An Automated Approach for Land Cover Classification Based on a Fuzzy Supervised Learning Framework

This paper proposes an automatic framework for land cover classification. In majority of published work by various researchers so far, most of the methods need manually mark the label of land cover types. In the proposed framework, all the information, like land cover types and their features, is defined as prior knowledge achieved from land use maps, topographic data, texture data, vegetation’s growth cycle and field data. The land cover classification is treated as an automatically supervised learning procedure, which can be divided into automatic sample selection and fuzzy supervised classification. Once a series of features were extracted from multi-source datasets, spectral matching method is used to determine the degrees of membership of auto-selected pixels, which indicates the probability of the pixel to be distinguished as a specific land cover type. In order to make full use of this probability, a fuzzy support vector machine (SVM) classification method is used to handle samples with membership degrees. This method is applied to Landsat Thematic Mapper (TM) data of two areas located in Northern China. The automatic classification results are compared with visual interpretation. Experimental results show that the proposed method classifies the remote sensing data with a competitive and stable accuracy, and demonstrate that an objective land cover classification result is achievable by combining several advanced machine learning methods.     

Entropy-based fuzzy classification parameter optimization using uncertainty variation across spatial resolution

In the past researchers have suggested hard classification approaches for pure pixel remote sensing data and to handle mixed pixels soft classification approaches have been studied for land cover mapping. In this research work, while selecting fuzzy c-means (FCM) as a base soft classifier entropy parameter has been added. For this research work Resourcesat-1 (IRS-P6) datasets from AWIFS, LISSIII and LISS-IV sensors of same date have been used. AWIFS and LISS-III datasets have been used for classification and LISS-III and LISS-IV data were used for reference data generation, respectively. Soft classified outputs from entropy based FCM classifiers for AWIFS and LISS-III datasets have been evaluated using sub-pixel confusion uncertainty matrix (SCM). It has been observed that output from FCM classifier has higher classification accuracy with higher uncertainty but entropy-based classifier with optimum value of regularizing parameter generates classified output with minimum uncertainty.     

一种利用像素邻域信息的模糊聚类图像分割算法

本文提出一种结合空间信息的模糊C均值聚类图像分割算法。该方法是利用每个像素的邻域像素的隶属度来修正FCM算法的隶属度函数,从而引入图像的空间信息,对隶属函数做了改进;依据平方误差和最小准则,从而确定模糊分类矩阵及聚类中心;并依据最大隶属度原则,划分图像像素的类别归属。实验结果表明,该方法能快速有效地分割图像,并且具有较强的抗噪能力。     

融入空间关系的二型模糊模型高分辨率遥感影像分割

为解决高分辨率遥感影像分割中,由光谱测度的空间复杂性、相同类型地物目标异质性增大带来的类属不确定性以及分割决策不确定性等引起的分割精度下降问题,提出一种融入空间关系的区间二型模糊模型高分辨率遥感影像监督分割方法。(1)建立高斯函数模型作为一型模糊模型,用来刻画像素类属的不确定性;(2)模糊化一型模糊模型中的均值或标准差,建立区间二型模糊模型,以强化类属的不确定表达和增加分割决策信息;(3)综合一型模糊模型及区间二型模糊模型的上、下隶属函数建模模糊决策模型;(4)融入邻域像素关系,使用待分像素及其邻域像素在模糊决策模型中的隶属度共同决定像素的类属。采用本文算法分别对真实高分辨遥感影像及合成影像进行分割,并对测试结果进行定性和定量分析。结果表明,本文算法可以得到更高的分割精度。     

Lightning flash mensuration using video from the space shuttle Columbia (STS‐32)

Abstract

Environmental data are often utilized to guide interpretation of spectral information based on context, however, these are also important in deriving vegetation maps themselves, especially where ecological information can be mapped spatially. A vegetation classification procedure is presented which combines a classification of spectral data from Landsat‐5 Thematic Mapper (TM) and environmental data based on topography and fire history. These data were combined utilizing fuzzy logic where assignment of each pixel to a single vegetation category was derived comparing the partial membership of each vegetation category within spectral and environmental classes. Partial membership was assigned from canopy cover for forest types measured from field sampling. Initial classification of spectral and ecological data produced map accuracies of less than 50% due to overlap between spectrally similar vegetation and limited spatial precision for predicting local vegetation types solely from the ecological information. Combination of environmental data through fuzzy logic increased overall mapping accuracy (70%) in coniferous forest communities of northwestern Montana, USA.     

