检索结果-内蒙古大学图书馆

International Conference on Information Fusion

作者： R. Mohamed A. El-Baz A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

The kernel function plays a basic role in support vector machines (SVM) algorithms. This paper presents an automatic method for selecting the parameters of the Gaussian radial basis function (GRBF) kernel which is one of the commonly used forms in SVM regression algorithms. The proposed method uses the expectation maximization (EM) algorithm for the automatic selection. The SVM regression algorithm is used to solve two major problems in remote sensing image segmentation: the density estimation problem and the Markov random field modeling problem. The density estimation is used for class conditional probabilities in Bayesian setups. The MRF is used for region modeling in boosting the Bayesian image segmentation. The proposed algorithms are integrated in a framework for remote sensing image segmentation. Experimental evaluation of the proposed algorithms using synthetic data set and hyperspectral data set illustrates the outstanding performance of the proposed algorithms.

关键词： Remote sensing image segmentation Support vector machines Kernel Probability Markov random fields Bayesian methods Covariance matrix computer vision image processing

来源：评论

学校读者我要写书评

暂无评论

Robust virtual forces-based camera positioning using a fusion of image content and intrinsic parameters

Robust virtual forces-based camera positioning using a fusio...

引用

International Conference on Information Fusion

作者： A.E. Abdel-Hakim A.A. Farag Computer Vision and Image Processing Laboratory CVIP Lab University of Louisville Louisville KY USA

In this paper, we present a novel and robust model for camera planning in smart vision systems. The proposed approach uses virtual forces to adjust camera parameters (pan and tilt) to the most proper values with respect to the application. The proposed model employs the information in the acquired image and some of the intrinsic camera parameters to estimate pan and tilt displacements required to bring a target object into a specific location of interest in the image. Our model is a general framework and any vision system can be easily modeled to use it. This approach has several advantages over previous work in camera planning. It is portable, expandable, robust, and flexible. Also, there is no need for complicated calibration for the cameras or their pan-tilt heads. The results show that our approach is efficient even with poor system initialization and it is robust against possible weakness in the auxiliary algorithms used.

关键词： Robustness Cameras Machine vision Calibration Process planning Head Lenses Focusing Surveillance computer vision

来源：评论

学校读者我要写书评

暂无评论

Shape-constraint for accurate segmentation in remote sensing imagery

Shape-constraint for accurate segmentation in remote sensing...

引用

International Conference on Information Fusion

作者： A. El-Baz R. Mohamed A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

A new approach is proposed for the segmentation of remote sensing images which is based on using a prior shape information. This information is obtained from a set of signed distance functions (SDF). Each SDF represents the training data set as a histogram of the occurrences of the data points inside and outside a specific object. A statistical approach is proposed for modeling each SDF, which is considered to have a random distribution. The mean field theory-based support vector machines (MF-based SVM) density estimator is used to estimate the probability density function which underlies the random distribution of the SDF. The statistical modeling of shapes enables realistic representation of objects especially those which are not contiguous within the image; i.e., objects which consist of multiple regions. This modeling is used to substitute for the class priors in a Bayes segmentation setup, in which the class conditional probabilities are estimated using the MF-based SVM algorithm also. Experiments with multispectral remote sensing data show that the proposed segmentation approach is more accurate and robust than other known alternatives.

关键词： image segmentation Remote sensing Shape measurement Surface cleaning Support vector machines computer vision Pixel image processing Laboratories Training data

来源：评论

学校读者我要写书评

暂无评论

A clique of active appearance models by minimum description length

A clique of active appearance models by minimum description ...

引用

2005 16th British Machine vision Conference, BMVC 2005

作者： Langs, Georg Peloschek, Philipp Donner, René Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Department of Diagnostic Radiology Medical University of Vienna Austria Pattern Recognition and Image Processing Group Vienna University of Technology Austria

ISBN: (纸本)1901725294

Autonomous model building is a crucial trend in model based methods like AAMs. This paper introduces an approach that deals with non-linearities by detecting distinct sub-parts in the data. Sub-models each representing an individual sub-part are derived from a minimum description length criterion. Thereby the resulting clique of models is more compact and obtains a better generalization behavior than a single model. The proposed AAM clique generation deals with non-linearities in the data in a generic information theoretic manner reducing the necessity of user interaction during training.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

A robust matching algorithm for active appearance models 1

引用

Workshops Bildverarbeitung fur die Medizin: Algorithmen - Systeme - Anwendungen, BVM 2005 - Workshop on image processing for Medicine: Algorithms - Systems - Applications, BVM 2005

作者： Beichel, Reinhard Bischof, Horst Langs, Georg Sonka, Milan Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/2 A-8010 Graz Austria Pattern Recognition and Image Processing Group Vienna University of Technology Favoritenstr. 9 A-1040 Vienna Austria Department of Electrical and Computer Engineering University of Iowa Iowa City IA 52242 United States

ISBN: (数字)9783540264316

ISBN: (纸本)3540250522

This paper proposes a method for robustly matching active appearance models (AAMs) on images with gross disturbances (outliers). The method consists of two steps. First, an initial residual is calculated by comparing model and image appearance, and modes of the residual are analyzed. Second, all possible mode combinations are tested by evaluating an objective function. The objective function allows the selection of an outlier-free mode combination. Experiments demonstrate the ability of the robust matching method to successfully cope with outliers - compared to standard AAM matching, no degeneration of the model during matching occurs.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Optimal sub-shape models by minimum description length

Optimal sub-shape models by minimum description length

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： G. Langs P. Peloschek H. Bischof Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria Department of Clinical Radiology Vienna Medical University Vienna Austria

Active shape models are powerful and widely used tool to interpret complex image data. By building models of shape variation they enable search algorithms to use a priori knowledge in an efficient and gainful way. However, due to the linearity of PCA, non-linearities like rotations or independently moving sub-parts in the data can deteriorate the resulting model considerably. Although non-linear extensions of active shape models have been proposed and application specific solutions have been used, they still need a certain amount of user interaction during model building. In this paper the task of building/choosing optimal models is tackled in a more generic information theoretic fashion. In particular, we propose an algorithm based on the minimum description length principle to find an optimal subdivision of the data into sub-parts, each adequate for linear modeling. This results in an overall more compact model configuration. Which in turn leads to a better model in terms of modes of variations. The proposed method is evaluated on synthetic data, medical images and hand contours.

