基于对地抽样总量控制下的玉米种植面积提取

提出了一种基于统计抽样总量控制下的中高分辨率遥感影像玉米种植面积信息提取方法, 该方法首先利用分层抽样技术对调查目标总体(玉米)进行分层抽样;然后对抽样小区进行目视解译, 反推区域总量真值;最后在总量控制下进行区域目标作物的空间分布提取。以河北省三河市中部地区的部分影像为研究区, 以该区2006-08-21的10m分辨率的SPOT 5多光谱影像为基础数据进行了试验研究。结果表明该方法基于群样本检验的总体精度达到93.8%, Kappa系数达到0.88, 均高于最大似然监督分类结果的精度。另外, 所提出的方     

The Nature and Classification of Unlabelled Neurons in the Use of Kohonen's Self-Organizing Map for Supervised Classification

Kohonen's Self‐Organizing Map is a neural network procedure in which a layer of neurons is initialized with random weights, and subsequently organized by inspection of the data to be analyzed. The organization procedure uses progressive adjustment of weights based on data characteristics and lateral interaction such that neurons with similar weights will tend to spatially cluster in the neuron layer. When the SOM is associated with a supervised classification, a majority voting technique is usually used to associate these neurons with training data classes. This technique, however, cannot guarantee that every neuron in the output layer will be labelled, and thus causes unclassified pixels in the final map. This problem is similar to but fundamentally different from the problem of dead units that arises in unsupervised SOM classification (neurons which are never organized by the input data). In this paper we specifically address the problem and nature of unlabelled neurons in the use of SOM for supervised classification. Through a case study it is shown that unlabelled neurons are associated with unknown image classes and, most particularly, mixed pixels. It is also shown that an auxiliary algorithm proposed here for assigning classes to unlabelled neurons performs with the same success as that experienced with Maximum Likelihood.     

Satellite remote sensing of forest type and landcover in the subalpine forest region,Kananaskis Valley,Alberta

Landsat Thematic Mapper (TM) imagery and a digital elevation model (DEM) of the Kananaskis Valley in southwestern Alberta have been used to separate three forest types and eight landcover classes with mapping accuracies up to 76% overall. Image transformations based on a principal components analysis (PCA) were used to distinguish vegetation type and separate surface features in visual interpretations, and to reduce the 10 channel data set (TM 1–7, elevation, slope and incidence) to a more manageable 7 channel data set (PCA 1–4, elevation, slope and incidence). The DEM was shown to be critical in providing explanation of surface cover variability even though the original model was produced from medium scale aerial photography on a relatively coarse 100 metre grid. Discrimination increased up to 50% for pure stands of Lodgepole Pine (Pinus contorta Dougl.) and Englemann Spruce (Picea englemanii Parry) based on analysis of 100 pixels in test areas. Overall increases in map accuracy were between 2 and 11%. Success at this level of classification is required prior to detailed ecological study and modelling of mountain vegetation productivity at the community level using current satellite and aerial remote sensing technology.     

Influence of sample size on line-based positional assessment methods for road data

Sample size influences considerably the variability of results of estimation processes, but this issue has never previously been analyzed for line-based positional assessment methods. The basis of the analysis is a simulation process which extracts homologous road axes from the product and from the control survey and applies the four methods. Sample sizes of road axes range from 10 Km up to 200 Km, and for each sample size 1000 simulations were run. Results for each sample size were compared to population parameters or population distribution functions by means of statistical tests. The variability of estimations was reduced in the order of 2.5-4.5 times when sample size increased from 10 Km to 200 Km.     

