Detection of temporary flooded areas with potential floodwater mosquito production using imaging radar

Temporarily flooded areas can produce enormous numbers of floodwater mosquitoes, causing tremendous nuisance to people living in the vicinity. The aim of this study is to develop a remote-sensing method for detecting temporary flooded areas that can produce floodwater mosquitoes. For this objective, synthetic aperture radar (SAR) imagery from the European Remote Sensing satellite (ERS-2) and the Environmental Satellite (Envisat) are chosen. The images cover both flooded and dry periods around Lake Färnebofjärden, located in the lowlands of the River Dalälven, central Sweden, during the vegetation season between 2000 and 2006. Unsupervised classification and principal component analysis (PCA) are tested as methods for detecting floodwater mosquito production sites. In the unsupervised classification experiment, four types of images are tested. The classification of a synthetic colour image gives the best result with an overall accuracy of 85.7% and a kappa value of 0.7, as well as a 46% detection rate of field-mapped flooded areas. PCA is performed on a data set of 16 time series radar images. The resulting principal component (PC) bands provide information about flooding probability as well as vegetation structures. Regular flooding increases the probability for an area to provide breeding sites for floodwater mosquitoes. Thus, this approach will be very useful in estimating the risk of floodwater mosquito establishment.     

Crop discrimination using multi-temporal SAR imagery

Seven ERS-1 SAR images obtained at different dates during the 1993 crop growing season are used in a study of the potential of multi-temporal SAR for agricultural crop discrimination for an area near Feltwell, Norfolk, UK. The study compares a per-pixel and a per-field approach. Pixel-based classification is based on raw intensity images, temporal subtraction images, filtered images, and texture features. Field-based classification uses the mean back-scatter coefficient derived for each field. Analysis of the contribution of each dataset uses statistical separability measures and confusion matrix methods. The classification algorithms used are maximum likelihood and Kohonen's self-organized feature map (SOM). We find that SAR-based texture features contribute nothing to crop discrimination. Filtered images produce the best result for the per-pixel approach, giving a classification accuracy of around 60%. The use of a SOM for field-based classification produces a classification accuracy greater than 75%. This is not a surprising result, as field-based classifications use averaged data, in which the noise effect is reduced.     

A framework of spatiotemporal fuzzy clustering for land-cover change detection using SAR time series

Compared with optical satellite images, synthetic aperture radar (SAR) images are less influenced by weather conditions such as cloud and haze. With the support of SAR image time series, a framework of change detection based on spatiotemporal fuzzy clustering is presented. This framework mainly consists of three components: (1) pixel-level SAR image time-series modelling, based on scale invariant feature transform (SIFT); (2) probability analysis of change node based on iterative binary partition-mean square error model of the series is calculated to ascertain change nodes; (3) spatiotemporal fuzzy clustering is used to determine the types of change detection. To validate the method, 26 SAR images of the study area between 2004 and 2010 are utilized to monitor annual changes of cultivated land to construction land, and comparative experiments are conducted to evaluate the detection accuracy. Experimental results showed that the proposed framework could effectively extract the change nodes and change pixels, with correctness of 84.52% and completeness of 82.64%, outperforming the traditional fuzzy clustering method, as well as traditional classification methods.     

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.     

基于GF-1和Sentinel-1A的漓江流域典型地物信息提取

漓江流域是桂林山水的核心,保护漓江流域生态环境已成为国家战略。以漓江流域为研究区域,以GF-1多光谱影像和SAR影像为数据源,采用小波融合算法将GF-1多光谱影像和SAR VV极化的后向散射影像进行影像融合,再利用随机森林算法分别对GF-1多光谱影像、GF-1和Sentinel融合影像构建典型地物高精度识别模型,提取与漓江流域生态环境紧密相关的河流、针叶林、阔叶林、水田、旱地以及居民地等地物类型。研究结果表明:①在95%置信区间内,基于GF-1影像分类的总体分类精度达到96.15%,基于GF-1和Sentinel-1A后向散射系数的影像总体分类精度达到了94.40%;②河流、阔叶林和旱地在基于GF-1多光谱影像的分类精度中分别达到了97.74%、93.20%、90.90%,比基于融合GF-1多光谱和SAR的数据分别高出7.57%、8.96%和1.22%,其余地物类型两者分类精度相近;③GF-1多光谱和SAR数据的融合中,利用了小波变换进行图像融合,发现融合图像的喀斯特地貌突出,增加了地物特征的差异性。     

