A support vector machine classifier based on a new kernel function model for hyperspectral data

The kernel function is a key factor to determine the performance of a support vector machine (SVM) classifier. Choosing and constructing appropriate kernel function models has been a hot topic in SVM studies. But so far, its implementation can only rely on the experience and the specific sample characteristics without a unified pattern. Thus, this article explored the related theories and research findings of kernel functions, analyzed the classification characteristics of EO-1 Hyperion hyperspectral imagery, and combined a polynomial kernel function with a radial basis kernel function to form a new kernel function model (PRBF). Then, a hyperspectral remote sensing imagery classifier was constructed based on the PRBF model, and a genetic algorithm (GA) was used to optimize the SVM parameters. On the basis of theoretical analysis, this article completed object classification experiments on the Hyperion hyperspectral imagery of experimental areas and verified the high classification accuracy of the model. The experimental results show that the effect of hyperspectral image classification based on this PRBF model is apparently better than the model established by a single global or local kernel function and thus can greatly improve the accuracy of object identification and classification. The highest overall classification accuracy and kappa coefficient reached 93.246% and 0.907, respectively, in all experiments.     

基于球结构支持向量机的QuickBird影像分类分析

在支持向量机多类识别基础上探讨以球结构替代传统超平面支持向量机对QuickBird影像进行分类的可行性,对重叠区域的数据分类采用新规则,提高球结构支持向量机算法的泛化性能,并将分类结果与最小距离法、最大似然法分类结果进行比较,实验结果表明该算法有效可行,降低了二次规划的复杂度,缩短了样本训练时间.     

Support vector machines in remote sensing: A review

A wide range of methods for analysis of airborne- and satellite-derived imagery continues to be proposed and assessed. In this paper, we review remote sensing implementations of support vector machines (SVMs), a promising machine learning methodology. This review is timely due to the exponentially increasing number of works published in recent years. SVMs are particularly appealing in the remote sensing field due to their ability to generalize well even with limited training samples, a common limitation for remote sensing applications. However, they also suffer from parameter assignment issues that can significantly affect obtained results. A summary of empirical results is provided for various applications of over one hundred published works (as of April, 2010). It is our hope that this survey will provide guidelines for future applications of SVMs and possible areas of algorithm enhancement.     

Assessment of Sentinel-1A data for rice crop classification using random forests and support vector machines

This study developed an approach to map rice-cropping systems in An Giang and Dong Thap provinces, South Vietnam using multi-temporal Sentinel-1A (S1A) data. The data were processed through four steps: (1) data pre-processing, (2) constructing smooth time series VH backscatter data, (3) rice crop classification using random forests (RF) and support vector machines (SVM) and (4) accuracy assessment. The results indicated that the smooth VH backscatter profiles reflected the temporal characteristics of rice-cropping patterns in the study region. The comparisons between the classification results and the ground reference data indicated that the overall accuracy and Kappa coefficient achieved from RF were 86.1% and 0.72, respectively, which were slightly more accurate than SVM (overall accuracy of 83.4% and Kappa coefficient of 0.67). These results were reaffirmed by the government’s rice area statistics with the relative error in area (REA) values of 0.2 and 2.2% for RF and SVM, respectively.     

Supervised change detection in VHR images using contextual information and support vector machines

In this paper we study an effective solution to deal with supervised change detection in very high geometrical resolution (VHR) images. High within-class variance as well as low between-class variance that characterize this kind of imagery make the detection and classification of ground cover transitions a difficult task. In order to achieve high detection accuracy, we propose the inclusion of spatial and contextual information issued from local textural statistics and mathematical morphology. To perform change detection, two architectures, initially developed for medium resolution images, are adapted for VHR: Direct Multi-date Classification and Difference Image Analysis. To cope with the high intra-class variability, we adopted a nonlinear classifier: the Support Vector Machines (SVM). The proposed approaches are successfully evaluated on two series of pansharpened QuickBird images.     

An innovative support vector machine based method for contextual image classification

Several remote sensing studies have adopted the Support Vector Machine (SVM) method for image classification. Although the original formulation of the SVM method does not incorporate contextual information, there are different proposals to incorporate this type of information into it. Usually, these proposals modify the SVM training phase or make an integration of SVM classifications using stochastic models. This study presents a new perspective on the development of contextual SVMs. The main concept of this proposed method is to use the contextual information to displace the separation hyperplane, initially defined by the traditional SVM. This displaced hyperplane could cause a change of the class initially assigned to the pixel. To evaluate the classification effectiveness of the proposed method a case study is presented comparing the results with the standard SVM and the SVM post-processed by the mode (majority) filter. An ALOS/PALSAR image, PLR mode, acquired over an Amazon area was used in the experiment. Considering the inner area of test sites, the accuracy results obtained by the proposed method is better than SVM and similar to SVM post-processed by the mode filter. The proposed method, however, produces better results than mode post-processed SVM when considering the classification near the edges between regions. One drawback of the method is the computational cost of the proposed method is significantly greater than the compared methods.     

