检索结果-内蒙古大学图书馆

Congress on image and Signal processing, CISP

作者： Han, Mingqin Jiang, Tao Zhang, Weizheng Dong, Shouyin Lu, Wenhu Remote Sensing Department Geometrics College Shandong University of Science and Technology Qingdao China Key Laboratory of Surveying and Mapping Technology on Island and Reed State Bureau of Surveying and Mapping Qingdao China Image Processing Department Information and Electrical College Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9781424465149

The paper first describes the method of decision tree classification and characteristics of domestic and foreign research and elaborated on the basic principles of decision tree classifier and decision tree classifier structure the conditions to be met. On this basis, we extract information from Landsat-ETM+ image in September 16, *** we draw the spectral reflectance curve of the samples from the image, and establish the initial decision tree model. After that, we adjust the initial decision tree model to a satisfactory result. At last;we compared the result of decision tree classification with the result of traditional classification. Studies show that the total accuracy of decision tree method increases by 12.96% and Kappa coefficient by 14.63%. ©2010 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Fusion of hyperspectral imagery and bathymetry information for inversion of bioptical models

Fusion of hyperspectral imagery and bathymetry information f...

引用

remote sensing of the Ocean, Sea Ice, and Large Water Regions 2009

作者： Torres-Madronero, Maria C. Velez-Reyes, Miguel Goodman, James A. Laboratory for Applied Remote Sensing and Image Processing Center for Subsurface Sensing and Image Systems University of Puerto Rico-Mayaguez Mayaguez 00681-3535 Puerto Rico

ISBN: (纸本)9780819477781

Bioptical models are used jointly with hyperspectral imaging in inversion procedures for mapping of benthic habitats. Several algorithms have been described in the literature to remove the effects of the water column and extract information about the sea bottom that only take into consideration the measured hyperspectral image. However the availability of LIDAR derived bathymetry information opens the possibility of using this information for improved retrieval of the bottom properties. We present in this paper a study using simulated and hyperspectral imagery on the improvement in benthic habitat mapping that can be achieved by fusing bathymetry and hyperspectral imagery. Simulation results show that it is possible to obtain accurate bottom abundance estimates 5-10 meters beyond what can be obtained with hyperspectral imaging alone in clear waters. With real data we demonstrate increase in accuracy with respect to ground truth. © 2009 SPIE.

关键词： Bathymetry

来源：评论

学校读者我要写书评

暂无评论

Effects of image restoration in classification and visual analysis of landsat imagery over Puerto Rico

Effects of image restoration in classification and visual an...

引用

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral imagery XV

作者： Morales-Irizarry, E. Veronica Velez-Reyes, Miguel Laboratory for Applied Remote Sensing and Image Processing Center for Subsurface Sensing and Imaging Systems University of Puerto Rico at Mayaguez Puerto Rico

ISBN: (纸本)9780819476005

In image processing, restoration is performed in order to enhance salient features or remove degradation effects to assist in subsequent human or machine analysis. Restoration algorithms deal with removing the effect of spatial blurring introduced by the imaging system which is introduced in multispectral remote sensing by limitations of the optical system, scanning, and electronics. This result in that the support of the signal received at a particular pixel comes from an area larger than the projection of the pixel on the surface ground. This hinders the ability to derive surface informati on from satellite images on a per-pixel basis. image deblurring is the problem of recovering the original image from its blurred noisy observation. In this study, we present how image reconstruction algorithms can help visual and machine-based analysis of Landsat imagery taken over coastal areas in southern Puerto Rico. image restoration improves image contrast near edges and improves visual appeal of different color composites. Improvements in infrared bands were more significant than in bands in the visual range. Performance of classifiers over nearly homogeneous areas used for training and testing areas was not significantly changed. However, small features that were not classified correctly in the original image were classified correctly in the restored image.©2009 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Volume-based magnetic resonance brain image classification

Volume-based magnetic resonance brain image classification

引用

International Conference on Genetic and Evolutionary Computing

作者： Chiou, Yaw-Jiunn Chai, Jyh-Wen Chen, Clayton Chi-Chang Chen, Shih-Yu Chen, Hsian-Min Ouyang, Yen-Chieh Su, Wu-Chung Tsai, Ching Tsorng Yang, Ching-Wen Lee, San-Kan Chang, Chein-I Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Section of Radiology College of Medicine China Medical University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung Taiwan Department of Biomedical Engineering Hungkuang University Taichung Taiwan Computer Science Department Tunghai University Taichung Taiwan Computer Center Taichung Veterans General Hospital Taichung Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780769542812

