Extending self-organizing maps for supervised classification of remotely sensed data

An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.     

基于SVG的分布式遥感图像特征提取方法

在遥感图像网络化分布式特征分析与表达过程中,有很多需要栅格数据与矢量数据的混合模型的网络化表达与传输问题,而矢量数据的网络化表达、传输与显示问题则是影响遥感图像分布式处理效率的关键性因素之一。本文首先对SVG技术及其对矢量数据的表达特点作了简介,在介绍遥感图像分布式特征提取系统的运行流程的基础上,对其在遥感图像分布式处理中相关的网络化数据表达与显示问题给出了相应的解决思路,并给出了相应的实例与效果分析。     

高分辨率遥感影像中提取特定地物的分区多阶段混合分类方法

遥感图像分类技术发展过程中出现了各种不同的分类方法,本文提出一种对分类过程控制和分类中间数据管理的综合分类方式,通过分类方法应用方式的改进用于提取局部的特定地物。应用多阶段循环分类过程,在一个阶段的分类中控制参与分类的像元范围,在一次分类中混合应用监督分类、非监督分类和区域生长分类法,以及各种分类后处理技术,目的在于综合应用目视解译、计算机自动分类等各种技术的优点,结合地物的光谱数据,用于局部区域的特定地物信息提取和分类。     

Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis

1 Introduction With the rapid development of remotely sensed (RS) information collection, transfer and storage in the last two decades, the limitation of RS application is becom- ing weaker because of availability of multiple RS data sources of increasingly finer spatial, temporal, spectral and radiant dimensions. In the high spatial-resolution RS imagery, characteristics of land-cover are fairly clear such as spatial shape, structure, texture, etc., so the mixture of different land covers …     

生态环境遥感分类数据矢量化方法与应用

遥感分类数据矢量化建库是生态环境遥感制图及其应用分析过程中主要的处理内容和基础工作。以福建省海岸带生态环境遥感分类数据为例 ,在分析遥感图像处理系统对遥感分类和专题信息提取后处理中矢量化能力不足和结果存在严重缺陷的基础上 ,综合应用遥感和地理信息基础软件平台 ,提供的系列数据管理、分析和数据转换功能模块 ,开展基于生态环境遥感影像分类数据的矢量化建库技术探讨 ,提出一个生态环境遥感分类数据矢量化建库的通用技术方法和流程 ,并对矢量化结果做了一个简要的评价和分析 ,以满足大面积生态环境遥感调查、分析和制图的实际需要。     

小波变换与FCM聚类的QuickBird影像特征空间识别分析

遥感影像分类是应用遥感影像进行地学分析等其他应用的重要准备工作,它的精度将直接影响到后续的分析工作。纹理特征对于提高高分辨率遥感影像的分类精度具有重要意义,小波变换的"时-频"分析方法在遥感影像纹理分析方面有着独特的优势。本文采用QuickBird影像,利用小波分解得到影像的纹理特征,结合光谱响应值组成特征空间,再利用模糊C均值聚类方法对影像进行分类。实验结果显示:加入了纹理特征的影像分类精度有所提高,同时,同一类地物的内部均一性有所改善。小波分析对于细微纹理特征的提取效果比粗纹理要好。     

一种面向对象的像元级遥感图像分类方法

本文提出一种面向对象的像元级分类方法(混合模型),并将其与单纯的以像元和面向对象的两种方法同时应用于分辨率分别为30m和0.5m的环境星CCD数据和航空影像进行对比分析。分类结果中不同地物类别之间光谱可分性的大小,很大程度上可反映分类结果的可靠性。若地物类型之间的光谱差异大,说明分类方法能将光谱差异大的地物很好地划分,显示出较可靠的分类结果;相反,如果分类结果中地物类型光谱差异小,则反映分类方法不够可靠。鉴此,本文通过计算分类结果中不同类别所对应的原始遥感影像像元之间的J-M(Jeffries-Matusita Distance)距离来度量分类结果中地物之间的光谱可分性,并用J-M距离比较分析了3种图像分类方法对2种不同分辨率影像的分类结果中各个类别之间的光谱可分性的变化。分析结果表明,混合模型不但能够得到较连续的分类结果,同时能够保持分类结果中类别之间的可分性。本文对分类结果进行了精度验证,结果发现混合模型的分类精度较其他2种方法要高。2种不同分辨率的遥感影像分析结果得到相同的结论,表明该模型适用于中分辨率和高分辨率影像。     

Response of fuzzy clustering on different threshold determination algorithms in spectral change vector analysis over Western Himalaya,India

