检索结果-内蒙古大学图书馆

Multimodality image registration and fusion using neural network

Journal of Harbin Institute of Technology(New Series) 2003年第3期10卷 235-240页

作者： Mostafa G Mostafa Aly A Farag Edward Essock Computer Vision and Image Processing Laboratory Dept. of Electrical and Computer Engineering University of Louisville Louisville KY 40292 USAComputer Vision and Image Processing Laboratory Dept. of Electrical and Computer Engineering University of Louisville Louisville KY 40292 USADept. of Psychology University of Louisville Louisville kY 40292 USA

Multimodality image registration and fusion are essential steps in building 3-D models from remotesensing data. We present in this paper a neural network technique for the registration and fusion of multimodali-ty remote sensing data for the reconstruction of 3-D models of terrain regions. A FeedForward neural network isused to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data arepresented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusionresults.

关键词： data fusion image registration image interpolation neural network, 3-D model building

来源：评论

学校读者我要写书评

暂无评论

Statistically Robust Approach to Lens Distortion Calibration with Model Selection

Statistically Robust Approach to Lens Distortion Calibration...

引用

Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003

作者： Taha El-Melegy, Moumen Farag, Aly A. Electrical Engineering Dept. Assiut University Assiut Egypt Computer Vision and Image Processing Lab. University of Louisville LouisvilleKY40292 United States

ISBN: (纸本)0769519008

This paper addresses the problem of calibrating camera lens distortion, which can be significant in medium to wide angle lenses. While almost all existing nonmetric distortion calibration methods need user involvement in one form or another,we present an approach to distortion calibration based on the robust the-least-median-of-squares (LMedS) estimator. Our approach is thus able to proceed in a ful ly-automatic manner while being less sensitive to erroneous input data such as image curves that are mistakenly considered as projections of 3D linear segments. Our approach uniquely uses fast, closed-form solutions to the distortion coefficients, which serve as an initial point for a non-linear optimization algorithm to straighten imaged lines. Moreover we propose a method for distortion model selection based on geometrical *** experiments to evaluate the performance of this approach on synthetic and real data are reported. © 2003 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Independent component analysis in statistical shape models

Independent component analysis in statistical shape models

引用

Medical Imaging 2003: image processing

作者： Üzümcü, Mehmet Frangi, Alejandro F. Reiber, Johan H.C. Lelieveldt, Boudewijn P.F. Div. of Image Processing Dept. of Radiology Leiden University Medical Center Leiden Netherlands Lab Aragon Inst. of Engineering Research University of Zaragoza Zaragoza Spain

Statistical shape models generally use Principal Component Analysis (PCA) to describe the main directions of shape variation in a training set of example shapes. However, PCA assumes a number of restrictions on the data that do not always hold. In this paper we explore the use of an alternative shape decomposition, Independent Component Analysis (ICA), which does not assume a Gaussian distribution of the input data. Several different methods for performing ICA are available. Three most frequently used methods were tested in order to evaluate their effect on the resulting vectors. In statistical shape models, generally not all the eigenvectors that result from the PCA are used. Vectors describing noise are discarded to obtain a compact description of the data set. The selection of these vectors is based on the natural ordering of the vectors according to the variance in that direction which is inherent to PCA. With ICA, however, there is no natural ordering of the vectors. Four methods for sorting the ICA vectors are investigated. The different ICA-methods yielded highly similar yet not identical results. Vectors obtained with ICA showed localized shape variations, whereas eigenvectors obtained with PCA show global shape variations. From the results of the ordering methods can be seen that PCA is better suited for dimensionality reduction. Of the ordering methods that were tested, the best results were obtained with the ordering according to the locality of the shape variations.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Shape registration based on modified chain codes

引用

5th International Workshop on Advanced Parallel processing Technologies, APPT 2003

作者： Bilal, Muhammad Park, Jong-An Chang, Min Hyuk Shim, Young-Suk Choi, Tae-Sun Signal and Image Processing Lab Dept. of Mechatronics Kwangju Institute of Science and Technology Kwangju Korea Republic of Electronics Information and Communications Engineering Chosun University Kwangju Korea Republic of

