利用空间抽样理论的遥感影像分类结果精度评价方法

遥感影像分类结果的准确性对于遥感信息的应用分析有着重要的影响。传统抽样方式下的遥感影像分类结果精度评价方法受样本量及空间布局的影响,存在效率低和信息冗余等问题。利用空间数据的相关性,将空间抽样理论应用于遥感影像分类结果的精度评价,通过与传统抽样方法比较,发现空间抽样方法应用于遥感影像分类结果的精度评价不仅降低了数据冗余,同时提高了精度评价的检验效率和准确性。     

水色水温遥感产品真实性检验误差分析

真实性检验是利用现场观测数据或其他高质量遥感产品来获取待检验遥感产品精度的技术,是遥感产品制作及其应用的前提。通过分析均方根误差、平均绝对误差和平均相对误差等多种遥感产品精度评价统计量的适用性,确定了一套水色、水温遥感产品真实性检验流程。以中分辨率成像光谱仪(MODIS)海表温度(SST)遥感产品的真实性检验实例展示了文中确定的水色水温遥感产品真实性检验流程的可行性。分析结果表明待检验产品的分布规律(样本均值和标准偏差)对检验结果的统计量会产生一定的影响,平均值对平均相对误差的影响呈现高相关性。     

基于航空高光谱影像的额济纳绿洲土地覆被提取

土地覆被分类是生态环境评价、植被变化分析以及区域生态水文过程研究的基础。航空高光谱遥感具有高机动、高空间分辨率和高光谱分辨率等特点,在土地覆被提取方面极具优势。以黑河下游机载高光谱遥感数据为基础,针对额济纳旗胡杨林国家级自然保护区植被单一、景观破碎和异质性强的景观特点,以及高光谱数据量大、冗余度高等数据特点,对比分析最小噪声变换与主成分分析两种降维方法,最大似然法、支持向量机与面向对象3种监督分类方法。依据研究结果,首先利用NDVI区分高光谱遥感数据中的植被与非植被类别,然后采用最小噪声变换分别进行降维处理,最后利用最大似然法对研究区内土地覆被类型进行分类提取,提取结果聚类处理。依据随机验证点结合地面调查数据和正射影像,对土地覆被分类结果进行精度验证,总体精度和Kappa系数分别为87.95%和0.855,表明分类结果精度高,能够为生态研究等提供有效数据。     

缅甸土地覆被遥感制图和空间格局分析

在“一带一路”倡议框架下,中缅经济走廊逐步从概念转入实质规划建设阶段,了解和掌握缅甸土地覆被的空间格局和分布特征对于合理开发利用资源、制定务实的经济廊道建设规划具有重要的战略意义。利用Landsat-8 OLI遥感影像数据,基于多分类器集成的面向对象迭代分类方法（OIC-MCE）,生产了缅甸2015年30 m分辨率土地覆被产品（MyanmarLC-2015）。采用Google Earth高分辨率影像获取验证样本用于产品精度验证,验证结果表明：MyanmarLC-2015产品的总体分类精度为89.05%,Kappa系数为0.87,各类别的用户精度和制图精度均超过72%,能够准确地反映缅甸土地覆被类型的空间格局。根据产品统计,林地是缅甸面积最大的土地覆被类型,占国土面积56.15%,以常绿阔叶林为主,占林地面积83.57%。耕地面积次之,占国土面积27.01%。地形因子对缅甸土地覆被类型空间分布格局有显著的影响,随着海拔升高,呈现出按如下顺序的垂直地带性特征：森林湿地、水田、旱地、落叶灌木林、落叶阔叶林、常绿灌木林、常绿阔叶林、常绿针叶林。从植被生产力的角度来看,缅甸东部、东北部和东南部植...     

遥感影像解译精度的分析

遥感影像的解译精度是指遥感解译图的判对率或错判率。解译精度的分析是遥感影像解译工作中一项不可缺少的过程,它对于解译成果的评价和使用都具有十分重要的意。遥感影像解译精度分析的基本方法是在解译图上选取一定数量的样本进行检验。根据检验样本的判对率得出解译图的解译精度。为了使得到的解译精度可靠,样本的选取应按照抽样理论的方法来进行。但是,从目前的遥感影像解译工作来看,解译精度的分析还没有系统规范的方法,样本的选取大多数还是按照人为的主观选择来进行。抽样的方式和样本的大小缺少科学依据,使得得到的解译精度可     

