基于ASTER数据的决策树自动构建及分类研究

 在对ASTER原始9个波段数据进行各种变换处理的基础上，采用数量化指标平均可分性方法确定参与分类的最佳特征组合； 结合研究区8种主要地物类型训练数据集，分别采用最大似然法、BP神经网络法和基于See 5.0数据挖掘的决策树分类法进行分类，提取主要地物的空间分布专题信息。经过379个野外样点的验证，结果表明： 决策树算法分类性能最优，神经网络算法次之，最大似然法效果最差； 与ENVI 4.1、ERDAS 8.7提供的传统决策树建立及分类方法比较，基于数据挖掘工具See 5.0和Cart的决策树生成和分类方法具有客观、高效率、分类性能可靠和精度高等优点。     

Techniques of classification for landuse/landcover with special reference to forest type mapping in Jaldapara Wildlife Sanctuary, Jalpaiguri District, West Bengal—a case study

The accuracy of three classification techniques namely Maximum likelihood, contextual and neural network for landuse/landcover with special emphasis on forest type mapping was evaluated in Jaldapara Wildlife Sanctuary area using IRS-1B LISS II data of Dec. 1994. The area was segregated into ten categories by using all the three classification techniques taking same set of training areas. The classification accuracy was evaluated from the error matrix of same set of training and validating pixels. The analysis showed that the neural net work achieved maximum accuracy of 95 percent, maximum likelihood algorithm with 91.06 percent and contextual classifier with 87.42 percent. It is concluded that the neural network classifier works better in heterogeneous and contextual in homogenous forestlands whereas the maximum likelihood is the best in both the conditions.     

遥感图像土地覆盖分类中多源特征数据选择研究

多源特征数据可以提高遥感图像的分类精度,选择合适的特征数据十分重要。利用基尼指数对多尺度纹理信息、主成分变换前三分量、地形数据等特征进行选择,选出最佳特征子集。利用支持向量机、神经网络分类法、最大似然法分别对全部特征数据和最佳特征子集结合多光谱数据进行分类。实验结果表明:基尼指数可以有效地对多源特征数据进行选择,特征选择可以提高分类器效率,提高分类精度。     

人工神经网络在高分影像防沙带识别中的应用

基于高分一号(GF-1)遥感影像,利用人工神经网络方法对新疆和田洛浦县沙漠边缘村庄周围的防沙带进行识别,并与目视解译的防沙带结果进行对比,验证识别精度.将人工神经网络方法的识别结果与传统的最大似然法进行对比分析,并利用图像识别领域中的准确率、召回率和F值3个指标对两种方法进行精度评价.结果表明,人工神经网络方法识别防沙...     

运用神经网络识别注射过金属离子溶液树冠的实验研究

本文运用神经网络ＢＰ算法对高分辨率航空多光谱图像进行了模式识别研究,成功地识别出注射过金属离子溶液树冠,并与最大似然法在分类结果进行比较。得出在分类精度上,神经网络模式识别比传统的最大似然分类方法具有优势的结论。     

A GIS‐based multi‐criteria seismic vulnerability assessment using the integration of granular computing rule extraction and artificial neural networks

This study proposes multi‐criteria group decision‐making to address seismic physical vulnerability assessment. Granular computing rule extraction is combined with a feed forward artificial neural network to form a classifier capable of training a neural network on the basis of the rules provided by granular computing. It provides a transparent structure despite the traditional multi‐layer neural networks. It also allows the classifier to be applied on a set of rules for each incoming pattern. Drawbacks of original granular computing (GrC) are covered, where some input patterns remained unclassified. The study was applied to classify seismic vulnerability of the statistical units of the city of Tehran, Iran. Slope, seismic intensity, height and age of the buildings were effective parameters. Experts ranked 150 randomly selected sample statistical units with respect to their degree of seismic physical vulnerability. Inconsistency of the experts' judgments was investigated using the induced ordered weighted averaging (IOWA) operator. Fifty‐five classification rules were extracted on which a neural network was based. An overall accuracy of 88%, κ = 0.85 and R² = 0.89 was achieved. A comparison with previously implemented methodologies proved the proposed method to be the most accurate solution to the seismic physical vulnerability of Tehran.     

