Integration of multitemporal/polarization C‐band SAR data sets for land‐cover classification

This paper investigates the potential of multitemporal/polarization C‐band SAR data for land‐cover classification. Multitemporal Radarsat‐1 data with HH polarization and ENVISAT ASAR data with VV polarization acquired in the Yedang plain, Korea are used for the classification of typical five land‐cover classes in an agricultural area. The presented methodologies consist of two analytical stages: one for feature extraction and the other for classification based on the combination of features. Both a traditional SAR signal property analysis‐based approach and principal‐component analysis (PCA) are applied in the feature extraction stage. Special concerns are in the interpretation of each principal component by using principal‐component loading. The tau model applied as a decision‐level fusion methodology can provide a formal framework in which the posteriori probabilities derived from different sensor data can be combined. From the case study results, the combination of PCA‐based features showed improved classification accuracy for both Radarsat‐1 and ENVISAT ASAR data, as compared with the traditional SAR signal property analysis‐based approach. The integration of PCA‐based features based on multiple polarization (i.e. HH from Radarsat‐1, and both VV and VH from ENVISAT ASAR) and different incidence angles contributed to a significant improvement of discrimination capability for dry fields which could not be properly classified by using only Radarsat‐1 or ENVISAT ASAR data, and thus showed the best classification accuracy. The results of this case study indicate that the use of multiple polarization SAR data with a proper feature extraction stage would improve classification accuracy in multitemporal SAR data classification, although further consideration should be given to the polarization and incidence angle dependency of complex land‐cover classes through more experiments.     

一种稳健的多时相遥感图像相对辐射校正方法

变化检测是通过分析多时相遥感图像实现土地利用动态监视的一种有效方法，但在变化检测 分析前，需要经过辐射校正消除光照等因素对地物光谱辐射的影响，使同一地物在不同时相 影像中具有相同的辐射量。根据地物在不同时相遥感图像中的光谱特性满足线性关系的 特点，提出一种自动实现多时遥感图像相对辐射校正的稳健方法，首先通过最小差分回归找 出非变化地物在多时相遥感图像中的辐射关系 |然后利用变化区域证实过程消除变化区域对 辐射校正处理的影响 |最后通过循环迭代实现图像间的辐射校正。提出的方法不仅可以自动 地实现多时相遥感图像的相对辐射校正，而且能够保证图像的辐射分辨率不会因为辐射校正而降低。     

Land cover discrimination potential of radar multitemporal series and optical multispectral images in a Mediterranean cultural landscape

The aim of the present study is (1) to evaluate the performances of two series of European Remote Sensing (ERS) Synthetic Aperture Radar (SAR) images for land cover classification of a Mediterranean landscape (Minorca, Spain), compared with multispectral information from Système Pour l'Observation de la Terre (SPOT) and Landsat Thematic Mapper (TM) sensors, and (2) to test the synergy of SAR and optical data with a fusion method based on the Demspter–Shafer evidence theory, which is designed to deal with imprecise information. We have evaluated as a first step the contribution of multitemporal ERS data and contextual methods of classification, with and without filtering, for the discrimination of vegetation types. The present study shows the importance of time series of the ERS sensor and of the vectorial MMSE (minimum mean square error) filter based on segmentation for land cover classification. Fifteen land cover classes were discriminated (eight concerning different vegetation types) with a mean producer's accuracy of 0.81 for a five-date time series within 1998, and of 0.71 for another four-date time series for 1994/1995. These results are comparable to those from SPOT XS images: 0.69 for July, 0.67 for October (0.85 for July plus October), and also from TM data (0.81). These results are corroborated by the kappa coefficient of agreement. The fusion between the 1994 series of ERS and XS (July), based on a derived method of the Dempster–Shafer evidence theory, shows a slight improvement on overall accuracies: +0.06 of mean producer's accuracy and +0.04 of kappa coefficient.     

A two-level Markov random field for road network extraction and its application with optical,SAR, and multitemporal data

This article introduces a method for road network extraction from satellite images. The proposed approach covers a new fusion method (using data from multiple sources) and a new Markov random field (MRF) defined on connected components along with a multilevel application (two-level MRF). Our method allows the detection of roads with different characteristics and decreases by around 30% the size of the used graph model. Results for synthetic aperture radar (SAR) images and optical images obtained using the TerraSAR-X and Quickbird sensors, respectively, are presented demonstrating the improvement brought by the proposed approach. In a second part, an analysis of different types of data fusion combining optical/radar images, radar/radar images, and multitemporal SAR (TerraSAR-X and COSMO-SkyMed) images is described. The qualitative and quantitative results show that the fusion approach improves considerably the results of the road network extraction.     