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。     

影像的土地覆被快速分类

精确的土地覆盖信息是进行碳循环、气候变化监测、土壤退化等相关科学研究的基础。随着云计算技术的不断成熟,一些高效算法与平台被不断提出,用来充分挖掘遥感数据所包含的海量信息。基于Google Earth Engine(GEE)云平台,利用随机森林监督分类法对1990、2000、2010、2017年的山西省土地覆被进行了分类。参考Google Earth高清影像选择的1580个样本点,对分类结果进行了验证;同时将分类结果与CNLUCC、GlobeLand30、FROM-GLC等现有土地覆被分类产品进行比较。验证和对比发现时间序列分类结果的总体精度达到86%~94%,比同期单时相分类总体精度提高了5%~10%;本文时间序列结果达到了CNLUCC、GlobeLand30、FROM-GLC等产品的分类精度。结果表明:①在快速准确土地覆被分类方面,时间序列影像与云平台结合,显示出时效性强、时间周期短、成本低等优势;②时间序列百分位数指标能有效地区分不同土地覆被类型的物候差别,在进行土地覆被分类方面显示出简单、易用、高效等特点。该方法对于深入研究大区域尺度的土地覆被变化过程具有重要的参考价值。     

叶面积指数产品真实性检验系统设计与实现

目前,遥感产品的真实性检验技术和方法日趋成熟,但仍无法实现标准化、自动化。标准化和自动化的真实性检验需要真实性检验数据库和软件平台的支撑。文章针对叶面积指数遥感产品,在已构建的叶面积指数真实性检验数据库的基础上,设计了叶面积指数遥感产品真实性检验系统,自动开展叶面积指数遥感产品直接验证、间接验证,给出产品精度评价报告,实现叶面积指数产品自动化真实性检验。     

多源卫星遥感土地覆被产品在南美洲的一致性分析

针对不同卫星遥感产品在不同区域缺乏一致性基准的问题,提出类型构成相似性、类别混淆程度、空间一致性及参考程度等4种方法,对比分析不同土地覆被产品间的一致性。鉴于南美洲区域土地覆被空间结构和变化对全球变化研究具有重要意义,利用上述4种方法研究了GLOBCOVER2005、GLOBCOVER2009、GLC2000、MODIS2000、GLOBELAND30-2010等5种全球卫星土地覆被产品在南美洲地区的一致性。结果表明,5种产品对于南美洲土地类型的构成刻画基本一致,且对林地识别的一致性最高;南美洲有近60%的土地具有较高的一致性;5种产品两两比较时,参考精度大致在42.27~87.59%之间,GLOBCOVER2009/GLOBCOVER2005组合的参考精度最高,反映出土地覆被动态变化所引起的误差远小于不同制作机构、不同数据源、不同判读方法所带来的制作误差。     

基于抽样理论的改进型星座覆盖分析方法

针对传统网格点方法在分析星座对目标区域的覆盖性能时,存在着计算效率不高的问题,利用抽样理论中借助样本统计量对总体参数进行估计的思想,对传统网格点方法加以了改进;通过分析星座对目标区域内所有网格点的覆盖情况与网格点经纬度之间的关系,确立了对所有网格点构成的总体采用先分层后随机的抽样方式,并分析了层的划分和样本量在各层的分配;根据不同指标的统计特征,给出了不同星座覆盖性能指标的估计方法和不同精度条件下总样本量的计算过程,并建立了改进网格点法的实施流程;最后利用改进方法计算了仿真时段内北斗卫星导航系统对某一地面区域的平均PDOP值,通过与传统网格点方法的仿真结果进行比较并对仿真数据进行分析,证明了该改进方法在保证计算精度的同时,有效地提升了计算效率。     

Accuracy assessment of mixed land cover using a GIS‐designed sampling scheme

Land cover maps, based on remotely sensed data, are widely developed and used for studying global ecosystems and land use/land cover change. However, accuracy assessment of mixed land cover classes, including varying dominance of invasive species, is complicated by uncertainty about where to define a threshold of presence/absence. Geographic Information Science (GIS) can be used to target sampling locations that encompass a range of mixed pixels, but are also easily accessible for an efficient accuracy assessment. Here, an accuracy assessment of a Landsat‐derived map of the invasive species cheatgrass (Bromus tectorum) in the state of Nevada, USA is presented. The stratified random design used GIS to increase efficiency by limiting the target area while still sampling the distribution of mixed pixels present in the larger study area, and a receiver operating characteristic (ROC) curve was used to assess overall map accuracy with different thresholds of cheatgrass presence/absence. This approach is useful for validating map accuracy in the presence of mixed pixels.     

