多波段遥感数据的自组织神经网络降维分类研究

介绍了基于聚类分析的自组织特征映射神经网络分类方法，神经网络的输出层结构选用了3D结构，可以更好地保持多波段遥感数据中的内在拓扑结构；并选择天津大港地区的AsTER数据中的9个波段作为试验数据，通过对验证点的统计，分类精度达到了94％以上。     

Kohonen神经网络在遥感影像分类中的应用研究

根据Kohonen网的生物学基础 ,基本结构和学习算法 ,提出了解决遥感影像分类的途径。依据实验区土地利用类别的光谱特征 ,采用主成分分析对遥感影像进行预处理 ,结合地理辅助数据的量化输入训练出Kohonen自组织图后对融合有地理辅助数据的影像进行土地利用分类 ,并与BP网和最大似然法分类结果进行分析比较。结果表明 ,地理辅助数据的参与对提高Kohonen网影像分类精度具有意义     

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。     

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     

基于TM影像的南京市土地利用遥感动态监测

基于南京市1988年和1998年两期TM影像，首先用辐射水准归一化法将1998年影像校正到1988年影像的辐射水平上，再经过几何校正、训练区纯化等预处理，对两期影像分别用最大似然法进行分类，然后在Arc／Info的GRID模块中编写AML语言，对得到的两期土地利用分类图进行叠置运算，提取出土地利用动态变化信息。分析结果表明，10a间南京市耕地面积大量减少，林地面积有所增加。     

Linking land cover dynamics with driving forces in mountain landscape of the Northwestern Iberian Peninsula

The mountainous areas of the northwestern Iberian Peninsula have undergone intense land abandonment. In this work, we wanted to determine if the abandonment of the rural areas was the main driver of landscape dynamics in Gerês–Xurés Transboundary Biosphere Reserve (NW Iberian Peninsula), or if other factors, such as wildfires and the land management were also directly affecting these spatio-temporal dynamics. For this purpose, we used earth observation data acquired from Landsat TM and ETM + satellite sensors, complemented by ancillary data and prior field knowledge, to evaluate the land use/land cover changes in our study region over a 10-year period (2000–2010). The images were radiometrically calibrated using a digital elevation model to avoid cast- and self-shadows and different illumination effects caused by the intense topographic variations in the study area. We applied a maximum likelihood classifier, as well as other five approaches that provided insights into the comparison of thematic maps. To describe the land cover changes we addressed the analysis from a multilevel approach in three areas with different regimes of environmental protection. The possible impact of wildfires was assessed from statistical and spatially explicit fire data. Our findings suggest that land abandonment and forestry activities are the main factors causing the changes in landscape patterns. Specifically, we found a strong decrease of the ‘meadows and crops’ and ‘sparse vegetation areas’ in favor of woodlands and scrublands. In addition, the huge impact of wildfires on the Portuguese side have generated new ‘rocky areas’, while on the Spanish side its impact does not seem to have been a decisive factor on the landscape dynamics in recent years. We conclude rural exodus of the last century, differences in land management and fire suppression policies between the two countries and the different protection schemes could partly explain the different patterns of changes recorded in these covers.     

Toward accountable land use mapping: Using geocomputation to improve classification accuracy and reveal uncertainty

The classification of satellite imagery into land use/cover maps is a major challenge in the field of remote sensing. This research aimed at improving the classification accuracy while also revealing uncertain areas by employing a geocomputational approach. We computed numerous land use maps by considering both image texture and band ratio information in the classification procedure. For each land use class, those classifications with the highest class-accuracy were selected and combined into class-probability maps. By selecting the land use class with highest probability for each pixel, we created a hard classification. We stored the corresponding class probabilities in a separate map, indicating the spatial uncertainty in the hard classification. By combining the uncertainty map and the hard classification we created a probability-based land use map, containing spatial estimates of the uncertainty. The technique was tested for both ASTER and Landsat 5 satellite imagery of Gorizia, Italy, and resulted in a 34% and 31% increase, respectively, in the kappa coefficient of classification accuracy. We believe that geocomputational classification methods can be used generally to improve land use and land cover classification from imagery, and to help incorporate classification uncertainty into the resultant map themes.     

