基于空间抽样的上海市GlobeLand302020数据精度评估

针对上海GlobeLand302020土地覆盖产品,应用顾及空间异质性的类别-异质性分层抽样方法进行抽样,将研究区各地图类别划分为匀质区和异质区子类,按照内曼分配方法布设验证样本,在研究区域内抽取2500个验证像素,并参考同时期多源Google Earth高分遥感影像数据进行样本判读,获得参考分类即真实类别信息,对区域...     

自适应模糊规则分类方法及在TM土地覆盖分类中的应用研究

根据自组织网络和模糊逻辑推理,实现土地覆盖自适应模糊规则分类方法。该方法通过网络的节点和权值提取出模糊规则,调整网络中节点个数(即相应增加规则节点数)和权值向量,使模糊规则自动生成,并利用模糊逻辑推理,完成TM土地覆盖分类。对拒分类的像元,自适应增加K值使其可分。该方法所得分类精度及Kapp系数与最大似然分类方法结果相比分别提高了2.7%和2.9%;与自组织网络相比,总精度相差不大,而Kapp系数低1%。实验证明,如何提取和表示非光谱知识,从而解决类别混淆等问题,是提高自适应模糊规则分类性能的关键     

面向类型特征的自适应阈值遥感影像变化检测

为了实现两个不同年份单时相遥感影像之间的土地覆盖变化检测，提出了一种基于土地覆盖类型特征自适应确定阈值的遥感影像变化检测方法。以2015年土地覆盖数据为基础，综合2013年和2015年Landsat 8-OLI影像数据，首先，采用时相不变点群法TIC（Temporally Invariant Cluster）保证了两期影像辐射水平的一致性。其次，对两期影像进行多尺度分割，并在各级尺度下构建分割对象的变化向量。然后，采用最大类间方差的方法分别进行单一变化阈值变化检测以及基于土地覆盖类型的多阈值变化检测分析，并利用目视解译样点进行精度验证与评价。结果表明：（1）单一阈值变化检测结果的总体精度为79.6%，Kappa系数为0.601，多阈值变化检测结果的总体精度为87.2%，Kappa系数为0.741，多阈值变化检测具有更高的精度。（2）进一步逐土地覆盖类型精度评价可知，多阈值变化检测能在一定程度上减弱物候期的影响，具有更高的稳定性。该研究以土地覆盖数据为底图，逐类别的选取变化检测阈值，提高了变化区域检测的精度，在大范围高效更新土地覆盖数据的应用中具有一定的参考价值。     

煤田火区特征的土地覆盖分类方法 ——以乌达煤田火区为例

土地覆盖变化是土地分析与评价和生态环境变化预测的重要科学基础, 通过精确的土地覆盖分类方法 获取高精度的土地覆盖图是研究煤田火区生态环境变化的必要手段。本文以最大似然法、光谱角度法、面向对象 分类法和基于复合分区的分层分类法进行乌达煤田火区土地覆盖分类的方法研究。研究结果表明, 基于复合分区的 分层分类方法分类精度较高, 总体分类精度为92.97%, kappa 系数为0.9155。该方法通过基于地表热辐射特征、热 异常状况、地貌类型, 以及对生态系统扰动状况等的划分, 减少了地物信息的混淆度, 即通过提     

基于多项Logit模型的土地覆被分层分类方法研究

探讨了一种利用多项Logit模型分层提取土地覆盖专题信息的方法.考虑客观存在的异物同谱现象,构建分层分类体系,针对不同层的地物类别选取不同的预测变量构建多项Logit模型,分步骤地提取各地物类专题信息.将此方法应用于美国蒙大拿州中部地区的土地覆盖专题信息提取,结果表明,该方法较常规的使用同一组特征变量构建单一模型一次性地划分所有地物类的方法在总体分类精度上有了明显改善.     

