检索结果-内蒙古大学图书馆

数据采集与处理 2006年第4期21卷 463-467页

作者：刘安斐李弼程张先飞解放军信息工程大学信息工程学院郑州450002

以多光谱图像为研究对象,综合利用遥感图像的光谱、纹理和数学变换特征,提出了一种基于数据融合的多特征遥感地物分类方法。该方法针对不同的特征分别构造了神经网络分类器和K-均值聚类器,并对前者利用A daboost算法进行提升,然后再将... 详细信息

以多光谱图像为研究对象,综合利用遥感图像的光谱、纹理和数学变换特征,提出了一种基于数据融合的多特征遥感地物分类方法。该方法针对不同的特征分别构造了神经网络分类器和K-均值聚类器,并对前者利用A daboost算法进行提升,然后再将各特征的分类结果利用证据理论合成公式融合得到最终结果。实验结果表明,该方法的分类效果要优于单特征的分类结果。

关键词：图像分类特征选择 Adaboost算法证据理论

来源：评论

学校读者我要写书评

暂无评论

A preprocessing and automated algorithm selection system for image registration

A preprocessing and automated algorithm selection system for...

引用

conference on Multisensor, Multisource Information Fusion

作者： Drozd, A. L. Blackburn, A. C. Kasperovich, I. P. Varshney, P. K. Xu, M. Kumar, B. Syracuse Univ Syracuse NY 13244 USA

ISBN: (纸本)0819462985

image registration is a technique for precisely aligning the content of two or more images. It is often used as a preprocessing stage for further analysis, such as automatic target recognition, change detection, and environmental remote sensing. However, there are many different registration algorithms available to the image analyst, and it's difficult to know which one is the best one to use for a particular pair of images. These various algorithms also have a multitude of settings and parameters that must be given proper values for best results. Consequently, it is often difficult to know which algorithm will perform the best in a given situation, under constraints of time or accuracy. We propose constructing an expert system, with rules based on experimental results, that will automatically select the appropriate registration algorithm and perform appropriate preprocessing steps to prepare the images for registration.

关键词： image registration data fusion image processing expert systems

来源：评论

学校读者我要写书评

暂无评论

Residual Error based Approach to Classification of Multisource remote sensing images

Residual Error based Approach to Classification of Multisour...

引用

International conference on Intelligent Systems Design and Applications (ISDA)

作者： Dongdong Cao Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China

Classification of multisource remote sensing images has been studied for decades, and many methods have been proposed. Most of these studies focus on how to improve the classifiers in order to obtain higher classification accuracy. However, as we know, even if the most promising neural network method, its good performance not only depends on the classifier itself, but also has relation to the training pattern (i.e. features). On consideration of this aspect, we propose an approach to feature selection and classification of multisource remote sensing image based on residual error in this paper. In particular, a feature-selection scheme approach is proposed, which is to select effective subsets of features as inputs of a classifier by taking into account the residual error associated with each land-cover class. In addition, a classification technique base on selected features by using a feedforward neural network is investigated. The results of experiments carried out on a multisource data set confirm the validity of the proposed approach

关键词： remote sensing Neural networks remote monitoring Earth Feedforward neural networks Computer errors Classification algorithms Bayesian methods Robustness image processing

来源：评论

学校读者我要写书评

暂无评论

A NewWay for the Detection and recognition of Bridges

A NewWay for the Detection and Recognition of Bridges

引用

International conference on Signal processing Proceedings (ICSP)

作者： Mengyu Zhu Department of Electronic Engineering Beijing Institute of technology Beijing China

In this paper, a two-step scheme based on the maximum variance cluster algorithm was presented to detect and recognize bridges over water with the complicated background from the remote sensing images. First, the water including bridges was detected in all region of image; then, image segmentation and feature extraction and recognition were performed over the water having been detected. According to the above thought, this paper presented one miniaturized system that is realized by hardware, which is based on the DSP and possess low power loss. And the remote sensing images about bridge are done some experiment, the result of experiment indicated this method for detecting and recognizing the bridge over waters is feasible and effective

关键词： Bridges Clustering algorithms image segmentation remote sensing image recognition Pixel Hardware Target recognition Layout Water

来源：评论

学校读者我要写书评

暂无评论

Proximity graph analysis for linear networks extraction from high-resolution satellite imagery - art. no. 62351C

Proximity graph analysis for linear networks extraction from...

引用

conference on Signal processing, Sensor Fusion, and Target recognition XV

作者： Skourikhine, Alexei N. Los Alamos Natl Lab Space & Remote Sensing Sci Grp Los Alamos NM 87545 USA

ISBN: (纸本)0819462918

Reliable and accurate methods for detection and extraction of linear network, such as road networks, in satellite imagery are essential to many applications. We present an approach to the road network extraction from high-resolution satellite imagery that is based on proximity graph analysis. We are jumping off from the classification provided by existing spectral and textural classification tools, which produce a set of candidate road patches. Then, constrained Delaunay triangulation and Chordal Axis transform are used to extract centerline characterization of the delineated candidate road patches. We refine produced center lines to reduce noise influence on patch boundaries, resulting in a smaller set of robust center lines authentically representing their road patches. Refined center lines are triangulated using constrained Delaunay triangulation (CDT) algorithm to generate a sub-optimal mesh of interconnections among them. The generated triangle edges connecting different center lines are used for spatial analysis of the center lines relations. A subset of the Delaunay tessellation grid contains the Euclidian Minimum Spanning Tree (EMST) that provides an approximation of road network. The approach can be generalized to the multi-criteria MST and multi-criteria shortest path algorithms to integrate other factors important for road network extraction, in addition to proximity relations considered by standard EMST.