Identification of Typical Land Features in the Lijiang River Basin with Fusion Optics and Radar

Lijiang River is the core of Guilin's landscape. Protecting the ecological environment of Lijiang River Basin has become a national strategy. In this paper, Lijiang River Basin was used as the research area. The GF-1 multispectral image and SAR image were used as the data source. The wavelet fusion algorithm was used to fuse the GF-1 multispectral image and the SAR VV polarized backscatter image. Using random forest algorithm to construct a high-precision recognition model for GF-1 multispectral imagery, GF-1 and sentinel fusion images. The model can extract rivers, coniferous forests, broad-leaved forests, paddy fields, drylands, residential land and other land types that are closely related to the ecological environment of the Lijiang River. The results show that ①the overall accuracy based on GF-1 image classification reaches 96.15% in the 95% confidence interval, and the overall accuracy based on GF-1 and sentinel-1A backscatter coefficient reaches 94.40%. ②The classification accuracy of rivers, broad-leaved forests and drylands based on GF-1 multispectral images reached 97.74%, 93.20%, and 90.90%. They are 7.57%, 8.96%, and 1.22% higher than those based on the fused GF-1 multispectral and SAR data, respectively. The classification accuracy of the other features is similar. ③In the fusion of GF-1 multispectral and SAR data, wavelet transform was used for image fusion. It was found that the karst topography of the fusion image was prominent, which increased the difference of the features of the ground features.     

Wetland classification using Radarsat-2 SAR quad-polarization and Landsat-8 OLI spectral response data: a case study in the Hudson Bay Lowlands Ecoregion

Circumboreal Canadian bogs and fens distinguished by differences in soils, hydrology, vegetation and morphological features were classified using combinations of Radarsat-2 synthetic aperture radar (SAR) quad-polarization data and Landsat-8 Operational Land Imager (OLI) spectral response patterns. Separate classifications were conducted using a traditional pixel-based maximum likelihood classifer and a machine learning algorithm following an object-based image analysis (OBIA). This study focused on two wetland classes with extensive coverage in the area (bog and fen). In the pixel-based maximum likelihood classification, accuracy increased from approximately 69% user’s accuracy and 79% producer’s accuracy using Radarsat-2 SAR data alone to approximately 80% user’s accuracy and 87% producer’s accuracy using Landsat-8 OLI data alone. Use of the Radarsat-2 SAR and Landsat-8 OLI data following principal components analysis (PCA) data fusion did not result in higher pixel-based maximum likelihood classification accuracy. In the object-based machine learning classification, higher bog and fen class accuracies were obtained when using Radarsat-2 and Landsat OLI data individually compared to the equivalent pixel-based classification. Subsequently, a PCA-data fusion product outperformed the individual bands of the Radarsat-2 and Landsat-8 imagery in object-based classification. Greater than 90% producer’s accuracy was obtained. The margin of error (MOE) was less than 5% in all classifications reported here. Further research will examine alternative data fusion techniques and the addition of Radarsat-2 SAR interferometric digital elevation model (DEM)-based geomorphometrics in object-based classification of different morphological types of bogs and fens.     

Integration of IRS-1A L2 data by fuzzy logic approaches for landuse classification

A methodology has been formulated to integrate images from IRS-1A LISS II of two dates for landuse/landcover classification. The methodology developed includes image classification by fuzzy k-means clustering and fusion of memberships by fuzzy set theoretic operators. The two date images have been geometrically coregistered and classified for the identification of land classes individually. The fuzzy memberships of the classified output images have been integrated by using fuzzy logic operators like algebraic sum and gamma (gamma) operator. The classification accuracy of the resultant land classes in the integrated images was verified with the ground data collected in situ. The resultant images have been evaluated by kappa (kappa) statistic and it was found that output from the image of fuzzy algebraic sum operator scored high in generating the land classes, with an overall accuracy of 95%.     