遥感影像变化检测样本自动抽样

在遥感影像结合矢量数据先验信息的变化检测中,需要从分割后的影像对象中抽取一定数量、具有相同类别属性的样本,其中不可避免地抽到类别属性不一致的样本,如何剔除这些样本是抽样过程中必须解决的重点问题,在目前已有的方法中,一般是通过人工目视判别完成的。样本的自动提取是实现自动变化检测的关键环节,本文提出一种变化检测样本自动抽样方法,主要包括样本的空间布设和异常样本自动检测两个环节。该方法首先利用矢量数据提取抽样图层,用抽样图层分割遥感影像,获取影像对象。其次是根据抽样区域范围、影像对象分布特征和地形特征布设变化检测样本。然后根据样本的先验类别属性构建特征空间向量,计算样本在特征空间的局部可达密度,由局部可达密度计算样本的异常度指数,并根据特征空间密度异常指数剔除异常样本,完成变化检测样本自动提取。最后以耕地、林地和居民地为例进行了抽样试验。结果表明,邻域参数k按样本布设总数的1/5—1/3取值、异常度阈值设定为80%时,可以实现异常样本0漏检率,能够准确、高效实现变化检测样本的自动提取。     

分类器和时相结合的流域下垫面分类方法

文章探讨提高卫星遥感大范围流域下垫面分类方法:通过集合贝叶斯分类器和决策树分类器的优势,充分利用TM影像覆被信息,结合影像时相动态信息以获得分类准确的土地覆盖/利用类型;再结合DEM生成的坡度信息得到下垫面类型,最终确定水文地理单元.以河南省的东湾流域为例进行验证,结果表明:贝叶斯法和决策树法分类各有优势,两者结合可以获取更准确的土地覆盖/利用分类结果,辅以时相类信息可以进一步修正类别间的混淆.     

基于不同抽样方法的安义县土地资源遥感监测精度评价研究

遥感已成为土地资源监测的主要手段,土地资源遥感监测结果在使用前,必须进行客观可靠的精度验证和分析,以保持遥感监测结果的可靠性。其中,抽样方法是影响土地资源遥感精度评价的一个重要因素。利用不同分辨率遥感数据获取的安义县土地利用/覆盖信息,进行简单随机抽样、分层抽样和等距抽样三种不同抽样方式下的精度检验分析,评估不同抽样方式下的精度检验效果。     

基于高分一号时间序列数据的沙化土地分类

以高分一号(GF-1)16 m空间分辨率多光谱影像为数据源,对沙化土地类型的光谱特征以及其全年的NDVI变化特征进行了分析,发现时间序列数据变化信息可提高沙化土地类别之间的可分离度。对单一时相影像的分类结果和加入时间序列NDVI之后的分类结果进行了对比分析,结果表明,基于生长季单一时相原始影像的分类结果精度为73.34%,Kappa系数为0.7;非生长季单一影像与NDVI时间序列数据的分类结果总体精度为81.44%,Kappa系数为0.77;生长季单一时相影像并加入NDVI时间序列数据之后精度提高到了92.04%,Kappa系数达0.87,明显改善了对沙化土地类型的识别精度。表明单时相影像结合时间序列NDVI数据在沙化土地分类识别中有巨大的应用潜力。     

老挝Phonxay区土地利用/土地覆盖遥感调查

老挝是一个发展中国家,境内的大多数地方没有开展过土地利用/土地覆盖调查。本文选择老挝琅勃拉邦省的Phonxay区为研究区域,利用Landsat OLI数据进行土地利用/土地覆盖遥感调查与分析。研究过程中,利用ArcGIS Desktop选择训练样本和验证样本,通过Python和ArcPy编程开发了图像分类、精度评价以及面积统计的工作流程序,实现了快速得到分类结果和精度评价信息,分类结果的总精度为89.53%,Kappa系数为0.81。     

Application of Earth Remote Sensing and GIS in Mapping Land Cover Patterns in Kinangop Division, Kenya

