共查询到20条相似文献，搜索用时 656 毫秒
1.
《ISPRS Journal of Photogrammetry and Remote Sensing》1999,54(5-6):305-316
This paper describes the development of a 1-km landcover dataset of China by using monthly NDVI data spanning April 1992 through March 1993. The method used combined unsupervised and supervised classification of NDVI data from AVHRR. It is composed of five steps: (a) unsupervised clustering of monthly AVHRR NDVI maximum value composites is performed using the ISOCLASS algorithm; (b) preliminary identification is carried out with the addition of digital elevation models, eco-region data and a collection of other landcover/vegetation reference data to identify the clusters with single landcover classes; (c) re-clustering is performed of clusters with size greater than a given threshold value and containing two or more disparate landcover classes; (d) cluster combining is performed to combine all clusters with a single landcover class in one cluster, and all other clusters into one mixed cluster; and (e) supervised classification is used to carry out post-classification of the mixed cluster generated in the previous step by using the maximum likelihood algorithm and the identified single landcover classes of the previous step as training data. The classification is based on extensive use of computer-assisted image processing and tools, as well as the skills of the human interpreter to take the final decisions regarding the relationship between spectral classes defined using unsupervised methods and landscape characteristics that are used to define landcover classes. 相似文献
2.
Temporal changes in the normalized difference vegetation index (NDVI) have been widely used in vegetation mapping due to the usefulness of NDVI data in distinguishing characteristic seasonal differences in the phenology of greenness of vegetation cover. Research has also shown that NDVI provides potential to derive meaningful metrics that describe ecosystem functions. In this paper, we have applied both unsupervised “k-means” classification and supervised minimum distance classification as derived from temporal changes in NDVI measured in 1997 along the North Eastern China Transect (NECT), and we have also utilized the same two classification methods together with NDVI-derived metrics, namely maximum NDVI, mean NDVI, NDVI amplitude, NDVI threshold, total length of growing season, fraction of growing season during greenup, rate of greenup, rate of senescence, integrated NDVI during the growing season, and integrated NDVI during greenup/integrated NDVI during senescence to map vegetation. The main objectives of this study are: (1) to test the relative performance of NDVI temporal profile metrics and NDVI-derived metrics for vegetation cover discrimination in NECT; (2) to test the relative performance of unsupervised (k-means) and supervised (minimum distance) methods for vegetation mapping; (3) to test the accuracy of the IGBP-DIS released land cover map for NECT; (4) to provide an up-to-date vegetation map for NECT. The results suggest that the classifications based on NDVI temporal profile metrics have higher accuracies than those based on any other metrics, such as NDVI-derived metrics, or all (NDVI temporal profile metrics + NDVI-derived metrics), or 15 metrics (NDVI temporal profile + Rate of greenup, Rate of senescence, and Integrated NDVI in greenup/integrated NDVI in senescence) for both methods. And among them, unsupervised k-means classification had the highest overall accuracy of 52% and Kappa coefficient of 0.2057. Both unsupervised (k-means) and supervised (minimum distance) methods achieved similar accuracies for the same metrics. The accuracy of IGBP-DIS released land cover map had an overall accuracy of 37% and a Kappa coefficient is 0.1441, and can improve to 46% by decomposing the crop/natural vegetation mosaic to cropland and other natural vegetation types. The results support using unsupervised k-means classification based on NDVI temporal profile metrics to provide an up-to-date vegetation cover classification. However, new effort is necessary in the future in order to improve the overall performance on this issue. 相似文献
3.
《地理信息系统科学与遥感》2013,50(4):365-387
Atlanta has continuously changed its physical landscape as well as its socioeconomic appearance over the past decades. A hybrid image processing approach, which integrated unsupervised, supervised, and spectral mixture analysis (SMA) classification methods, was used to identify urban land use/land cover changes over a decade (from 1990 to 2000) in the Atlanta metropolitan area. During this process, SMA was proven to be an effective analytical approach for characterizing mixed feature areas, such as a metropolitan area. According to accuracy assessment, the classification results were acceptable. 相似文献
4.