This paper develops a volume-based technique, called Volume Sphering Analysis (VSA) which can process all acquired Magnetic Resonance (MR) image slices-formed image cube using only one set of training samples obtained from an image slice. So, several significant advantages and benefits can be gained from our proposed VSA. In the past, when MR image classification is performed, each image slice requires its own specific training samples and training samples obtained from one slice are not applied to another slice. The VSA allows users to reduce computational time. In addition, it saves significant effort in selecting training samples for each of image slices. Thirdly, it is robust to all image slices compared to the traditional one-slice MR image classification which is sensitive to each image slice. Experimental results demonstrate that the VSA performs as well as does that using specifically selected training samples for individual image slices. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Underwater unmixing and water optical properties retrieval using HyCIAT

Underwater unmixing and water optical properties retrieval u...

引用

Imaging Spectrometry XIV

作者： Torres-Madronero, Maria C. Velez-Reyes, Miguel Goodman, James A. Laboratory for Applied Remote Sensing and Image Processing Center for Subsurface Sensing and Imaging Systems University of Puerto Rico-Mayagez Mayagez 00681-3535 Puerto Rico

ISBN: (纸本)9780819477477

Unmixing of the seabed for benthic habitat mapping in shallow coastal waters is a difficult problem due to the confounding effects of space variant bathymetry and water optical properties, which result in signatures for the same habitat classes to look different at the water surface across the image. This paper discusses different approaches to modify the linear unmixing approach to account for variable water optical properties and bathymetry and their implementation in the Hyperspectral Coastal image Analysis Toolbox (HyCIAT). This toolbox allows the processing of hyperspectral imagery of shallow coastal areas to estimate water column optical properties, bathymetry, and perform unmixing for bottom composition. HyCIAT has been developed as part of the UPRM Hyperspectral Solutionware project to develop software tools for hyperspectral image processing. The tool has been developed under the MATLABTM environment and it includes a series of algorithms developed by UPRM researches under a graphical user interface that facilitates its use by the remote sensing community. The paper describes algorithms implemented in the toolbox, gives an overview of the graphical user interface, and presents results of its applications to AVIRIS and AISA hyperspectral imagery collected over Kaneohe Bay in Hawaii and over Southwestern Puerto Rico, respectively. © 2009 SPIE.

关键词： Bathymetry

来源：评论

学校读者我要写书评

暂无评论

Techniques for automatic magnetic resonance image classification

Techniques for automatic magnetic resonance image classifica...

引用

International Conference on Genetic and Evolutionary Computing

作者： Chen, Hsian-Min Chen, Shih-Yu Chai, Jyh Wen Chen, Clayton Chi-Chang Wu, Chao-Cheng Ouyang, Yen-Chieh Tsai, Ching Tsorng Yang, Ching-Wen Lee, San-Kan Chang, Chein-I Department of Biomedical Engineering Hungkuang University Taichung Taiwan Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Section of Radiology College of Medicine China Medical University Taichung Taiwan Department of Radiology Taichung Veterans General Hospital Taichung Taiwan Department of Radiological Technology Central Taiwan University of Science and Technology Taichung Taiwan Department of Electrical Engineering National Taipei University of Technology Taipei Taiwan Computer Science Department Tunghai University Taichung Taiwan Computer Center Taichung Veterans General Hospital Taichung Taiwan Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780769542812

Designing and developing automatic techniques for magnetic resonance images (MR) for data analysis is very challenging. One popular and public available method, FAST (FMRIB Automatic Segmentation Tool) has been widely used for automatic brain tissue segmentation for this purpose. This paper investigates limitations of this software algorithm on implementation and further develops a new approach to automatic MR brain tissue classification. The proposed new technique first implements an unsupervised training sample generation process (UTSGP) which includes a Pixel Purity Index (PPI) to generate an initial set of training samples that are further refined by a Support Vector Machine. The resulting training samples are then as a set of training samples for an Iterative Fisher's Linear Discriminant Analysis (IFLDA) which implements FLDA iteratively to improve classification. In order to conduct a fair comparison synthetic images are used for performance evaluation. Experimental results show that our proposed technique is superior in practical implementation to this software algorithm in several aspects of generalization ability, flexibility of choosing number of classes to be classified, avoidance of inconsistent results caused by different initial conditions. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Classifier-based feature fusion for texture discrimination