Land cover discrimination from multitemporal ERS images and multispectral Landsat images: A study case in an agricultural area in France

More and more remote sensing data corresponding to various wavelength domains is becoming available. Visible/infrared data were first used for land cover classification. However, radar data are becoming more widely used for hydrological and agricultural applications. This paper discusses the performance, for land cover type discrimination, of an optical image acquisition and a multitemporal radar series. For the majority of land cover types existing within the test site (representative of northern European agricultural areas), both ERS multitemporal SAR and Landsat multispectral visible/infrared classifications lead to good results, with the latter being more robust. For better identification of cultures that are less represented, the complementarity of the two datasets may be exploited using an efficient data fusion algorithm based on the Dempster-Shafer evidence theory. The performance of this combination was verified on two successive vegetation cycles.     

A comparison of fuzzy and neuro-fuzzy data fusion for flooded area mapping using SAR images

A comparison of change detection approaches for flooded area mapping using Synthetic Aperture Radar (SAR) images is provided. The aim was to assess the usefulness of fuzzy and neuro-fuzzy techniques for classification of SAR data. The work addresses both options of data-level fusion and decision-level fusion. The former is realized with multitemporal fuzzy or neural classification and the latter by combining classifications or fuzzy memberships for the pre- and post-event images. Highest overall accuracy values and flooded area accuracy values (90.3% producer's, 71.9% user's) were obtained from the neuro-fuzzy approach.     

Land cover assessment with MODIS imagery in southern African Miombo ecosystems

Global land use and land cover products in highly dynamic tropical ecosystems lack the detail needed for natural resource management and monitoring at the national and provincial level. The MODIS sensor provides improved opportunities to combine multispectral and multitemporal data for land use and land cover mapping. In this paper we compare the MODIS Global Land Cover Classification Product with recent land use and land cover maps at the national level over a characteristic location of Miombo woodlands in the province of Zambezia, Mozambique. The performances of three land cover-mapping approaches were assessed: single-date supervised classification, principal component analysis of band-pair difference images, and multitemporal NDVI analysis. Extensive recent field data were used for the definition of the test sites and accuracy assessment. Encouraging results were achieved with the three approaches. The classification results were refined with the help of a digital elevation model. The most consistent results were achieved using principal component analysis of band-pair difference images. This method provided the most accurate classifications for agriculture, wetlands, grasslands, thicket and open forest. The overall classification accuracy reached 90%. The multitemporal NDVI provided a more accurate classification for the dense forest cover class. The selection of the right image dates proved to be critical for all the cases evaluated. The flexibility of these alternatives makes them promising options for rapid and inexpensive land cover mapping in regions of high environmental variability such as tropical developing countries.     

Multisource ERS-1 and optical data for vegetal cover assessment and monitoring in a semi-arid region of Algeria

This paper highlights advantages of using Synthetic Aperture Radar (SAR) data combined with multispectral data to improve vegetal cover assessment and monitoring in a semi-arid region of southern Algeria. We present a number of preprocessing and processing techniques using multidate optical data analysis alone and SAR ERS-1 and Landsat Thematic Mapper (TM) data integration due to aspects of radar image enhancement techniques and the study of roughness of different types of vegetation in steppic regions. Image data integration has become a valuable approach to integrate multisource satellite data. It has been found that image data from different spectral domains (visible, near-infrared, microwave) provides datasets with complementarity information content and can be used to improve the spatial resolution of satellite images. In this communication, we present a part of the cooperation research project which deals with fusing ERS-1 SAR geocoded images with Landsat TM data, investigating different combinations of integration and classification techniques. The methodology consists of several steps: (1) Speckle noise reduction by comparative performance of different filtering algorithms. Several filtering algorithms were implemented and tested with different window sizes, iterations and parameters. (2) Geometric superposition and geocoding of optical images regarding SAR ERS-1 image and resampling at unique resolution of 25 m. (3) Application of different numerical combinations of integration techniques and unsupervized classifications such as the Forgy method, the MacQueen method and other methods. The results were compared with vegetal cover mapping from aerial photographs of the region of Foum Redad in the south of the Saharian Atlas. The combinations proposed above allow us to distinguish different themes in the arid and semi-arid regions in the south of the Saharian Atlas using a colour composite image and show a good correlation between different types of land cover and land use and radar backscattering level in the SAR data which corresponds essentially to the roughness of the soil surface.     

