基于CNN的不同空间分辨率影像土地覆被分类研究

基于卷积神经网络（Convolutional Neural Networks, CNN）和5种不同空间分辨率的遥感影像,对西宁市东部一区域开展土地覆被分类研究,旨在探索CNN在不同空间分辨率下进行影像分类的差异性和对不同地物的提取能力。为提高样本的选择效率,引入了窗口滑动方法进行辅助选样。研究表明5种不同空间分辨率影像的总体分类精度均达89%以上,Kappa系数达0.86以上,分类精度较高。在所涉及的分辨率尺度范围内,空间分辨率越高,CNN分类结果越精细,并能保持较高的分类精度,表明CNN更适合高空间分辨率影像分类;但同时影像空间分辨率越高,地物表现出较高的类内变异性和低类间差异性,分类精度有降低的趋势。相比较而言,SPOT 6影像的分类精度最高,同时窗口滑动是一种有效的样本辅助选择方法。研究对今后同类工作具有一定的借鉴意义。     

Sentinel-2 Satellite Image Fusion Methodand Quality Evaluation Analysis

Sentinel-2 satellite sensors acquire three kinds of optical remote sensing images with different spatial resolutions.How to improve the spatial resolution of lower spatial resolution bands by fusion method is one of the problems faced by Sentinel-2 applications.Taking the Sentinel\|2B image as the data source,a high spatial resolution band was generated or selected from the four 10m spatial resolution bands by four methods:the maximum correlation coefficient,the central wavelength nearest neighbor,the pixel maximum and the principal component analysis.We fused the one high spatial resolution band produced and six multispectral bands with 20 m spatial resolution by the five fusion methods of PCA,HPF,WT,GS and Pansharp to produce six multispectral bands with 10 m spatial resolution and the fusion results were evaluated from three aspects:qualitative and quantitative (information entropy,average gradient,spectral correlation coefficient,root mean square error and general image quality index) and classification accuracy of fused images.Results show that the fusion quality of Pansharp with the maximum correlation coefficient is better than other fusion methods,and the classification accuracy is slightly lower than the GS with the pixel maximum of the highest classification accuracy and far higher than the original four multispectral image with 10 m spatial resolution.According to the classification accuracy of experimental data,different fusion methods have different advantages in extraction of different ground objects.In application,appropriate schemes should be selected according to actual research needs.This research can provide reference for Sentinel-2 satellite and similar satellite data processing and application.     

An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification

In recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classi?cation. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images.     

基于CNN的吉林一号卫星城市土地覆被制图潜力评估

以吉林一号视频07B星高分遥感影像为基础,采用卷积神经网络（CNN）对城区土地覆被进行精细分类,设置多组光谱变量集合,并与最大似然法、多层感知机和支持向量机分类方法进行对比,全面评估分析各方法对城区土地覆被信息提取的适用性及波谱特征对分类精度的影响。结果表明：CNN模型的分类精度最高,总体精度高于90%,相比其他方法提高幅度达12%以上,能够显著降低“椒盐”噪音;红边波段对所有方法总体分类精度贡献十分有限,而近红外波段对分类精度的提升较为明显;总体而言,红边和近红外波段对CNN分类精度影响较为微弱。深度学习应用于吉林一号高分遥感数据能获取高精度城区土地覆被分类图,可为城市土地资源配置,城市规划与管理提供重要的支撑。     

Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case

The purpose of this paper is to evaluate spatial resolution effects on image classification. Classification maps were generated with a maximum likelihood (ML) classifier applied to three multi-spectral bands and variance texture images. A total of eight urban land use/cover classes were obtained at six spatial resolution levels based on a series of aggregated Colour Infrared Digital Orthophoto Quarter Quadrangle (DOQQ) subsets in urban and rural fringe areas of the San Diego metropolitan area. The classification results were compared using overall and individual classification accuracies.

Classification accuracies were shown to be influenced by image spatial resolution, window size used in texture extraction and differences in spatial structure within and between categories. The more heterogeneous are the land use/cover units and the more fragmented are the landscapes, the finer the resolution required. Texture was more effective for improving the classification accuracy of land use classes at finer resolution levels. For spectrally homogeneous classes, a small window is preferable. But for spectrally heterogeneous classes, a large window size is required.     