结合多分类器的遥感数据专题分类方法研究

采用标准的多分类器结合方法进行遥感图像的分类研究。首先介绍了标准的多分类器结合的算法,然后以Landsat-TM多光谱遥感数据的土地覆被分类为例,分别给出了抽象级上相同训练特征的多分类器结合、抽象级上不同训练特征的多分类器结合和测量级上的多分类器结合进行土地覆被分类的方法,并进行了实例研究。参与分类器结合的单个分类器包括最大似然分类器,最小距离分类器,马氏距离分类器,K-NN分类器,多层感知器神经网络分类器。分类器的分类精度用总体精度、用户精度、生产者精度、kappa系数和条件kappa系数评价。结果表明,每一种多分类器结合的分类方法都能够比较显著地提高总体分类精度。文章最后对不同多分类器结合方式的优缺点进行了分析。     

A Comparison of Multisensor Integration Methods for Land Cover Classification in the Brazilian Amazon

Many data fusion methods are available, but it is poorly understood which fusion method is suitable for integrating Landsat Thematic Mapper (TM) and radar data for land cover classification. This research explores the integration of Landsat TM and radar images (i.e., ALOS PALSAR L-band and RADARSAT-2 C-band) for land cover classification in a moist tropical region of the Brazilian Amazon. Different data fusion methods—principal component analysis (PCA), wavelet-merging technique (Wavelet), high-pass filter resolution-merging (HPF), and normalized multiplication (NMM)—were explored. Land cover classification was conducted with maximum likelihood classification based on different scenarios. This research indicates that individual radar data yield much poorer land cover classifications than TM data, and PALSAR L-band data perform relatively better than RADARSAT-2 C-band data. Compared to the TM data, the Wavelet multisensor fusion improved overall classification by 3.3%-5.7%, HPF performed similarly, but PCA and NMM reduced overall classification accuracy by 5.1%-6.1% and 7.6%-12.7%, respectively. Different polarization options, such as HH and HV, work similarly when used in data fusion. This research underscores the importance of selecting a suitable data fusion method that can preserve spectral fidelity while improving spatial resolution.     

A methodology for semi detailed soil surveys using medium scale aerial photographs

A methodology for the preparation of semi detailed soil maps using medium scale aerial photographs for an area of about 3600 ha in Merida area, Spain is presented. The new concepts such as ‘Basic Land Units’, ‘Soil Consociation’ and ‘Soil Set’ developed by Elbersen (1976) were adopted for this study to see their utility for the preparation of semidetailed soil maps which can be used for land evaluation, land classification and also for making prodictions about the feasibility of a particular project for rural development plannning purposes. Basic land units and their subdivisions like major and minor compo-nents were used for the delineation of interpretation units. Mapping units, viz, Soil Consoication, Soil Complex and miscellaneous land type were used for mapping soils. Soils were classified upto family level and shown as subgroups in the 1:50,000 scale soil map. Soils were mapped as soil sets per basic land unit per subgroup. A model legend for use in the preparation of seimdetailed physiographic cum soil maps is given which is in terms of physiography and Soil Taxonomy qualified by soil sets.     

A kernel functions analysis for support vector machines for land cover classification

Information about the Earth's surface is required in many wide-scale applications. Land cover/use classification using remotely sensed images is one of the most common applications in remote sensing, and many algorithms have been developed and applied for this purpose in the literature. Support vector machines (SVMs) are a group of supervised classification algorithms that have been recently used in the remote sensing field. The classification accuracy produced by SVMs may show variation depending on the choice of the kernel function and its parameters. In this study, SVMs were used for land cover classification of Gebze district of Turkey using Landsat ETM+ and Terra ASTER images. Polynomial and radial basis kernel functions with their estimated optimum parameters were applied for the classification of the data sets and the results were analyzed thoroughly. Results showed that SVMs, especially with the use of radial basis function kernel, outperform the maximum likelihood classifier in terms of overall and individual class accuracies. Some important findings were also obtained concerning the changes in land use/cover in the study area. This study verifies the effectiveness and robustness of SVMs in the classification of remotely sensed images.     

Texture classification of Mediterranean land cover

Maximum likelihood (ML) and artificial neural network (ANN) classifiers were applied to three Landsat Thematic Mapper (TM) image sub-scenes (termed urban, agricultural and semi-natural) of Cukurova, Turkey. Inputs to the classifications comprised (i) spectral data and (ii) spectral data in combination with texture measures derived on a per-pixel basis. The texture measures used were: the standard deviation and variance and statistics derived from the co-occurrence matrix and the variogram. The addition of texture measures increased classification accuracy for the urban sub-scene but decreased classification accuracy for agricultural and semi-natural sub-scenes. Classification accuracy was dependent on the nature of the spatial variation in the image sub-scene and, in particular, the relation between the frequency of spatial variation and the spatial resolution of the imagery. For Mediterranean land, texture classification applied to Landsat TM imagery may be appropriate for the classification of urban areas only.     