Multitemporal SAR images for monitoring cultivation systems using case-based reasoning

This paper demonstrates that multitemporal satellite SAR images are most suitable for monitoring the rapid changes of cultivation systems in a subtropical region. A new method is proposed by applying case-based reasoning (CBR) techniques to the classification of SAR images. Stratified sampling is carried out to collect the cases so that the variations of backscatters within a class can be appropriately captured. The use of discrete cases can conveniently represent the internal changes of a class under complicated situations, such as spatial changes in soil conditions and terrain features. These spatial variations are difficult to represent by using rules or mathematical equations. The proposed method has better classification performance than supervised classification methods in the study area. The case library is reusable for time-independent classification when the SAR images are acquired at the same time of the crop growth cycles for different years. The proposed method has been tested in the Pearl River Delta in South China.     

Multitemporal ensemble learning for snow cover extraction from high-spatial-resolution images in mountain areas

ABSTRACT

High-spatial and -temporal resolution snow cover products in mountain areas are important to hydrological applications. The GF-1 satellite provides multispectral images with 8-m resolution and a revisit up to 2 days, which makes it possible to produce snow cover products. However, it is challenging to extract snow cover from these images because of limited spectral bands, severe mountain shadows, and dataset-shift problem in multitemporal classification. To overcome the limitations above, this study proposes a multitemporal ensemble learning framework to extract snow cover from high-spatial-resolution images in mountain areas. The principle behind ensemble learning, i.e. learning from disagreement, is extended from single image classification to multitemporal ones. We assume that multitemporal training samples selected within time-invariant classes at the same locations can be different in feature space. Such disagreements are used in multitemporal ensemble learning to improve classification accuracy. To enhance both accuracy and diversity of the multiple classifiers trained on these samples, a joint feature selection method is suggested to select the optimal multitemporal feature space and a joint parameter optimization method is designed to ensemble classifiers trained for multitemporal images. The experiments show that the performances of multitemporal ensemble classifiers are superior to that of single classifiers, confirming the effectiveness of the proposed framework.     

单极化合成孔径雷达影像在土地利用分类中的潜力分析

从我国土地利用调查应用出发,为了解决我国多云多雨地区土地利用分类及遥感动态监测问题,以面向对象影像分割、分类软件--Definiens Developer作为处理平台,对中分辨率星载合成孔径雷达（SAR）（以ENVISAT ASAR和Radarsat-1为例）、高分辨率星载SAR（以TerraSAR-X为例）进行分类处理,分析了单极化星载中、高分辨率星载SAR在土地利用分类中的能力,并对该模式星载SAR在土地利用分类中的影像特征和可解析程度进行了小结。     

Contribution of multispectral and multitemporal information from MODIS images to land cover classification

The goal of this study is to evaluate the relative usefulness of high spectral and temporal resolutions of MODIS imagery data for land cover classification. In particular, we highlight the individual and combinatorial influence of spectral and temporal components of MODIS reflectance data in land cover classification. Our study relies on an annual time series of twelve MODIS 8-days composited images (MOD09A1) monthly acquired during the year 2000, at a 500 m nominal resolution. As our aim is not to propose an operational classifier directed at thematic mapping based on the most efficient combination of reflectance inputs — which will probably change across geographical regions and with different land cover nomenclatures — we intentionally restrict our experimental framework to continental Portugal. Because our observation data stream contains highly correlated components, we need to rank the temporal and the spectral features according not only to their individual ability at separating the land cover classes, but also to their differential contribution to the existing information. To proceed, we resort to the median Mahalanobis distance as a statistical separability criterion. Once achieved this arrangement, we strive to evaluate, in a classification perspective, the gain obtained when the dimensionality of the input feature space grows. We then successively embedded the prior ranked measures into the multitemporal and multispectral training data set of a Support Vector Machines (SVM) classifier. In this way, we show that, only the inclusion of the approximately first three dates substantially increases the classification accuracy. Moreover, this multitemporal factor has a significant effect when coupled with combinations of few spectral bands, but it turns negligible as soon as the full spectral information is exploited. Regarding the multispectral factor, its beneficence on classification accuracy remains more constant, regardless of the number of dates being used.     