基于多时相协同变化检测的耕地撂荒遥感监测

针对地表覆被复杂、地块破碎等原因导致的撂荒地提取精度较低问题,提出一种基于多时相协同变化检测的耕地撂荒信息提取方法。以河北省石家庄市鹿泉区为研究区,采用Sentinel?2A和Landsat 7多光谱影像,在野外样本的支持下,分析耕地各种覆盖类型的归一化植被指数（Normalized Difference Vegetation Index,NDVI）季相变化规律,以季节性撂荒、常年性撂荒、冬小麦、多年生园地为分类体系,构建多时相协同变化检测模型,开展研究区耕地撂荒状态遥感监测。研究结果表明：基于Sentinel?2A影像的季节性撂荒和常年撂荒耕地的分类精度分别为95.83%和96.55%;基于Landsat 7影像的季节性撂荒和常年撂荒耕地的分类精度分别为91.67%和93.10%;2019年鹿泉区季节性撂荒占耕地面积的4.7%,常年撂荒耕地占7.1%。利用该方法能够快速、准确地获取研究区耕地空间分布、面积等信息,对于不同分辨率的影像均具有较好的撂荒地提取精度。     

基于卷积神经网络的青海湖区域遥感影像分类

科学准确的获取青海湖区域土地覆盖分类对于研究该区域生态环境变化有着重要的意义.本文使用30米分辨率的LandSat 8 OLI青海湖区域遥感影像数据展开相关研究,30米分辨率属于中等分辨率,当前中分遥感影像的分类方法尚存在特征提取困难、分类精度不高等问题.本文借鉴GoogLeNet Inception结构,设计并提出了一种卷积神经网络模型进行特征提取及分类,分析了用于样本生成的邻域窗口尺寸对分类结果的影响,并与最大似然分类和SVM分类方法进行比较.结果表明,在窗口尺寸为9×9时,CNN模型的总体分类效果最好,且CNN的分类结果明显优于最大似然分类方法和SVM.     

面向土地覆盖分类的MODIS影像融合研究

MODIS影像的多波段及其1、2波段的250 m中等分辨率为大区域中空间分辨率的土地覆盖制图提供了可能。为了有效利用MODIS影像的空间和光谱信息,使用SFIM、HPF和PCA变换等遥感影像融合方法,分别采用MODIS影像的波段1(b1)和波段2(b2)对3~7(b3~b7)波段进行融合,并就融合影像的光谱保真度和分类精度对6种不同融合结果进行评价。结果表明不同的融合结果得到的分类精度均有不同程度的提高;3种融合方法中使用b2的融合效果均优于b1;SFIM变换在光谱失真较小的情况下能够较大程度地提高分类精度。因此使用b2的SFIM变换可以用于提高MODIS土地覆盖图的空间分辨率和精度。     

The use of texture for image classification of black & white air photographs

The use of black & white (B&W) air photographs for the production of historic land cover maps can be done by image classification, using additional texture features. In this paper we evaluate the importance of a number of parameters in the image classification process based on texture, such as the window size, angle and distance used to produce the texture features, the number of features used, the image quantization level and its spatial resolution. The evaluation was performed using five photographs from the 1950s. The influence of the classification method, the number of classes searched for in the images and the post‐processing tasks were also investigated. The effect of each of these parameters for the classification accuracy was evaluated by cross‐validation. The selection of the best parameters was performed based on the validation results, and also on the computation load involved for each case and the end user requirements. The final classification results were good (average accuracy of 85.7%, k = 0.809) and the method has proven to be useful for the production of historic land cover maps from B&W air photographs.     

U-Net Neural Networks and Its Application in High Resolution Satellite Image Classification

High-resolution remote sensing images have precise geometric structure and spatial layout, but the spectral information is limited, which increases the difficulty of classifying similar features of spectral features. Aiming at the problem of high resolution remote sensing image classification, a U-Net convolutional neural network classification method based on deep learning is proposed. Based on the remote sensing image of the Ejina Oasis GF-2 in the lower reaches of the Heihe River, the U-Net model was used to extract the five types of land cover types of Populus euphratica, Tamarix chinensis, cultivated land, grassland and bare land. The overall classification accuracy and Kappa coefficient were 85.024% and 0.795 6 respectively. Compared with the traditional Support Vector Machine(SVM) and object-oriented method, the results show that compared with SVM and object-oriented method, the U-Net model is used to classify the high-resolution remote sensing, and the classification effect is better. The ground extracts the essential features of the features to meet the accuracy requirements.     