Distribution of Errors in a Classified Map of Satellite Data

Abstract

The output from any spatial data processing method may contain some uncertainty. With the increasing use of satellite data products as a source of data for Geographical Information Systems (GIS), there have been some major concerns about the accuracy of the satellite‐based information. Due to the nature of spatial data and remotely sensed data acquisition technology, and conventional classification, any single classified image can contain a number of mis‐classified pixels. Conventional accuracy evaluation procedures can report only the number of pixels that are mis‐classified based on some sampling observation. This study investigates the spatial distribution and the amount of these pixels associated with each cover type in a product of satellite data. The study uses Thematic Mapper (TM) and SPOT multispectral data sets obtained for a study area selected in North East New South Wales, Australia. The Fuzzy c‐Means algorithm is used to identify the classified pixels that contained some uncertainty. The approach is based on evaluating the strength of class membership of pixels. This study is important as it can give an indication of the amount of error resulting from the mis‐classification of pixels of specific cover types as well as the spatial distribution of such pixels. The results show that the spatial distribution of erroneously classified pixels are not random and varies depending on the nature of cover types. The proportions of such pixels are higher in spectrally less clearly defined cover types such as grasslands.     

二型模糊集合在遥感影像土地利用分类中的应用

在遥感影像土地利用分类中,传统的布尔分类法只考虑地物光谱信息,用"是"与"非"的二值确定逻辑状态分类影像,当存在较多混合像元时,其不能满足一些实际应用的要求。模糊分类法综合了地物光谱特征、空间特征和对象的拓扑关系,对每个像元的归属用[0～1]的模糊度来表示,有效地解决了该问题。通过对研究区TM影像进行传统布尔法分类和模糊分类法分类的结果比较可知:对混合像元较多且波段较少的遥感影像土地利用分类,二型模糊集合分类能够适应用户不同精度需求,并能交互式输出结果。     

利用Landsat TM影像进行地表温度像元分解

提出了一种基于Landsat TM的地表温度二次像元分解方法,将地表温度的空间分辨率从120 m提高到30 m。首先,利用地表类型的线性统计模型（E-DisTrad）获取初次分解子像元的地表温度,计算得到初次分解子像元的辐亮度;然后,利用面向对象的图像分割方法获取二次分解子像元的权重,实现对地表温度的二次分解;最后,采用升尺度再分解的验证方法进行精度分析,并选取了北京市TM影像进行实例分析。实验结果表明,二次像元分解模型不仅能有效地提高地表温度的空间分辨率,反映出不同地表类型地表温度的空间差异性,而且保证了像元分解前后能量值的一致性,非常适合于复杂地表覆盖地区的热红外波段遥感影像数据的降尺度处理。     

A fuzzy topology-based maximum likelihood classification

Classification is one of the most widely used remote sensing analysis techniques, with the maximum likelihood classification (MLC) method being a major tool for classifying pixels from an image. Fuzzy topology, in which the set concept is generalized from two values, {0, 1}, to the values of a continuous interval, [0, 1], is a generalization of ordinary topology and is used to solve many GIS problems, such as spatial information management and analysis. Fuzzy topology is induced by traditional thresholding and as such gives a decomposition of MLC classes.Presented in this paper is an image classification modification, by which induced threshold fuzzy topology is integrated into the MLC method (FTMLC). Hence, by using the induced threshold fuzzy topology, each image class in spectral space can be decomposed into three parts: an interior, a boundary and an exterior. The connection theory in induced fuzzy topology enables the boundary to be combined with the interior. That is, a new classification method is derived by integrating the induced fuzzy topology and the MLC method. As a result, fuzzy boundary pixels, which contain many misclassified and over-classified pixels, are able to be re-classified, providing improved classification accuracy. This classification is a significantly improved pixel classification method, and hence provides improved classification accuracy.     

