检索结果-内蒙古大学图书馆

Comparison of Vector Stacking, Multi-SVMs Fuzzy Output, and Multi-SVMs Voting Methods for Multiscale VHR Urban Mapping

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2010年第2期7卷 261-265页

作者： Huang, Xin Zhang, Liangpei Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

The objective of this letter is to integrate multiscale information for urban mapping using very high resolution (VHR) imagery. Three multiscale fusion methods were presented: 1) vector stacking (VS);2) multiple support vector machines (multi-SVMs) fuzzy output;and 3) multi-SVMs voting. Two kinds of spatial features were used to obtain multiscale representations of VHR images: morphological structural features and object-based approaches. In experiments, the Reflective Optics System Imaging Spectrometer-03 Pavia Center and University, the Hyperspectral Digital Imagery Collection Experiment Washington DC Mall, and the Quickbird Beijing data sets were used for algorithm validation. The experimental results revealed that, in most cases, the VS fusion outperformed other methods because it was able to create a new high-dimensional multiscale feature space and enhance the class separability. It was also shown that the multi-SVMs fuzzy fusion could optimize and reorganize the multiscale information effectively. Furthermore, multi-SVMs fuzzy output was better than multi-SVMs voting because the former was able to exploit the probabilistic output, while the latter only considered the crisp classification label. In addition, it is suggested that VS fusion is suitable for morphological features;however, for the object-based classification, the multiscale fusion methods do not necessarily yield better results than the single-scale classification in terms of accuracies.

关键词： Fusion high resolution morphological multiscale object-based classification support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

Modeling and valuation of ecological impacts of land cover and land use changes on Tenerife (Canary Islands)

Modeling and valuation of ecological impacts of land cover a...

引用

Conference on Earth Resources and Environmental Remote Sensing - GIS Applications

作者： Guenthert, S. Siegmund, A. Naumann, S. Heidelberg Univ Inst Geog Berliner Str 48 D-69120 Heidelberg Germany Univ Educ Heidelberg Dept Geog Res Grp Earth Observat Rgeo D-69115 Heidelberg Germany

ISBN: (纸本)9780819483485

The island Tenerife is a popular destination for tourists, especially from European countries. From the middle of the 1970s, the mass tourism increased from about 1.3 million to 6 million tourists nowadays (2008). 1 This development lead not only to an increasing expansion of infrastructure but also to a spatial concentration of settlements. 2 Moreover, the Canary Islands and especially Tenerife are a hotspot of climate change with possible reorientation of atmospheric circulation. The presented research project follows the question how sensitive ecosystems (e.g. laurel forest or pinewood) on Tenerife will be affected by, on the one hand, global impacts of climate change and on the other hand by local socioeconomic effects in future. For this purpose existing time series of land cover and land use change, derived from medium spatial scaled remotely sensed data, will be upgraded with regard to the spatial and temporal resolution. Therefore an object-based classification of high spatial scaled satellite scenes has to be done followed by a change detection analysis. Taking into account the different local and global driving forces for these changes the spatial future development of the most important land use processes like e. g. increase of agricultural land (monocultures) and fallow land will then be simulated and visualised. based on these results the impacts for different sensitive ecosystems can finally be analysed and valuated.

关键词： Tenerife object-based classification Change detection analysis Land use modeling

来源：评论

学校读者我要写书评

暂无评论

SHADOW EXTRACTION AND CORRECTION FROM QUICKBIRD IMAGES 30

SHADOW EXTRACTION AND CORRECTION FROM QUICKBIRD IMAGES

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Liu, Wen Yamazaki, Fumio Chiba Univ Dept Urban Environm Syst Chiba Japan

ISBN: (纸本)9781424495665

Shadows in remote sensing images often result in problems for many applications such as land-cover classification, change detection, and damage detection in disasters. Due to these reasons, it is very useful if the radiance of shadowed areas is corrected to the same radiance as shadow-free areas. In this study, a shadow detection and correction method is proposed. Shadowed areas are detected by object-based classification, using brightness values and a neighbor relationship. Then the detected shadowed areas are corrected by a liner function to produce a shadow-free image. The shadowed areas with different darkness are corrected with different ratios to improve the accuracy of the result. The spectral characteristics of sunlit and shadowed areas in several QuickBird images were studied and then the shadow-free radiance was obtained.

关键词： Optical image radiance measurement object-based classification shadow detection shadow correction

来源：评论

学校读者我要写书评

暂无评论

Improving urban land use and land cover classification from high-spatial-resolution hyperspectral imagery using contextual information

引用

JOURNAL OF APPLIED REMOTE SENSING 2010年第1期4卷 041890-041890页

作者： Yang, He Ma, Ben Du, Qian Yang, Chenghai Mississippi State Univ Dept Elect & Comp Engn Geosyst Res Inst Mississippi State MS 39762 USA ARS USDA Kika de la Garza Subtrop Agr Res Ctr Weslaco TX 78596 USA

In this paper, we propose approaches to improve the pixel-based support vector machine (SVM) classification for urban land use and land cover (LULC) mapping from airborne hyperspectral imagery with high spatial resolution. Class spatial neighborhood relationship is used to correct the misclassified class pairs, such as roof and trail, road and roof. These classes may be difficult to be separated because they may have similar spectral signatures and their spatial features are not distinct enough to help their discrimination. In addition, misclassification incurred from within-class trivial spectral variation can be corrected by using pixel connectivity information in a local window so that spectrally homogeneous regions can be well preserved. Our experimental results demonstrate the efficiency of the proposed approaches in classification accuracy improvement. The overall performance is competitive to the object-based SVM classification.