Validation of a large area land cover product using purpose-acquired airborne video

Large area land cover products generated from remotely sensed data are difficult to validate in a timely and cost effective manner. As a result, pre-existing data are often used for validation. Temporal, spatial, and attribute differences between the land cover product and pre-existing validation data can result in inconclusive depictions of map accuracy. This approach may therefore misrepresent the true accuracy of the land cover product, as well as the accuracy of the validation data, which is not assumed to be without error. Hence, purpose-acquired validation data is preferred; however, logistical constraints often preclude its use — especially for large area land cover products. Airborne digital video provides a cost-effective tool for collecting purpose-acquired validation data over large areas. An operational trial was conducted, involving the collection of airborne video for the validation of a 31,000 km² sub-sample of the Canadian large area Earth Observation for Sustainable Development of Forests (EOSD) land cover map (Vancouver Island, British Columbia, Canada). In this trial, one form of agreement between the EOSD product and the airborne video data was defined as a match between the mode land cover class of a 3 by 3 pixel neighbourhood surrounding the sample pixel and the primary or secondary choice of land cover for the interpreted video. This scenario produced the highest level of overall accuracy at 77% for level 4 of classification hierarchy (13 classes). The coniferous treed class, which represented 71% of Vancouver Island, had an estimated user's accuracy of 86%. Purpose acquired video was found to be a useful and cost-effective data source for validation of the EOSD land cover product. The impact of using multiple interpreters was also tested and documented. Improvements to the sampling and response designs that emerged from this trial will benefit a full-scale accuracy assessment of the EOSD product and also provides insights for other regional and global land cover mapping programs.     

Assessing the impacts of human uncertainty in the accuracy assessment of land-cover maps using linguistic scales and fuzzy intervals

The accuracy assessment of land-cover maps requires reference databases which are intended to represent ground truth. However, these reference databases are usually obtained through photo-interpretation of aerial or very-high-resolution satellite images and therefore have uncertainty which will influence the results of the accuracy assessment. Previous efforts to account for this source of uncertainty have employed a linguistic scale to translate the degree of correspondence between the ground conditions and each land-cover class for each sample location. The linguistic scale is transformed into fuzzy intervals with this transformation based on a photo-interpreter’s hypothetical ideal perception of the land-cover areal coverage for a sample unit. The end result is a fuzzy accuracy assessment. The objectives of this article are to assess the degree to which the real response of photo-interpreters corresponds to the assumed ideal response and to evaluate the impact these differences have on the results of an accuracy assessment. To achieve this objective, we examine linguistic scales with five and seven values. Furthermore, we develop a method to transform these scales into interpreter-derived fuzzy intervals expressing the proportion of area of land cover for each sample unit. This transformation is accomplished using a control sample in which the area occupied by each land-cover class is assessed. The methodology is tested via a case study where a map with five land-cover classes is evaluated. The accuracy assessment is performed with both hypothetical ideal interpreter response and with the interpreter-derived fuzzy intervals. The results for the fuzzy accuracy measures produced from the different analyses show that there are considerable differences between the results obtained with the linguistic scale with five and seven values, and that the interpreter-derived seven-value linguistic scale provides results very similar to those obtained with the ideal interpreter response.     

A global land-cover validation data set,part I: fundamental design principles

A number of land-cover products, both global and regional, have been produced and more are forthcoming. Assessing their accuracy would be greatly facilitated by a global validation database of reference sites that allows for comparative assessments of uncertainty for multiple land-cover data sets. We propose a stratified random sampling design for collecting reference data. Because the global validation database is intended to be applicable to a variety of land-cover products, the stratification should be implemented independently of any specific map to facilitate general utility of the data. The stratification implemented is based on the Köppen climate/vegetation classification and population density. A map of the Köppen classification was manually edited and intersected by two layers of population density and a land water mask. A total of 21 strata were defined and an initial global sample of 500 reference sites was selected, with each site being a 5?×?5 km block. The decision of how to allocate the sample size to strata was informed by examining the distribution of the sample area of land cover for two global products resulting from different sample size allocations to the 21 strata. The initial global sample of 500 sites selected from the Köppen-based stratification indicates that these strata can be used effectively to distribute sample sites among rarer land-cover classes of the two global maps examined, although the strata were not constructed using these maps. This is the first article of two, with the second paper presenting details of how the sampling design can be readily augmented to increase the sample size in targeted strata for the purpose of increasing the sample sizes for rare classes of a particular map being evaluated.     

The efficiency of sampling very high resolution images for area estimation in the European Union

Very high resolution (VHR) images are a valuable information source to estimate land cover area and land cover change. When full coverage of a region with VHR images is not affordable, a sample of images can be considered. Square grids provide a practical sampling frame for VHR images. When using a land cover map as pseudo-truth, the sampling variance is easily assessed but may be overestimated if the land cover map has a coarse resolution. To estimate the potential sampling variance of a cluster sampling scheme, we propose a method based on intra-cluster correlation (ICC) computed from a correlogram. The ‘equivalent number of points’ is a useful indicator to quantify cost-efficiency of sites of a given size. We obtained poor efficiency results for area estimation of major land cover types in the European Union (EU) with a sample of 10 km?×?10 km sites, but results are more encouraging for classes with a more scattered layout or for land cover change.     