Classifiers vs. input variables—The drivers in image classification for land cover mapping

The study investigates the performance of image classifiers for landscape-scale land cover mapping and the relevance of ancillary data for the classification success in order to assess and to quantify the importance of these components in image classification. Specifically tested are the performance of maximum likelihood classification (MLC), artificial neural networks (ANN) and discriminant analysis (DA) based on Landsat7 ETM+ spectral data in combination with topographic measures and NDVI. ANN produced high accuracies of more than 75% also with limited input information, while MLC and DA produced comparable results only by incorporating ancillary data into the classification process. The superiority of ANN classification was less pronounced on the level of the single land cover classes. The use of ancillary data generally increased classification accuracy and showed a similar potential for increasing classification accuracy than the selection of the classifier. Therefore, a stronger focus on the development of appropriate and optimised sets of input variables is suggested. Also the definition and selection of land cover classes has shown to be crucial and not to be simply adaptable from existing land cover class schemes. A stronger research focus towards discriminating land cover classes by their typical spectral, topographic or seasonal properties is therefore suggested to advance image classification.     

Enhanced land use/cover classification of heterogeneous tropical landscapes using support vector machines and textural homogeneity

Land use/cover classification is a key research field in remote sensing and land change science as thematic maps derived from remotely sensed data have become the basis for analyzing many socio-ecological issues. However, land use/cover classification remains a difficult task and it is especially challenging in heterogeneous tropical landscapes where nonetheless such maps are of great importance. The present study aims at establishing an efficient classification approach to accurately map all broad land use/cover classes in a large, heterogeneous tropical area, as a basis for further studies (e.g., land use/cover change, deforestation and forest degradation). Specifically, we first compare the performance of parametric (maximum likelihood), non-parametric (k-nearest neighbor and four different support vector machines – SVM), and hybrid (unsupervised–supervised) classifiers, using hard and soft (fuzzy) accuracy assessments. We then assess, using the maximum likelihood algorithm, what textural indices from the gray-level co-occurrence matrix lead to greater classification improvements at the spatial resolution of Landsat imagery (30 m), and rank them accordingly. Finally, we use the textural index that provides the most accurate classification results to evaluate whether its usefulness varies significantly with the classifier used. We classified imagery corresponding to dry and wet seasons and found that SVM classifiers outperformed all the rest. We also found that the use of some textural indices, but particularly homogeneity and entropy, can significantly improve classifications. We focused on the use of the homogeneity index, which has so far been neglected in land use/cover classification efforts, and found that this index along with reflectance bands significantly increased the overall accuracy of all the classifiers, but particularly of SVM. We observed that improvements in producer's and user's accuracies through the inclusion of homogeneity were different depending on land use/cover classes. Early-growth/degraded forests, pastures, grasslands and savanna were the classes most improved, especially with the SVM radial basis function and SVM sigmoid classifiers, though with both classifiers all land use/cover classes were mapped with producer's and user's accuracies of ∼90%. Our classification approach seems very well suited to accurately map land use/cover of heterogeneous landscapes, thus having great potential to contribute to climate change mitigation schemes, conservation initiatives, and the design of management plans and rural development policies.     

A support vector machine to identify irrigated crop types using time-series Landsat NDVI data

Site-specific information of crop types is required for many agro-environmental assessments. The study investigated the potential of support vector machines (SVMs) in discriminating various crop types in a complex cropping system in the Phoenix Active Management Area. We applied SVMs to Landsat time-series Normalized Difference Vegetation Index (NDVI) data using training datasets selected by two different approaches: stratified random approach and intelligent selection approach using local knowledge. The SVM models effectively classified nine major crop types with overall accuracies of >86% for both training datasets. Our results showed that the intelligent selection approach was able to reduce the training set size and achieved higher overall classification accuracy than the stratified random approach. The intelligent selection approach is particularly useful when the availability of reference data is limited and unbalanced among different classes. The study demonstrated the potential of utilizing multi-temporal Landsat imagery to systematically monitor crop types and cropping patterns over time in arid and semi-arid regions.     

面向对象规则和支持向量机的天宫一号高光谱影像分类

传统的高光谱分类方法通常基于单一像元的光谱或纹理特征,很少考虑地物空间结构信息与空间相关特征.本文将面向对象规则与基于像元的分类进行融合,利用对象的空间结构特征和光谱特征进行混合分类,旨在克服像元层次分类的不足.本文尝试性的提出了两种混合分类方法:(1)基于分形网络演化的多尺度分割支持向量机分类(2)基于多层分水岭分割的SVM分类,并将这两种方法应用到天宫一号高光谱数据上.结果表明:基于面向对象规则的混合分类方法有效地提高了分类精度,不仅能够改善同谱异物现象,而且解决分类结果中地物破碎的问题.     