关键词： urban land use land cover mapping hyperspectral imaging support vector machine pixel-based classification object-based classification

来源：评论

学校读者我要写书评

暂无评论

Optimal Envisat advanced synthetic aperture radar image parameters for mapping and monitoring Sahelian floodplains

引用

JOURNAL OF APPLIED REMOTE SENSING 2010年第1期4卷 043511-043511页

作者： Westra, Toon De Wulf, Robert Van Coillie, Frieke Crabbe, Sarah Univ Ghent Lab Forest Management & Spatial Informat Tech FOR B-9000 Ghent Belgium

Floodplains in the Sahel region of Africa are of exceptional socio-economical and ecological importance. Due to their large extent and highly dynamic nature, monitoring these ecosystems can only be performed by means of remote sensing. The capability of the Envisat Advanced Synthetic Aperture Radar (ASAR) sensor to capture radar backscattering at various incident angles and with different polarization combinations, provides opportunities for improved wetland mapping and monitoring. However, little is known of the optimal image parameters, i.e. incident angle, polarization combination, and acquisition time. Backscatter sigma(o) signatures of Land Use and Land Cover (LULC) classes in and around the Waza-Logone floodplain (Cameroon) were analyzed to determine these optimal image parameters. based on Jeffries-Matusita (JM) distances between all LULC classes it was determined that best separation was obtained with images acquired in the middle of the flooding cycle at a steep incident angle. Furthermore, separability of cross-polarized images was higher than for co-polarized images. The combination of two and three ASAR Alternating Polarization images with highest separability were used as input for a LULC classification. Two methods were evaluated: Pixel-based Maximum Likelihood and object-based Nearest Neighbour (NN) classification. Best results were obtained with the object-based approach.

关键词： SAR Envisat ASAR wetlands object-based classification

来源：评论

学校读者我要写书评

暂无评论

Improvement of Low Level Bark Beetle Damage Estimates with Adaptive Cluster Sampling

引用

SILVA FENNICA 2010年第2期44卷 289-301页

作者： Coggins, Sam B. Coops, Nicholas C. Wulder, Michael A. Univ British Columbia Dept Forest Resources Management Vancouver BC V6T 1Z4 Canada Nat Resources Canada Canadian Forestry Serv Pacific Forestry Ctr Victoria BC V8Z 1M5 Canada

Detection of low level infestation in forest stands is of principle importance to determine effective control strategies before the attack spread to large areas. Of particular concern is the ongoing mountain pine beetle, Dendroctonus panderosae (Hopkins) epidemic, which has caused approximately 14 million hectares of damage to lodgepole pine (Pious comma Dougl. ex. Loud var. latifolia Engl.) forests in western Canada. At the stand level attacked trees are often difficult to locate and can remain undetected until the infestation has become established beyond a small number of trees. As such, methods are required to detect and characterise low levels of attack prior to infestation expansion, to inform management, and to aid mitigation activities. In this paper, an adaptive cluster sampling approach was applied to very fine-scale (20 cm) digital aerial imagery to locate mountain pine beetle damaged trees at the leading edge of the current infestation. Results indicated a mean number of 7.36 infested trees per hectare with a variance of 18.34. In contrast a non-adaptive approach estimated the mean number of infested trees in the same area to be 61.56 infested trees per hectare with a variance of 41.43. Using a relative efficiency estimator the adaptive cluster sampling approach was found to be over two times more efficient when compared to the non-adaptive approach.

关键词： object-based classification high spatial resolution satellite digital aerial imagery mountain pine beetle forest inventory adaptive cluster sampling

来源：评论

学校读者我要写书评

暂无评论

Texture and Scale in object-based Analysis of Subdecimeter Resolution Unmanned Aerial Vehicle (UAV) Imagery

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2009年第3期47卷 761-770页

作者： Laliberte, Andrea S. Rango, Albert New Mexico State Univ USDA ARS Jornada Expt Range Las Cruces NM 88003 USA