<正>Land cover is a fundamental variable that links many facets of the natural environment and a key driver of global environmental change.Alterations in its status can have significant ramifications at local,regional and global levels.Hence,it is imperative to map land cover at a range of spatial and temporal scales with a view to understanding the inherent patterns for effective characterization,prediction and management of the potential environmental impacts.This paper presents the results of an effort to map land cover patterns in Kinangop division,Kenya,using geospatial tools.This is a geographic locality that has experienced rapid land use transformations since Kenya's independence culminating in uncontrolled land cover changes and loss of biodiversity.The changes in land use/cover constrain the natural resource base and presuppose availability of quantitative and spatially explicit land cover data for understanding the inherent patterns and facilitating specific and multi-purpose land use planning and management.As such,the study had two objectives viz.(i) mapping the spatial patterns of land cover in Kinangop using remote sensing and GIS and;(ii) evaluating the quality of the resultant land cover map.ASTER satellite imagery acquired in January 23,2007 was procured and field data gathered between September l0 and October 16,2007.The latter were used for training the maximum likelihood classifier and validating the resultant land cover map.The land cover classification yielded 5 classes,overall accuracy of 83.5%and kappa statistic of 0.79,which conforms to the acceptable standards of land cover mapping. This qualifies its application in environmental decision-making and manifests the utility of geospatial techniques in mapping land resources.     

Modelling Changes in Land Cover Patterns in Mtunzini,South Africa Using Satellite Imagery

Land is the basic resource that is needed by man in order to survive: It provides humans with living space, nutrition and energy resources. The rapid growth of the human population, climate change and pollution on a catastrophic scale has caused the quality of land resources to be compromised. Remote sensing is a useful tool in land cover change detection providing information to decision makers. The aim of this study was to evaluate land cover changes in the Mtunzini area in South Africa over the past 18 years; determine why changes have occurred and predict land cover patterns for future years. In this study a supervised classification was used to detect land cover classes of the Mtunzini area from 1992 to 2009 using four Landsat images in the time series analysis. The supervised classification had an accuracy of 80.80 % which was used to model land cover changes. Commercial sugar cane and forest plantation classes increased throughout the time series. It was estimated in the modelling procedure that bushland (42.11 %) and bare soil (35 %) would be changed to commercial sugar cane. This is indicative of the expanding agriculture sector in Mtunzini. Natural vegetation is predicted to be disturbed: 18 % of bushland and 15.07 % of dense bush are expected to be replaced by rural dwellings. This is owing to a potential increase in the rural population and a reduced local economic growth. This study highlights the need for increased vigilance of the forestry industry and commercial sugar cane farms which may be encroaching on natural vegetation and livelihoods of local residents. Strategic planning and proper management of natural vegetation types is needed as these land cover types are decreasing rapidly.     

Monitoring Detailed Land‐Cover Changes in Shrubland Habitat Reserves Using Multi‐temporal IKONOS Data

Abstract

The objective of this study was to explore the utility of multi‐temporal, multi‐spectral image data acquired by the IKONOS satellite system for monitoring detailed land cover changes within shrubland habitat reserves. Sub‐pixel accuracy in date‐to‐date registration was achieved, in spite of the irregular relief of the study area and the high spatial resolution of the imagery. Change vector classification enabled features ranging in size from tens of square meters to several hectares to be detected and six general land cover change classes to be identified. Interpretation of the change vector classification product in conjunction with visual inspection of the multi‐temporal imagery enabled identification of specific change types such as: vegetation disturbance and associated increase in soil exposure, shrub removal, urban edge vegetation clearing and fire maintenance, increase in vegetation cover, spread of invasive plant species, fire scars and subsequent recovery, erosional scouring, trail and road development, and expansion of bicycle disturbances.     