Classifier-based feature fusion for texture discrimination

引用

2009 International Conference on Information Engineering and Computer Science, ICIECS 2009

作者： Ma, Jianglin Zhang, Zhouwei Wang, Chengyi Chen, Zhong Remote Sensing Image Processing Laboratory Institute of Remote Sensing Applications CAS Beijing China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424449941

A classifier-based method to select and fuse grey level co-occurrence matrix (GLCM), Gaussian Markov random field (GMRF) and discrete wavelet transform (DWT) features to improve texture discrimination is presented. Feature selection via wrapper approaches is applied to find the optimal combination of texture features. The fused features have obtained higher discrimination accuracy compared with individual features. The curse of dimensionality is shown to affect discrimination accuracy, and feature selection and reduction helps obtain higher accuracy. Overall our proposed classifier-based method obtains the highest discrimination accuracy compared to other feature reduction methods such as principal component analysis (PCA) and linear discriminant analysis (LDA). Meanwhile GLCM features are found to produce higher discrimination accuracy than GMRF and DWT, and LDA is demonstrated to obtain higher discrimination accuracy than PCA. ©2009 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Comparison of unmixing algorithms for hyperspectral imagery

A Comparison of unmixing algorithms for hyperspectral imager...

引用

Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral imagery XV

作者： Santos-García, Andrea Velez-Reyez, Miguel Rosario-Torres, Samuel Chinea, Jesus D Laboratory for Applied Remote Sensing and Image Processing Center for Subsurface Sensing and Imaging Systems University of Puerto Rico-Mayaguez PR United States Biology Department University of Puerto Rico-Mayaguez PR United States

ISBN: (纸本)9780819476005

In this paper, we present an experimental comparison of unmixing using the constrained positive matrix factorization (cPMF) with SMACC and MaxD unmixing algorithms that retrieve endmembers from the image *** comparison was made using hyperspectral images collected over Vieques Island in Puerto Rico using the AISA sensor. Based on field work, six information classes were identified in the area of interest and the algorithms are evaluated in their capability to retrieve information about the classes of interest. The cPMF was the only approach capable of identifying all six informational classes with one or more spectral classes assigned to them. SMACC and MaxD were unable to extract one of the classes. The abundance maps from cPMF describe the spatial distribution of the information classes.©2009 SPIE.

关键词： Hyperspectral imaging

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

引用

Procedia Earth and Planetary Science 2009年第1期1卷 1133-1139页

作者： Xu, Sheng Fang, Tao Huo, Hong Li, Deren Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China The State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430072 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 classifica-tion performance. © 2009.

关键词： Object recognition image analysis image classification image segmentation Aerial images Bag of visual words Local descriptors Local feature Local region Novel methods Object based Region of interest Saliency map Selective attention model Very high spatial resolutions

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of real-time endmember extraction algorithms for hyperspectral imagery

Design and analysis of real-time endmember extraction algori...

引用

Satellite Data Compression, Communication, and processing V

作者： Chang, Chein-I Wu, Chao-Cheng Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD 21250 United States

ISBN: (纸本)9780819477453

Endmember extraction has recently received considerable attention in hyperspectral data exploitation since they represent crucial and vital information for hyperspectral data analysis. So far, no work has been reported on how to implement endmember extraction algorithms in real-time. An endmember is defined as an idealized signature and may or may not exist as a data sample or an image pixel. The interest of endmember extraction arises in the use of hundreds of contiguous spectral channels that allows a hyperspectral imaging sensor to uncover many subtle substances in diagnostic bands. However, finding such substances also presents a great challenge to hyperspectral data analysts and becomes imperative when it comes to satellite communication if a hyperspectral imaging sensor is operated in space platform where bandwidths used by satellite links may be very limited and downloading all the data may not be realistic in many practical applications. In order to address this need many endmember extraction algorithms have been developed and designed in the past, but no work has been reported on how to implement endmember extraction algorithms in real-time. This paper investigates this issue in designing algorithms for real time processing of endmember extraction and developed several endmember extraction algorithms derived from the widely used N-finder algorithm (NFINDR) that can be implemented in real time. © 2009 SPIE.

关键词： Space platforms

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：