Imagery acquired with unmanned aerial vehicles (UAVs) has great potential for incorporation into natural resource monitoring protocols due to their ability to be deployed quickly and repeatedly and to fly at low altitudes. While the imagery may have high spatial resolution, the spectral resolution is low when lightweight off-the-shelf digital cameras are used, and the inclusion or texture measures can potentially increase the classification accuracy. Texture measures have been used widely in pixel-based image analysis, but their use in an object-based environment has not been well documented. Our objectives were to determine the most suitable texture measures and the optimal image analysis scale for differentiating rangeland vegetation using UAV imagery segmented at multiple scales. A decision tree was used to determine the optimal texture features for each segmentation scale. Results indicated the following: 1) The error rate of the decision tree was lower;2) prediction success was higher;3) class separability was greater;and 4) overall accuracy was higher (high 90% range) at coarser segmentation scales. The inclusion of texture measures increased classification accuracies at nearly all segmentation scales, and entropy was the texture measure with the highest score in most decision trees. The results demonstrate that UAVs are viable platforms for rangeland monitoring and that the drawbacks of low-cost off-the-shelf digital cameras can be overcome by including texture measures and using object-based image analysis which is highly suitable for very high resolution imagery.

关键词： object-based classification rangelands scale texture unmanned aircraft

来源：评论

学校读者我要写书评

暂无评论

Adaptation of building extraction rule sets derived from MFC3 and UltraCamD aerial image data sets

Adaptation of building extraction rule sets derived from MFC...

引用

SPIE Conference on Remote Sensing for Environmental Monitoring, GIS Applications, and Geology IX

作者： Trosset, A. M. Bucher, T. Lehmann, F. German Aerosp Ctr DLR Inst Robot & Mechatron Rutherfordstr 2 D-12489 Berlin Germany

ISBN: (纸本)9780819477835

In the context of rapid expansion of many cities to enormous agglomerations with high population density and a worldwide urbanization process serious impacts on environment in urban areas evolve. There is a high demand for the development and application of efficient methods to analyze and monitor changes in urban areas, to support the planning decisions in these regions and for security and risk assessment. Efficient, accurate and reliable extraction of buildings and roof surfaces and their inventory in geographic information systems plays a major role in this context. Previous analyses of digital airborne data sets show up that the inventory mapping and assessment of building changes is only possible on the basis of multi-temporal data sets and digital surface models with high resolution. These analyses confirm explicitly that both high heterogeneity and diversification of urban regions as well as the availability of data sets from different camera systems increase the need for automated and transferable extraction methods. In this context two data sets from different high resolution sensors are used for the development of transferable extraction rule sets within the object-based classification method in Definiens Developer. The Multifunctional Camera (MFC3) and the UltraCamD (UCD) data sets not only have diverse geometric but also different radiometric characteristics. As a study area the centre of Berlin, Germany was selected. Two approaches to generate comparable results from different data sources are tested. The first step deals with the generation of statistical parameters and the normalization of the two data sets. The second step addresses the development and adaptation of the rule set for a robust and universal segmentation and classification process.

关键词： Automated building extraction object-based classification MFC3 UltraCamD aerial image data

来源：评论

学校读者我要写书评

暂无评论

A novel method of aerial image classification based on attention-based local descriptors

A novel method of aerial image classification based on atten...

引用

International Conference on Mining Science and Technology

作者： Xu, Sheng Fang, Tao Huo, Hong Li, Deren Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430072 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China

This paper proposes a novel method for object-based classification in very high spatial resolution aerial image. It combines the saliency maps very closely to extract the conspicuous local regions for better description of object and classification. Unlike the previous work on detection of the local regions, a biologically motivated selective attention model is presented in this paper, since not all the local regions are important for describing the objects. In order to model the attention region, we propose a new attention-based local descriptor using the saliency map and relative local features to reflect the region of interest (ROI). The experimental results on the VHR aerial image dataset show that the proposed approach can obtain the state-of-the-art classification performance.

关键词： Bag-of-visual-words object-based classification saliency map

来源：评论

学校读者我要写书评

暂无评论

Interpretability of TerraSAR-X fused data

Interpretability of TerraSAR-X fused data

引用

SPIE Conference on Remote Sensing for Environmental Monitoring, GIS Applications, and Geology IX

作者： Rosso, Pablo H. Ehlers, Manfred Klonus, Sascha Univ Osnabruck Inst Geoinformat & Remote Sensing D-49069 Osnabruck Germany

ISBN: (纸本)9780819477835

Pansharpening is an image fusion technique that combines the spatial structure of a high resolution panchromatic image with the spectral information of a lower resolution multispectral image to produce a high resolution multispectral image. Image data of the new German RADAR satellite TerraSAR-X were used to sharpen optical multispectral data. To assess the advantages and limitations of fusion, the interpretability of terrain features at different image resolutions was determined. We concluded that a resolution ratio of 1:10 (TerraSAR: Multispectral) is optimal to benefit from the synergism of a SAR/multispectral fusion. Q index and an object-based classification were used to assess fusion quality and to compare their efficacy to determine the best fusion algorithms. Both approaches are appropriate methods to asses quality but only on judging some aspects of the fusion products. We conclude that a more comprehensive fusion quality assessment method still needs to be developed.

关键词： Pansharpening image fusion TerraSAR-X Q index object-based classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：