Analysis of temporal sar and optical data for rice mapping

This study investigates the potential of multi-temporal signature analysis of satellite imagery to map rice area in South 24 Paraganas district of West Bengal. Two optical data (IRS ID LISS III) and three RADARSAT SAR data of different dates were acquired during 2001. Multi-temporal SAR backscatter signatures of different landcovers were incorporated into knowledge based decision rules and kharif landcover map was generated. Based on the spectral variation in signature, the optical data acquired during rabi (January) and summer (March) season were classified using supervised maximum likelihood classifier. A co-incidence matrix was generated using logical approach for a combined “rabi-summer” and “kharif-rabi-summer” landcover mapping. The major landcovers obtained in South 24 Paraganas using remote sensing data are rice, water, aquaculture ponds, homestead, mangrove, and urban area. The classification accuracy of rice area was 98.2% using SAR data. However, while generating combined “kharif-rabi-summer” landcovers, the classification accuracy of rice area was improved from 81.6% (optical data) to 96.6% (combined SAR-Optical). The primary aim of the study is to achieve better accuracy in classifying rice area using the synergy between the two kinds of remotely sensed data.     

Effects of Training Samples and Classifiers on Classification of Landsat-8 Imagery

In this study, we used Landsat-8 imagery to test object- and pixel-based image classification approaches in an urban fringe area. For object-based classification, we applied four machine learning classifiers: decision tree (DT), naive Bayes (NB), random trees (RT), and support vector machine (SVM). For pixel-based classification, we utilized the maximum likelihood classifier (MLC). Specifically, we explored the influence of repeated sampling on classification results with different training sample sizes. We found that (1) except the overall accuracy of NB, those of the other four classifiers increased as the training sample size increased; (2) repeated sampling had a significant effect on classification accuracy, especially for the DT and NB classifiers; and (3) SVM achieved the best classification accuracy. In addition, the performance of the object-based classifiers was superior to that of the pixel-based classifier. The results of this study can provide guidance on the training sample size and classifier selection.     

面向对象和GURLS结合的高空间分辨率遥感数据云检测

遥感信息获取过程中云是重要的干扰因素,随着国产高空间分辨率卫星数据的应用,实现数据的准确云检测对有效获取地面信息具有重要意义。本文以高分一号、高分二号多光谱影像为数据源,利用图像分割获取了同质对象,基于对象光谱、纹理和几何8种属性特征建立了规则集,以规则集为输入,利用阈值法和GURLS分类器结合进行了云检测。针对不同时相和场景的高分数据,将该方法与基于像素的最大似然法和SVM法进行了对比,结果表明该方法云提取精度均在95%以上,Kappa系数在0.9以上。     

Performance Analysis of Maximum Likelihood and Artificial Neural Network Classifiers for Training Sets with Mixed Pixels

This study evaluates the performance of an artificial neural network, specifically a multilayer perceptron, and a maximum likelihood algorithm to classify multitemporal Landsat ETM+ remote sensor data. The study area in Turkey is a mountainous region that contains many small scattered fields, usually 5-10 pixels in size. The classifiers were employed to identify eight land cover/use features covering the bulk of the study area using the same training and test datasets in order to avoid any difference resulting from sampling variations. Results show that the neural network approach performed better in extracting land cover information from multispectral and multitemporal images with training data sets including a large amount of mixed and atypical pixels. The maximum likelihood classifier was found to be ineffective, particularly in classifying spectrally similar categories and classes having subclasses.     