A refined classification approach by integrating Landsat Operational Land Imager (OLI) and RADARSAT-2 imagery for land-use and land-cover mapping in a tropical area

Producing accurate land-use and land-cover (LULC) mapping is a long-standing challenge using solely optical remote-sensing data, especially in tropical regions due to the presence of clouds. To supplement this, RADARSAT images can be useful in assisting LULC mapping. The fusion of optical and active remote-sensing data is important for accurate LULC mapping because the data from different parts of the spectrum provide complementary information and often lead to increased classification accuracy. Also, the timeliness of using synthetic aperture radar (SAR) fills information gaps during overcast or hazy periods. Therefore, this research designed a refined classification procedure for LULC mapping for tropical regions. Determining the best method for mapping with a specific data source and study area is a major challenge because of the wide range of classification algorithms and methodologies available. In this study, different combinations and the potential of Landsat Operational Land Imager (OLI) and RADARSAT-2 SAR data were evaluated to select the best procedure for LULC classification. Results showed that the best filter for SAR speckle reduction is the 5 × 5 enhanced Lee. Furthermore, image-sharpening algorithms were employed to fuse Landsat multispectral and panchromatic bands and subsequently these algorithms were analysed in detail. The findings also confirmed that Gram–Schmidt (GS) performed better than the other techniques employed. Fused Landsat data and SAR images were then integrated to produce the LULC map. Different classification algorithms were adopted to classify the integrated Landsat and SAR data, and the maximum likelihood classifier (MLC) was considered the best approach. Finally, a suitable classification procedure was designed and proposed for LULC as mapping in tropical regions based on the results obtained. An overall accuracy of 98.62% was achieved from the proposed methodology. The proposed methodology is a useful tool in industry for mapping purposes. Additionally, it is also useful for researchers, who could extend the method for different data sources and regions.     

An efficient neural classification chain of SAR and optical urban images

In this paper a suitable neural classification algorithm, based on the use of Adaptive Resonance Theory (ART) networks, is applied to the fusion and classification of optical and SAR urban images. ART networks provide a flexible tool for classification, but are ruled by a large number of parameters. Therefore, the simplified ART2-A algorithm is used in this paper, and the neural approach is integrated into a classification chain where fuzzy clustering for merging of classes is also considered. The interaction between the two methods leads to encouraging results in less CPU time than classification with fuzzy clustering alone or other classical approaches (ISODATA). Examples of classification are provided using C-band total power AIRSAR data and optical images of Santa Monica, Los Angeles.     

Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images

This paper describes a comparative evaluation of several speckle reduction and texture analysis techniques, with particular emphasis on their applicability to supervised land cover classification from SAR images. Issues related to suppression of speckle in a uniform area, preservation of edges, and texture preservation are pursued in these filters. Quality of texture features is measured by the relevancy, discriminative power and ease of computation of the features. The discriminative power of texture features is measured using the Jeffreys-Matusita distance and classification performance measured on a validation set independent from the classifier's training set. Classifiers investigated are maximum-likelihood, multi-layer perceptron (MLP) and radial basis function (RBF) neural networks. Classification accuracy is measured by KHAT statistic calculated from confusion matrices. Two SAR images of ERS-1 and E-SAR programme showing different land cover categories within the regions of Douala and Ngaoundere (Cameroon), and a bi-polarized Synthetic Aperture Radar (SAR) image from an agricultural station near the city of Altona (Canada) are used for analysis. Speckle suppression techniques based on the wavelet transform performs the best, followed by the modified K-nearest neighbours and the Lee's local statistic filters. Depending on the nature of the land cover types being classified, texture features derived from second- and third-order histogram performed the best, followed by first-order statistics and features derived using the grey-level difference vector method. Among all classifiers considered, the MLP and the RBF neural networks performed the best, achieving up to 94% overall accuracy for the E-SAR image of Douala, for example.     

Mapping of flooded vegetation by means of polarimetric Sentinel-1 and ALOS-2/PALSAR-2 imagery

This article presents for the first time the combination of dual-polarimetric C-band Sentinel-1 synthetic aperture radar (SAR) data and quad-polarimetric L-band ALOS-2/PALSAR-2 imagery for mapping of flooded areas with a special focus on flooded vegetation. L-band SAR data is well suited for mapping of flooded vegetation, while C-band enables an accurate extraction open water areas. Polarimetric decomposition-based unsupervised Wishart classification is combined with object-based post-classification refinement and the integration of spatial contextual information and global auxiliary data. In eight different scenarios, focusing on single datasets or fusion of classification results of several ones, respectively, different polarimetric decomposition and classification principles, including the entropy/anisotropy/alpha and the Freeman–Durden–Wishart classification, were investigated. The helix scattering component of the Yamaguchi decomposition, derived from ALOS-2 imagery, showed high suitability to refine the Sentinel-1-based detection of flooded vegetation. A test site at the Evros River (Greek/Turkish border region) was chosen, which was affected by a flooding event that occurred in spring 2015. The validation was based on high spatial resolution optical WorldView-2 imagery acquired with short temporal delay to the SAR data.     

