利用随机森林的高分一号遥感数据进行城市用地分类

为了探究国产高分一号卫星遥感影像数据面向城市用地分类的实际应用方法和效果,本文以北京市某区域为例,基于高分一号PMS数据,使用随机森林、支持向量机、最大似然法3种分类器进行了城市用地分类对比研究。结果表明,随机森林和支持向量机的总体分类精度明显优于最大似然法;最大似然法在运算时间上明显优于随机森林和支持向量机。综合分析发现,随机森林算法表现更优。它既能保证分类精度,又能保持一定的时间效率,更适合高分辨率、大数据量、多特征参数的高分一号遥感影像分类的实际生产应用。     

卷积神经网络在高分遥感影像分类中的应用

针对目前应用于高分辨率遥感影像分类的常用算法,其精度已无法满足大数据环境下的分类要求的问题,该文提出了卷积神经网络分类算法。卷积神经网络模型降低了因图像平移、比例缩放、倾斜或者共他形式的变形而引起的误差。在大数据环境下,采用卷积神经网络算法对高分辨率遥感影像进行分类,避免了特征提取和分类过程中数据重建的复杂度,提高了分类精度。通过实验比对分析,证明了卷积神经网络在高分辨率遥感影像分类中的可行性及精度优势,对遥感图像处理领域等相关工作提供了参考价值。     

高分辨率遥感影像分割方法研究

在遥感应用分析中,遥感影像分割是低层影像处理和中高层影像分析和理解的桥梁,是实现遥感影像信息自动提取的关键步骤,具有重要的意义。随着大量高分辨率遥感影像的出现,传统基于像素的影像处理方法已不能适应高分辨率遥感影像。近年来,国内外研究者们提出了面向对象影像的分析方法,而面向对象影像分析方法的关键就是影像分割,影像分割精度直接影响着高分辨率遥感信息提取和目标识别的精度。首先给出一般图像分割方法的综述;然后分析和总结了当前主要的高分辨率遥感影像分割方法,着重阐述了均值漂移、分形网络进化、马尔科夫随机场等分割方法的特点和研究现状;最后,对高分辨率遥感应用分析中影像分割方法的发展趋势进行了讨论与展望。     

高分辨率遥感影像处理进展与城市应用若干实例

遥感对地观测技术正在进入以高空间分辨率、高光谱分辨率、高时间分辨率为代表的"三高"时代,为城市绿色、健康和可持续发展提供了丰富、持续的数据源。在综述高空间分辨率遥感影像分类与目标识别、高光谱遥感影像分析与处理、多时相遥感影像信息提取发展现状与进展的基础上,结合若干实例对高分辨率遥感在城市分析中的应用进行了探讨。     

面向对象和规则的高分辨率影像分类研究

随着航天遥感技术的发展,遥感数据的空间分辨率、光谱分辨率和时间分辨率极大提高,高效解译并处理海量的、具有空间几何信息和纹理信息的地物高分辨率遥感影像数据已成为遥感领域研究的重点与难点。对此,本文提出一种面向对象和规则的遥感影像数据的分类提取方法,即通过发现和挖掘高分辨率影像丰富的光谱和空间特征知识,建立影像对象多层次网络分割分类结构,实现对遥感影像准确快速的地物分类和精度评价。以藏南地区WorldView-2影像数据为试验研究对象,采用面向对象和规则的影像分类方法进行验证试验,即综合采用均值方差法、最大面积法、精度比较法进行分析,选择3种最佳分割尺度建立多层次影像对象网络层次结构进行影像分类试验。结果表明,采用面向对象规则分类方法对高分辨率影像进行分类,能使高分辨率影像分类结果近似于目视判读的结果,分类精度更高。面向对象规则分类法的综合精度和Kappa系数分别为97.38%、0.967 3;与面向对象SVM法相比,分别高出6.23%、0.078;与面向对象KNN法相比,分别高出7.96%、0.099 6。建筑物的提取精度、用户精度分别比面向对象SVM法高出18.39%、3.98%,比面向对象KNN法高出21.27%、14.97%。     

K-L变换与NDBI指数法提取ASTER影像城市用地信息的比较

运用K-L变换和NDBI(Normalized Difference Barren Index)指数法,对试验区--沧州市及其周边地区的ASTER遥感影像进行处理,然后分别对两种方法处理后的图像采用最小距离法监督分类,提取城市用地信息,并对分类后的图像进行对比,结果表明:NDBI指数法对城市用地信息提取的效果较好.     

