辅以纹理特征的高分辨率遥感影像分类

为了提高对高分辨率影像的分类精度,通过灰度差矢量法快速提取纹理特征,利用BP神经网络并辅以纹理特征,对一幅江西某地0.2m分辨率的航空影像进行分类。结果显示,对比度纹理特征能较好地反映该影像的纹理信息;对光谱特征不典型、纹理特征明显的人工树林,分类精度可达到90%以上;增加纹理特征后,影像分类的总精度也由55%提高到94%。表明这种结合纹理特征和BP神经网络的分类方法,能提高对高分辨率影像分类的精度。     

顾及纹理特征贡献度的变化影像对象提取算法

遥感影像变化检测是全球变化研究的重要内容。基于两期遥感影像的变化检测方法存在数据条件要求苛刻、难以充分利用快速发展的多源遥感影像数据等问题。目前许多变化检测的参考数据中包含了一期分类矢量数据,矢量数据中往往包含了位置、形状、大小和类别属性等先验信息,充分利用这些先验信息将可提高变化检测精度。提取变化影像对象是结合矢量数据和遥感影像进行变化检测的核心步骤。本文提出了一种顾及纹理特征贡献度的变化影像对象提取方法。该方法利用矢量数据分割遥感影像,获取影像对象,计算影像对象纹理特征值。根据信息增益原理计算纹理特征参数的特征贡献度,选择特征参数。由贡献度指数大小确定纹理特征参数权重,计算影像对象与先验要素类别的相似度系数,提取变化影像对象。试验结果表明,基于纹理特征贡献度的特征参数选择,能有效地提高变化影像对象提取结果的精度。     

Wavelet Based Post Classification Change Detection Technique for Urban Growth Monitoring

Urban areas are the most dynamic region on earth. Their size has been constantly increased during the past and this process will go on in the future. Since there is no standard policy and guidelines for construction of buildings and urban planning, cities tend to have irregular growth. Many cities in the world face the problem of urban sprawl in its suburbs. So issues of urban sprawl need to be settled with the help of technologies such as satellite remote sensing and automated change detection. This paper presents a wavelet based post classification change detection technique that is applied to 1996 and 2004 MSS images of Madurai City, South India to determine the urban growth. The classification stage of the technique uses coilflet wavelet filter to correlate with the MSS land cover images of Madurai city to derive texture feature vector and this feature vector is inputted to a fuzzy-c means classifier, an unsupervised classification procedure. The post classification change detection technique is employed for identifying the newly developed urban fringe of the study area. The error matrix analysis is used to assess the accuracy of the change map. The performance of the presented technique is found superior than that of classical change detection methods such as image differencing, change vector analysis and principal component analysis.     

A new approach for finding an appropriate combination of texture parameters for classification

This article is an attempt to suggest a new approach for eliminating the lengthy process of selecting various parameters for extracting texture features and to quantify the relative importance of the parameters affecting textural classification. A multivariate data analysis technique called ‘conjoint analysis’ has been used in the study to analyse the relative importance of these parameters. Results indicate that the choice of texture feature and window size have higher relative importance in the classification process than quantization level or the choice of image band for extracting texture feature. Results of the classification of an Indian urban environment using spatial property (texture) have also been reported. It was observed that the classification incorporating texture features using grey level co-occurrence matrix and wavelet-based approach improves the overall accuracy in a statistically significant manner in comparison to pure spectral classification.     

Sentinel-2A数据支持下的雷州半岛植被类型识别

本文以雷州半岛为研究区,利用Sentinel-2A影像数据和真实植被样本数据,综合探讨了机器学习中随机森林与支持向量机的分类效果,并与传统的最大似然法进行比较。提取Sentinel-2A影像9个波段、7个植被指数、72个纹理特征,通过递归特征消除法挑选了10个特征组合,并将其应用于3种分类方法中,对其分类效果进行比较。结果表明:①有效使用多种特征变量是提高植被类型识别精度的关键,就不同特征对植被类型识别的重要性而言,光谱特征与纹理特征相当且大于植被指数,三者重要性相差不大;②随机森林分类效果最佳,不但能对特征进行有效选择,而且能保证植被类型提取精度,提高运行效率;③基于随机森林特征选择的递归特征消除法得到的特征组合不能对其他分类器性能进行优化,对随机森林模型本身的优化效果也有限。     

广义马尔可夫随机场及其在多光谱纹理影像分类中的应用

在二维马尔可夫随机场模型的基础上，提出顾及波段间的空间相关性，发展了一种适用于多光谱纹理影像分类的广义马尔可夫随机场模型。鉴于广义马尔可夫随机场模型的复杂性，利用最大伪似然法建立了求解模型参数的简化方程式，实现了纹理特征的快速提取。结合提取的纹理特征影像和光谱特征影像，采用概率松弛算法实现影像的分类。实验证明，提出的基于广义马尔可夫随机场的多光谱纹理影像分类算法克服了传统的基于光谱特征的分类算法的局限性，提高了纹理影像的分类精度。     