基于SAR与Landsat TM的小区域稻田的识别研究——以南京市江宁区为例

以南京市江宁区为研究区域,根据区域特征、作物物候期和水稻的生长特点,采用分层分类的方法提取稻田分布信息。通过比较多时相SAR数据、TM和多时相SAR融合与TM和单时相SAR融合数据识别水稻的精度和提取的水稻种植面积,分析了不同数据对区域多云雨,不同种植方式、面积小且分布破碎的水稻稻田的识别程度,并根据野外实地走访调查分析了主要影响因素。结果表明:多时相SAR数据、TM和多时相SAR数据的水稻识别精度都高于72%,高于TM和单时相SAR融合数据的结果;前两者提取的水稻种植面积和稻田分布接近,主要影响因素是地物分布、不同种植方式水稻物候期和水稻稻田面积小且分布破碎。     

单波段单极化SAR图像水体和居民地信息提取方法研究

SAR图像上水体和居民地信息的提取在实际应用中具有重要的意义。为了更好地提取SAR图像上水体和居民地,以单波段单极化Radarsat-1 SAR图像为研究对象,首先利用半变异函数分析样本图像的结构特性来确定纹理信息提取的最佳参数;然后,在此基础上基于灰度共生矩阵计算SAR图像均值、角二阶矩和熵3种纹理测度,建立了适于图像分类的多维特征空间,从而有效地增强了水体和居民地信息;最后通过样本采集,使用支持向量机分类器进行水体和居民地信息提取,并采用近期归一化植被指数(NDVI)数据和分类结果进行目标层融合来消除山体因素的影响,信息提取的结果显示,分类总体精度为82.57%,Kappa系数为0.58,较准确地提取了水体和居民地信息。     

基于ENVISat ASAR影像的湿地植被冠层下淹水范围提取以扎龙保护区为例

以扎龙自然保护区湿地为例,结合ENVISat ASAR多极化(HH/HV)雷达影像与传统的光学影像Landsat TM (band1~5,7),分析雷达影像后向散射系数与Landsat TM影像不同波段反射率在淹水植被、非淹水植被、明水面和裸土不同地表覆被类型的差异。选择训练样本,采用分类回归树(Classification and Regression Tree,CART)模型,分别对两种影像进行分类,可视化表达湿地植被淹水范围空间分布情况。基于实测的植被冠层下淹水范围与非淹水范围样本点对两种数据源的分类结果进行精度验证。结果表明:HH/HV极化影像中,植被覆盖下水体的后向散射系数与其他地表覆被类型有明显区别,分类结果总精度为79.49%,Kappa系数为0.70,湿地植被淹水范围提取精度较高。而TM影像分类结果中,由于部分地区植被覆盖水体,淹水植被分类误差较高。将雷达影像引入沼泽湿地研究,提高了植被淹水范围提取效果,为有效分析湿地生态水文过程提供基础,对湿地水资源合理利用及生物多样性保护具有重要意义。     

Analysis of different polarimetric target decomposition methods in forest density classification using C band SAR data

The ability of synthetic aperture radar (SAR) C-band microwave energy to penetrate within forest vegetation makes it possible to extract information on crown components, which in turn gives a better approximation of relative canopy density than optical data-derived canopy density. Many studies have been reported to estimate forest biomass from SAR data, but the scope of C-band SAR in characterizing forest canopy density has not been adequately understood with polarimetric techniques. Polarimetric classification is one of the most significant applications of polarimetric SAR in remote sensing. The objective of the present study was to evaluate the feasibility of different polarimetric SAR data decomposition methods in forest canopy density classification using C-band SAR data. Landsat (Land Satellite) 5 TM (Thematic Mapper) data of the same area has been used as optical data to compare the classification result. RADARSAT (Radar Satellite)-2 image with fine quad-pol obtained on 27 October 2011 over tropical dry forests of Madhav National Park, India, was used for the analysis of full polarimetric data. Six decomposition methods were selected based on incoherent decomposition for generating input images for classification, i.e. Huynen, Freeman and Durden, Yamaguchi, Cloude, Van zyl, and H/A/α. The performance of each decomposition output in relation to each land cover unit present in the study area was assessed using a support vector machine (SVM) classifier. Results show that Yamaguchi 4-component decomposition (overall accuracy 87.66% and kappa coefficient (κ) 0.86) gives better classification results, followed by Van Zyl decomposition (overall accuracy 87.20% and κ 0.85) and Freeman and Durden (overall accuracy 86.79% and κ 0.85) in forest canopy density classification. Both model-based decompositions (Freeman and Durden and Yamaguchi4) registered good classification accuracy. In eigenvector or eigenvalue decompositions, Van zyl registered the second highest accuracy among different decompositions. The experimental results obtained with polarimetric C-band SAR data over a tropical dry deciduous forest area imply that SAR data have significant potential for estimating canopy density in operational forestry. A better forest density classification result can be achieved within the forest mask (without other land cover classes). The limitations associated with optical data such as non-availability of cloud-free data and misclassification because of gregarious occurrence of bushy vegetation such as Lantana can be overcome by using C-band SAR data.     

