检索结果-内蒙古大学图书馆

Observer forms for perspective systems

AUTOMATICA 2010年第11期46卷 1829-1834页

作者： Dahl, Ola Wang, Yebin Lynch, Alan F. Heyden, Anders DDA Consulting AB Malmo Sweden Mitsubishi Elect Res Labs Cambridge MA USA Univ Alberta Dept Elect & Comp Engn Edmonton AB Canada Lund Univ Dept Appl Math Ctr Math Sci Lund Sweden

The estimation of three-dimensional position information from two-dimensional images in computer vision systems can be formulated as a state estimation problem for a nonlinear perspective dynamic system. The multi-output state estimation problem has been treated by several authors using methods for nonlinear observer design. This paper shows that a perspective system can be transformed to two observer forms, and provides constructive methods for arriving at the transformations. These observer forms lead to straightforward observer designs. First, it is shown that, using an output transformation, the system admits an observer form which leads to an observer with linear error dynamics. A second observer design is based on a time-scaled block triangular form. Both designs assume a commonly used observability condition. The designs are demonstrated in simulation. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Nonlinear observers Perspective systems Observer forms Structure estimation computer vision systems

来源：评论

学校读者我要写书评

暂无评论

Context based object categorization: A critical survey

引用

computer vision AND IMAGE UNDERSTANDING 2010年第6期114卷 712-722页

作者： Galleguillos, Carolina Belongie, Serge Univ Calif San Diego Dept Comp Sci & Engn La Jolla CA 92093 USA CALTECH Dept Elect Engn Pasadena CA 91125 USA

The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images include occlusion, poor quality, noise or background clutter, and this task becomes even more challenging when many objects are present in the same scene. Several models for object categorization use appearance and context information from objects to improve recognition accuracy. Appearance information, based on visual cues, can successfully identify object classes up to a certain extent. Context information, based on the interaction among objects in the scene or global scene statistics, can help successfully disambiguate appearance inputs in recognition tasks. In this work we address the problem of incorporating different types of contextual information for robust object categorization in computer vision. We review different ways of using contextual information in the field of object categorization, considering the most common levels of extraction of context and the different levels of contextual interactions. We also examine common machine learning models that integrate context information into object recognition frameworks and discuss scalability, optimizations and possible future approaches. (C) 2010 Elsevier Inc. All rights reserved.

关键词： Object recognition Context Object categorization computer vision systems

来源：评论

学校读者我要写书评

暂无评论

Development of Fully Functional Miniature Unmanned Rotorcraft systems

Development of Fully Functional Miniature Unmanned Rotorcraf...

引用

The 29th Chinese Control Conference(第二十九届中国控制会议)

作者： Guowei CAI Feng LIN Tong H. LEE Ben M. CHEN Temasek Laboratories National University of Singapore Singapore 117411 Department of Electrical and Computer Engineering National University of Singapore Singapore 11757

We document in this article a general introduction to modern miniature unmanned rotorcraft systems. More specifi- cally, we present a fairly detailed overview on the hardware configuration, software integration, aerodynamic modeling, automatic flight control system, and computer vision system involved in forming an unmanned rotorcraft system.

关键词： Unmanned Aerial Vehicles Aerodynamic Modeling Avionic systems Flight Control systems computer vision systems

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking for Groups of Unicycles with Convergence of the Orientation Angles

Trajectory Tracking for Groups of Unicycles with Convergence...

引用

2010 49th IEEE Conference on Decision and Control

作者： E.G. Hernandez-Martinez E. Aranda-Bricaire Department of Industrial Engineering Tecnologico de Estudios Superiores de Coacalco 55700 Mexico Department of Electrical Engineering Mechatronics Section CINVESTAV-IPN AP 14-740 07000 Mexico

ISBN: (纸本)9781424477456

This paper presents a trajectory tracking control strategy for unicycles based on local potential functions and the leader-followers scheme. The leader robot must follow a prescribed trajectory and the rest of the robots follows the leader whereas achieves a desired formation at the same time. Every follower robot does not possess a global information about the leader path and the goals of the other followers. The control strategy does not influence directly the orientation angles, however a sufficient condition is established for their convergence to the same value. Finally, the performance of the proposed strategy is evaluated over an experimental set-up consisting of three unicycle-type robots and a computer vision system.

关键词： trajectory tracking Unicycles Converge control strategy Robot computer vision systems ORIENTATION ANGLE

来源：评论

学校读者我要写书评

暂无评论

computer vision system for automated cell pressure probe operation

引用

BIOsystems ENGINEERING 2009年第2期103卷 129-136页

作者： Wong, E. S. Slaughter, D. C. Wada, H. Matthews, M. A. Shackel, K. A. Univ Calif Davis Dept Biol & Agr Engn Davis CA 95616 USA Univ Calif Davis Dept Viticulture & Enol Davis CA 95616 USA Univ Calif Davis Dept Plant Sci Davis CA 95616 USA

An automated cell pressure probe was designed to allow robust measurements of cellular water relations without the limitations caused by operator skill levels (rapid response time, good hand-eye coordination, and manual dexterity). The system was based upon a real-time (30 Hz) computer vision system that employed a radial basis function, artificial neural network using direct greyscale template matching for meniscus recognition and control. The system did not require any custom-built hardware but used readily available off-the-shelf components and was designed to be highly portable, scalable, and relatively simple to set up. The system was robust in the presence of debris or dust on or in the glass capillary, and for tapered capillary probes, tolerant of variations in contrast due to changes in the velocity or travel direction of the meniscus. The system was capable of controlling the pressure within +/-0.0005 MPa and could perform pressure-clamp experiments at +/-0.001 MPa or greater pressure steps. The automatic meniscus system recognition could accurately detect the meniscus location with a mean error of under 6 mu m and a standard deviation of less than 3.2 mu m. Mean errors in automatic volume estimation ranged from 0.07 to 0.6%, depending upon capillary diameter. (C) 2009 IAgrE. Published by Elsevier Ltd. All rights reserved.

