检索结果-内蒙古大学图书馆

Chinese Conference on pattern recognition (CCPR)

作者： Shijin Li Wanguo Wang Dingsheng Wan School of Computer and Information Engineering Hohai University HHU Nanjing China

An adaptive level set model with feature selection for remote sensing image segmentation is proposed. The traditional C-V Model based on level set pays much attention to the color features, but with less emphasis on texture features. In the processing of remote sensing image, sometimes texture feature is more important for the purpose of image segmentation. To solve the problem, this paper firstly takes the components of different color spaces and the texture features as the initial feature set. Then feature selection is performed through local similarity analysis. Meanwhile, the weights of different features are adjusted accordingly. The selected features are utilized in the C-V model as inputs to segment the remote sensing image. Experimental results on various remote sensing imagery show that the newly proposed approach not only outperforms the traditional model efficiently, but also reduces the time cost greatly.

关键词： Capacitance-voltage characteristics Level set image segmentation remote sensing image color analysis Active contours Computational modeling

来源：评论

学校读者我要写书评

暂无评论

An adaptive level set model with feature selection for remote sensing image segmentation

An adaptive level set model with feature selection for remot...

引用

Chinese Conference on pattern recognition

作者： Li, Shijin Wang, Wanguo Wan, Dingsheng School of Computer and Information Engineering Hohai University Nanjing 210098 China

ISBN: (纸本)9781424472109

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

ASSESSMENT OF THE MULTIPLE ENDMEMBER SPECTRAL MIXTURE ANALYSIS (MESMA) MODEL APPLIED TO THE HYPERION/EO-1 HYPERSPECTRAL DATA OF THE COASTAL PLAIN OF RIO GRANDE DO SUL, BRAZIL

ASSESSMENT OF THE MULTIPLE ENDMEMBER SPECTRAL MIXTURE ANALYS...

引用

ISPRS Technical Commission VII Symposium - 100 Years ISPRS - Advancing remote sensing Science

作者： Linn, R. M. Rolim, S. B. A. Galvao, L. S. Univ Fed Rio Grande do Sul Ctr Estadual Pesquisas Sensoriamento Remoto & Met Porto Alegre RS Brazil Inst Nacl Pesquisas Espaciais Div Sensoriamento Remoto Sao Jose Dos Campos Brazil

The objective of this work was to evaluate the potential use of the Multiple Endmember Spectral Mixture Analysis (MESMA) when applied to EO-1 Hyperion hyperspectral data to discriminate land covers in the southern state of Rio Grande do Sul, Brazil. The methodology involved: (a) pre-processing and atmospheric correction of Hyperion data;(b) sequential use of the Minimum Noise Fraction (MNF), Pixel Purity Index (PPI) and n-Dimensional Visualizer techniques in the 454-2334 nm range for the initial selection of a general group of endmember candidates (first spectral library) and of another group of pixels to be used for model validation;(c) use of the Visualization and image processing for Environmental Research Tools (VIPER Tools) to perform the final selection of endmembers based on the first spectral library and to obtain MESMA models;and (d) evaluation of resultant fraction images and root mean square error (RMSE) values to determine the optimal number of components of the MESMA model. Results showed that a four-endmember MESMA model (soil = dunes and dry fields;green vegetation = pinus, eucalyptus and grasslands;water = without sediments, with sediments, and with chlorophyll;and shade) adequately described the diversity of the scene components, including that of materials within the same class (e. g., pinus and eucalyptus) and produced the largest fractions and the lowest RMSE values on a per-pixel basis. Results demonstrated the potential use of the MESMA with EO-1 Hyperion hyperspectral data to discriminate land covers in the coastal plains of Rio Grande do Sul, even considering the low signal-to-noise ratio of the instrument, especially in the shortwave infrared range.

关键词： Land Cover Radiometry Classification processing pattern Hyper spectral

来源：评论

学校读者我要写书评

暂无评论

Sub-manifold distance based object recognition in clutter

Sub-manifold distance based object recognition in clutter

引用

International Conference on Natural Computation

作者： Zhou, Hua Cai, Chao Ding, Mingyue National Lab for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Imaging Processing and Intelligence Control Key Laboratory of Education Ministry School of Life Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424459612

Object recognition is challenging problem in computer vision due to appearance variation and presence of visual clutter and occlusions. Recently manifolds are thought to be fundamental for visual perception, and manifold learning algorithms are developed for discovering intrinsical features. Selective visual attention mechanism provides tools to reduce computation cost and avoid the influence of clutter background. In this paper, we described a new object recognition method, the submanifold distance (SMD) algorithm, which is induced by the visual attention mechanism to provide complex object recognition. Experiments with airport remote sensing images illustrated that our proposed algorithm can recognize complex objects accurately, robustly and quickly. ©2010 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

VEGETATION TYPES MAPPING USING ALOS/AVNIR-2 AND PRISM DATA USING UNIVERSAL pattern DECOMPOSITION METHOD

VEGETATION TYPES MAPPING USING ALOS/AVNIR-2 AND PRISM DATA U...