Change detection is a standard tool to extract and analyze the earth's surface features from remotely sensed data. Among the different change detection techniques, change vector analysis(CVA) have an exceptional advantage of discriminating change in terms of change magnitude and vector direction from multispectral bands. The estimation of precise threshold is one of the most crucial task in CVA to separate the change pixels from unchanged pixels because overall assessment of change detection method is highly dependent on selected threshold value. In recent years, integration of fuzzy clustering and remotely sensed data have become appropriate and realistic choice for change detection applications. The novelty of the proposed model lies within use of fuzzy maximum likelihood classification(FMLC) as fuzzy clustering in CVA. The FMLC based CVA is implemented using diverse threshold determination algorithms such as double-window flexible pace search(DFPS), interactive trial and error(TE), and 3×3-pixel kernel window(PKW). Unlike existing CVA techniques, addition of fuzzy clustering in CVA permits each pixel to have multiple class categories and offers ease in threshold determination process. In present work, the comparative analysis has highlighted the performance of FMLC based CVA overimproved SCVA both in terms of accuracy assessment and operational complexity. Among all the examined threshold searching algorithms, FMLC based CVA using DFPS algorithm is found to be the most efficient method.     

遥感数据的高斯金字塔尺度上推方法研究

尺度转换是遥感信息科学领域的研究热点,其传统研究方法大多局限于统计模型,对数据的空间结构信息考虑较少,很难满足遥感数据的多尺度表达要求。基于此,针对遥感数据的尺度不一致问题,本文提出了一种利用高斯金字塔的图像模糊特性进行遥感数据尺度上推的方法,在对金字塔每一层的数据高斯模糊的基础上,通过多次连续的降采样,得到一系列不同尺度的数据,从而满足实际应用的空间分辨率要求。为了验证本文所提方法的有效性,本文选择Landsat7 ETM影像和ASTER GDEM为研究数据进行尺度上推,并与传统的最邻近、双线性以及立方卷积等方法进行了实验对比,采用均值、方差、均方根误差、平均绝对误差等评价指标,以及相同分辨率的ASTER GDEM和SRTM DEM的等高线套合结果来衡量高斯金字塔方法的性能。实验结果表明,本文使用的高斯金字塔尺度上推方法能够有效地实现连续遥感数据的尺度转换,在保持遥感数据局部细节特征的基础上,较好地保持了原始遥感数据的信息量以及空间结构特征。     

基于Adaboost的高分遥感影像自动变化检测方法

基于监督分类的高分辨率遥感影像变化检测需要大量人工标注,且单个监督分类器难以适应高分影像中复杂多样的地表变化信息提取,检测结果中“椒盐噪声”严重、变化图斑破碎。因此,本文提出一种基于Adaboost集成算法、自动标注训练样本的变化检测方法。首先利用非监督分类方法完成变化初检,接着在初检结果中进行“非等距”区间采样自动获取均匀分布的训练样本;然后以Adaboost算法为集成框架,选择决策树桩、Logistic回归和kNN作为弱分类器,构建一种混合分类器集成系统,充分挖掘和利用高分影像中的空间信息以提升分类精度和分类器泛化能力,最后利用SLIC分割算法和空间邻域信息对像元级检测结果进行空间约束滤波,进一步提升变化检测精度。为验证本文方法的有效性,选取SPOT-5和WorldView-2影像为实验数据,结果表明本文方法能有效降低训练样本人工标注成本、提高变化检测精度。     

基于联合主题特征的网络新闻文本蕴含环境污染事件检测

网络新闻文本在环境污染事件感知方面具有重要的应用价值。然而,由于环境污染事件的“多米诺效应”,网络新闻文本往往存在对多类型污染事件的混合描述,现有事件检测方法容易导致文本分类错误。本文提出一种基于联合主题特征的网络新闻文本蕴含环境污染事件检测方法,通过兼顾环境网络新闻文本的全局特征和主题分布特征来改善检测分类效果。该方法采用词频-逆文档频率向量对文档进行全局特征表示,并结合文档的主题分布特征向量,构建联合主题特征向量作为监督分类模型的输入,实现环境污染事件检测。实验结果表明,使用联合主题特征的支持向量机方法进行事件类别检测平均F1值相较于全局特征提高15%,相较于主题特征提高36%。本文提出的网络新闻文本蕴含环境污染事件检测方法可支持污染事件类型检测和影响信息抽取,有助于环境污染事件的时空统计与变化趋势预测。     