Improving neural network performance on the classification of complex geographic datasets

Neural Networks are now established computational tools used for search minimisation and data classification. They offer some highly desirable features for landuse classification problems since they are able to take in a variety of data types, recorded on different statistical scales, and combine them. As such, neural networks should offer advantages of increased accuracy. However, a barrier to their general acceptance and use by all but `experts' is the difficulty of configuring the network initially.  This paper describes the architectural problems of applying neural networks to landcover classification exercises in geography and details some of the latest developments from an ongoing research project aimed at overcoming these problems. A comprehensive strategy for the configuration of neural networks is presented, whereby the network is automatically constructed by a process involving initial analysis of the training data. By careful study of the functioning of each part of the network it is possible to select the architecture and initial weights on the node connections so the constructed network is `right first time'. Further adaptations are described to control network behaviour, to optimise functioning from the perspective of landcover classification. The entire configuration process is encapsulated by a single application which may be treated by the user as a `black box', allowing the network to the applied in much the same way as a maximum likelihood classifier, with no further effort being required of the user.     

基于神经网络的遥感影像分类方法研究

本文在研究BP神经网络和模糊理论的基础上,提出了传统BP算法的一种改进方法和基于模糊系统的神经网络遥感影像分类方法。通过试验表明:基于模糊技术的神经网络分类方法要优于BP神经网络方法,取得了令人满意的效果。     

一种适用于多类别遥感图象分类的新方法——复合神经网络分类方法

该文提出一种由多层神经网络与自组织神经网络相结合进行类别遥感图象分类的复合神经网络分类方法。第１步半训练样本按其统计特征分成若干组，用不同级别的训练样本分别训练ＢＰ网络。第２步将这些训练好的ＢＰ网络并联构成有监督分类器，对遥感图象进行有监督分类。第３步用ＢＰ网络的分类结果对Ｋｏｈｏｎｅｎ网络进行自组织训练，用训练好的Ｋｏｈｏｎｅｎ网络构造无监督分类器，对遥感图象进行细分。通过对ＳＰＯＴ遥感图象的分     

山区植被类型信息提取方法研究

根据遥感图像的光谱信息和空间信息特征及不同植被的分布规律,研究利用计算机处理技术提取山区植被类型的方法。分类过程采用四个步骤完成：①均一目标的象限四分树提取分类；②多光谱数据的最小距离分类；③综合利用波谱曲线的形态和地形数据进行分类；④高程数据修正分类。在分类处理过程中,分别利用了图像的空间信息、光谱信息以及地形数据。利用该分类方法在实验小区内进行植被类型提取试验,其精度为90%.与最大似然分类方法所得结果相比较,其分类精度提高了10%.     

Classifier ensembles for land cover mapping using multitemporal SAR imagery

SAR data are almost independent from weather conditions, and thus are well suited for mapping of seasonally changing variables such as land cover. In regard to recent and upcoming missions, multitemporal and multi-frequency approaches become even more attractive. In the present study, classifier ensembles (i.e., boosted decision tree and random forests) are applied to multi-temporal C-band SAR data, from different study sites and years. A detailed accuracy assessment shows that classifier ensembles, in particularly random forests, outperform standard approaches like a single decision tree and a conventional maximum likelihood classifier by more than 10% independently from the site and year. They reach up to almost 84% of overall accuracy in rural areas with large plots. Visual interpretation confirms the statistical accuracy assessment and reveals that also typical random noise is considerably reduced. In addition the results demonstrate that random forests are less sensitive to the number of training samples and perform well even with only a small number. Random forests are computationally highly efficient and are hence considered very well suited for land cover classifications of future multifrequency and multitemporal stacks of SAR imagery.     