A multi‐temporal sequence of seven NOAA‐n, Advanced Very High Resolution Radiometer (AVHRR) satellite scenes (April 10, May 18, June 6, June 29, July 20, and August 18, 1987) were composited to derive cover‐type information in the heterogeneous landscape of University Lake Watershed, North Carolina, U.S.A. The Normalized Difference Vegetation Index (NDVI) was calculated for each scene and merged into a seven‐dimensional dataset, representing each time period sampled. An unsupervised classification was performed on the multi‐temporal composite to derive five cover‐type classes. Similar classifications were generated on single scene information. Ground control information was derived from an unsupervised classification of one kilometer grid compositional percentages initially derived from photo‐interpreted landcover information. The multi‐temporal NDVI classification more consistently characterized phenologic responses on a spatially dissected landscape than single scene clustering. Sub‐pixel information showed how the algorithm separated compositional information between classes. Temporal vectors were plotted to illustrate differentiation on the basis of NDVI profiles. 相似文献
5.
土地利用/覆盖分类通常是利用地物的波谱反射特征进行监督或非监督分类,分类结果由于"同物异谱、异物同谱"现象的存在,往往分类精度不高。而植被指数和地表温度作为表征地表覆盖状况的生物物理参数,已成功用于宏观尺度的土地利用/覆盖分类,使得分类结果有所提高,而对于区域尺度的土地利用/覆盖分类却少见报道。本文充分利用TM数据的多光谱特征,从中提取了植被指数NDVI、地表温度Ts、温度植被角度TVA和温度植被距离TVD这四种分类特征进行监督分类,通过对7种组合方案(反射率波段组合、NDVI与反射率波段组合、Ts与反射率波段组合、NDVI与Ts和反射率波段组合、TVA与反射率波段组合、TVD与反射率波段组合、TVA与TVD和反射率波段组合)的分类结果进行比较,得出以下结论:①NDVI、Ts、NDVI和Ts、TVD作为分类特征参与到多波段地表反射率影像分类中,能够提高分类精度,而TVA、TVA和TVD的加入却没有改善分类结果;②总体分类精度受到训练样本与检验样本比例的影响。 相似文献
6.
I. K. Lur'ye 《地理信息系统科学与遥感》2013,50(3):255-261
Algorithms, designed for digital image processing in standard mainframe computers and representing sequential stages in a land-use classification procedure, are used to produce maps of agricultural crop types from multispectral satellite imagery. Pixel reflectance values are first grouped according to an unsupervised “rapid classification algorithm,” or data compression procedure. Mean reflectance values of the resulting classes then go into a supervised “sequential clustering algorithm” where classes are refined according to training value and other parameter inputs. The objective is to increase the accessibility of automated image interpretation while balancing classification accuracy and processing time. Translated from: Vestnik Moskovskogo Universiteta, geografiya, 1984, No. 4, pp. 63-69. 相似文献
7.
This paper presents a land use and land cover (LULC) classification approach that accounts landscape heterogeneity. We addressed this challenge by subdividing the study area into more homogeneous segments using several biophysical and socio-economic factors as well as spectral information. This was followed by unsupervised clustering within each homogeneous segment and supervised class assignment. Two classification schemes differing in their level of detail were successfully applied to four landscape types of distinct LULC composition. The resulting LULC map fulfills two major requirements: (1) differentiation and identification of several LULC classes that are of interest at the local, regional, and national scales, and (2) high accuracy of classification. The approach overcomes commonly encountered difficulties of classifying second-level classes in large and heterogeneous landscapes. The output of the study responds to the need for comprehensive LULC data to support ecosystem assessment, policy formulation, and decision-making towards sustainable land resources management. 相似文献
8.
M. Munsi G. Areendran A. Ghosh P. K. Joshi 《Journal of the Indian Society of Remote Sensing》2010,38(3):441-452
Deforestation and degradation are important aspects of landscape dynamics and have global significance. Quantification of
landscape pattern using landscape metrics help in characterisation of landscapes and thus overall health of the forest cover.
Himalayan foothills are one of the most important and fragile landscapes. Developmental activities and depdendence on the
forest resources have altered the spatial pattern of these natural landscapes to a great extent. These changes in the landscape
were analysed using satellite data from 1990, 2001 and 2006. The vegetation type maps of Dehradun forest division were prepared
by supervised classification technique in order to study the landscape dynamics. Patch density, edge density, shape index,
cohesion index, interspersion and juxtaposition index, normalised entropy, and relative richness are some important landscape
metrics used in the study for quantifying the characteristics of landscape. The landscape metrics analysis and transformation
analysis show that the forested areas are getting degraded and physical connectedness between the patches have also decreased
making them isolated. The study demonstrates the importance of geospatial tools for monitoring the impact of disturbances
on the forest ecosystem health, which can further help in landscape management. 相似文献
9.