引用

8th Symposium on Networking the World with remote sensing of ISPRS-Technical-Commission

作者： Muramatsu, K. Masugi, K. Soyama, N. Furumi, S. Daigo, M. Nara Womens Univ KYOUSEI Sci Ctr Life & Nat Nara 6308506 Japan Nara Womens Univ Dept Informat & Comp Sci Nara 6308506 Japan Tenri Univ Nara Japan Nara Saho Coll Presch Educ Nara 630 Japan Doshisha Univ Fac Econ Kyoto Japan

Vegetation species maps are useful for forestry managements and environmental ecological study. From the forestry management, broad and conifer leaf forest should be mapped. In addition to them, land-cover mapping data with high resolution is needed as validation data sets for low resolution's land-cover mapping results. SGLI sensor on board GCOM-C satellite, which will be launched in 2014, has 250m spatial resolution and it's data will be used for making global land-cover data set. ALOS satellite was launched in 2006. It has AVNIR-2 sensor and PRISM sensor. AVNIR-2 sensor has four spectral bands 460, 560, 650 and 830nm with 10-m spatial resolution. PRISMsensor has panchromatic band from 520nm to 770 nm with 2.5m spatial resolution. If use the both of image, pseudo high spatial multi-spectal image can be processed. Because of the spatial resolution and multi-spectral information, these sensor data are expected to useful for making high resolution land-cover data set. We have developed Universal pattern Decomposition Method (UPDM)(Zhang, L.F. et. al, 2006 (Zhang et al., 2006)) and Modified Vegetation Index based on UPDM (MVIUPD)(Zhang, L. F. et. al, 2007 (Zhang et al., 2007) and Xiong, Y., 2005 (?)) for satellite sensor data analysis for land cover mapping and vegetation monitoring. In the UPDM method, three coefficients of water, vegetation and soil is calculated using three standard patterns of water, vegetation and soil. One of this method's characteristics is the UPDM coefficients from different sensors for the same object being same as each other. The capability of vegetation species mapping was studied with ALOS/AVNIR-2 data and UPDM method. Japanese cedar, Japanese cypress, deciduous forest, bamboo forest, orchard and grass land can be classified using AVNIR-2 summer and winter data. In this study, AVNIR-2 and PRISM data are used for vegetation types mapping using universal pattern decomposition method. Firstly, the pan-sharpen image was processed using AVNIR-

关键词： pan-sharpen processing reflectance characteristics

来源：评论

学校读者我要写书评

暂无评论

The effects of radiometry on the accuracy of intensity based registration

The effects of radiometry on the accuracy of intensity based...

引用

2010 20th International Conference on pattern recognition, ICPR 2010

作者： Selby, Boris Peter Sakas, Georgios Walter, Stefan Groch, Wolf-Dieter Stilla, Uwe Medcom GmbH Rundeturmstr. 12 64283 Darmstadt Germany Fraunhofer IGD Cognitive Computing and Medical Imaging 64283 Darmstadt Germany University of Applied Sciences Fachbereich Informatik 64295 Darmstadt Germany Technische Universitaet Muenchen Photogrammetry and Remote Sensing Germany

ISBN: (纸本)9780769541099

Besides several other factors, radiometric differences between a reference and a floating image greatly influence the achievable accuracy of image registration. In this work we derive the magnitude of registration inaccuracy coming from changes in radiometric properties. This is done for the example of medical X-ray image registration. We therefore estimate the change of image intensity with respect to object shape, X-ray attenuation of the object material and the initial X-ray energy by modeling a simplified image formation process. The change in intensity is then used to determine a closed form estimation of the resulting registration error, independent from a specific registration algorithm. Finally the theoretical calculations are compared to the accuracy of intensity based registration performed on X-ray images with different radiometric properties. Results show that the herewith derived accuracy estimation is well suited to predict the achievable accuracy of a registration for images with radiometric differences. © 2010 IEEE.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Soil erosion assessment using geomorphological remote sensing techniques: an example from southern Italy

引用

EARTH SURFACE PROCESSES AND LANDFORMS 2010年第3期35卷 262-271页

作者： Lo Curzio, Sergio Magliulo, Paolo Univ Sannio Dipartimento Studi Geol & Ambientali I-82100 Benevento Italy

The aim of this study is to assess of the distribution and map the geomorphological effects of soil erosion at the basin scale identifying newly-formed erosional landsurfaces (NeFELs), by means of an integration of Landsat ETM 7+ remotely sensed data and field-surveyed geomorphological data. The study was performed on a 228.6 km(2)-wide area, located in southern Italy. The study area was first characterized from a lithological, peclological, land-use and morpho-topographic point of view and thematic maps were created. Then, the georeferenced Landsat ETM 7+ satellite imagery was processed using the RSI ENVI 4.0 software. The processing consisted of contrast stretching, principal component analysis (PCA), decorrelation stretching and RGB false colour compositing. A field survey was conducted to characterize the features detected on the imagery. Particular attention was given to the NeFELs, which were located using a global positioning system (GPS). We then delimited the Regions of Interest (ROI) on the Landsat ETM 7+ imagery, i.e. polygons representing the 'ground-truth', discriminating the NeFELs from the other features occurring in the imagery. A simple statistical analysis was conducted on the digital number (DN) values of the pixels enclosed in the ROI of the NeFELs, with the aim to determine the spectral response pattern of such landsurfaces. The NeFELs were then classified in the entire image using a maximum likelihood classification algorithm. The results of the classification process were checked in the field. Finally, a spatial analysis was performed by converting the detected landsurfaces into vectorial format and importing them into the ESRI ArcViewGIS 9.0 software. Application of these procedures, together with the results of the field survey, highlighted that some 'objects' in the classified imagery, even if displaying the same spectral response of NeFELs, were not landsurfaces subject to intense soil erosion, thus confirming the strategic importance of t