ISBN: (纸本)3540200541

Shape descriptions based on the traditional chain codes are very susceptible to small perturbations in the contours of the objects. Therefore, direct matching of traditional chain codes could not be used for image retrieval based on the shape boundaries from the large databases. In this paper, a histogram based chain codes are proposed which could be used for image retrieval. The modified chain codes matching are invariant to translation, rotation and scaling transformations, and have high immunity to noise and small perturbations. © Springer-Verlag Berlin Heidelberg 2003.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

New signal subspace direction-of-arrival estimator for wideband sources

New signal subspace direction-of-arrival estimator for wideb...

引用

2003 IEEE International Conference on Accoustics, Speech, and Signal processing

作者： Yoon, Yeo-Sun Kaplan, Lance M. McClellan, James H. Ctr. for Signal and Image Processing Sch. of Elec./Computer Engineering Georgia Institute of Technology Atlanta GA 30332-0250 United States CTSPS Dept. of Engineering Clark Atlanta University Atlanta GA 30314 United States

Signal subspace methods in DOA estimation for wideband sources require preprocessing to find initial values which are close enough to the true values or to convert sensor outputs into desired forms. The preprocessing procedure should be carefully done lest it introduce some distortion. Failure to find proper initial values may prevent convergence of the estimator or cause biases in the estimator. The proposed method detects uncorrelated wideband sources using the signal subspace and the noise subspace of decomposed wideband signals. It does not require any initial values. The only preprocessing is narrowband decomposition of the sensor output which is very common in other wideband methods. Computer simulation showed that the proposed method has less bias and comparable variance than CSSM with small focussing errors.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

A hyperspectral fluorescence imaging system for biological applications

A hyperspectral fluorescence imaging system for biological a...

引用

2003 IEEE Nuclear Science Symposium Conference Record - Nuclear Science Symposium, Medical Imaging Conference

作者： Zavattini, Guido Vecchi, Stefania Leahy, Richard M. Smith, Desmond J. Cherry, Simon R. Dept. of Biomedical Engineering University of California-Davis Davis CA United States Sign. and Image Processing Institute University of Southern California Los Angeles CA United States Department of Molecular Pharmacology UCLA School of Medicine Los Angeles CA United States

We are developing a hyperspectral imaging system aimed at imaging fluorescent molecules in two different contexts: In vivo 3-D molecular imaging of mice and multi-fluorophore imaging of 2-D tissue samples. The main concept is to add high resolution spectral information to the intensity data to improve imaging capabilities. The system is based on an imaging spectrograph, ImSpector, coupled to a CCD camera. The system has been characterized and calibrated. Spectral imaging of tissue samples stained with fluorescent dyes has been performed to validate the principle and the 2-D imaging capabilities. Near infrared 3-D in vivo fluorescence tomography is based on the intensity and spatial distribution of the fluorescent light reaching the surface of the animal as a function of the localized external excitation position. Based on the fact that the absorption coefficient of tissue is wavelength dependent, the measured spectrum of the fluorescent light will provide additional information, thus allowing an improvement of the 3-D reconstruction. By using solely spectral data we have demonstrated the capability of determining the 3-D position of a localized source within a red meat phantom.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Vision chip for navigating and controlling micro unmanned aerial vehicles

Vision chip for navigating and controlling micro unmanned ae...