变端元混合像元分解冬小麦种植面积测量方法

针对线性混合像元分解(Linear Spectral Unmixing,LSU)在端元(Endmember)个数不变情况下常会出现端元分解过剩现象导致分解结果精度不高的问题,以地物分布的聚集性特征为基础,提出了基于格网的变端元线性混合像元分解(Dynamic Endmember LSU,DELSU)方法.以冬小麦为研究...     

基于模糊推理的最大似然分类算法研究

本文将模糊集理论与最大似然分类原理相结合,用模糊均值和模糊协方差代替传统最大似然分类的均值和协方差矩阵,依据极大隶属度原则,对最大似然分类算法进行改进。并尝试采用一种基于相异像素空间分布算法的分类精度评定方法,得到相异像素空间分布图,依据该空间分布图对不同的分类方法进行精度评定。实验结果表明,改进后的最大似然分类法的正确率、Kappa系数均优于传统的最大似然分类方法,所采用的精度评定方法也较传统方法在有效性、效率等方面有所改善。     

自适应模糊规则分类方法及在TM土地覆盖分类中的应用研究

根据自组织网络和模糊逻辑推理,实现土地覆盖自适应模糊规则分类方法。该方法通过网络的节点和权值提取出模糊规则,调整网络中节点个数(即相应增加规则节点数)和权值向量,使模糊规则自动生成,并利用模糊逻辑推理,完成TM土地覆盖分类。对拒分类的像元,自适应增加K值使其可分。该方法所得分类精度及Kapp系数与最大似然分类方法结果相比分别提高了2.7%和2.9%;与自组织网络相比,总精度相差不大,而Kapp系数低1%。实验证明,如何提取和表示非光谱知识,从而解决类别混淆等问题,是提高自适应模糊规则分类性能的关键     

作物种植成数的遥感监测精度评价

以河南开封和山西太谷地区作为研究区域 ,选用LandsatTM作为农作物种植面积遥感监测的数据源。利用LandsatTM提取河南开封实验区 2 0 0 1年的夏季作物和山西太谷地区 2 0 0 3年秋季作物的作物种植成数。同时 ,利用IKONOS ,QuickBird高分辨率遥感影像 ,通过地面调查进行了地面作物填图和分类 ,同样得到实验区的农作物种植成数。最后通过两种结果对比 ,表明开封实验区夏季作物的监测精度达到 99%以上 ,太谷实验区秋季作物的监测精度达到 97%以上 ,由此推断 ,表明利用LandsatTM监测农作物种植成数的精度能够满足中国农情遥感监测的运行化要求     

基于PCM改进算法的遥感混合像元模拟分析

混合像元的存在是影响遥感图像分类精度的主要原因,模糊分类是进行混合像元分解的重要方法,其效果的好坏取决于各像元分类后对各类别的隶属度值能否准确地反映像元的类别组成。当非监督分类中的聚类数目与实际类别数目不符,或者监督分类中训练样本存在未训练类别时,常用的模糊c-均值(FCM)方法的效果将大大降低,而可能性c-均值(PCM)方法则可以解决这个问题。该文提出了基于PCM算法的遥感图像混合像元分解方法,并用监督分类方法实例说明PCM方法的优越性。     

一种新的高分辨率遥感影像模糊监督分类方法

针对高分辨率遥感影像分类中由于细节特征突出、同质区域光谱测度变异性增大所带来的像素类属的不确定性及模型的不确定性等造成的误分结果,提出一种基于模糊隶属函数的监督分类方法。对同质区域定义高斯隶属函数模型用来表征像素类属不确定性;模糊化该隶属函数参数建立影像模糊隶属函数,以建模同质区域光谱测度的不确定性;用训练样本在所有类别中的模糊隶属函数及原隶属函数（高斯隶属函数）中的隶属度为输入,建立模糊线性神经网络模型作为目标函数,实现分类决策。该算法和经典算法对World View-2全色合成影像及真实影像进行定性和定量分类实验,分类结果验证了文中方法具有更高的分类精度。     