Characterization and classification of South American land cover types using satellite data

Abstract

Various methods are compared for carrying out land cover classifications of South America using multitemporal Advanced Very High Resolution Radiometer data. Fifty-two images of the normalized difference vegetation index (NDVI) from a 1-year period are used to generate multitemporal data sets. Three main approaches to land cover classification are considered, namely the use of the principal components transformed images, the use of a characteristic curves procedure based on N DVI values plotted against time, and finally application of the maximum likelihood rule to multitemporal data sets. Comparison of results from training sites indicates that the last approach yields the most accurate results. Despite the reliance on training site figures for performance assessment, the results are nevertheless extremely encouraging, with accuracies for several cover types exceeding 90 per cent.     

基于ALOS PALSAR数据时相特征的土地覆盖识别

合成孔径雷达遥感具备全天时、全天候的观测能力,是多时相数据获取的有效保证。以福建省漳浦县为研究区,利用ALOS PALSAR双极化数据开展土地覆盖识别研究。首先基于多时相的强度数据构建时相稳定性指数,基于重复轨道干涉数据的相位信息计算相干性,以此分析和描述该地区典型地物的雷达数据时相特征。然后以典型地物的时相特征为基础,构建决策树分类器,进行土地覆盖识别。最后以实地考察数据、ALOS AVNIR\|2影像和Google Earth影像为参考,进行分类结果的精度评价,总体精度达到81.43%,比利用不同时期的后向散射强度图像为输入波段的最大似然法的分类精度(总体精度为63.06%)高出很多。结果表明:在分类中有效融合时相信息,可以充分提高地物的可分性。     

Regional land cover mapping in the humid tropics using combined optical and SAR satellite data—a case study from Central Sulawesi,Indonesia

The frequent mapping of the spatial extent of land cover and its change from satellite data at the regional level provides essential input to spatially explicit land use analysis and scenario modelling. The accuracy of a land cover map is the key factor describing the quality of a map, and hence affecting the results of land use modelling. In tropical regions, land cover mapping from optical satellites is hampered by cloud coverage and thus alternative data sources have to be evaluated. In the present study, data from Landsat‐ETM+ and Envisat‐ASAR satellite sensors were tested for their ability to assess small scaled landscape patterns in a tropical environment. A focus was on the detection of intensively managed perennial and intra‐annual cropping systems (cocoa, rice). The results confirm previous knowledge about the general potential and advantages of multi‐temporal SAR data compared to mono‐temporal SAR‐based mapping but also show the limitations of different polarization modes in SAR analysis for land cover mapping. In the present case study, cross‐polarized data from Envisat‐ASAR did not yield notable profit for tropical land cover mapping compared to common, co‐polarized time series of ASAR data. However, the general outcome of the study underlines the synergy of optical and radar satellite data for land cover mapping in tropical regions.     

Spatial pattern analysis of land cover change trajectories in Tarim Basin,northwest China

This study attempts to develop a methodology to quantify spatial patterns of land cover change using landscape metrics. First, multitemporal land cover types are derived based on a unified land cover classification scheme and from the classification of multitemporal remotely sensed imagery. Categorical land cover change trajectories are then established and reclassified according to the nature and driving forces of the change. Finally, spatial pattern metrics of the land cover change trajectory classes are computed and their relationships to human activities and environmental factors are analysed. A case study in the middle reach of Tarim River in the arid zone of China from 1973 to 2000 shows that during the 30‐year study period, the natural force is dominant in environmental change, although the human impact through altering water resources and surface materials has increased dramatically in recent years. The human‐induced change trajectories generally show lower normalized landscape shape index (NLSI), interspersion and juxtaposition index (IJI) and area‐weighted mean patch fractal dimension (FARC_AM), indicating greater aggregation, less association with others and simpler and larger patches in shape, respectively. The results suggest that spatial pattern metrics of land cover change trajectories can provide a good quantitative measurement for better understanding of the spatio‐temporal pattern of land cover change due to different causes.     