基于Fuzzy ARTMAP神经网络的高分辨率图象土地覆盖分类及其评价

主要讨论了基于Fuzzy ARTMAP神经网络的高分辨率遥感图象土地覆盖分类方法及其实践．首先介绍了Fuzzy ARTMAP神经网络的原理，然后用SPOT XS图象试验数据进行土地覆盖分类．分类结果与传统的最大似然监督分类(MLC)、反馈式(Back Propagation，BP)神经网络的分类结果进行了比较．通过抽取500个样点对3种分类结果进行精度评价表明，Fuzzy ARTMAP神经网络相对其他两种方法，分类精度均有不同程度的改善，具有更好的分类结果，总分类精度比MLC和BP算法分别提高17．41％、7．32％．最后，对不同分类方法对于土地覆盖分类结果的影响进行了评价和分析．试验表明，Fuzzy ARTMAP神经网络用于高分辨图象土地覆盖分类研究可以获得相对较好的分类结果．     

Thematic accuracy of the National Land Cover Database (NLCD) 2001 land cover for Alaska

The National Land Cover Database (NLCD) 2001 Alaska land cover classification is the first 30-m resolution land cover product available covering the entire state of Alaska. The accuracy assessment of the NLCD 2001 Alaska land cover classification employed a geographically stratified three-stage sampling design to select the reference sample of pixels. Reference land cover class labels were determined via fixed wing aircraft, as the high resolution imagery used for determining the reference land cover classification in the conterminous U.S. was not available for most of Alaska. Overall thematic accuracy for the Alaska NLCD was 76.2% (s.e. 2.8%) at Level II (12 classes evaluated) and 83.9% (s.e. 2.1%) at Level I (6 classes evaluated) when agreement was defined as a match between the map class and either the primary or alternate reference class label. When agreement was defined as a match between the map class and primary reference label only, overall accuracy was 59.4% at Level II and 69.3% at Level I. The majority of classification errors occurred at Level I of the classification hierarchy (i.e., misclassifications were generally to a different Level I class, not to a Level II class within the same Level I class). Classification accuracy was higher for more abundant land cover classes and for pixels located in the interior of homogeneous land cover patches.     

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.     

Application of spectral mixture analysis for terrain evaluation studies

In this article, we describe an approach to calculate the spectral mixture within pixels and classify multispectral images. The results are compared with the classified images by traditional supervised rules such as Maximum Likelihood and appreciable results were accomplished. The method considers the number of endmembers that form the scene spectra, followed by the determination of their nature and finally the decomposition of the spectra into their endmembers. The only requirement for this method is a radiometrically corrected image because the endmembers are directly selected from the image. To make the method presented here more efficient, we propose to apply it only to the classes having low accuracy after a traditional supervised classification. Because the land cover classes in this study are related to a geomorphological terrain unit, we propose to mask the terrain units having problematic classes and decompose these units into their endmembers. A geomorphological analysis of the study area (Tonle Sap basin in Cambodia) was made to establish the relationship between land cover, landforms and soils through terrain mapping units. Then we performed a supervised classification of a Landsat Thematic Mapper (TM) image and of the same image merged with a SPOT-panchromatic (PAN) image, based on the land covers corresponding to the terrain mapping units. Then we masked a terrain unit having problematic spectral classes and applied the spectral mixture analysis which allowed an efficient separation of the land cover classes agglomerated in the preliminary classification. The result of this re-classification was re-inserted into the first classification and was compared statistically with the results obtained in the preliminary classification. We consider this procedure an efficient method to improve the results obtained from a supervised classification. The method can separate different land covers that were agglomerated in the preliminary segmentation. In our case, the classification accuracy for the terrain unit used (the fluvial terrace) increases from 62% (using only the TM bands) and 69% (using TM+ SPOT) to 83%.     

Estimating standard errors of accuracy assessment statistics under cluster sampling

Cluster sampling is a viable sampling design for collecting reference data for the purpose of conducting an accuracy assessment of land-cover classifications obtained from remotely sensed data. The formulas for estimating various accuracy parameters such as the overall proportion of pixels correctly classified, the kappa coefficient of agreement, and user's and producer's accuracy are the same under cluster sampling and simple random sampling, but the formulas for estimating standard errors differ between the two designs. If standard error formulas appropriate for cluster sampling are not employed in an accuracy assessment based on this design, the reported variability of map accuracy statistics is likely to be grossly misleading. The proper standard error formulas for common map accuracy statistics are derived for one-stage cluster sampling. The validity of these standard error formulas is verified by a small simulation study, and the standard errors computed according to the usual simple random sampling formulas are shown to underestimate the true cluster sampling standard errors by 20–70% if the intracluster correlation is moderate.