观测数据采样化的遥感影像非监督分割

为了实现影像的自动化分割,提出一种利用非监督方式将观测数据采样化的遥感影像分割方法。该方法利用欧氏空间的概率分布建模采样数据和观测数据,并将其映射到黎曼空间,通过不断将观测数据转换为采样数据的方式实现影像的自动采样化。每次采样过程只需计算观测数据点到采样点的测地线距离,将距采样点测地线距离最小的观测数据转化为采样数据,以保证采样数据不断趋于该类数据的真实分割结果,同时使算法能够有效分割具有不同像素数的类别。将算法应用于模拟影像和真实遥感影像分割,对其分割结果以及传统基于统计、基于模糊的非监督算法和基于神经网络的监督算法相应分割结果定性定量的对比分析验证了该算法的有效性及可行性。     

Evaluation and analysis of training sets and training statistics of multispectral scanner data related to agricultural crop cover types

The size and reliability of the training sets or sample area for the classification of airborne multispectral scanner data obtained over an agricultural area with the help of an interactive computer system have been examined in this study. The experiment reported herein suggests that a training set of not less than 50 pixels would adequately represent all the likely variations in any particular field. The evaluation of the results further reveals that if the training sets can adequately represent the field variations characteristic of the region, the corresponding training statistics can be utilized both on scanline and pixel directions.     

A novel approach to optimize hierarchical vegetation mapping from hyper-temporal NDVI imagery,demonstrated at national level for Namibia

This paper presents a novel methodological approach to countrywide vegetation mapping. We used green vegetation biomass over the year as captured by coarse resolution hyper-temporal NDVI satellite-imagery, to generate vegetation mapping units at the biome, ecoregion and at the next lower hierarchical level for Namibia, excluding the Zambezi Region. Our method was based on a time series of 15 years of SPOT-VGT-MVC images each representing a specific 10-day period (dekad). The ISODATA unsupervised clustering technique was used to separately create 2–100 NDVI-cluster maps. The optimal number of temporal NDVI-clusters to represent the information on vegetation contained in the imagery was established by divergence separability statistics of all generated NDVI-clusters. The selected map consisted of legend of 81 cluster-specific temporal NDVI-profiles covering each a 15-year period of averaged NDVI data representing all pixels classified to that cluster. Then, by legend-entry using the dekad-medians of all 15 annual repeats, we produced generalized legend-entries without year-specific anomalies for each cluster. Subsequently, a hierarchical cluster analysis of these temporal NDVI-profiles was used to produce a dendrogram that generated grouping options for the 81 legend-entries. Maps with cluster-groups of 8 and 4 legend-entries resulted. The 81-cluster map and its 65 legend-entries vector version have no equivalent in published vegetation maps. The 8 cluster-group map broadly corresponds with published ecoregion level maps and the 4 cluster-group map with the published biome maps in their number of legend units. The published vegetation maps varied considerably from our NDVI-profile maps in the location of mapping unit boundaries. The agreement index between our map and published biome maps ranges from 70−93. For the ecoregion level, the agreement index is much lower, namely 51−75. Our methodological approach showed a considerably higher discretionary power for hierarchical levels and the number of vegetation mapping units than the approaches applied to previously published maps. We recommended an approach to transform our three hyper-temporal NDVI-profiles based legend-entries into more specific vegetation units. This might be accomplished by re-analysis of available, spatially-comprehensive plant species occurrence data.     

Evaluation of different topographic correction methods for Landsat imagery

The recent free availability of Landsat historical data provides new potentials for land-cover change studies. Multi-temporal studies require a previous radiometric and geometric homogenization of input images, to better identify true changes. Topographic normalization is one of the key steps to create consistent and radiometricly stable multi-temporal time series, since terrain shadows change throughout time. This paper aims to evaluate different methods for topographic correction of Landsat TM-ETM+ data. They were assessed for 15 ETM+ images taken under different illumination conditions, using two criteria: (a) reduction of the standard deviation (SD) for different land-covers and (b) increase in temporal stability of a time series for individual pixels. We observed that results improve when land-cover classes where processed independently when applying the more advanced correction algorithms such as the C-correction and the Minnaert correction. Best results were obtaining for the C-correction and the empiric–statistic correction. Decreases of the SD for bare soil pixels were larger than 100% for the C-correction and the empiric–statistic correction method compared to the other correction methods in the visible spectrum and larger than 50% in the IR region. In almost all tests the empiric–statistic method provided better results than the C-correction. When analyzing the multi-temporal stability, pixels under bad illumination conditions (northern orientation) improved after correction, while a deterioration was observed for pixels under good illumination conditions (southern orientation). Taken this observation into account, a simple but robust method for topographic correction of Landsat imagery is proposed.     