对ASTER GDEM数字高程模型的精度评价及修正

针对ASTER GDEM高程精度还未得到充分验证,以江西省莲花县为试验区,使用ICESat-2数据系统分析了ASTER GDEM在坡度、地形起伏度和土地利用类型中的误差分布。结果表明,ASTER GDEM受坡度、地形起伏度影响严重,随坡度、地形起伏度增加,GDEM误差呈上升趋势;对于不同土地利用类型,GDEM误差存在较大差异,在水域误差最大,在建设用地误差最小。最后,使用后向传播神经网络(BPNN)对莲花县ASTER GDEM修正,结果发现BPNN模型可以有效改善其高程精度。     

基于遥感影像数据的土地利用动态监测

以松原地区TM影像为实验数据,利用遥感分类软件通过最大似然法作为平行六面体判别规则对遥感影像数据进行监督分类,并通过遥感影像地图代数和拓扑运算,完成了土地动态监测过程.     

Approaches for delineating landslide hazard areas using different training sites in an advanced artificial neural network model

The current paper presents landslide hazard analysis around the Cameron area, Malaysia, using advanced artificial neural networks with the help of Geographic Information System (GIS) and remote sensing techniques. Landslide locations were determined in the study area by interpretation of aerial photographs and from field investigations. Topographical and geological data as well as satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten factors were selected for landslide hazard including: 1) factors related to topography as slope, aspect, and curvature; 2) factors related to geology as lithology and distance from lineament; 3) factors related to drainage as distance from drainage; and 4) factors extracted from TM satellite images as land cover and the vegetation index value. An advanced artificial neural network model has been used to analyze these factors in order to establish the landslide hazard map. The back-propagation training method has been used for the selection of the five different random training sites in order to calculate the factor’s weight and then the landslide hazard indices were computed for each of the five hazard maps. Finally, the landslide hazard maps (five cases) were prepared using GIS tools. Results of the landslides hazard maps have been verified using landslide test locations that were not used during the training phase of the neural network. Our findings of verification results show an accuracy of 69%, 75%, 70%, 83% and 86% for training sites 1, 2, 3, 4 and 5 respectively. GIS data was used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool for landslide hazard analysis. The verification results showed sufficient agreement between the presumptive hazard map and the existing data on landslide areas.     

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。     

Burned area mapping and post-fire impact assessment in the Kassandra peninsula (Greece) using Landsat TM and Quickbird data

The purpose of this study was to assess the environmental impacts of forest fires on part of the Mediterranean basin. The study area is on the Kassandra peninsula, prefecture of Halkidiki, Greece. A maximum likelihood supervised classification was applied to a post-fire Landsat TM image for mapping the exact burned area. Land-cover types that had been affected by fire were identified with the aid of a CORINE land-cover type layer. Results showed an overall classification accuracy of 95%, and 83% of the total burned area was ‘forest areas’. A normalized difference vegetation index threshold technique was applied to a post-fire Quickbird image which had been recorded six years after the fire event to assess the vegetation recovery and to identify the vegetation species that were dominant in burned areas. Four classes were identified: ‘bare soil’, ‘sparse shrubs’, ‘dense shrubs’ and ‘tree and shrub communities’. Results showed that ‘shrublands’ is the main vegetation type which has prevailed (65%) and that vegetation recovery is homogeneous in burned areas.     

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.     

北京城市地表温度的遥感时空分析

运用Landsat TM/ETM+和Terra ASTER数据,对北京市1990~2007年夏季的地表温度进行了反演,并对地表温度的空间分布、时间变化作出了分析。对Landsat TM/ETM+数据的温度反演采用了普适性单波段算法,ASTER数据的温度反演采用了劈窗算法。通过对地表温度数据的直方图均衡处理以及综合对比分析,总结出北京地区历年来夏季地表温度的空间分布格局及该格局随北京城市发展的变化规律,分析了研究成果的不足,提出了下一步要努力的方向。     

一个用神经网络优化的针对ASTER数据反演地表温度和发射率的多波段算法

提出了针对ASTER数据同时反演地表温度和发射率的多波段算法。即利用ASTER数据的第11~14热红外波段建立热辐射传输方程，并同时对相应波段的发射率建立近似线性方程，得到6个方程6个未知数，从而形成了针对ASTER数据的同时反演地表温度和发射率的多通道算法。利用3种方法求解方程： ①先分类，然后进行数学计算； ②利用最小二乘法； ③利用神经网络方法。利用辐射传输模型MODTRAN 4模拟数据进行反演及验证分析，结果表明，神经网络能够提高算法的精度和实用性，反演的地表温度平均误差为0.5 ℃，反演的发射率平均误差分别在0.007(11、12波段)和0.006(13、14波段)以下。