高分辨率SAR与光学遥感影像中道路提取方法的研究

高分辨率影像能够提供丰富的地表细节信息,从高分辨率遥感影像中进行高精度的道路提取是目前遥感信息处理的研究热点。分别以高分辨光学IKONOS影像和COSMO-Skymed SAR影像为数据源,对北京市某区域进行了道路信息自动提取方法的研究。高分辨率光学影像中采用最大似然分类进行道路信息提取,在SAR影像中则采用Otsu阈...     

结合nDSM的高分辨率遥感影像深度学习分类方法

针对高分辨率遥感影像因其地物类内差异大、光谱信息相对欠缺导致现有影像分类方法存在错分现象较多、地物边界残缺不完整等问题,本文提出了一种归一化数字表面模型（nDSM）约束的高分辨率遥感影像深度学习分类方法。首先,将nDSM数据作为附加波段叠加在遥感影像上并获取训练样本;然后,利用优化的U-Net网络进行模型训练得到最优模型;最后,利用最优模型对附加了nDSM波段的遥感影像进行地物分类。试验结果表明,本文方法引入nDSM数据用于U-Net模型训练和分类,可有效提高影像分类精度,得到更加真实可靠的分类结果。     

融入超像素分割的高分辨率影像面向对象分类

针对高分辨率遥感影像面向对象分类中容易受分割参数的影响、分类精度不稳定的问题,本文提出了一种融入超像素分割的高分辨率影像面向对象分类方法。该方法通过简单线性迭代聚类（SLIC）算法对原始影像进行聚类生成超像素影像,并在此基础上采用分形网络演化方法（FNEA）进行多尺度分割生成同质性对象,最后利用最邻近分类方法进行地物分类。试验结果表明,该方法不易受多尺度分割参数的影响,分类效果稳定,而且分类精度明显高于传统的面向对象分类方法,对于高分辨率遥感影像的广泛应用具有重要意义。     

高分辨率遥感影像下沿海地区地表覆盖信息的提取

沿海地区地表覆盖信息是全国地理国情普查的重要内容,遥感影像分类技术为沿海地区地表覆盖信息提供了一种重要方法。本文基于GF-1高分辨率遥感影像,建立了沿海地区地表覆盖分类系统,采用中国测绘科学研究院自主研发的面向对象GLC决策树分类方法和软件进行了地表覆盖分类。通过对某试验区进行分类试验,并结合该区地表覆盖标准分类图进行精度评价,验证了基于高分辨率影像,面向对象GLC决策树分类方法在沿海地区地表覆盖信息提取上的有效性及优越性,其总体分类精度和Kappa系数分别为87.201 8%、0.840 6,均高于SVM分类法。最后提出基于高分辨率遥感影像的沿海地区地表覆盖信息提取流程。     

基于高分一号卫星的城市扩张变化监测研究

廊坊是京津冀城市群的地理中心,位于京津两个国际都市之间。本文选取廊坊市中心为研究对象,利用高分一号卫星数据和航空影像,分析廊坊市2010~2016年的城市扩张变化情况,为京津冀协同发展制定政策并为城市制订规划提供依据。首先对遥感影像进行预处理,对高分一号卫星影像,按用地类型分别采用监督分类、面向对象和植被指数法提取城市2016年地表现状信息,并进行精度评价;对2010年的航空影像进行数字化,两类数据结合进行基于分类的变化检测和精度评价,分析城市空间变化特征。结果表明,厂房、建筑和未建成区分别采用监督分类、建筑阈值分类和面向对象法分类效果较好;廊坊市城市扩张的驱动力主要为经济发展、政策因素、历史条件、地形等。     