高光谱遥感影像SVM分类中训练样本选择的研究

支持向量机(SVM)分类的关键是发现分类最优超平面及类别间隔,而混合像元比纯净像元更接近类别边界,更容易找出最优超平面。本文针对SVM分类器的特点,在高光谱数据分类中采用混合像元作为训练样本对SVM进行训练,试验表明采用类别边界上的混合像元作为训练样本是可行的,能够获得与纯净训练样本接近的分类精度,进一步验证了SVM分类对训练样本空间分布依赖度较低的特点。     

Development of a 1-km landcover dataset of China using AVHRR data

This paper describes the development of a 1-km landcover dataset of China by using monthly NDVI data spanning April 1992 through March 1993. The method used combined unsupervised and supervised classification of NDVI data from AVHRR. It is composed of five steps: (a) unsupervised clustering of monthly AVHRR NDVI maximum value composites is performed using the ISOCLASS algorithm; (b) preliminary identification is carried out with the addition of digital elevation models, eco-region data and a collection of other landcover/vegetation reference data to identify the clusters with single landcover classes; (c) re-clustering is performed of clusters with size greater than a given threshold value and containing two or more disparate landcover classes; (d) cluster combining is performed to combine all clusters with a single landcover class in one cluster, and all other clusters into one mixed cluster; and (e) supervised classification is used to carry out post-classification of the mixed cluster generated in the previous step by using the maximum likelihood algorithm and the identified single landcover classes of the previous step as training data. The classification is based on extensive use of computer-assisted image processing and tools, as well as the skills of the human interpreter to take the final decisions regarding the relationship between spectral classes defined using unsupervised methods and landscape characteristics that are used to define landcover classes.     

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.     

A Multispectral Remote Sensing Data Spectral Unmixing Algorithm Based on Variational Bayesian ICA

Mixed pixel is a key issue in medium to coarse resolution remote sensing image, and it seriously restricts the remote sensing classification. This paper presents an Independent component analysis (ICA) algorithm based on the variational Bayesian (VB) methods, named VBICA, for spectral unmixing in multispectral remote sensing image. The model assumes that the mixed pixels to be separated are given as linear mixtures. The matrixes of linear mixtures are assumed to be unknown. In the Bayesian framework, the endmember and abundance have finally been achieved with Bayesian inference and approximate variational algorithm. The proposed method is evaluated and tested on a numerical simulative image from the noise resistance, area size, pixel purity, estimated number of endmembers and real multispectral remote sensing image of 100?×?100 pixels. Experimental results on simulated image demonstrated that compared to the Fast ICA algorithm, the proposed algorithm can give more accurate results, and the validity of the proposed algorithm is verified by the real multispectral remote sensing image of the similarity on spectral curves, average similarity and ground objects distribution maps.     

基于单邻点多波段预测的高光谱图像无损压缩算法

提出了一种基于聚类-单邻点、多波段预测-熵编码的高光谱数据无损压缩方法。根据谱向特征,进行高光谱图像矢量聚类。对各个分类,采用单个空间位置邻点、多个波段作为预测数据,训练预测系数,进行三维预测。残差采用Golomb-Rice编码。实验证实了算法的有效性。     

遥感数据监督分类中训练样本的纯化

本文分析了训练样本对遥感数据监督分类结果的影响,提出了训练样本纯化的理论与方法,即根据样本像元的光谱和空间信息来剔除训练样本中不合要求的样本像元。一个例子的试验研究表明,训练样本纯化后,各类型间的发散度、样本像元的概率密度函数与高斯分布的拟合度以及分类结果的精度都得到不同程度提高。     

高光谱亚像元定位的线特征探测法

未考虑地物亚像元级空间结构特征是影响高光谱亚像元定位精度的因素之一。为了有效解决这一问题,本文提出一种基于混合像元线特征探测的亚像元定位算法。首先,通过光谱解混确定含典型线状地物的混合像元。然后,基于完备直线集的最大线性指数方法确定其余含线特征的混合像元,使用模板匹配方法结合像元引力确定含线特征混合像元的亚像元类别。最后,基于线性优化的方法迭代确定剩余混合像元的亚像元类别。通过真实数据及仿真数据的试验,结果表明所提出的方法能有效提高亚像元定位精度。     