Detecting Sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data,random forest and support vector machines classifiers

The visual progression of sirex (Sirex noctilio) infestation symptoms has been categorized into three distinct infestation phases, namely the green, red and grey stages. The grey stage is the final stage which leads to almost complete defoliation resulting in dead standing trees or snags. Dead standing pine trees however, could also be due to the lightning damage. Hence, the objective of the present study was to distinguish amongst healthy, sirex grey-attacked and lightning-damaged pine trees using AISA Eagle hyperspectral data, random forest (RF) and support vector machines (SVM) classifiers. Our study also presents an opportunity to look at the possibility of separating amongst the previously mentioned pine trees damage classes and other landscape classes on the study area. The results of the present study revealed the robustness of the two machine learning classifiers with an overall accuracy of 74.50% (total disagreement = 26%) for RF and 73.50% (total disagreement = 27%) for SVM using all the remaining AISA Eagle spectral bands after removing the noisy ones. When the most useful spectral bands as measured by RF were exploited, the overall accuracy was considerably improved; 78% (total disagreement = 22%) for RF and 76.50% (total disagreement = 24%) for SVM. There was no significant difference between the performances of the two classifiers as demonstrated by the results of McNemar’s test (chi-squared; χ² = 0.14, and 0.03 when all the remaining ASIA Eagle wavebands, after removing the noisy ones and the most important wavebands were used, respectively). This study concludes that AISA Eagle data classified using RF and SVM algorithms provide relatively accurate information that is important to the forest industry for making informed decision regarding pine plantations health protocols.     

组合核支持向量回归提取高光谱影像不透水面

由于城市地表组成的复杂性,基于单核函数的支持向量回归模型很难满足精度。本文结合空间-光谱组合核函数和支持向量回归,提出了一种提取高光谱影像不透水面丰度的改进算法。首先从高光谱遥感图像上提取波谱特征和多通道灰度共生矩阵空间纹理特征,选取研究区10%像元特征数据作为训练数据,以线性加权求和核为多核组合方式,建立结合光谱信息和空间信息的组合核支持向量回归模型。然后,用生成的回归模型预测未知像元不透水面丰度值。最后,对实验结果进行评价。在模拟数据试验中,本文算法比单核回归均方根误差平均降低1.4%,决定系数比单核回归平均提高0.6%。在Hyperion数据两组试验中,该算法比单核回归均方根误差平均降低1.8%,决定系数比单核回归平均提高11.7%。模拟和真实两种高光谱数据实验中,本文算法均得到了空间形态上更准确的不透水面结果,单核回归结果存在失真现象。研究结果表明:本文算法能够有效提取城市不透水面丰度,与单核方法相比有较明显的精度提升。     

支持向量机在GPS高程异常中的应用

本文论述了支持向量机的回归算法,提出了基于支持向量机的GPS高程异常拟合方法,并在MATLAB中编制了相应的支持向量机程序,建立了相应的GPS高程异常模型.以实例数据讨论了基于支持向量机的GPS高程异常分析方法.研究表明:用支持向量机技术建立GPS高程异常模型是可行的和有效的.     

径向基核函数在DEM内插中的适用性分析

针对空间插值中不同核函数在不同地形条件下的适用性问题,该文选取了平原、丘陵和山地3种地貌类型区,采用5种常用的径向基核函数分别生成若干分辨率的DEM,通过高程统计参数、空间自相关特性和等高线套合分析DEM的精度差异。综合而言,平原地区中多重对数函数、多重二次曲面函数、反多重二次曲面函数和自然三次样条曲面函数插值效果没有显著差别,薄板样条曲面函数相对略差;丘陵地区选择多重二次曲面函数和薄板样条曲面函数插值效果最好,多重对数函数和自然三次样条曲面函数次之,反多重二次曲面函数最差;山地地区采用多重二次曲面函数插值能取得较为满意的效果,其他4种核函数逊之。     

Land cover classification of VHR airborne images for citrus grove identification

Managing land resources using remote sensing techniques is becoming a common practice. However, data analysis procedures should satisfy the high accuracy levels demanded by users (public or private companies and governments) in order to be extensively used. This paper presents a multi-stage classification scheme to update the citrus Geographical Information System (GIS) of the Comunidad Valenciana region (Spain). Spain is the first citrus fruit producer in Europe and the fourth in the world. In particular, citrus fruits represent 67% of the agricultural production in this region, with a total production of 4.24 million tons (campaign 2006-2007). The citrus GIS inventory, created in 2001, needs to be regularly updated in order to monitor changes quickly enough, and allow appropriate policy making and citrus production forecasting. Automatic methods are proposed in this work to facilitate this update, whose processing scheme is summarized as follows. First, an object-oriented feature extraction process is carried out for each cadastral parcel from very high spatial resolution aerial images (0.5 m). Next, several automatic classifiers (decision trees, artificial neural networks, and support vector machines) are trained and combined to improve the final classification accuracy. Finally, the citrus GIS is automatically updated if a high enough level of confidence, based on the agreement between classifiers, is achieved. This is the case for 85% of the parcels and accuracy results exceed 94%. The remaining parcels are classified by expert photo-interpreters in order to guarantee the high accuracy demanded by policy makers.     