10.
Although multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do not match the geometries of the target objects, which reduces the classification accuracy. MRS can, however, be guided to produce results that approach the desired object geometry using either supervised or unsupervised approaches. Although some studies have suggested that a supervised approach is preferable, there has been no comparative evaluation of these two approaches. Therefore, in this study, we have compared supervised and unsupervised approaches to MRS. One supervised and two unsupervised segmentation methods were tested on three areas using QuickBird and WorldView-2 satellite imagery. The results were assessed using both segmentation evaluation methods and an accuracy assessment of the resulting building classifications. Thus, differences in the geometries of the image objects and in the potential to achieve satisfactory thematic accuracies were evaluated. The two approaches yielded remarkably similar classification results, with overall accuracies ranging from 82% to 86%. The performance of one of the unsupervised methods was unexpectedly similar to that of the supervised method; they identified almost identical scale parameters as being optimal for segmenting buildings, resulting in very similar geometries for the resulting image objects. The second unsupervised method produced very different image objects from the supervised method, but their classification accuracies were still very similar. The latter result was unexpected because, contrary to previously published findings, it suggests a high degree of independence between the segmentation results and classification accuracy. The results of this study have two important implications. The first is that object-based image analysis can be automated without sacrificing classification accuracy, and the second is that the previously accepted idea that classification is dependent on segmentation is challenged by our unexpected results, casting doubt on the value of pursuing ‘optimal segmentation’. Our results rather suggest that as long as under-segmentation remains at acceptable levels, imperfections in segmentation can be ruled out, so that a high level of classification accuracy can still be achieved. 相似文献
11.
顾及尺度效应和景观格局的土地利用数据综合指标研究 总被引：6，自引：0，他引：6
从尺度效应和土地利用案观格局影响两个层面研究土地利用数据综合的宏观和微观综合指标,设计土地利用数据综合的指标体系和指标定量化描述模型.在全国各个土地利用分区采集不同尺度的具有典型代表性的土地利用数据样本集,通过空间统计分析等方法,得到土地利用数据综合中的宏观控制性指标和微观图形综合指标的尺度变化规律及其与土地利用格局的关系.以一个县为试验区,验证其合理性.Abstract： Indices for land use data generalization are critical for generating multiscale land use maps and databases. Previous research suffers from two major setbacks. Firstly, determination of threshold values for multi-scale land use data generalization in a large area, such as a nation, remains subjective. A second problem is general ignorance of landscape pattern. This paper studies the index system of land use data generalization from both scale and landscape pattern perspective. We discuss the macro and micro indices of land use data generalization with consideration of spatial scales and landscape pattern. To quantitatively relate the indices and scale and landscape pattern metrics, land use data samples have been collected at multiple spatial scales in various land use regions across China. Based on statistic analysis, we then generate both macro and micro control rules for land use data generalization at various spatial scales and land use patterns. Finally, we prove the proposed method and achieved results to be effective and reasonable with sample data at county level. 相似文献
12.
The Nature and Classification of Unlabelled Neurons in the Use of Kohonen's Self-Organizing Map for Supervised Classification 总被引：2，自引：0，他引：2
Kohonen's Self‐Organizing Map is a neural network procedure in which a layer of neurons is initialized with random weights, and subsequently organized by inspection of the data to be analyzed. The organization procedure uses progressive adjustment of weights based on data characteristics and lateral interaction such that neurons with similar weights will tend to spatially cluster in the neuron layer. When the SOM is associated with a supervised classification, a majority voting technique is usually used to associate these neurons with training data classes. This technique, however, cannot guarantee that every neuron in the output layer will be labelled, and thus causes unclassified pixels in the final map. This problem is similar to but fundamentally different from the problem of dead units that arises in unsupervised SOM classification (neurons which are never organized by the input data). In this paper we specifically address the problem and nature of unlabelled neurons in the use of SOM for supervised classification. Through a case study it is shown that unlabelled neurons are associated with unknown image classes and, most particularly, mixed pixels. It is also shown that an auxiliary algorithm proposed here for assigning classes to unlabelled neurons performs with the same success as that experienced with Maximum Likelihood. 相似文献
13.
