特征维数对支持向量机分类器性能影响的研究——以高光谱遥感影像为例

本文为验证SVM对高维特征的适应性和可靠性,针对不同特征提取方法与特征组合,以国产OMISⅡ传感器获得的北京昌平地区高光谱遥感据为例,对SVM分类器中特征维数对分类准确率的影响进行了试验,通过对主成分分析、最小噪声分离算法、相关系数分组后特征提取、导数光谱等的分析,表明SVM分类器的分类精度随着特征维数波动,其中主成分分析降维后提取的特征具有用于分类能够获得最高的准确率。通过与最大似然法和光谱角制图分类算法的比较,说明在同样的特征输入情况下SVM分类算法分类的准确率高于最大似然法和光谱角制图分类器。     

城市道路的多特征多核SVM提取方法

针对高分辨率遥感影像中城市道路提取的复杂性及SVM的分类性能,提出了一种城市道路的多特征多核SVM提取方法。首先利用FCM算法将原始影像粗分为建成区和非建成区两类,剔除非建成区;然后根据分水岭分割算法分割建成区并提取分割对象的光谱特征与空间特征,以全局核函数和局部核函数加权组合的方式构建多核SVM对建成区进行二次分类,去除建成区中的建筑物等非道路信息;最后利用数学形态学处理,获得最终的道路提取结果。试验结果表明：文中所提方法能够较精确地提取城市道路信息,分类精度高于单核SVM提取及其他对比方法。     

聚类特征和SVM组合的高光谱影像半监督协同分类

本文提出了一种聚类特征和SVM组合的高光谱影像半监督协同分类方法。利用构建的协同分类框架能够将KSFCM聚类算法与半监督SVM分类器相结合,同时利用聚类和分类优势,提高分类器的分类准确率。其中,通过聚类损耗函数、分类一致函数、分类差异性、样本差异性四个指数用以构建协同分类框架,以充分利用少量类标签样本信息,避免高光谱类标签样本获取困难问题,在一定程度上解决SVM支持向量随着训练样本增加而线性增加的问题,从而寻求最佳分类结果。实验结果表明,本文所提方法得到的分类精度优于直接利用SVM进行半监督分类。     

基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类

针对卷积神经网络特征维度高且单层特征不能准确表达复杂高分辨率遥感影像语义信息的问题,本文提出了一种提取低维卷积神经网络（LDCNN）深层次特征进行多核SVM分类的场景分类方法。首先将预训练的卷积神经网络改造成低维网络结构,其次提取低维网络的不同深层特征并进行不同核函数的SVM分类,找到对应的最优核函数;然后将多种最优核函数加权融合成为一个新的合成核;最后进行多核SVM分类。试验表明,本文方法不仅特征维度低,且通过多核SVM能够充分结合各层特征的优点,在两个标准数据集上均取得了99%以上的分类精度。此外,该试验还证明了本文方法具有较强的迁移学习能力。     

NWFE结合纹理特征的SVM土地覆被分类方法研究

为提高土地覆被分类精度,采用非参数权重特征提取(nonparametric weighted feature extraction,NWFE)结合纹理特征的支持向量机(support vector machines,SVM)的分类法,对新疆玛纳斯河流域绿洲区2006年的土地覆被进行分类,并将该方法与主成分分析(principal component analysis,PCA)结合纹理特征的SVM分类、原始波段结合纹理特征的SVM分类进行对比。结果表明,NWFE结合纹理特征的SVM分类结果优于其他2种分类结果,不仅反映了土地覆被分布的整体情况,而且使不同土地覆被类型得到较好的区分,总体分类精度达89.17%。     

基于支持向量机的航空影像纹理分类研究

提出一种用SVM解决航空影像纹理分类的方法。在利用一些常用的纹理特征的基础上，将SVM用于航空影像纹理分类，有效地解决了特征选择难和高维数问题。试验表明，这种方法可以取得较好的结果。     

基于纹理特征和支持向量机的ALOS图像土地覆被分类

高空间分辨率遥感图像在土地覆被分类方面应用广泛,但传统的基于像元分类方法的精度较低.为了提高高分辨率图像的分类精度,通过灰度共生矩阵法快速提取纹理特征,利用支持向量机(SVM)并辅以纹理特征,对浙江湖州典型实验样区的ALOS图像进行土地覆被分类.结果表明:基于纹理特征和SVM的图像分类能更好地提取地物信息,分类总精度达...     

基于EMP与混合核SVM的高光谱遥感影像分类

传统的SVM模型采用同一映射形式的单核模式对叠加的空间特征和光谱特征进行处理,往往无法得到理想的结果,为了解决该问题,提出了一种基于扩展的形态学剖面(EMP)与混合核SVM的高光谱遥感影像分类方法.该方法首先通过EMP有效提取空间信息,再采用不同的核函数处理空间信息与光谱信息,最终完成混合核SVM的高光谱影像分类.对多种组合形式的单核以及多核SVM模型进行了对比分析,结果表明,该方法具有较高的适应性,对于高光谱遥感影像的分类精度较高.     