引用

Proceedings of the 2003 IEEE International Symposium on Circuits and Systems

作者： Massie, Mark Baxter, Chris Curzan, J.P. McCarley, Paul Etienne-Cummings, Ralph Nova Biomimetics Solvang CA 93463 United States AFRL MNGI Seeker Image/Sign. Processing Branch Eglin Air Force Base FL 32542 United States Dept. of Electrical Engineering Johns Hopkins University Baltimore MD 21218 United States

A single chip which visually measures the Yaw, Pitch and Roll (YPR) and images the direction of travel of a Micro Unmanned Aerial Vehicle (MUAV) is described. The YPR measurement modules, constructed using an elaborated Reichardt model of the fly's motion detection system, are used to measure the drift rate of features in the field of view. A variable acuity superpixellation imager (VASI), constructed using an active pixel sensor (APS) with networked integration capacitors, allows multiple high resolution foveae to be interspersed in a low resolution image of the environment. The 49 sq. mm chip, containing twelve 90-pixel linear arrays for the YPR modules and a 128 × 128 VASI array, is fabricated in a 0.5 μm 2P3M CMOS process. Measured results indicate that YPR rates of over 300 pixels/second and VASI images ranging from 1 × 1 to 128 × 128, with multiple, dynamically variable foveae, can be obtained with this chip. It is intended to be used to control and navigate a MUAV, but it can also be used for visual tracking and many other "multimode" imaging operations.

关键词： Microprocessor chips

来源：评论

学校读者我要写书评

暂无评论

Statistically Robust Approach to Lens Distortion Calibration with Model Selection

Statistically Robust Approach to Lens Distortion Calibration...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Moumen Taha El-Melegy Aly A. Farag Computer Vision and Image Processing Laboratory University of Louisville Louisville KY USA Electrical Engineering Dept. Assiut University Assiut Egypt Computer Vision and Image Processing Lab. University of Louisville Louisville KY

关键词： Nonlinear distortion Calibration Robustness Lenses Cameras image edge detection Distortion measurement

来源：评论

学校读者我要写书评

暂无评论

New signal subspace direction-of-arrival estimator for wideband sources

New signal subspace direction-of-arrival estimator for wideb...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yeo-Sun Yoon L.M. Kaplan J.H. McClellan Center for Signal and Image Processing Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta GA USA Center for Signal and Image Processing School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA CTSPS Dept. of Engineering Clark Atlanta University Atlanta GA

Signal subspace methods in DOA estimation for wideband sources require preprocessing to find initial values which are close enough to the true values or to convert sensor outputs into desired forms. The preprocessing procedure should be carefully done lest it introduce some distortion. Failure to find proper initial values may prevent convergence of the estimator or cause biases in the estimator. The proposed method detects uncorrelated wideband sources using the signal subspace and the noise subspace of decomposed wideband signals. It does not require any initial values. The only preprocessing is narrowband decomposition of the sensor output which is very common in other wideband methods. Computer simulation showed that the proposed method has less bias than and comparable variance to CSSM with small focusing errors.

关键词： Wideband Direction of arrival estimation Narrowband Frequency estimation Array signal processing Multiple signal classification Collaboration Government Signal processing image processing

来源：评论

学校读者我要写书评

暂无评论

Security of digital entertainment content from creation to consumption

Security of digital entertainment content from creation to c...

引用

作者： Eskicioglu, Ahmet M. Town, John Delp, Edward J. Dept. of Comp./Information Science Brooklyn College City University of New York Brooklyn NY 11210 United States Technicolor P.O. Box 7427 Charlottesville VA 22906 United States Video/Image Processing Laboratory Sch. of Elec./Computer Engineering Purdue University West Lafayette IN 47907 United States

With the advent of digital technologies, many new market opportunities have emerged for content owners, content distributors, and consumer electronics/information technology industries. An essential requirement for developing a thriving marketplace is the protection of copyrighted content in digital form. There are four major stages in the delivery of content to the consumer: (1) capturing on digital media, (2) packaging, (3) distribution to home networks, and (4) transfer to the final audio/visual device within the home network. Entertainment content is of particular importance as it will be in high demand for many years to come. If an end-to-end security cannot be provided in a digital market, there would be no incentive for content creation. Lack of new supplies would result in detrimental effects for all the industries involved in the delivery chain. In this paper, we present the primary means of securing the entertainment content from creation to consumption in an attempt to understand the overall complexity of the problem. © 2003 Elsevier Science B.V. All rights reserved.

关键词： Multimedia systems

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：