An experimental approach for selection/elimination in stream network generalization using support vector machines

Multi-representation databases (MRDB) are used in several Geographical Information System applications for different purposes. MRDB are mainly obtained through model and cartographic generalizations. The model generalization is essentially achieved with the selection/elimination process in which a decision must be made to include or exclude the object at the target level. In this study, support vector machines (SVM) was, for the first time, used for the selection/elimination process in stream network generalization. Within this context, the attributes to be used as input data in the SVM method were determined and weighted according to the associations determined in a chi-squared independence test. 1:100,000-scale (medium resolution) stream networks were derived from two 1:24,000-scale (high resolution) stream networks with different patterns in the United States Geological Survey National Hydrography Data-sets. The derived stream networks were quite similar to the 1:100,000-scale original stream networks in both qualitative and visual aspects.     

最小二乘支持向量机回归的卫星钟差非线性组合预报

针对应用单一方法预报卫星钟差的局限性,文章提出了基于最小二乘支持向量机回归的卫星钟差非线性组合预报方法:首先根据历史钟差数据建立二次多项式模型和灰色模型,然后利用这些模型进行钟差预报,最后采用最小二乘支持向量机回归算法对两种模型的预报结果进行非线性组合,以获得最终预报值;对比了RBF核函数、线性核函数和多项式核函数对组合预报性能的影响,并将本文组合预报方法与经典权组合方法进行比较。结果表明,本文方法优于经典权法,且线性核函数更适合组合预报。     

Margin-based feature selection for hyperspectral data

A margin-based feature selection approach is explored for hyperspectral data. This approach is based on measuring the confidence of a classifier when making predictions on a test data. Greedy feature flip and iterative search algorithms, which attempts to maximise the margin-based evaluation functions, were used in the present study. Evaluation functions use linear, zero–one and sigmoid utility functions where a utility function controls the contribution of each margin term to the overall score. The results obtained by margin-based feature selection technique were compared to a support vector machine-based recurring feature elimination approach. Two different hyperspectral data sets, one consisting of 65 bands (DAIS data) and other with 185 bands (AVIRIS data) were used. With digital airborne imaging spectrometer (DAIS) data, the classification accuracy by greedy feature flip algorithm and sigmoid utility function was 93.02% using a total of 24 selected features in comparison to an accuracy of 91.76% with full set of 65 features. The results suggest a significant increase in classification accuracy with 24 selected features. The classification accuracy (93.4%) achieved by the iterative search margin-based algorithm with 20 selected features using sigmoid utility function is also significantly more accurate than that achieved with 65 features. To judge the usefulness of margin-based feature selection approaches, another hyperspectral data set consisting of 185 features was used. A total of 65 selected features were used to evaluate the performance of margin-based feature selection approach. The results suggest a significantly improved performance by greedy feature flip-based feature selection technique with this data set also. This study also suggest that margin-based feature selection algorithms provide a comparable performance to support vector machine-based recurring feature elimination approach.     

西北旱区遥感影像分类的支持向量机法

针对较大范围、不同时相、不同气候和地貌类型的遥感影像的土地利用现状分类问题,提出了一种结合标准植被指数和纹理特征的支持向量机法。此方法改进了陕西延安、甘肃嘉峪关和青海果洛的遥感影像分类,有效地解决了最大似然法和BP神经网络法的缺陷造成的分类精度不高的问题。分类结果表明:与最大似然法和BP神经网络法相比,结合标准植被指数和纹理特征的支持向量机法的分类总精度最高(97.75%),Kappa系数为0.9691。该方法可为西北旱区遥感影像解译和土地资源可持续发展战略提供方法支撑。     

混合核特征加权SVM遥感湿地空间分类

针对湿地空间信息的复杂性和SVM的分类性能,设计一种基于混合核函数的特征加权SVM分类模型,综合利用多种特征信息,避免被弱相关特征所支配,从而提供更佳的映射性能和泛化能力。实验结果表明,该分类模型兼具良好的外推和内推能力,能够有效地融合不同信息源特征,得到更完整和准确的分类结果,在总体精度、Kappa系数等多项指标上都表现出更高的水平。