面向对象的无人机遥感影像岩溶湿地植被遥感识别

以广西桂林会仙喀斯特国家湿地公园为研究区,以无人机航摄影像为数据源,综合利用面向对象的影像分析技术、随机森林算法、阈值分类方法和Boruta全相关特征变量选择算法进行岩溶湿地植被的遥感识别。结果表明：针对不同特征变量对岩溶湿地遥感识别的贡献率而言,光谱特征（DOM > DSM） > 纹理特征（DOM > DSM） > 几何特征 > 上下文变量;两个航摄影像数据集的总体分类精度都在85%以上,Kappa系数也高于0.85。本文研究结果对基于高空间分辨率无人机可见光影像的岩溶湿地植被遥感识别在特征变量选择、分割参数选择及方法选择方面具有一定的借鉴意义。     

基于多尺度纹理和光谱信息的SVM分类研究

基于单尺度纹理和光谱信息的地物分类较难取得理想效果,本文结合多尺度纹理与光谱信息,运用SVM分类方法,对IKONOS遥感影像进行分类。结果表明:结合多尺度纹理和光谱信息的SVM高分辨率遥感影像分类,能够更好地描述地物,分类总体精度达到83.9%,与基于光谱信息的最大似然法和基于单尺度纹理和光谱信息的SVM分类方法比较,分类精度分别提高了13.8%和4.9%,该方法有助于提高高分辨率影像的分类正确率。     

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。     

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。     

结合双树复小波纹理特征和MRF模型的遥感图像分割

针对经典的小波纹理不能准确地表达影像纹理特征的问题,以及影像分割结果缺少对像元空间相关性和分布关系的考虑。本文提出了结合双树复小波（DT-CWT）纹理和马尔可夫随机场（MRF）模型的高分辨率遥感影像分割方法。首先,通过双树复小波变换提取影像纹理特征,联合光谱特征形成表达影像信息的混合特征向量;然后,将混合特征向量高斯归一化处理,并用K-means聚类的方法对特征空间中的混合特征向量聚类得到初始分割图;最后,借助马尔可夫随机场模型在初始分割结果中引入上下文信息,基于贝叶斯最大后验概率准则得到最终的分割结果。本文通过双树复小波纹理提高了特征表达的准确度,同时使用马尔可夫随机场模型减弱了分割结果中同质区域的“椒盐噪声”,从而进一步提高了高分辨率遥感影像分割的精度。     

Evaluation of semivariogram features for object-based image classification

Inclusion of textures in image classification has been shown beneficial. This paper studies an efficient use of semivariogram features for object-based high-resolution image classification. First, an input image is divided into segments, for each of which a semivariogram is then calculated. Second, candidate features are extracted as a number of key locations of the semivariogram functions. Then we use an improved Relief algorithm and the principal component analysis to select independent and significant features. Then the selected prominent semivariogram features and the conventional spectral features are combined to constitute a feature vector for a support vector machine classifier. The effect of such selected semivariogram features is compared with those of the gray-level co-occurrence matrix (GLCM) features and window-based semivariogram texture features (STFs). Tests with aerial and satellite images show that such selected semivariogram features are of a more beneficial supplement to spectral features. The described method in this paper yields a higher classification accuracy than the combination of spectral and GLCM features or STFs.     

利用Sentinel-2A数据提取长江中下游丘陵地带农作物种植信息

长江中下游丘陵地带地块细小破碎、种植结构复杂,导致作物遥感光谱特征相互纠缠,信息精确提取困难等。本文基于Sentinel-2A数据提出了多特征组合优化的丘陵地带农作物种植结构精确识别方法。首先获取研究区内主要农作物的关键物候特征信息;然后计算其光谱特征、纹理特征、地形特征值,构建原始特征集;最后采用随机森林方法对特征进行重要性排序,对原始特征集进行特征变量优化,并选择优化后的组合特征进行监督分类提取出研究区农作物信息。试验结果表明,相较于单变量特征,通过多特征优化组合分类总体精度和Kappa系数分别从80.4%和0.748提高到96.3%和0.954,有效地提高了南方丘陵地带农作物分类精度,算法稳定性较强。在南方丘陵地带农作物的识别过程中,进行特征变量优化后的地形特征与纹理特征能显著提高分类精度。     

基于分形和灰度共生矩阵纹理特征的种植型药用植物遥感分类

遥感技术应用已成为中国中药资源普查的一个重要探索方向。以红花(Carthams Tinctorius L.)为种植型药用植物实验样本品种,分别基于分形理论和灰度共生矩阵(GLCM)两种方法提取不同的纹理特征,结合光谱信息对资源三号卫星(ZY-3)影像进行最大似然方法的监督分类,对比分析分类效果和精度评价。结果显示:加入纹理特征后,总体分类精度提高了0.49%—5.31%,Kappa系数提高了0.01—0.07,结合基于双毯法的分形纹理较GLCM纹理分类总体效果提高至少两倍,其中在Matlab环境下,使用5×5滑动窗口提取的分形纹理特征的分类效果最显著,总体分类精度提高了5.31%,Kappa系数提高了0.07。对于红花分类精度,引入分形纹理特征的分类精度提高到了100%,识别的红花样地效果最完整,破碎程度最小,与其他类别区分度最高;而引入GLCM的分类精度却降低了0.55%—1.28%,可见采用分形理论比采用GLCM提取纹理特征能够更加有效地辅助ZY-3影像识别种植型药用植物。     

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.     