地震与爆破波形信号的EEMD多尺度分布熵提取和WOA-SOM神经网络识别研究

针对地震信号中存在大量环境噪声的问题,基于天然地震事件和人工爆破事件建立初始数据集,利用集合经验模态分解（EEMD）技术对波形信号进行分解、降噪,提取出较纯净的各阶本征模态函数（IMF）分量,然后对前10阶分量分别计算分布熵,即EEMD多尺度分布熵,建立神经网络输入矩阵。应用鲸鱼优化算法（WOA）对自组织特征映射（SOM）神经网络参数（竞争层维数、网络训练次数）进行优化,针对不同训练样本寻找对应的最优参数值以改善模式识别的稳定性,从而提高地震识别率。结果表明,EEMD多尺度分布熵结合WOA-SOM模型可有效识别天然地震和人工地震。     

运用BP网络预测地下水位

人工神经网络是一门新兴的交叉学科，是处理非线性问题的有效方法。本文把影响地下水位的因素集作为网络的输入向量，地下水位本身作为网络的输出向量，构成了预测地下水位的ＢＰ网络模型。一个实例的应用实践表明，用ＢＰ网络预测地下水位较准确地反映了客观实际，比其它方法如回归模型具有较高的拟合精度和预测精度。     

遥感影像混合像元的分解——基于加权后验概率的支持向量机分类算法

混合像元是遥感影像中普遍存在的现象,对此,本文提出基于加权后验概率的支持向量机进行影像混合像元分解。该分类算法可判定端元种类的同时得到每种地物的后验概率,从而进行非线性模型的混合像元分解。由于加权后验概率的支持向量机分类算法能够减少分类器受土地覆盖类型模糊样本点的干扰,因此,改善了非线性混合像元分解模型的精度。首先,由样本点计算得到核函数参数值,然后,计算影像中每一种土地覆盖类型的后验概率,将其作为各个两类支持向量机分类器的权系数并求得多类后验概率值,确定影像每一种土地覆盖类型并得到丰度值。本文采用TM多波段遥感影像验证该方法的可行性,实验区位于我国东北部的大兴安岭中北段地区,土地覆盖类型包含农田、居民地、水体、荒地等。将本文提出的混合像元分解方法结果与标准支持向量机模型分解的结果对比表明,以加权后验概率的支持向量机遥感影像混合像元分解方法精度优于标准支持向量机模型。     

深度学习和遥感影像支持的矢量图斑地类解译真实性检查方法

空间数据质量检查是数据准确可靠的重要保障,是数据的生命线。然而,目前的空间数据质量检查主要针对拓扑关系、属性一致性以及数据间的相关性进行检查,往往忽视矢量图斑地类解译真实性问题。因此,本文提出深度学习和高分遥感影像支持的矢量图斑地类解译真实性检查方法,选用深度学习经典模型Inception_v3进行迁移学习,对分割后的影像进行自动场景分类,以高分遥感影像块的场景分类结果作为参照依据,对场景分类结果与矢量图斑原始数据进行叠加分析,自动查找出类别信息不符的分割单元,从而提取出可疑图斑,实现矢量图斑地类解译真实性自动检查,并在徐州市贾汪区青山泉镇和大吴镇的矢量图斑地类解译真实性检查中进行验证。实验结果表明,本文方法在研究区图斑地类解译真实性检查中的精确率和召回率分别高达0.925和0.817,可为矢量图斑地类解译真实性检查提供可靠的技术支撑。     

Topographically derived subpixel-based change detection for monitoring changes over rugged terrain Himalayas using AWiFS data

Continuous and accurate monitoring of earth surface changes over rugged terrain Himalayas is important to manage natural resources and mitigate natural hazards.Conventional techniques generally focus on per-pixel based processing and overlook the sub-pixel variations occurring especially in case of low or moderate resolution remotely sensed data.However,the existing subpixel-based change detection(SCD)models are less effective to detect the mixed pixel information at its complexity level especially over rugged terrain regions.To overcome such issues,a topographically controlled SCD model has been proposed which is an improved version of widely used per-pixel based change vector analysis(CVA)and hence,named as a subpixel-based change vector analysis(SCVA).This study has been conducted over a part of the Western Himalayas using the advanced wide-field sensor(AWiFS)and Landsat-8 datasets.To check the effectiveness of the proposed SCVA,the cross-validation of the results has been done with the existing neural network-based SCD(NN-SCD)and per-pixel based models such as fuzzybasedCVA(FCVA)andpost-classification comparison(PCC).The results have shown that SCVA offered robust performance(85.6%-86.4%)as comparedtoNN-SCD(81.6%-82.4%),PCC(79.2%-80.4%),and FCVA(81.2%-83.6%).We concluded that SCVA helps in reducing the detection of spurious pixels and improve the efficacy of generating change maps.This study is beneficial for the accurate monitoring of glacier retreat and snow cover variability over rugged terrain regions using moderate resolution remotely sensed datasets.     