高分二号遥感影像提取冬小麦空间分布

精细的农作物空间分布数据对于资源、环境、生态、气候变化和粮食安全问题均具有重要的意义,卷积神经网络已经成为从遥感影像中提取农作物空间分布数据的主要方法,但提取结果中的种植区域边缘往往比较粗糙。本文以高分二号遥感影像为数据源,选择冬小麦为提取目标,利用RefineNet模型和最大后验概率模型构建冬小麦遥感提取模型WWRSE(Winter Wheat Remote Sensing Extraction),获取精细的冬小麦空间分布数据。WWRSE模型利用RefineNet网络提取像素的语义特征,使用改进的SoftMax模型生成像素的类别概率向量;以类别概率向量的最大分量与次大分量的差值作为置信度,根据置信度将类别概率向量分为可信和不可信两组,可信组直接使用最大分量对应的类别标签作为相应像素的分类结果;结合最大后验概率模型确定不可信组像素的分类结果。利用随机梯度法对WWRSE模型进行训练。选择SegNet、DeepLab、RefineNet作为对比模型进行实验,WWRSE提取结果的精度为92.9%,比SegNet提高了13.8%,比DeepLab提高了10.9%,比RefineNet提高了8.6%。实验结果表明WWRSE模型在提取冬小麦空间分布数据方面具有一定的优势。WWRSE模型提取的结果能够为大范围冬小麦种植面积统计提供依据。     

条件随机场模型约束下的遥感影像模糊C-均值聚类算法

遥感影像具有丰富的空间相关信息,而传统的基于像元光谱的聚类算法并不能将空间信息融入聚类,聚类结果往往不好。针对这一问题,本文提出了一种条件随机场模型约束下的模糊C-均值聚类算法,通过邻域像元的分类先验信息对中心像元的类别进行约束从而提取空间相关信息,基于二阶条件随机场将光谱信息和空间相关信息同时融入聚类,并使用环形置信度迭代算法得到像元分类后验概率的全局最优推测。试验证明,本文算法能够有效地保持地物的形状特征,分类精度相比传统算法有所提高。     

Updating land cover automatically based on change detection using satellite images: case study of national forests in Southern California

Observing dynamic change patterns and higher-order complexities from remotely sensed images is warranted, but the main challenges include image inconsistency, plant phenological differences, weather variations, and difficulties of incorporating natural conditions into automatic image processing. In this study, we proposed a new algorithm and demonstrated it by producing 2002–2008 and 2010 land-cover maps in heterogeneous Southern California based on an existing 2009 land-cover map. The new algorithm improves the baseline land-cover map quality by discarding potential bad land-cover pixels and dividing each land-cover type into several subclasses. Time series Landsat images were used to detect changed and unchanged areas between baseline year and target year t. Subsequently, for each individual year t, each pixel that was identified as unchanged inherited the baseline classification. Otherwise, each pixel in the changed areas was classified by a similar surrogate majority classifier. The demonstration results in Southern California showed that the land-cover temporal pattern captured the observed successional stages of the ecosystem very well. The accuracy assessment had an overall classification accuracies ranging from 81% to 86% and overall kappa coefficients ranging from 0.79 to 0.83.     

TM classification using local spectral variability

A classification method which takes into account not only spectral but also spatial features for LANDSAT‐4 and 5 Thematic Mapper (TM) data is proposed. In accordance with improvement of Instantaneous Field of View (IFOV), spatial information such as textural, contextual, etc. is also increased so that some treatments of such information is highly required. One of the simplest spatial features is local spectral variability such as standard deviation, variability constant, variance, etc. in small cells such as 2x2,3x3 pixels. Such information can be used together with conventional spectral features in an unified way, for the traditional classifier such as a pixel‐wise Maximum Likelihood Decision Rule (MLDR). From the experiments, there was a substantial improvement in overall classification accuracy for TM forestry data. The probability of correct classification (PCC) for the new clearcut and the alpine meadow classes increased by 7% to 97% correct. The confusion between alpine meadow and new clearcut was reduced from 9% to 3%.     

遥感影像决策级融合方法实验研究

遥感影像融合是遥感图像处理中的研究热点和难点之一。对下列两种遥感影像决策级融合方法进行了实验研究:一种是基于支持向量机(SVM),另一种是基于自组织神经网络。融合实验分别采用这两种方法对Landsat TM多光谱数据(30 m/像素)与IRS-C全色数据(5.8 m/像素)间分别进行影像融合。融合结果表明:基于SVM的方法可有效地融合不同影像的信息,并且可获得较高的融合分类精度。在分类精度方面,基于SVM方法的融合影像明显优于基于自组织神经网络方法的融合影像。