Optical and radar data comparison and integration: Kenya example

The purpose of this study was to evaluate the relative classification accuracies of four land covers/uses in Kenya using spaceborne quad polarization radar from the Japanese ALOS PALSAR system and optical Landsat Thematic Mapper data. Supervised signature extraction and classification (maximum likelihood) was used to classify the different land covers/uses followed by an accuracy assessment. The original four band radar had an overall accuracy of 77%. Variance texture was the most useful of four measures examined and did improve overall accuracy to 80% and improved the producer’s accuracy for urban by almost 25% over the original radar. Landsat provided a higher overall classification accuracy (86%) as compared to radar. The merger of Landsat with the radar texture did not increase overall accuracy but did improve the producer’s accuracy for urban indicated some advantages for sensor integration.     

遥感图像土地覆盖分类中多源特征数据选择研究

多源特征数据可以提高遥感图像的分类精度,选择合适的特征数据十分重要。利用基尼指数对多尺度纹理信息、主成分变换前三分量、地形数据等特征进行选择,选出最佳特征子集。利用支持向量机、神经网络分类法、最大似然法分别对全部特征数据和最佳特征子集结合多光谱数据进行分类。实验结果表明:基尼指数可以有效地对多源特征数据进行选择,特征选择可以提高分类器效率,提高分类精度。     

合理尺度纹理分析遥感影像分类方法研究

纹理分析是提高遥感影像分类精度的重要手段之一。纹理特征与地物类别尺度密切相关,应用纹理特征进行遥感影像分类, 关键在于纹理尺度的确定。对于灰度共生矩阵纹理分析来说,就是选择大小合适的纹理窗口。根据样本半变异值在较小范围内有较 大变化的特性,研究遥感影像相邻像素之间的空间关系,将半变异值开始趋于恒值时所对应的步长作为纹理分析的窗口大小,并在 纹理特征提取过程中针对每一个像素,在最大似然分类结果的约束下,适时改变其窗口大小,提取纹理特征,提出一种合理尺度纹 理分析的遥感影像分类方法。最后,选择北京市昌平区2006年SPOT 5遥感影像,利用TitanImage二次开发环境实现了该方法。实践 证明,该方法能有效提高遥感影像的分类精度。     

An Analysis of Texture Measures in PCA-Based Unsupervised Classification of SAR Images

In single-band single-polarized SAR images, intensity and texture are the information source available for unsupervised land cover classification. Every textural feature measure identifies texture patterns by different approaches. For efficient land cover classification, textural measures have to be chosen suitably. Therefore, in this letter, the role of various intensity and textural measures is analyzed for their discriminative ability for unsupervised SAR image classification into various land cover types like water, urban, and vegetation areas. To make the algorithm adaptable, these textural features are fused using principal component analysis (PCA), and principal components are used for classification purposes. To highlight the effectiveness of PCA, the difference between PCA- and non-PCA-based classifications is also analyzed. Analysis of the role of texture measures for unsupervised classification of real-world SAR data with application of PCA is presented in this letter. The analysis of how every individual feature measure contributes for classification process is presented, and then, textural measures for a feature set are chosen according to their role in improving classification accuracy. By analysis, it is observed that the feature set comprising mean, variance, wavelet components, semivariogram, lacunarity, and weighted rank fill ratio provides good classification accuracy of up to 90.4% than by using individual textural measures, and this increased accuracy justifies the complexity involved in the process.     

单变量特征选择的苏北地区主要农作物遥感识别

遥感识别多源特征综合和特征优选是提高遥感影像分类精度的关键技术。农作物遥感识别中,识别特征的相对单一和数量过多均会导致作物识别精度不理想。随机森林(random forests)采用分类与回归树(CART)算法来生成分类树,结合了bagging和随机选择特征变量的优点,是一种有效的分类方法。单变量特征选择(univariate feature selection)能够对每一个待分类的特征进行测试,衡量该特征和响应变量之间的关系,根据得分舍弃不好的特征,优选得到的特征用于分类。本文基于随机森林和单变量特征选择,利用多时相光谱信息、植被指数信息、纹理信息及波段差值信息,设计多组分类实验方案,对江苏省泗洪县的高分一号(GF-1)和环境一号(HJ-1A)影像进行分类研究,旨在选择最佳的分类方案对实验区主要农作物进行识别和提取。实验结果表明:(1)多源信息综合的农作物分类精度明显高于单一的原始光谱特征分类,说明不同类型特征的引入能改善分类效果;(2)基于单变量特征选择算法的优选特征分类效果最佳,总体精度97.07%,Kappa系数0.96,表明了特征优选在降低维度的同时,也保证了较高的分类精度。随机森林和单变量特征选择结合的方法可以提高遥感影像的分类精度,为农作物的识别和提取研究提供了有效的方法。