关键词： Active shape model Biomedical imaging Principal component analysis computer vision Linearity Polynomials Pattern recognition computer graphics Radiology image processing

来源：评论

学校读者我要写书评

暂无评论

Novel vibro-acoustical technology for pipe deposition monitoring

引用

International Journal of COMADEM 2005年第4期8卷 24-32页

作者： Gelman, L. Jenkin, P. Petrunin, I. Sanderson, M. Thompson, C. Cranfield University National Technical University of Ukraine Cranfield University Department of Process and Systems Engineering Applied Mathematics and Computing Group Cranfield Beds MK43 0AL United Kingdom Applied Mathematics and Computing Group Cranfield University National Technical University of Ukraine KPI Department of Process and Systems Engineering Department of Fluid Instrumentation School of Engineering Cranfield University Centre for Computer Vision and Image Processing

Deposits (waxes, hydrates, etc.) change the damping properties of pipelines. The damping ratio of the pipeline increases with increments in deposit thickness. Thus, the evaluation of the damping ratio of the pipeline provides a condition monitoring of the pipeline deposits. Deposits could, be detected by monitoring the vibro-acoustical response of the pipeline while it is subjected to vibration excitation. Vibro-acoustical pipeline condition monitoring is a promising technology, but it has been little investigated. A novel vibro-acoustical technology of deposit detection in pipelines is proposed, developed, and validated through simulation. A new generic feature representation approach is used. Comparison of the proposed technology with the traditional technology based on the magnitude of the frequency response function is undertaken using simulation (by the Simulink) and Monte Carlo procedure. It is shown that the proposed technology provides an essential monitoring effectiveness gain vs. that of the technology based on the magnitude of the frequency response function. Thus, the proposed technology significantly improves the accuracy of vibro-acoustical deposit monitoring in pipelines. © 2005 COMADEM International.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Performance Evaluation of 3-D Reconstruction Techniques

A Unified Framework for Performance Evaluation of 3-D Recons...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： A. Eid A. Farag Computer Vision and Image Processing (CVIP) Laboratory University of Louisville Louisville KY USA

In this paper we consider the problem of performance evaluation of 3-D reconstruction techniques from calibrated sequence of images. We propose a unified framework for the evaluation process assuming the existence of ground truth data collected by a 3-D laser scanner. Firstly, we propose a new pre-evaluation technique for 3-D data registration based on silhouettes alignment. The performance of this technique is independent of the output quality of the 3-D reconstruction technique under test. This is a major advantage of our technique since the quality issue, which is not guarantee under the evaluation topic, is a challenge for any 3-D registration technique. Secondly, we propose a geometrically based evaluation methodology. The method is based on the geometrical matching of uniformly distributed patches of both ground truth and under-test data sets. The method is insensitive to the relative density of data sets. In addition, it provides a method for localizing errors which is a crucial step for diagnosis and data fusion post-evaluation techniques. Finally, we provide experimental results on the evaluation of stereo and space carving techniques.

关键词： Three dimensional displays Stereo vision Testing computer vision Optical sensors Cameras image processing Laboratories Stereo image processing Fuses

来源：评论

学校读者我要写书评

暂无评论

Detecting regional abnormal cardiac contraction in short-axis MR images using independent component analysis

引用

7th International Conference on Medical Imaging and computer Assisted Intervention, MICCAI 2004

作者： Suinesiaputra, A. Üzümcü, M. Frangi, A.F. Kaandorp, T. Reiber, J. Lelieveldt, B. Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Computer Vision Group Aragon Institute of Engineering University of Zaragoza Zaragoza Spain

ISBN: (纸本)3540229760

Regional myocardial motion analysis is used in clinical routine to inspect cardiac contraction in myocardial diseases such as infarction or hypertrophy. Physicians/radiologists can recognize abnormal cardiac motion because they have knowledge about normal heart contraction. This paper explores the potential of Independent Component Analysis (ICA) to extract local myocardial contractility patterns and to use them for the automatic detection of regional abnormalities. A qualitative evaluation was performed using 42 healthy volunteers to train the ICA model and 6 infarct patients to test the detection and localization. This experiment shows that the evaluation results correlate very well to the clinical gold standard: delayed-enhancement MR images. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Robust occupancy detection from stereo images

Robust occupancy detection from stereo images

引用

International Conference on Intelligent Transportation

作者： B. Alefs M. Clabian H. Bischof W. Kropatsch F. Khairallah Advanced Computer Vision GmbH-ACV Vienna Austria Advanced Computer Vision GmbH-ACV Austria Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group Institute of Computer Aided Automation Computer Science Department University of Technology Vienna Vienna Austria TRW Automotive GmbH Farmington Hills MI USA

Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This work presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.

关键词： Robustness Magnetic heads Vehicle crash testing Sensor systems Stereo vision Layout Statistical analysis Support vector machines Support vector machine classification Vehicle detection

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：