融合多特征深度学习的地面激光点云语义分割

针对当前点云语义分割研究对地面站激光点云特征利用不足、正确率较低的问题,该文提出了一种基于多尺度球形邻域特征的深度神经网络算法。该算法基于多尺度球形邻域计算的地面激光点云的粗糙度、高斯曲率,以及全方差、线性度等基于协方差的多种特征,结合XYZ坐标、RGB颜色、激光反射强度组成47维特征向量作为神经网络的输入,经过多组参数组合实验优化神经网络结构,最后通过softmax分类器输出每个点的类别。利用Semantic-3D测试集验证所提的深度神经网络模型,取得了较好的分类精度,总体正确率和平均交并比分别达到了86.6%和55.0%。实验结果表明,所提算法充分利用了地面站激光点云的特征,可有效提升语义分割的正确率。     

基于误差分析的组合分类器研究

提出了一种基于误差分析的组合分类器,通过结合两种监督分类方法,提出的算法分别估计了两种监督分类方法在计算过程中的误差,给出了规则输出的置信区间,再根据置信区间的大小对两种分类方法的输出结果进行加权平均,从而得到更精确的规则输出.利用该方法对遥感图像进行分类实验,在不同训练样本分布与不同训练样本数量的情况下,比较新的组合分类器与单一分类器的精度.结果表明新的组合分类器能够取得比单一的分类器更高的分类精度.结果还显示出,两个分类器的独立性越强,组合分类器的效果越好.另外一个实验比较了新的组合分类器与和式规则组合分类器的分类精度,结果仍显示出了新方法的优越性.     

影像融合技术应用于地表分类之探讨

本论文尝试讨论两个主题：主题一为利用主成分分析PCA方法应用于像元阶层资料融合技术的研究。主题二为应用Dempster-Shafer evidence theory方法于特征阶层数据融合技术的研究。在第一个主题中，由于合成孔径雷达的数据具有全偏极特性，在此选取了对植被较为敏感的HV极化合成孔径雷达数据，与具有光谱特性的光学SPOT数据做数据融合处理以利接下来的地物分类。首先，本研究利用小波转换技术来滤除合成孔径雷达斑驳噪声，在接下来融合步骤中，主成分分析出来的第一部分（PCI）是用做完滤除噪声后的合成孔径雷达取代，在数据融合后，进行地物分类是采用最大似然法来分类融合影像。在第二个主题中，利用全偏极雷达数据的极化特性结合SPOT数据的光谱特性，其主要目的是为了增加分类的精确度。首先使用李式滤波器滤除全偏极雷达数据噪声，接下来同样是使用采用最大似然法来分类融合影像，（不同的在于全偏极雷达影像使用Wishart几率分布，在光学影像采用multivariate Gaussian几率分布）将每个类别中每个像元属于某个类别的几率值计算出来，再利用Dempster-Shafer evidence theory来结合这些类别的机率值。最后产生出一张新的分类影像。实验的结果显示分类的精确度比较于未融合的资料都有明显提升的效果，也证明了此两个数据融合方法对于不同数据特性的融合都是很成功的。     

基于GIS和神经网络的森林植被分类

本文综述了国际遥感分类研究,使用Landsat7 ETM＋遥感数据和地理辅助数据,应用BP神经网络方法,将莽汉山林场作为研究区进行了遥感影像的分类研究。比较了BP神经网络分类与最大似然、简单和复杂非监督分类法之间的类型与数量精度。BP神经网络分类的总类型精度是70.5%,总数量精度为84.65%,KAPPA系数是0.6455。结果说明BP神经网络的分类质量优于其他方法,其总的类型精度与其他三种分类方法相比分别增加了10.5%、32%和33%,总的质量精度增加了5.3%。因此,辅以地理参考数据的BP神经网络分类可以作为一种有效的分类方法。     

Accuracy assessment in cotton acreage estimation using Indian remote sensing satellite data

The accuracy of cotton crop classification using satellite data has been assessed with respect to a detailed land cover map prepared by field survey. The effect of spatial resolution on classification accuracy was studied using LISS-I (spatial resolution 72.6 m) and LISS-II data (spatial resolution 36.25 m) of the Indian remote sensing satellite IRS-1B. The performances of the maximum likelihood and the minimum distance to mean as classifiers have also been assessed. LISS-II data have been found to give a higher classification accuracy. The estimate of cotton acreage using LISS-II data was closer to that obtained from the base map. The maximum likelihood classifier (MXL) and the minimum distance to mean (MDM) classifier performed equally well.