深度学习U-Net方法及其在高分辨卫星影像分类中的应用

高分辨率遥感影像有精确的几何结构和空间布局,但是光谱信息有限,增大了对光谱特征相似地物的分类难度。针对高分辨率遥感影像分类的问题,采用深度学习U-Net模型分类方法。基于黑河下游额济纳绿洲高分二号遥感影像,通过U-Net模型提取胡杨、柽柳、耕地、草地和裸地五种地物覆被类型,分类总体精度和Kappa系数分别为85.024%和0.795 6,并与传统的支持向量机（SVM, Support Vector Machine）和面向对象的分类方法比较,结果表明：相对于SVM和面向对象,基于U-Net模型的高分辨率卫星影像地物覆被分类,能够更好地对地物本质特征进行提取,分类效果较好,满足精度要求。     

Some issues in the classification of DAIS hyperspectral data

Classification accuracy depends on a number of factors, of which the nature of the training samples, the number of bands used, the number of classes to be identified relative to the spatial resolution of the image and the properties of the classifier are the most important. This paper evaluates the effects of these factors on classification accuracy using a test area in La Mancha, Spain. High spectral and spatial resolution DAIS data were used to compare the performance of four classification procedures (maximum likelihood, neural network, support vector machines and decision tree). There was no evidence to support the view that classification accuracy inevitably declines as the data dimensionality increases. The support vector machine classifier performed well with all test data sets. The use of the orthogonal MNF transform resulted in a decline in classification accuracy. However, the decision‐tree approach to feature selection worked well. Small increases in classifier accuracy may be obtained using more sophisticated techniques, but it is suggested here that greater attention should be given to the collection of training and test data that represent the range of land surface variability at the spatial scale of the image.     

Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery

Improvement in remote sensing techniques in spatial/spectral resolution strengthens their applicability for urban environmental study. Unfortunately, high spatial resolution imagery also increases internal variability in land cover units and can cause a ‘salt-and-pepper’ effect, resulting in decreased accuracy using pixel-based classification results. Region-based classification techniques, using an image object (IO) rather than a pixel as a classification unit, appear to hold promise as a method for overcoming this problem. Using IKONOS high spatial resolution imagery, we examined whether the IO technique could significantly improve classification accuracy compared to the pixel-based method when applied to urban land cover mapping in Tampa Bay, FL, USA. We further compared the performance of an artificial neural network (ANN) and a minimum distance classifier (MDC) in urban detailed land cover classification and evaluated whether the classification accuracy was affected by the number of extracted IO features. Our analysis methods included IKONOS image data calibration, data fusion with the pansharpening (PS) process, Hue–Intensity–Saturation (HIS) transferred indices and textural feature extraction, and feature selection using a stepwise discriminant analysis (SDA). The classification results were evaluated with visually interpreted data from high-resolution (0.3 m) digital aerial photographs. Our results indicate a statistically significant difference in classification accuracy between pixel- and object-based techniques; ANN outperforms MDC as an object-based classifier; and the use of more features (27 vs. 9 features) increases the IO classification accuracy, although the increase is statistically significant for the MDC but not for the ANN.     

基于卷积神经网络的图像分类算法

针对传统图像分类方法分类精度不高的问题,文章采用了两层卷积和池化的卷积神经网络(Convolutional Neural Network, CNN)算法来对图像进行分类。从不同方面将CNN与支持向量机(Support Vector Machines, SVM)、反向传播算法(Back Propagation, BP)进行图像分类的准确率对比,实验结果表明,CNN算法图像分类的准确率高于其它两种算法。     

改进卷积神经网络在遥感图像分类中的应用

针对传统卷积神经网络（CNN）稀疏网络结构无法保留全连接网络密集计算的高效性和实验过程中激活函数的经验性选择造成结果不准确或计算量大的问题,提出一种改进卷积神经网络方法对遥感图像进行分类。首先,利用Inception模块的不同尺度卷积核提取图像多尺度特征,然后利用Maxout模型学习隐藏层节点的激活函数,最后通过Softmax方法对图像进行分类。在美国土地使用分类数据集（UCM_LandUse_21）上进行的实验结果表明,在卷积层数相同的情况下,所提方法比传统的CNN方法分类精度提高了约3.66%,比同样也基于多尺度深度卷积神经网络（MS_DCNN）方法分类精度提高了2.11%,比基于低层特征和中层特征的视觉词典等方法分类精度更是提高了10%以上。因此,所提方法具有较高的分类效率,适用于图像分类。     

土地利用分类规则集的构建与应用研究

利用高空间分辨率影像,采用面向对象的分类方法,通过多种方法确定了土地利用类型的适宜尺度,形成了多尺度的影像对象层次网络体系。对影像对象进行多特征与空间关系描述,有效集成了辅助特征和专家知识,构建了影像对象分类规则集。研究区分类结果表明:地物分布特征及其空间关系规则的应用,可以有效地提高分类精度,得到更好的语义区分和更精确的分类结果。以期仅作少许改动就可将方案应用到条件类似的高分辨率影像分类中。     