With increasing attention being paid to sustainable urban development and human habitation improvement, urban ecological land cover (UELC), i.e., surface water and green space, has played an important role of the highly compact inner urban regions. In this study, we developed an efficient approach for UELC mapping by coupling Sentinel-2 multi-spectral imagery and Google Earth high-resolution imagery. In contrast with the conventional single-source and multi-source imagery-based classification methods, the proposed method respectively achieved the highest overall accuracies of 91.50% and 94.05% in the UELC mapping for two test sites (i.e. Shanghai and Seoul). The proposed method is used for urban surface mapping among six world-class cities. For an in-depth analysis of the landscape structures for inner urban regions, seven landscape metrics are introduced for the quantification of the UELC structure based on the obtained high-precision UELC maps. The result shows that London appears to have the best UELC-induced ecological quality, that is, with high percentage of landscape, area-weighted mean fractal dimension, edge density, Shannon’s evenness index values and a low contagion index value, while Tokyo is exactly the opposite. Several common characteristics found through the statistical analysis are: 1) all the inner-city regions have small UELC coverage (< 50%) and low shape complexity; 2) green space generally contributes more to urban eco-environment than the urban surface water; and 3) all cities show high landscape consistency in the inner urban region. 相似文献
14.
Abstract Landsat MSS, TM and SPOT XS imageries were used in conjunction with unsupervised, supervised and hybrid classilication techniques to classify land cover types in semi‐arid savannas of Mathison Pastoral Station in the Katherine region of northern Australia. Accuracy assessment was based on field data from 246 ground survey sites over a 745‐km2 study area. Of 14 land cover classes identified by traditional mapping means, all combinations of imageries and classification techniques differentiated at least seven land cover types. The overall accuracy for these classifications ranged between 43% and 67%. SPOT XS image delivered the best accuracy followed by TM and MSS; unsupervised classification performed better than supervised and hybrid methods. User's and producer's accuracy of individual land units ranged from 0% to 100%. Riparian woodlands, woodland on limestone slopes, shrubland on clay plains, woodland on limestone plains and shadows were the best‐mapped classes. The land units that were associated with undulating hills were not mapped accurately. However, incorporation of a digital elevation model (DEM) in a GIS improved the overall accuracy. The user's and producer's accuracy of dominant land cover types were also enhanced. The classification results and the efficacy of the techniques at Mathison were similar to those found for a nearby semi‐arid area (Kidman Springs) about 200 km from Mathison. However, the overall accuracy was lower at Mathison than at Kidman Springs. Spectral classification masks were developed from the SPOT XS and TM imageries at Kidman Springs, and were applied to classify SPOT XS and TM imageries at Mathison. Initial results showed that the classification mask could be successfully extrapolated to map dominant land cover types but only with moderate accuracy (50%). 相似文献
15.
Martin Yemefack Wietske Bijker Steven M. De Jong 《International Journal of Applied Earth Observation and Geoinformation》2006
This paper investigates statistical relationships between land use/land cover (LULC), Landsat-7 ETM+ imagery and landscape mosaic structure in southern Cameroon where the conversion of tropical rain forest to shifting cultivation leads to dynamic processes, acting on the spatial aggregation of various LULC types. A Global Positioning System (GPS) was used in the field to identify a total of 171 shifting cultivation patches representing eight LULC types in two sub-areas. Because of the lack of a cloud-free image for the date of field sampling, the ETM+ imagery was acquired 2 months after field survey, during which it was assumed that no significant changes in LULC occurred (all dry season). Per pixel correlations were developed between spectral reflectance data, vegetation indices and LULC. As an exploratory study, several statistical methods (analysis of variance, means separations (Tukey HSD), principal component analysis (PCA), geo-statistical analysis, image classification and landscape metrics) were applied on point data and sensor images for evaluating the spatial variability within the landscape. Most variables explained 30–72% of LULC variation in the whole dataset. Those variables with high information content of LULC (infrared bands 4, 5, 7 and derived indices and PC1) also showed long ranges (6 km) spatial dependence as compared to those varying only within 1 km range. The results of these statistical analyses suggested the need to group some LULC types and the application of the Maximum Likelihood Classifier (MLC) for supervised classification provided a LULC map with the highest accuracy (81%) after consolidation of perennial LULC types, such as bush fallow, forest fallow and cocoa plantations. Landscape metrics computed from this map showed a high level of patch diversity and connectivity within the landscape and provided input data that can further be used to simulate predictive maps as substitute to cloud-covered sensor imageries. Landsat-7 ETM+ imagery proved to be useful in discriminating (with about 80% accuracy) the most dynamic LULC types such cropped plots and young fallow patches (shifting every season) and the extension front of the agricultural landscape. 相似文献
16.
