遥感分类识别原理，是利用地物的光谱能量特征差异性和结构特征差异性来识别地物信息。
The principle of computer-RS classification recognizing is using the difference of feature of structure and spectrum energy to recognize information of surface features.
遥感分类是森林资源调查和监测不可缺少的内容，分类的精度直接影响遥感数据的应用水平和实用价值。
Remote sensing classification is one of indispensable parts of forest resource survey and supervision. The classification accuracy directly influences the applicable level and practical value.
支持向量机因其适用高维特征、小样本与不确定性问题的优越性，是一种极具潜力的高光谱遥感分类方法。
Support Vector Machines(SVM) is a potential hyperspectral remote sensing classification method because it is advantageous to deal with problems with high dimensions, small samples and uncertainty.
本文结合第四纪沉积物类型的划分，讨论了遥感分类中最佳波段和波段组合的选取以及特征空间的扩充方法。
The optimum selection of bands and its combinations in remote sensing classification and the method for expanding feature space are presented.
最后，利用矢量格式的遥感分类结果对原森林小班图层进行更新，获得新的可燃物类型图层，作为林火可视化模型的输入图层。
Finally, the vector format data of remote sensing classification result was used to update the original forest stand layer in order to get the available inputs of fire visualization modeling.
对重复传播网络在权值初始化、网络学习进行修改，实现在一定警戒条件下竞争层节点的动态分配，并在遥感分类上进行实验。
The study improves the CP neural network including the weight vectors initial, network learning, the competitive nodes dynamic allocation and the vigilance parameter design etc.
本文通过分析遥感分类图栅格像元之间的关系，快速自动地提取矢量数据点及其连接信息，进而利用连接信息快速生成弧段，由弧段自动组建多边形并建立完整的拓扑关系。
In this paper, we analyzed the relations between pixel and pixel in the classified raster map. Based on the relations, all vector points and the connection information between them can be extracted.
最大似然法分是常规遥感图像最常用、最有效的分类方法。
Maximum likelihood classifier (MLC) is the most used and effective classification method.
研究了面向对象高分辨遥感图像分类技术。
Study the object-oriented classification technology of high resolution remote sensing image.
给出一种抽取纹理特征的算法，该算法实时性强，适于在线遥感图像分类。
This paper proposes a fast algorithm for texture feature extraction. The new algorithm is suitable for remote image classification on line.
本文提出了一种基于知识的遥感图像模糊分类算法，在传统的模糊分类方法中加入了从GIS数据库中发现的知识，用它来辅助进行遥感图像分类。
In this paper, a knowledge-based fuzzy image classification method is proposed. In the method, knowledge discovery from GIS is introduced in to assist fuzzy image classification.
本文提出了一种基于知识的遥感图像模糊分类算法，在传统的模糊分类方法中加入了从GIS数据库中发现的知识，用它来辅助进行遥感图像分类。
In this paper, a knowledge-based fuzzy image classification method is proposed. In the method, knowledge discovery from GIS is introduced in to assist fuzzy image classification.
应用推荐