基于条件随机场的多时相遥感影像分类*

多时相遥感影像分类方法通常使用人工设置的转移矩阵作为时间上下文信息,这样不仅难以获得准确的转移矩阵,而且没有充分利用时间上下文信息。针对多时相遥感图像中的时间与空间上下文信息难以构建的问题,提出了一种基于条件随机场模型的多时遥感影像分类方法。首先运用最大期望算法生成用于描述时间上下文信息的时间势能,然后结合空间以及时间上下文信息构造了条件随机场模型,最后使用该模型对多时相遥感影像进行分类。一系列的实验结果表明,该方法可以有效提高遥感影像的分类精度。     

基于多源多时相遥感影像的山地森林分类决策树模型研究

山地是森林重要的分布区,然而山地多样的森林类型、高度异质化的景观格局、突出的地形效应以及云、雾的干扰均不同程度地影响了山地森林类型的遥感自动制图。多源多时相遥感影像提供的季相节律信息是当前提高土地覆被遥感制图精度的重要信息源之一。以岷江上游地区为研究区,以国产环境减灾卫星多光谱CCD(简称HJ CCD)影像和美国Landsat TM影像为数据源,以决策树为分类方法,根据参与分类影像的时相差异设计了5组对比实验(生长季单时相组、非生长季单时相组、生长季多时相组、非生长季多时相组、全时相组),对比论证多源多时相遥感影像对山地森林类型自动制图的贡献和作用。对比结果表明:生长季和非生长季相结合的多时相遥感影像较单时相或单一类型(生长季或非生长季)多时相遥感影像,更能显著提高山地森林类型自动制图精度,且能降低分类决策树的复杂程度,更有利于山地森林类型的自动提取。     

Comparison of atmospheric correction methods using ASTER data for the area of Crete,Greece

The purpose of atmospheric correction is to produce more accurate surface reflectance and to potentially improve the extraction of surface parameters from satellite images. To achieve this goal the influences of the atmosphere, solar illumination, sensor viewing geometry and terrain information have to be taken into account. Although a lot of information from satellite imagery can be extracted without atmospheric correction, the physically based approach offers advantages, especially when dealing with multitemporal data and/or when a comparison of data provided by different sensors is required. The use of atmospheric correction models is limited by the need to supply data related to the condition of the atmosphere at the time of imaging. Such data are not always available and the cost of their collection is considerable, hence atmospheric correction is performed with the use of standard atmospheric profiles. The use of these profiles results in a loss of accuracy. Therefore, site-dependent databases of atmospheric parameters are needed to calibrate and to adjust atmospheric correction methods for local level applications. In this article, the methodology and results of the project Adjustment of Atmospheric Correction Methods for Local Studies: Application in ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) (ATMOSAT) for the area of Crete are presented. ATMOSAT aimed at comparing several atmospheric correction methods for the area of Crete, as well as investigating the effects of atmospheric correction on land cover classification and change detection. Databases of spatio-temporal distributions of all required input parameters (atmospheric humidity, aerosols, spectral signatures, land cover and elevation) were developed and four atmospheric correction methods were applied and compared. The baseline for this comparison is the spatial distribution of surface reflectance, emitted radiance and brightness temperature as derived by ASTER Higher Level Products (HLPs). The comparison showed that a simple image based method, which was adjusted for the study area, provided satisfactory results for visible, near infrared and short-wave infrared spectral areas; therefore it can be used for local level applications. Finally, the effects of atmospheric correction on land cover classification and change detection were assessed using a time series of ASTER multispectral images acquired in 2000, 2002, 2004 and 2006. Results are in agreement with past studies, indicating that for this type of application, where a common radiometric scale is assumed among the multitemporal images, atmospheric correction should be taken into consideration in pre-processing.     

Comparison of multisource image fusion methods and land cover classification

The aim of this study is to explore the performances of different data fusion techniques for the enhancement of urban features and evaluate the features obtained by the fusion techniques in terms of separation of urban land cover classes when multisource images are under consideration. For the data fusion, multiplicative method, Brovey transform, principal component analysis (PCA), Gram–Schmidt fusion, wavelet-based fusion and Elhers fusion are used and the results are compared. Of these methods, the best result is obtained by the use of the optical/synthetic aperture radar (SAR) wavelet-based fusion. The classification methods of multisource images, statistical maximum likelihood classification (MLC) and the knowledge-based method are used and the results are compared. The knowledge-based method is based on a hierarchical rule-based approach and it uses a hierarchy of rules describing different conditions under which the actual classification has to be performed. Overall, the research indicates that multisource information can significantly improve the interpretation and classification of land-cover types and the knowledge-based method is a powerful tool in the production of a reliable land-cover map.