基于多层支持向量机的极化合成孔径雷达特征分析与分类

为了充分利用极化合成孔径雷达（SAR）图像不同极化特征对不同地物目标类型的刻画能力,提出一种基于多层支持向量机（SVM）的极化SAR特征分析与分类方法。该方法首先通过特征分析确定适合不同地物类型的最佳特征子集;然后采用分层分类树的方式,根据每一种地物类型的特征子集逐层进行SVM分类;最终得到整体分类结果。RadarSAT-2极化SAR图像分类实验结果表明所提方法水域、耕地、林地、城区4类地物分类精度为85%左右,总体分类精度达到86%。该算法充分利用了不同地物目标类型的特性,提高了分类精度,也降低了算法时间复杂度。     

改进Xception模型的乳腺钼靶图像识别研究

乳腺X线摄影技术是早期发现乳腺癌的主要方法,但其结果很大程度上受放射科医师临床诊断经验的限制;基于卷积神经网络对乳腺钼靶图像自动分类的研究可以为放射科医师临床诊断提供意见,然而乳腺癌肿块边缘模糊且良恶性肿块特征差异较小,分类任务面临重重挑战;为了提高乳腺钼靶图像分类的准确率,提出一种基于Xception模型的改进优化算法,改进模型中的残差连接模块,并嵌入Squeeze-and-excitation（SE）注意力机制对模型进行优化;采用优化后的Xception模型并结合迁移学习算法进行乳腺钼靶图像特征提取,并优化全连接层网络进行图像分类,使用公开的乳腺癌图像数据库CBIS-DDSM进行实验,将乳腺钼靶图像自动分为良性和恶性;实验结果表明该方法可以有效提高模型的分类效果,准确率和AUC分别达到了97.46%和99.12%。     

差异特征融合的无监督SAR图像变化检测

针对Siamese网络忽略不同层级差异特征之间的关联导致检测精度有限的问题,提出了基于差异特征融合的无监督SAR(synthetic aperture radar)图像变化检测算法。首先,利用对数比值算子和均值比值算子构建两幅信息互补的差异图,通过引入能量矩阵对差异图进行像素级融合以提高其信噪比;其次,设计了一种基于差异特征融合的Siamese网络(difference feature fusion for Siamese,DFF-Siamese),该网络能够通过差异特征提取模块在决策层综合衡量不同层级特征之间的差异程度,从而有效增强网络的特征表达能力;最后,利用模糊聚类算法对融合结果进行分类构建“伪标签”,用于训练DFF-Siamese网络以实现高精度SAR图像变化检测。在3组真实遥感数据集上的实验结果表明,本文提出的算法与其他对比算法相比具有更高的检测精度和更低的错误率。     

The study of ERS-1 SAR and Landsat TM synergism for land use classification

This work presents a comparative analysis of ERS-1 Synthetic Aperture Radar (SAR) and Landsat-5 Thematic Mapper (TM) images used for land use classification. The study area of 361 km² is located in the City of Campinas, Sao Paulo State, Brazil, and contains several classes of land use, including urban, agricultural and forests. The TM and SAR images were registered and transformed using the principal components transformation. SAR images were also filtered using an average filter. The principal components derived from SAR filtered, SAR, TM and coregistered TM/SAR and TM/SAR filtered images were classified using the maximum likelihood approach. Tests of 'goodness of fit' were also made to assess the statistical properties of the images. The results, confirmed by Kappa statistics, show a significant improvement when classifying the principal components of filtered SAR and TM images for urban, pasture and forest classes.