Land-use scene classification based on a CNN using a constrained extreme learning machine

ABSTRACT

Classifying land-use scenes from high-resolution remote-sensing imagery with high quality and accuracy is of paramount interest for science and land management applications. In this article, we proposed a new model for land-use scene classification by integrating the recent success of convolutional neural network (CNN) and constrained extreme learning machine (CELM). In the model, the fully connected layers of a pretrained CNN have been removed. Then, CNN works as a deep and robust convolutional feature extractor. After normalization, deep convolutional features are fed to the CELM classifier. To analyse the performance, the proposed method has been evaluated on two challenging high-resolution data sets: (1) the aerial image data set consisting of 30 different aerial scene categories with sub-metre resolution and (2) a Sydney data set that is a large high spatial resolution satellite image. Experimental results show that the CNN-CELM model improves the generalization ability and reduces the training time compared to state-of-the-art methods.     

深度学习对不同分辨率影像冬小麦识别的适用性研究

定量分析遥感影像尺度与分类精度之间的关系是进行土地覆盖分类的基础。深度学习具有从底层到高层特征非监督学习的能力，解决了传统分类模型中需要人工选择特征的问题。这种新型的分类方法的分类精度是否受到不同分辨率尺度影响，有待研究。利用深度卷积神经网络（Deep Convolutional Neural Network, DCNN）——金字塔场景分析网络（Pyramid Scene Parsing Network, PSPNet）进行4种分辨率（8、3.2、2和0.8 m）的米级、亚米级影像冬小麦分类。实验结果表明: PSPNet能够有效地进行大样本的学习训练，非监督提取出空间特征信息，实现“端—端”的冬小麦自动化分类。不同于传统分类器分类精度与分类尺度之间的关系，随着影像分辨率的逐步增高，地物表达特征越来越清晰，PSPNet识别的冬小麦精度会逐步增高，识别地块结果也越来越规整，不受分辨率尺度的影响。这对于选择甚高亚米级影像提高作物分类精度提供了实验基础。     

深度学习对不同分辨率影像冬小麦识别的适用性研究

定量分析遥感影像尺度与分类精度之间的关系是进行土地覆盖分类的基础。深度学习具有从底层到高层特征非监督学习的能力,解决了传统分类模型中需要人工选择特征的问题。这种新型的分类方法的分类精度是否受到不同分辨率尺度影响,有待研究。利用深度卷积神经网络（Deep Convolutional Neural Network, DCNN）——金字塔场景分析网络（Pyramid Scene Parsing Network, PSPNet）进行4种分辨率（8、3.2、2和0.8 m）的米级、亚米级影像冬小麦分类。实验结果表明: PSPNet能够有效地进行大样本的学习训练,非监督提取出空间特征信息,实现“端—端”的冬小麦自动化分类。不同于传统分类器分类精度与分类尺度之间的关系,随着影像分辨率的逐步增高,地物表达特征越来越清晰,PSPNet识别的冬小麦精度会逐步增高,识别地块结果也越来越规整,不受分辨率尺度的影响。这对于选择甚高亚米级影像提高作物分类精度提供了实验基础。     

结合深度学习与条件随机场的遥感图像分类

目的 为进一步提高遥感影像的分类精度,将卷积神经网络（CNN）与条件随机场（CRF）两个模型结合,提出一种新的分类方法。方法 首先采用CNN对遥感图像进行预分类,并将其类成员概率定义为CRF模型的一阶势函数;然后利用高斯核函数的线性组合定义CRF模型的二阶势函数,用全连接的邻域结构代替常见的4邻域或8邻域;接着加入区域约束,使用Mean-shift分割方法得到超像素,通过计算超像素的后验概率均值修正各像素的分类结果,鼓励连通区域结果的一致性;最后采用平均场近似算法实现整个模型的推断。结果 选用3组高分辨率遥感图像进行地物分类实验。本文方法不仅能抑制更多的分类噪声,同时还可以改善过平滑现象,保护各类地物的边缘信息。实验采用类精度、总体分类精度OA、平均分类精度AA,以及Kappa系数4个指标进行定量分析,与支持向量机（SVM）、CNN和全连接CRF相比,最终获得的各项精度均得到显著提升,其中,AA提高3.28个百分点,OA提高3.22个百分点,Kappa提高5.07个百分点。结论 将CNN与CRF两种模型融合,不仅可以获得像元本质化的特征,而且同时还考虑了图像的空间上下文信息,使分类更加准确,后加入的约束条件还能进一步保留地物目标的局部信息。本文方法适用于遥感图像分类领域,是一种精确有效的分类方法。