联合光谱和纹理特征的支持向量机滩涂分类方法研究

滩涂作为海岸带的重要组成部分,是重要的土地资源。针对遥感影像滩涂分类的提取,文中提出一种联合光谱和纹理特征支持向量机(SVM)滩涂分类的方法。首先介绍纹理特征影像获取方法,通过灰度共生矩阵分析得到滩涂纹理特征影像;然后将光谱影像与纹理影像叠加形成一幅多维特征影像,用SVM分类算法中的OAR分类器进行分类实验,对分类结果进行实验分析。实验结果表明,该算法对提高海岸带地理信息获取能力,提升海洋遥感测绘信息化保障水平有积极意义。     

MRELBP特征、Franklin矩和SVM相结合的遥感图像建筑物识别方法

为了进一步提高遥感图像建筑物区域的识别精度,提出了一种基于中值稳健扩展局部二值模式(median robust extended local binary pattern,MRELBP)、Franklin矩和布谷鸟优化支持向量机(support vector machine,SVM)的分类方法。首先,通过MRELBP特征算子计算图像块的纹理特征向量,并根据Franklin矩得到形状特征向量,组合图像块的纹理特征向量和形状特征向量得到综合特征向量;然后,利用训练样本对SVM进行训练,同时由布谷鸟搜索算法对SVM的核函数参数和惩罚因子进行优化;最后,通过训练好的SVM得到建筑物区域识别结果。通过30组试验的结果表明,与基于三原色(red green blue,RGB)和SVM的分类方法、基于LBP和SVM的分类方法、基于Zernike矩和SVM的分类方法相比,本文提出的方法所识别的遥感图像建筑物区域准确度更高。     

A Multiple SVM System for Classification of Hyperspectral Remote Sensing Data

With recent technological advances in remote sensing sensors and systems, very high-dimensional hyperspectral data are available for a better discrimination among different complex land-cover classes. However, the large number of spectral bands, but limited availability of training samples creates the problem of Hughes phenomenon or ‘curse of dimensionality’ in hyperspectral data sets. Moreover, these high numbers of bands are usually highly correlated. Because of these complexities of hyperspectral data, traditional classification strategies have often limited performance in classification of hyperspectral imagery. Referring to the limitation of single classifier in these situations, Multiple Classifier Systems (MCS) may have better performance than single classifier. This paper presents a new method for classification of hyperspectral data based on a band clustering strategy through a multiple Support Vector Machine system. The proposed method uses the band grouping process based on a modified mutual information strategy to split data into few band groups. After the band grouping step, the proposed algorithm aims at benefiting from the capabilities of SVM as classification method. So, the proposed approach applies SVM on each band group that is produced in a previous step. Finally, Naive Bayes (NB) as a classifier fusion method combines decisions of SVM classifiers. Experimental results on two common hyperspectral data sets show that the proposed method improves the classification accuracy in comparison with the standard SVM on entire bands of data and feature selection methods.     

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.     

Optimizing support vector machine learning for semi-arid vegetation mapping by using clustering analysis

In remote sensing communities, support vector machine (SVM) learning has recently received increasing attention. SVM learning usually requires large memory and enormous amounts of computation time on large training sets. According to SVM algorithms, the SVM classification decision function is fully determined by support vectors, which compose a subset of the training sets. In this regard, a solution to optimize SVM learning is to efficiently reduce training sets. In this paper, a data reduction method based on agglomerative hierarchical clustering is proposed to obtain smaller training sets for SVM learning. Using a multiple angle remote sensing dataset of a semi-arid region, the effectiveness of the proposed method is evaluated by classification experiments with a series of reduced training sets. The experiments show that there is no loss of SVM accuracy when the original training set is reduced to 34% using the proposed approach. Maximum likelihood classification (MLC) also is applied on the reduced training sets. The results show that MLC can also maintain the classification accuracy. This implies that the most informative data instances can be retained by this approach.     

Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery

Land cover classification using remotely sensed data requires robust classification methods for the accurate mapping of complex land cover area of different categories. In this regard, support vector machines (SVMs) have recently received increasing attention. However, small number of training samples remains a bottleneck to design suitable supervised classifiers. On the other hand, adequate number of unlabeled data is available in remote sensing images which can be employed as additional source of information about margins. To fully leverage all of the precious unlabeled data, integration of filtering in a transductive SVM is proposed.Using two labeled image datasets of small size and two large unlabeled image datasets, the effectiveness of the proposed method is explored. Experimental results show that the proposed technique achieves average overall accuracies of around 4.5–7.8%, 0.8–2.6% and 0.9–2.2% more than the standard inductive SVM (ISVM), progressive transductive SVM (PTSVM) and low density separation (LDS) classifiers, respectively on larger domains in case of labeled datasets. Using image datasets, visual interpretation from the classified images as well as the segmentation quality reveal that the proposed method can efficiently filter informative data from the unlabeled samples.     

结合随机森林面向对象的森林资源分类

针对森林资源分类研究较少且缺少相对简单有效的方法的情况,提出一种结合面向对象和随机森林的森林资源分类方法。面向对象分割技术可减少“椒盐效应”,随机森林分类算法具有高准确度、抗噪声能力强、性能稳定等优势。鉴于此,通过调整面向对象的分割参数,构造最优特征空间及估算随机森林中决策树的数量等,构建了最优的面向对象随机森林分类模型。另外,选择了SVM算法作对比试验。试验结果显示,本文分类算法的总体精度达到83.34%,Kappa系数为0.7892,明显高于SVM,能够有效提高森林资源分类的精度。     

结合光谱与纹理信息的SVM遥感土壤盐渍化信息提取研究

本文为了提高地物识别的正确性,克服异物同谱和同物异谱现象,以渭干河?库车河三角洲绿洲为例,利用ETM+数据,探讨了该绿洲盐渍化土地覆盖信息的提取方法。文章提出了基于SVM的光谱和纹理两种信息复合的分类方法,通过此方法对该绿洲进行分类研究,并将分类结果与最小距离法、最大似然法(MLC)和单源数据(光谱)SVM分类结果进行定性和定量比较分析。研究结果表明:该方法能够有效地解决单数据源分类效果破碎、分类精度不高等问题,并对高纬输入向量具有较高的推广能力,因此该方法更适合于遥感图像分类和盐渍化信息提取,是地物遥感信息提取的有效途径。