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。     

Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area

In this study, we investigated the performance of different fusion and classification techniques for land cover mapping in Hilir Perak, Peninsula Malaysia using RADAR and Landsat-8 images in a predominantly agricultural area. The fusion methods used are Brovey Transform, Wavelet Transform, Ehlers and Layer Stacking and their results classified into seven different land cover classes which include (1) pixel-based classifiers (spectral angle mapper (SAM), maximum likelihood (ML), support vector machine (SVM)) and (2) Object-based (rule-based and standard nearest neighbour (NN)) classifiers. The result shows that pixel-based classification achieved maximum accuracy of the optical data classification using SVM in Landsat-8 with 74.96% accuracy compared to SAM and ML. For multisource data classification, the highest overall accuracy recorded for layer stacking (SVM) was 79.78%, Ehlers fusion (SVM) with 45.57%, Brovey fusion (SVM) with 63.70% and Wavelet fusion (SVM) 61.16%. And for object-based classifiers, the overall classification accuracy is 95.35% for rule-based and 76.33% for NN classifier, respectively. Based on the analysis of their performances, object-based and the rule-based classifiers produced the best classification accuracy from the fused images.     

A semilabeled-sample-driven bagging technique for ill-posed classification problems

In this letter, a semilabeled-sample-driven bootstrap aggregating (bagging) technique based on a co-inference (inductive and transductive) framework is proposed for addressing ill-posed classification problems. The novelties of the proposed technique lie in: 1) the definition of a general classification strategy for ill-posed problems by the joint use of training and semilabeled samples (i.e., original unlabeled samples labeled by the classification process); and 2) the design of an effective bagging method (driven by semilabeled samples) for a proper exploitation of different classifiers based on bootstrapped hybrid training sets. Although the proposed technique is general and can be applied to any classification algorithm, in this letter multilayer perceptron neural networks (MLPs) are used to develop the basic classifier of the proposed architecture. In this context, a novel cost function for the training of MLPs is defined, which properly considers the contribution of semilabeled samples in the learning of each member of the ensemble. The experimental results, which are obtained on different ill-posed classification problems, confirm the effectiveness of the proposed technique.     

生成式对抗网络的高光谱遥感图像分类方法研究

针对基于深度学习的分类模型在训练样本较少时所遭受的潜在过拟合问题,提出一种具备过拟合抑制的生成式对抗网络分类算法,并应用于高光谱图像分类.该算法在每次迭代时,首先,依据训练样本的标签信息使判别器网络拟合训练样本的数据分布;然后对训练样本的高维特征进行均值最小化,该过程会重新更新判别器网络参数,减小参数的值和方差,以抑制...     

Ensemble Stacked Auto-encoder Classification on LIDAR Remote Sensing Images

Light detection and ranging system (LIDAR) can obtain diverse remote sensing datasets which contains different land cover information. The datasets offer vital and significant features for land cover classification. As a new and effective deep learning algorithm, stacked auto-encoders (SAE) consists of multiple auto-encoders in which the code of each auto-encoder is the input of the successive one. The classification precision is closely related to hidden layers, and the number of samples in fine-tuning step also affects classification results. In this paper we study the classifiers based on different number of samples and hidden layers. According to appropriate parameters, we promote SAE with adaptive boosting ensemble strategy to build new classification method. Two tests which are based on LIDAR datasets are implemented. The experiment results prove that the fusion of deep learning and ensemble learning is effective to LIDAR remote sensing images. The proposed method is robust to similar scenes classification. The overall accuracy increases 6% compared with bagging method on test 1.     

土地覆盖制图：基于最优化遥感数据的支撑向量机分类

遥感数据具有在不同空间、光谱和时间尺度上获取地表测量信息的能力,使其成为获取土地覆盖信息的一个主要数据源。影像分类即把卫星影像上的相关像元划分给某类已知的土地覆盖类型的过程。支撑向量机（SVMs）是一种土地覆盖分类的新技术。三种常用的SVMs是：基于线性和多项式的SVM以及具有高斯核函数的SVM分类器,分类能否成功地应用有赖于其各自选择的最佳参数。但是海量的遥感数据使得这些参数的确定速度十分缓慢。本文研究了一种新的基于最优化遥感数据压缩技术的SVM分类方法。研究显示用于获取SVM参数的数据量能够在不影响土地覆盖的分类精度的前提下进行压缩。数据压缩成功的应用于多项式和高斯核函数的SVM分类,而线性SVM的分类精度却非常低。     

优化子空间SVM集成的高光谱图像分类

随机子空间集成是很有前景的高光谱图像分类技术,子空间的多样性和单个子空间的性能与集成后的分类精度密切相关。传统方法在增强单个子空间性能的同时,往往会获得大量最优但相似的子空间,因而减小它们之间的多样性,限制集成系统的分类精度。为此,提出优化子空间SVM集成的高光谱图像分类方法。该方法采用支持向量机(SVM)作为基分类器,并通过SVM之间的模式差别对随机子空间进行k-means聚类,最后选择每类中J-M距离最大的子空间进行集成,从而实现高光谱图像分类。实验结果显示,优化子空间SVM集成的高光谱图像分类方法能够有效解决小样本情况下的Hughes效应问题;总体精度达到75%–80%,Kappa系数达到0.61–0.74;比随机子空间集成方法和随机森林方法分类精度更高、更稳定,适合高光谱图像分类。     