遥感信息与知识交换共享元数据系统设计

随着遥感技术的飞速发展,遥感数据成为城市规划、地球科学研究、数字地球等重大科学研究和工程建设的重要数据源。但随着遥感数据量的不断增加和应用领域的扩大,如何科学有效地管理、存储、更新和重用已有的遥感数据资源,已成为当前空间信息元数据研究的热点。因此,有必要制订专门用于描述遥感数据及其相关资源的元数据系统,满足用户正确了解和使用遥感数据的需要,推动遥感数据共享。本文在研究和参考现有国家和国际地理信息元数据标准的基础上,设计了针对遥感信息与知识交换共享的元数据系统,该系统实现了遥感数据、相关辅助测量数据、应用方法模型以及传感器、平台等相关知识等信息的统一、规范表示,为遥感信息与知识交换共享搭建了元数据层次上的平台。     

基于图分割的高分辨率遥感影像建筑物变化检测研究

建筑物是城市地理数据库中最容易发生变化和最需要更新的部分,其更新工作量巨大,因此开展对高分辨率遥感影像中的建筑物进行自动提取和变化检测研究具有重要的意义.本文以精确提取变化建筑物的位置和轮廓为目标,基于图分割提出一种高分辨率遥感影像建筑物变化检测方法.首先,将遥感影像中的每个像元映射成图的顶点,利用像元之间的距离阈值构造图的边,综合利用位置,灰度和边缘3种特征计算边的权值,将遥感影像的分割转化为图的分割,并用归一化图分割方法得到分割对象集合;然后,以长宽比和矩形度作为约束条件,对2期遥感影像中的分割对象集合进行筛选,提取建筑物对象;最后,根据2期影像中建筑物之间的空间,面积和格局关系识别建筑物的变化类型(包括新增,消失和改建),并对其进行可视化表达.为了验证本文方法的有效性,分别以深圳市的WorldView影像和北京市的QuickBird全色影像为数据源,从中选取13组具有代表性的子影像进行实验.结果表明,本文提出的方法对配准精度较低的影像组具有一定的适应性,容许的配准误差达到20个像元(10 m),平均查准率和平均查全率分别达到93.16%和87.90%.     

Groundwater quality modeling using self-organizing map(SOM) and geographic information system(GIS) on the Caspian southern coasts

Groundwater is the main source for water provision in the arid and semi-arid areas such as Iran. The groundwater quality was simulated by using a hybrid model integrating a Self-Organizing Map(SOM) and geographic information system(GIS). SOM and GIS were used as pre-processing and postprocessing tools in the Mazandaran Plain. Further, the Ground Water Quality Index(GWQI) and its effective factors were estimated by using digital maps and the secondary data. Neuro Solutions software was used for simulating the groundwater quality. To do this, a model was trained and optimized in the SOM and then the optimized model was tested. In the next step, the performance of SOM in groundwater quality simulation was confirmed(test stage, Rsqr=0.8, and MSE=0.008). Then, the digital maps of the SOM inputs were converted to raster format in GIS. In the last step, a raster layer was generated by combining the model input layers which comprised the model inputs values. The tested SOM was used to simulate GWQI in the sites without the secondary data of the groundwater quality. Finally, the groundwater quality map was generated by coupling the results of SOM estimations and GIS capabilities. The results revealed that the coupling of SOM and GIS has high performance in the simulation of the groundwater quality. According to the results, a limited area of the studied plain has groundwater resources with low quality(GWQI0.04). Therefore, that will be a threat to the life of humans, animals, and vegetative species. Therefore, it is necessary to plan for managing the groundwater quality in the Mazandaran plain.     

Modeling transportation of suspended solids in Zhujiang River estuary, South China

A three-dimensional transportation model for suspended solids （SS） in Zhujiang （Pearl） River estuary, South China, was developed by coupling with a three-dimensional hydrodynamic model. The model was validated using hourly measured data of sediment contents during 25-26, July 1999. The results showed that modeled contents matched well with measured ones and that the modeled top layer distribution agreed with the remotely sensed image of suspended solids in summer. The modeled results showed clearly the layers of suspended solids in depth, with larger sediment contents in lower layers though in the interface between salt water and freshwater the lowest contents appeared in middle layer. In overall, the suspended solids inflow from 8 rivers,transport southwestward, and carried by strong coastal flow in Zhujiang River estuary. Contours of sediment contents in the estuary spread further to the open sea during ebb tide rather than flood tide which reflects that the suspended solids in the estuary are land sourced.