This paper investigates the synergistic use of high-resolution multispectral imagery and Light Detection and Ranging (LiDAR) data for object-based classification of urban area. The main contribution of this paper is the development of a semi-automated object-based and rule-based classification method. In the implemented approach, the diverse knowledge about land use/land cover classes are transformed into a set of specialized rules. Further, this paper explores supervised Gaussian Mixture Models for classification, which have been primarily used for unsupervised classification. The work is carried out on test data from two different sites. Contribution of the LiDAR data resulted in a significant improvement of overall Kappa. Accuracy assessment carried out for aforementioned classification methods shows higher overall kappa for both the study sites. 相似文献
17.
Timothy G. Whiteside Guy S. Boggs Stefan W. Maier 《International Journal of Applied Earth Observation and Geoinformation》2011
The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to ‘traditional’ pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern Territory of Australia. The object-based approach involved segmentation of image data into objects at multiple scale levels. Objects were assigned classes using training objects and the Nearest Neighbour supervised and fuzzy classification algorithm. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-based classification produced slightly higher accuracies overall and for certain classes; however this was not statistically significant over the object-based using spectral information solely. The results indicate object-based analysis has good potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia. 相似文献
18.
通过训练样本采样处理改善小宗作物遥感识别精度 总被引：1，自引：0，他引：1
训练样本质量是决定农作物遥感识别精度的关键因素,虽然高空间分辨率卫星的发展有效地解决了农作物遥感识别过程中的混合像元问题,但是当区域内不同作物种植面积差异较大时,训练集中不同类别样本数量往往相差较大,这样的不均衡数据集影响分类器的训练,导致少数类别的识别精度不理想。为研究作物遥感识别过程中的不均衡样本问题,本文基于GF-2号卫星数据,首先挖掘了地物的光谱信息、纹理信息,用特征递归消除RFE (Recursive Feature Elimination)方法进行特征优选,然后从数据处理的角度采用了5种采样算法对不均衡训练集进行处理,最后使用采样后的均衡数据集训练分类器,对比数据采样前后决策树与Adaboost(Adaptive Boosting)两种分类器的识别结果,发现:(1)经过采样处理后两种分类算法明显提升了小宗作物的分类精度;(2)经过ADASYS (Adaptive synthetic sampling)采样处理后,分类器性能提升最多,决策树的Kappa系数提高了14.32%,Adaboost的Kappa系数提高了10.23%,达到最高值0.9336;(3)过采样的处理效果优于欠采样,过采样对分类器的性能提升更多。综上所述,选择合适的采样方法和分类方法是提高不均衡数据集遥感分类精度的有效途径。 相似文献
19.
《制图学和地理信息科学》2013,40(3):289-301
This paper reports on generalization and data modeling to create reduced scale versions of the National Hydrographic Dataset (NHD) for dissemination through The National Map, the primary data delivery portal for USGS. Our approach distinguishes local differences in physiographic factors, to demonstrate that knowledge about varying terrain (mountainous, hilly or flat) and varying climate (dry or humid) can support decisions about algorithms, parameters, and processing sequences to create generalized, smaller scale data versions which preserve distinct hydrographic patterns in these regions. We work with multiple subbasins of the NHD that provide a range of terrain and climate characteristics. Specifically tailored generalization sequences are used to create simplified versions of the high resolution data, which was compiled for 1:24,000 scale mapping. Results are evaluated cartographically and metrically against a medium resolution benchmark version compiled for 1:100,000, developing coefficients of linear and areal correspondence. 相似文献