主动学习与图的半监督相结合的高光谱影像分类

针对当前高光谱影像分类时,人工标注样本费时费力以及大量未标记样本未有效利用等问题,提出了一种主动学习与图的半监督相结合的高光谱影像分类方法。首先,将像素的光谱信息与其邻域内的空间信息相结合,利用重排序机制得到一种旋转不变的空谱特征表达。在此基础上,利用主动学习算法选择最不确定性样本(即分类模糊度最大的样本),提交操作者标注得到标记样本集。最后将该标记样本与未标记样本组合,用于图的半监督分类。该算法可保证类别边界样本的选择,利于分类器的边界构造,同时,在较少标记样本情况下,通过引入大量的未标记样本,可以达到较好的分类效果。在3幅真实高光谱影像上的试验表明,该方法可以取得精度较高的分类结果。     

高光谱影像的引导滤波多尺度特征提取

为了解决高光谱遥感影像分类中单一尺度特征无法有效表达地物类间差异和区分地物边界的不足,提高影像分类精度和改善分类目视解译效果,提出了采用引导滤波提取多尺度的空间特征的方法。首先,利用主成分分析对高光谱影像进行降维,移除噪声并突出主要特征;然后,将第1主成分作为引导影像,将包含信息量最多的若干主成分分别作为输入影像,应用依次增加的滤波半径分别进行引导滤波处理提取多个尺度的特征,获得影像不同尺度的结构信息;最后,将多尺度特征输入分类器中进行影像监督分类。采用仿真数据和帕维亚大学(Pavia University)、帕维亚城区(Pavia Centre)等3幅高光谱实验数据,提取了基于引导滤波的多尺度特征、多尺度形态特征和多尺度纹理特征,输入到支持向量机、随机森林和K近邻分类器中,进行了实验。实验结果表明:采用支持向量机分类Pavia University数据,相对于采用多尺度形态特征的分类结果,引导滤波特征的总体精度提高了6.5%;Pavia Centre和Salinas两幅影像最高分类精度均由引导滤波特征实现,分别达到98.51%和98.39%。实验证实基于引导滤波提取的多尺度特征能有效地描述地物结构,进而获得更高的分类精度和改善目视解译效果。     

Object-based classification of hyperspectral data using Random Forest algorithm

This paper presents a new framework for object-based classification of high-resolution hyperspectral data. This multi-step framework is based on multi-resolution segmentation (MRS) and Random Forest classifier (RFC) algorithms. The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images. Given the high number of input features, an automatic method is needed for estimation of this parameter. Moreover, we used the Variable Importance (VI), one of the outputs of the RFC, to determine the importance of each image band. Then, based on this parameter and other required parameters, the image is segmented into some homogenous regions. Finally, the RFC is carried out based on the characteristics of segments for converting them into meaningful objects. The proposed method, as well as, the conventional pixel-based RFC and Support Vector Machine (SVM) method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics. These data were acquired by the HyMap, the Airborne Prism Experiment (APEX), and the Compact Airborne Spectrographic Imager (CASI) hyperspectral sensors. The experimental results show that the proposed method is more consistent for land cover mapping in various areas. The overall classification accuracy (OA), obtained by the proposed method was 95.48, 86.57, and 84.29% for the HyMap, the APEX, and the CASI data-sets, respectively. Moreover, this method showed better efficiency in comparison to the spectral-based classifications because the OAs of the proposed method was 5.67 and 3.75% higher than the conventional RFC and SVM classifiers, respectively.     

A Composite Semisupervised SVM for Classification of Hyperspectral Images

This letter presents a novel composite semisupervised support vector machine (SVM) for the spectral-spatial classification of hyperspectral images. In particular, the proposed technique exploits the following: 1) unlabeled data for increasing the reliability of the training phase when few training samples are available and 2) composite kernel functions for simultaneously taking into account spectral and spatial information included in the considered image. Experiments carried out on a hyperspectral image pointed out the effectiveness of the presented technique, which resulted in a significant increase of the classification accuracy with respect to both supervised SVMs and progressive semisupervised SVMs with single kernels, as well as supervised SVMs with composite kernels.     