关键词： road network satellite image visual perception minimum spanning tree Delaunay triangulation vector image SVG

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Based on Inscribed circle

Image Segmentation Based on Inscribed circle

引用

International conference on pattern recognition

作者： Zhanrong Li Jianqing Zhang School of Remote Sensing and Information Engineering Wuhan University of China China School of Computer and Electronics and Information Guangxi University China

ISBN: (纸本)0769525210

We present an image segmentation algorithm based on inscribed circle (ICseg) in this paper. The algorithm includes multi-step. It examines edges at first, and then produces a binary image with edges as foreground. After that, inscribed circles are created to cover the background of the binary image. In the first partition, the image is subdivided into separated regions by combining inscribed circles. Finally, the regions are merged by computing their shape and gray level features. This approach integrates the boundary-based and region-based techniques. It is a simple and efficient way for full image segmentation

关键词： image segmentation image edge detection Partitioning algorithms Shape Phase detection remote sensing Focusing Pixel Robustness Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Interactive Road Extraction with Pixel Force Fields

Interactive Road Extraction with Pixel Force Fields

引用

International conference on pattern recognition

作者： V. Bucha S. Uchida S. Ablameyko United Institute of Informatics Problems National Academy of Science of Belarus Minsk Belarus Department of Intelligent Systems Kyushu University Fukuoka Japan

Pixel force field (PFF) is a novel image representation where at each pixel a two-dimensional vector is defined for representing interaction of pixels. The vector is oriented to the center of the region composed of pixels having the same qualitative property, such as color and gray-scale level. Using the pixel force field and improved live-wire segmentation technique the task of interactive road extraction from remote sensing images is solved

关键词： Pixel Roads image segmentation Gray-scale image representation remote sensing Color Geographic Information Systems Costs Informatics

来源：评论

学校读者我要写书评

暂无评论

Application of remote sensing techniques for water resources planning and management

Application of remote sensing techniques for water resources...

引用

2006 International conference on Advances in Space Technologies, ICAST

作者： Shakoor, A. Shehzad, A. Asghar, M.N. Pakistan

ISBN: (纸本)1424405149

This paper describes the importance and capabilities of modern techniques such as remote sensing (RS) and geographic information systems (GIS) as water resource management and conservation tool. RS/GIS analysis can show where water enters a system and how it leaves through evapotranspiration and runoff. Using this information, planners can identify areas where there is potential for development of new water resources;where water can be reallocated from one use or one basin to another;and identify potential areas of water scarcity before water shortages occur. The main objective of this research is to calculate accurate crop water requirement by using RS/GIS in combination with hydraulic models. The results helped in devising guidelines, which in turn will help the policy makers to release the water supplies based on crop requirement only rather than supply based. Multi temporal satellite images were used to identify various crops and cropping pattern in the area. This study was conducted for the Pehure High Level Canal (PHLC) and the Upper Swat Canal (USC) system in the North Western Frontier Province (NWFP) of Pakistan. Crop identification at distributary level was made from multi-temporal remote sensing satellite images. Various image processing techniques such as supervised, unsupervised classification and spectral mixture analysis were used to correctly identify various types of crops in the region and ultimately accurate areas of all the classified crops was calculated from the satellite images. These calculated areas were compared with the seasonal data recorded by the irrigation department. ET was calculated using CROPWA T model at various stages of crop growth. Then water required for each individual crop was calculated. The results are very encouraging. The results of this study can be used while devising guidelines for water managers to release the canal supplies based on crop water requirement. This practice will help in avoiding wastage of canal water at

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Evidential Reasoning Based Classifier Combination for an Optimal remote sensing image Classification

Evidential Reasoning Based Classifier Combination for an Opt...

引用

International conference on Information and Communication Technologies: From Theory to Applications, ICTTA

作者： S. Chitroub Electronics and Computer Science Faculty U.S.T.H.B. Signal Image Processing Laboratory

The work presented here addresses the problem of the enhancement of the remote sensing image classification. For that, an evidential reasoning based classifier combination method is proposed. The originality of the work lies in the fact that the method treats the outputs of the classifiers by completely ignoring the internal characteristics of the latter. The method is thus general and applicable to any type of classifier. It cumulates the advantages of each classifier without cumulating the disadvantages of them. It overcomes the disadvantages of the remote sensing image classification methods developed in the literature. Thus, it constitutes a powerful tool for several remote sensing image processing applications

关键词： remote sensing image classification image processing Classification algorithms Signal processing Laboratories Computer science Layout pattern classification Merging

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Fusion on Gradient Field

Remote Sensing Image Fusion on Gradient Field

引用

International conference on pattern recognition

作者： Jianting Wen Yan Li Haifeng Gong School of Computer South China Normal University China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences China

This paper presents two methods to fuse a low spatial resolution multispectral image and a high spatial resolution panchromatic one to produce a new multispectral image with high spatial resolution. First, the Poisson fusion method is developed based on minimizing the gradient difference between the synthesized image and the panchromatic image with boundary conditions sampled from the multispectral image. The fusion result can therefore be achieved by solving the Poisson equation with Dirichlet boundary conditions. Secondly, an optimal fusion technique, which minimizes the gradient difference and the color difference with respect to the panchromatic and multispectral images respectively is given and the result is induced by an iterative optimization algorithm. Both of them can be applied to color composites and individual bands. Their advantages of the fidelity to spectral property and the spatial resolution improvement over the HSI, Brovey, PCA and wavelet transform are convincingly demonstrated in the experiments from visual evaluation and statistical analysis

关键词： remote sensing image fusion Spatial resolution Multispectral imaging Boundary conditions Fuses Poisson equations Iterative algorithms Principal component analysis Wavelet analysis

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：