Performance Analysis of Maximum Likelihood and Artificial Neural Network Classifiers for Training Sets with Mixed Pixels

This study evaluates the performance of an artificial neural network, specifically a multilayer perceptron, and a maximum likelihood algorithm to classify multitemporal Landsat ETM+ remote sensor data. The study area in Turkey is a mountainous region that contains many small scattered fields, usually 5-10 pixels in size. The classifiers were employed to identify eight land cover/use features covering the bulk of the study area using the same training and test datasets in order to avoid any difference resulting from sampling variations. Results show that the neural network approach performed better in extracting land cover information from multispectral and multitemporal images with training data sets including a large amount of mixed and atypical pixels. The maximum likelihood classifier was found to be ineffective, particularly in classifying spectrally similar categories and classes having subclasses.     

Production of global land cover data – GLCNMO

Abstract

Global land cover is one of the fundamental contents of Digital Earth. The Global Mapping project coordinated by the International Steering Committee for Global Mapping has produced a 1-km global land cover dataset – Global Land Cover by National Mapping Organizations. It has 20 land cover classes defined using the Land Cover Classification System. Of them, 14 classes were derived using supervised classification. The remaining six were classified independently: urban, tree open, mangrove, wetland, snow/ice, and water. Primary source data of this land cover mapping were eight periods of 16-day composite 7-band 1-km MODIS data of 2003. Training data for supervised classification were collected using Landsat images, MODIS NDVI seasonal change patterns, Google Earth, Virtual Earth, existing regional maps, and expert's comments. The overall accuracy is 76.5% and the overall accuracy with the weight of the mapped area coverage is 81.2%. The data are available from the Global Mapping project website (http://www.iscgm.org/). The MODIS data used, land cover training data, and a list of existing regional maps are also available from the CEReS website. This mapping attempt demonstrates that training/validation data accumulation from different mapping projects must be promoted to support future global land cover mapping.     

Land cover dynamics monitoring with Landsat data in Kunming,China: a cost-effective sampling and modelling scheme using Google Earth imagery and random forests

Changes in forest composition impact ecological services, and are considered important factors driving global climate change. A hybrid sampling method along with a modelling approach to map current and past land cover in Kunming, China is reported. MODIS land cover (2001–2011) data-sets were used to detect pixels with no apparent change. Around 3000 ‘no change points’ were systematically selected and sampled using Google Earth’s high-resolution imagery. Thirty-five per cent of these points were verified and used for training and validation. We used Random forests to classify multi-temporal Landsat imagery. Results show that forest cover has had a net decrease of 14385?ha (1.3% of forest area), which was primary converted to shrublands (11%), urban and barren land (2.7%) and agriculture (2.5%). Our validation indicates an overall accuracy (Kappa) of 82%. Our methodology can be used to consistently map the dynamics of land cover change in similar areas with minimum costs.     

Multi-temporal remote sensing data applied in automatic land cover update using iterative training sample selection and Markov Random Field model

Automatic land cover update was an effective means to obtain objective and timely land cover maps without human disturbance. This study investigated the efficacy of multi-temporal remote sensing data and advanced non-parametric classifier on improving the classification accuracy of the automatic land cover update approach integrating iterative training sample selection and Markov Random Fields model when the historical remote sensing data were unavailable. The results indicated that two-temporal remote sensing data acquired in one crop growth season could significantly improve the classification accuracy of the automatic land cover update approach by approximately 3–4%. However, the support vector machine (SVM) classifier was not suitable to be integrated in the automatic land cover update approach, because the huge initially selected training samples made the training of the SVM classifier unrealizable.     

基于多级决策树分类的土地利用与覆盖信息提取

结合Landsat-8遥感数据,采用多级决策树分类方案,利用归一化植被指数、波段比值、主成分分量等光谱特征参数并融合其他非遥感知识,对黄河三角洲地区土地利用与覆盖的信息展开了全面的提取、研究与分析,获得了该地区5个一级类、12个二级类地物的分布情况,分类总体精度93.88%,优于传统监督分类。同时采用聚类、分类叠加和人机交互等分类后处理操作以获得更贴近地面实际的制图效果,开展基于海岸线的缓冲区分析以获得各地物特别是距离海岸线10 km、20 km范围内地物类型的空间分布并完成相关制图与分析,为黄河三角洲地区滨海土地的利用与开发提供了数据支持。