基于决策树的CBERS遥感影像分类及分析评价

以江苏省徐州市为研究区,以城市土地利用遥感分类为目标,采用CBERS多光谱数据的近红外波段、全球环境监测植被指数(GEMI)、归一化植被指数(NDVI)及主成分分析得出的第一和第二主成分作为分类的特征数据,基于先验知识和统计分析构建层次分类决策树,进而发展和改进了决策树交互式构建算法,实现了城市土地利用遥感分类。通过与最大似然分类器(MLC)和支持向量机分类器(SVM)分类结果的比较分析,表明基于多种特征的决策树分类器能够有效应用于CBERS遥感数据分类,在研究区具有良好的推广性。     

Land Use/Cover Change Detection of Tiruchirapalli City, India, Using Integrated Remote Sensing and GIS Tools

The rapid growth of urban population in India is a cause of concern among country??s urban and town planners for efficient urban planning. The drastic growth of urban areas has resulted in sharp land use and land cover changes. In recent years, the significance of spatial data technologies, especially the application of remotely sensed data and geographical information systems (GIS) has been widely used. The present study investigates the urban growth of Tiruchirapalli city, Tamilnadu using IRS satellite data for the years 1989, 1992, 1995, 1998, 2001, 2004, 2007, and 2010. The eight satellite images are enhanced using convolution spatial enhancement method with Kernel (7?×?7) edge enhance function. Supervised classification method is used to classify the urban land use and land cover. The GIS is used to prepare the different layers belonging to various land uses identified from remotely sensed data. The analysis of the results show the drastic increase of built up area and reduced green cover within the city boundary limit.     

A comparative study on four major cities in Northeastern Thailand using urban land density function

Urban land density is an important factor to understand how cities expand. An “Inverse S-shape Rule” was implemented for the first time to analyze urban land density in Northeastern Thailand using the four cities Khon Kaen, Udon Thani, Nakhon Phanom, and Nong Khai as study sites. Land density function was tested using different data classification techniques from previous studies. Each city was investigated over two different time periods between 2002 and 2015. Declining pattern characteristics of metropolitan area density outward from city centers can be quantified by fitting the parameters to urban land density functions. An inverse S-shape function was identified as the best data fit. The four selected cities showed conventional density variation for decline in urban land area from city centers to outlying areas. Overall trend indicated that cities became more compact over time since the density differences between the urban core and urban fringe were greater with increasing infilling growth within the urban boundary. All four cities increased in size over time; however, the increasing amount of built-up land in the surrounding rural areas did not follow the same trend in each case. Some functional parameters required careful interpretation because of the linear shape of the city as in the case of Nakhon Phanom. Using highly detailed urban data resulted in lower densities of urban areas compared to the conventional pixel-based classification, and this affected the overall shape of the inverse S-shape function. The fitted parameters and their changing trends indicated that the urban land density function was useful for understanding urban form and urban sprawl in Thailand. Results can be used to develop a specific framework for other cities with similar attributes in the future.     

山地城市建设用地遥感动态监测研究

为了准确掌握重庆两江新区城市建设情况,有效支撑新区规划编制及规划管理工作,利用高分辨率遥感影像,采用面向对象的遥感分类方法,结合相关辅助资料,对2009年和2010年重庆两江新区的城市建设用地现状进行了遥感监测,获取了区内的城市建设用地规模、结构和布局现状及其变化信息,并对其城市建设用地特征进行了分析,为城市精细化管理提供了技术支撑。     

Utility of image point cloud data towards generating enhanced multitemporal multisensor land cover maps

Multitemporal land cover classification over urban areas is challenging, especially when using heterogeneous data sources with variable quality attributes. A prominent challenge is that classes with similar spectral signatures (such as trees and grass) tend to be confused with one another. In this paper, we evaluate the efficacy of image point cloud (IPC) data combined with suitable Bayesian analysis based time-series rectification techniques to improve the classification accuracy in a multitemporal context. The proposed method uses hidden Markov models (HMMs) to rectify land covers that are initially classified by a random forest (RF) algorithm. This land cover classification method is tested using time series of remote sensing data from a heterogeneous and rapidly changing urban landscape (Kuopio city, Finland) observed from 2006 to 2014. The data consisted of aerial images (5 years), Landsat data (all 9 years) and airborne laser scanning data (1 year). The results of the study demonstrate that the addition of three-dimensional image point cloud data derived from aerial stereo images as predictor variables improved overall classification accuracy, around three percentage points. Additionally, HMM-based post processing reduces significantly the number of spurious year-to-year changes. Using a set of 240 validation points, we estimated that this step improved overall classification accuracy by around 3.0 percentage points, and up to 6 to 10 percentage points for some classes. The overall accuracy of the final product was 91% (kappa = 0.88). Our analysis shows that around 1.9% of the area around Kuopio city, representing a total area of approximately 0.61 km², experienced changes in land cover over the nine years considered.     