极化SAR参数优化与光学波谱相结合的面向对象土地覆盖分类

提出一种基于极化参数优化的面向对象分类方法。该方法结合光学和SAR数据,有效提高了对地物的识别能力。本文方法的关键在于:在■分解中,使用光学影像指导SAR影像选择同质点,使其更精确地估计极化参数并结合光学波谱信息作为输入特征;使用面向对象的分类方法,仅将光学影像作为分割输入,避免SAR噪声引起的分割错误。以美国Bakersfield地区的Sentinel-1/2数据为例,确定7种地物类型,对比分析不同输入与不同分类器对分类结果的影响。研究表明,优化输入参数在纹理丰富区域能够有效提高分类精度;面向对象的分类结果更加稳定并较好地维持地表几何特征;改进分类方法较传统分类方法总体精度提高了近10%,达到92.6%。     

生成模型学习的遥感影像半监督分类

以生成模型最大似然估计为例,引入结合已标记样本和未标记样本的半监督分类方法来解决遥感影像分类中的小样本问题,应用已有的少量已标记样本初始化一个分类器,结合大量未标记样本,通过递归计算的方式对分类器进行优化,直到包含所有样本的似然函数收敛到局部极大值。通过分析遥感影像待分类类别与影像中地物类型固有特征之间的关系,设计两个在不同生成模型假设下的分类实验。结果表明,未标记样本的参与可在很大程度上提高小样本条件下的影像分类精度,但两种样本的数量应保持一个适当的比例。最后通过与在解决小样本分类问题方面有独特优势的SVM方法的分类比较,发现在小样本情况下,本文方法具有更好的应用潜力。     

半监督条件随机场的高光谱遥感图像分类

善于捕捉空间信息的条件随机场模型虽然已被应用于高光谱遥感图像分类,但条件随机场的性能受到了标注训练样本数量的制约。为解决上述问题,本文提出了一种半监督条件随机场模型用于高光谱遥感图像分类。在该模型中,首先,利用空间-光谱拉普拉斯支持向量机定义关联势函数,以利用未标注样本中包含的信息获取样本类别概率;然后,在交互势函数中嵌入未标注的空间邻域样本,以充分利用空间信息实现对样本类别概率的修正;最后,采用分布式学习策略和平均场完成半监督条件随机场的训练和推断。本文在两个公开的高光谱数据集(Indian Pines数据集,Pavia University数据集)上进行了实验。实验结果表明Kappa系数提升3.94%。     

Semisupervised Remote Sensing Image Classification With Cluster Kernels

A semisupervised support vector machine is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictions.     

迁移学习用于多时相极化SAR影像的水体提取

基于机器学习分类器的极化合成孔径雷达（synthetic aperture radar, SAR）影像水体提取方法具有较高的可靠性,但其通常依赖于大量的训练样本,利用该方法进行多时相极化SAR影像的水体提取时,在每一景影像上都人工标注足够数量的训练样本是十分困难且耗时的。同时,SAR影像上固有的相干斑点噪声会进一步加剧样本标注的难度。对此,引入迁移学习方法,利用其知识迁移能力将已有的训练样本的类别标签信息迁移至未标注的样本,以降低获取新样本所需的人工代价,提高水体提取的时效性。使用6景极化SAR影像和4种迁移学习方法进行最佳源域影像选取、样本标签迁移和水体提取实验,实验结果表明,迁移学习方法可以准确地将源域影像上的训练样本的标签信息迁移至其他影像,有效减少其他影像进行水体提取需要的人工标注样本的数量,同时能够维持较高的水体提取精度,在洪涝灾害应急响应中具有一定的应用价值。     

高分辨率遥感影像语义分割的半监督全卷积网络法

在遥感领域,利用大量的标签影像数据来监督训练全卷积网络,实现影像语义分割的方法会导致标签绘制成本昂贵,而少量标签数据的使用会导致网络性能下降。针对这一问题,本文提出了一种基于半监督全卷积网络的高分辨率遥感影像语义分割方法。通过采用一种集成预测技术,同时优化有标签样本上的标准监督分类损失及无标签数据上的非监督一致性损失,来训练端到端的语义分割网络。为验证方法的有效性,分别使用ISPRS提供的德国Vaihingen地区无人机影像数据集及国产高分一号卫星影像数据进行试验。试验结果表明,与传统方法相比,无标签数据的引入可有效提升语义分割网络的分类精度并可有效降低有标签数据过少对网络学习性能的影响。     

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.     

高分五号高光谱影像的关联对齐域适应与分类

高分五号(GF-5)搭载的高光谱传感器兼顾宽覆盖和高分辨率的特性,但在实际应用中宽覆盖范围内各种地物类别的标注十分困难。当标记样本很少甚至没有标记样本时,遥感图像分类异常困难。此时,可以采用域适应方法,借助已标记的历史数据(源域)实现对未标记数据(目标域)的分类。本文提出了一种基于稀疏矩阵变换的关联对齐域适应分类算法。首先,利用稀疏矩阵变换估计源域和目标域的协方差矩阵;然后,运用协方差关联对齐方法估计源域到目标域的变换矩阵;接着,运用估计得到的变换矩阵将源域数据进行变换,使得其与目标域对齐;最后,在变换后的源域数据上建立分类器,实现对目标域数据的分类。本文的算法在两个真实的GF-5高光谱数据集上进行了验证。实验结果表明,本文算法要优于常用的子空间对齐算法和关联对齐算法。特别地,在黄河口GF-5数据上,本文算法比原始关联对齐方法的最近邻分类准确率提升了3.5%,支持向量机分类准确率提升了2.3%。