Urban Shadow Detection and Classification Using Hyperspectral Image

Shadow is an inevitable problem in high-resolution remote sensing images. There are need and significance in extracting information from shadow-covered areas, such as in land-cover mapping. Although the illumination energy of shadow pixels is low, hyperspectral image can provides rich enough band information to differentiate various urban targets/materials and to classify them. This study firstly analyzes the spectra difference between shadow and non-shadow classes so as to detect shadow-pixel. To classify the shadow pixels, Spectral Angle Mapper (SAM) method was adopted to classify urban land-cover mapping, because it can reduce the influence resulted from different illumination intensity. Then, training samples were collected among different classes from the shadow pixels, and their Jeffries–Matusita (J–M) distance were computed to validate the spectral separability among classes, with the square distances of J–M among classes all bigger than 1.9. Finally, Maximum Likelihood Classifier (MLC) and Support Vector Machine (SVM) classifier were used to classify all the shadow pixels as different land-cover types. The results showed MLC and SVM outperform the SAM in classifying similar classes. The classification result in SVM was validated to find having conformity with ground truth.     

Mapping the Spatial and Temporal Pattern of Day-Night Temperature Difference in Greece from MODIS Imagery

The regional temporal and spatial multi-temporal land surface temperature (LST) MODIS dataset and elevation data are used to compute the day and night temperature variation in Greece in 2008. Clustering was applied and eight cluster centroids captured the temporal pattern of near-diurnal temperature (01:30 a.m. and 01:30 p.m.) variability while elevation statistics were computed per cluster. The spatial distribution of the clusters indicate that mean elevation, elevation variability, proximity to the sea, and the major inland water bodies were the key factors controlling the near-diurnal LST variability in Greece.     

基于Freeman散射熵和各向异性度的极化SAR影像分类算法研究

极化SAR影像中阴影、水体和裸露的耕地3种地物类型有非常相似的极化散射特性,常规基于非相干分解的分类方法难以将其有效地区分。对此,本文引入基于Freeman分解的散射熵Hf和各向异性度Af两个特征参数,并将其用于极化SAR影像分类。首先利用Hf和Af参数将阴影和水体提取出来,然后将其他地物按散射机制分为3大类,并对每一类再次利用Hf和Af参数进行细分,最后通过基于Wishart分布的聚类和迭代分类,得到最终的分类结果。通过利用Radarsat-2在河南登封获取的全极化SAR数据进行试验,表明该算法执行效率高,能够有效地区分阴影、水体和裸露的耕地,并且对其他地物类型也有很好的分类效果。     

数码相机实施摄像测量的几个问题

提出像方几何量均取像素为单位处理，以直接使用现有摄影测量程序并使检校过程简化，给出α值的检校要求关系式，罗列主距的锁定方式，总结数码相机所摄影像的多种处理方法并充分利用数码相机功能。     

Mapping the heterogeneity of natural and semi-natural landscapes

Natural and semi-natural landscape cover is heterogeneous. Ideally, mapping land cover requires an approach that represents both gradients and land covers spatiotemporal variability. These aspects can be visualized and depicted by applying a new spatio-temporal analysis based Landscape Heterogeneity Mapping (LaHMa) method to natural and semi-natural landscapes. Using MODIS NDVI 16-day imagery (February 2000–July 2009) for Crete, a 65-cluster image was selected from ISODATA classification results using the separability values of the divergence statistics. The 65 clusters appropriately generalize the spatial and temporal variability in land cover. Using classified outputs from 10 to 65 clusters, the frequency of pixels identified as boundaries of homogeneous land cover classes was translated into the form of a landscape heterogeneity map, which was then validated using field data. The results show that the heterogeneity map had moderate correlation (R² = 0.60 and 0.63 in two transects) with the sum of differences between neighbouring transect pixels in all land cover components. In general, the study found this new approach (LaHMa) to be suitable for mapping landscape heterogeneity in the natural and semi-natural landscape of Crete, Greece. The new method appears to be of potential use for informing gradient analyses in landscape ecological studies.