多时相遥感数据对城市热岛效应的研究——以西安市为例

热岛效应是影响我国城市环境的重要因素,本文基于多时相的Landsat 7 ETM+和Landsat 8 TIRS影像,对西安市2002年和2013年的土地进行分类以及地表温度反演,在此基础上将土地分类影像图和温度分割影像图进行叠加,分析了不同的土地利用类型温度差异、下垫面的空间结构与热场分布的关系以及热场的分布变化与城市变迁的关系。结果表明:不同的土地利用类型的物理属性和生物学属性差异是造成城市热岛效应的内在原因,下垫面空间结构的差异是造成城市热岛效应的外在原因,城市热场的动态变化方向与城市的变迁方向具有一致性。     

基于SOM神经网络的城市土地覆盖遥感分类研究

土地覆盖及其变化的研究作为区域及全球环境变化研究所需的极为重要的地表参数,是遥感应用分析的主要内容之一。以往所采用的遥感分类方法主要针对侧重于土地社会属性的土地利用类型的分类研究且很难获得理想的精度。本文在非监督的自组织映射神经网络的基础上进行了一定的改进,构建了有监督的神经网络模型,以湖南省长沙市主城区的土地自然属性为侧重点,对其土地覆盖进行分类。实验结果表明:利用本文所使用的方法得到的分类结果,其总体精度和Kappa系数均高于传统的分类方法得出来的分类结果。     

基于多时相遥感影像的龙岩市景观格局变化分析

基于龙岩市多时相Landsat TM/ETM+数据,应用最大似然、决策树及支持向量机分类方法对龙岩市景观类型进行分类.从3种分类方法的比较得知,支持向量机分类方法表现出较高的性能,分类精度明显高于其他的分类方法.因此选择最佳的支持向量机分类结果,并结合景观生态学方法,分析了1992-2008年龙岩市新罗区景观格局及其动态变化信息.结果表明,1992-2008年新罗区主城区农业用地大幅度降低,相应转化为建筑用地,但是却保持着良好的森林覆盖率.同时城市景观组分经历了由扩散式增长过程到粘合式集聚增长过程的转变,城市形态由不稳定形态逐步向稳定形态演化.整体上而言,城市景观呈现出破碎度变小、多样性降低和聚集度升高的发展趋势,建筑用地是龙岩市新罗区的主要景观类型.     

GIS-based sustainable city compactness assessment using integration of MCDM,Bayes theorem and RADAR technology

In recent decades, compact urban development and smart cities are recognised as most sustainable urban form in an effort to protect natural environment. Therefore, evaluation of existing compactness and sustainability of an area is an essential task before the real development takes place. In the literature, it is possible to see some studies on city’s compactness assessment and most of them have considered only a few aspects of compact development analysis. This paper aims to analyse urban sustainability of Kajang city (Malaysia) through a comprehensive city compactness assessment using geographical information system and radar remote sensing technology. To measure building density, a RADAR image of the study area was used to extract built-up areas with the aid of pixel-based and object-based classification schemes. Mixed land use development, urban density and intensity were the main indicators of the analysis. Finally, multicriteria decision-making and Bayes theorems were applied for overall compactness assessment. Building density analysis was validated using standard confusion matrix, which showed more than 90% accuracy. Similarly, the root-mean squared error showed 0.35 for object-based classification. The results classified the zones of the Kajang city in the range of least to most compact zones with the compactness value of 0.00273–0.0146, respectively. The results obtained in this study can help local government to improve the compactness of least compact zones to make Kajang city more sustainable. Furthermore, the results revealed that efficient public transportation and proper community facilities are the key factors to achieve sustainable urban development.