关键词： soil erosion remote sensing GIS geomorphology southern Italy

来源：评论

学校读者我要写书评

暂无评论

Cluster-based Training Data Preselection and Classification for remote sensing images

Cluster-based Training Data Preselection and Classification ...

引用

IEEE 10th International Conference on Signal processing

作者： Bian, Xiaoyong Zhang, Tianxu Fang, Zheng Sheng, Yuxia Zhang, Xiaolong Huazhong Univ Sci & Technol Inst Pattern Recognit & Artificial Intelligence Wuhan 430074 Peoples R China Wuhan Univ Sch Comp Sci & Technol Wuhan Peoples R China Wuhan Univ Sch Informat Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9781424458981

In classical image classification approaches, it assumes that there are a number of labeled training data per class. In real applications, labeled data generally are difficult to obtain while unlabeled data are sufficient and helpful to improve the accuracy of classifier. Bipartition based clustering method is to generate better initial cluster centers and to preselect representative data samples from each cluster region with given area under clustering model. To attack the quantity and quality problems of training samples, we propose a Cluster-based Classification Algorithm (CCA) for remote sensing images, and different data samples selection methods are evaluated. Using this approach, the confident unlabeled data both cluster centroid and the ones nearest to the centroid are labeled as training data and extracted. SVM can subsequently be trained with the labeled dataset. The conducted experiments by clustering and classification on real remote sensing images have validated the proposed approach.

关键词： representative data clustering model unlabeled data classification accuracy

来源：评论

学校读者我要写书评

暂无评论

Characterization of Texture in images by Using a Cellular Automata Approach

Characterization of Texture in Images by Using a Cellular Au...

引用

3rd World Summit on the Knowledge Society

作者： Leguizamon, Saturnino Espinola, Moises Ayala, Rosa Iribarne, Luis Menenti, Massimo Natl Technnol Univ Reg Fac Mendoza Mendoza Argentina Univ Almeria Appl Comp Grp Almeria Spain Delft Univ Technol Aerosp Engn Opt & Laser Remote Sensing Delft Netherlands

ISBN: (纸本)9783642163234

Spatial patterns in an image that shows a visual perception of roughness or softness of the surface is known as the texture of the image. Most of the analysis and description of texture found in the literature is based on statistical or structural properties of this attribute [2]. The field of cellular automata (CA), which has been developed mainly to model the dynamical behavior of systems, is based on the behavior or arrangements of pixel values and their neighborhood which, according to some rules behaves in different manners [2, 8]. In this paper, within the frame of structural approach, a novel method based on the properties of linear cellular automata is proposed to characterize different sort of textures. To this purpose, it is assumed that a binary version of the image under study was generated by a cellular automata technique. By using this model a number of textural primitives are found which allows the production of a characterizing image. In order to verify the feasibility of the proposed method, texture images generated by CA techniques as well as natural images has been used.

关键词： Texture image texture cellular automata image interpretation pattern recognition

来源：评论

学校读者我要写书评

暂无评论

2-D DHT-based fast gabor transform for image processing

2-D DHT-based fast gabor transform for image processing

引用

2010 2nd IITA Conference on Geoscience and remote sensing, IITA-GRS 2010

作者： Tan, Min Gu, Juan-Juan Hu, Xue-You Tao, Liang Dept. of Electronic Information and Electrical Engineering Hefei University Hefei Anhui 230022 China School of Compute Science and Technology Anhui University Hefei Anhui 230039 China

ISBN: (纸本)9781424485154

The 2-D Gabor transform has been recognized as being useful in diverse areas such as image compression, texture analysis, image segmentation, and image recognition;however, its real time applications have been limited due to the high computational complexity of the traditional 2-D complex-valued discrete Gabor transform (CDGT) algorithms. In this paper, 2-D discrete Hartley transform (DHT)-based real-valued discrete Gabor transform (RDGT) is presented, which can utilize the fast DHT algorithm for fast computation and has a simple relationship with the CDGT such that the 2-D CDGT coefficients can be directly computed from the 2-D DHT-based RDGT coefficients. Due to this simple relationship, the 2-D DHT-based RDGT also offers a faster and more efficient method to compute the 2-D CDGT. In addition, an efficient algorithm for the fast computation of the biorthogonal analysis window given a synthesis window is also presented. The results indicate that the proposed algorithms for the RDGT are attractive for real time image processing. © 2010 IEEE.

关键词： image compression

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：