关键词： automatic control automation machine vision neural networks plant water relations pressure Plant water relations Pressure probes Automation mean errors System identification computer vision systems automatic control robot vision Neural network

来源：评论

学校读者我要写书评

暂无评论

Quantification of enzymatic browning kinetics in pear slices using non-homogenous L* color information from digital images

引用

LWT-FOOD SCIENCE AND TECHNOLOGY 2009年第8期42卷 1367-1373页

作者： Quevedo, Roberto Diaz, Oscar Caqueo, Arnaldo Ronceros, Betty Aguilera, J. M. Univ Los Lagos FITOGEN Program Dept Food Sci & Technol Osorno Chile Pontificia Univ Catolica Chile Dept Chem Engn & Bioproc Santiago Chile

A "fractal browning indicator" (FBI) methodology is presented, describing enzymatic browning based on irregular color patterns from digital pear slice surface images. It uses the Fourier fractal texture images to calculate a fractal dimension (FD) value in a selected area of the image, which represents the complexity of color distribution (lightness or L*) in the area analyzed. During the procedure, colors from digital images were first transformed to L*a*b* space color using a transformation function, in order to derivate a lightness color parameter (L*). Experiments were carried out in three pear cultivars: Packham pear (PP);Hosui Asiatic pear (AP) and Berries Pear (BIP). During the kinetics, the L* decreased when the FD increased, indicating a greater complexity in the distribution of the L* values in a selected analyzed area, during enzymatic browning kinetics, for all cultivars. The empirical power-law model was suitable for correlating enzymatic browning kinetics data both for the FBI and the traditional method (L* mean value is used). However, enzymatic browning rates for PP cultivars, using the FBI method, were 25 times higher than the rates obtained with the traditional method;and 4 times higher for other cultivars respectively. The empirical non first-order model was established for all cultivars for the FBI and traditional methods. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Enzymatic browning Color Pear slices computer vision systems Fourier fractal texture

来源：评论

学校读者我要写书评

暂无评论

Description of the kinetic enzymatic browning in banana (Musa cavendish) slices using non-uniform color information from digital images

引用

FOOD RESEARCH INTERNATIONAL 2009年第9期42卷 1309-1314页

作者： Quevedo, Roberto Diaz, Oscar Ronceros, Betty Pedreschi, Franco Miguel Aguilera, Jose Univ Los Lagos Dept Sci & Food Technol FITOGEN Program Osorno Chile Pontificia Univ Catolica Chile Dept Chem Engn & Bioproc Santiago Chile

A novel methodology "fractal browning indicator" (FBI) is presented, that describes the enzymatic browning kinetic based on the use of irregular color patterns from banana slice images. It uses the fractal Fourier texture image value in a selected area, to calculate a fractal dimension (FD), which represents the complexity of color distribution. During the procedure, colors from digital images were first transformed to L*a*b* space color using a transformation function (quadratic model), in order to derivate three color channels, lightness (L*), redness (a*), and yellowness (b*). In the results, lightness and yellowness parameters decreased during the browning kinetic, when their respective FD values increased, indicating major color distribution complexity in a selected area analyzed during the kinetic. The redness color (a*) did not show any statistical variation. The empirical power law model was suitable to correlate enzymatic browning kinetic data both for FBI and for the traditional method (when an L* mean was used). However, enzymatic browning rates using the FBI method, were between 8.5 and 35 times higher than rates calculated with the traditional method. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Enzymatic browning Banana slices computer vision systems Fourier fractal texture

来源：评论

学校读者我要写书评

暂无评论

Quantification of enzymatic browning in apple slices applying the fractal texture Fourier image

引用

JOURNAL OF FOOD ENGINEERING 2009年第2期95卷 285-290页

作者： Quevedo, Roberto Jaramillo, Marcela Diaz, Oscar Pedreschi, Franco Miguel Aguilera, Jose Univ Lagos Dept Sci & Food Technol FITOGEN Program Osorno Chile Pontificia Univ Catolica Chile Dept Chem Engn & Bioproc Santiago Chile

A new approach (FBI) describing the enzymatic browning kinetics for three apple cultivars, is presented. It is based on quantification of the irregular color patterns that emerge from the apple surface during enzymatic browning, rather than using the color average in the same area analyzed. In the experiments, three apple cultivars slices were placed under a computer vision system and color digital images were captured. The images were transformed to Lab space color using a quadratic transformation function and the Fourier fractal texture image was used to calculate a fractal dimension value (FD), in order to represent the complexity of lightness intensity distribution (L) over the surface. FD (proposed method) and the mean L value (traditional method) were used indistinctly (as a fractional conversion) to model the enzymatic kinetic using the power-law model. The results showed that the fractal theory can be used to describe the browning kinetic and to distinguish apple cultivars, based on their browning sensitivity under the same experimental conditions. Enzymatic browning rates derived using the fractal kinetic method, were between 14.3 and 23.2 times (in absolute value) higher than the rates calculated with the traditional method. The fractional first-order model was established only for kinetics calculated using the traditional method. (c) 2009 Elsevier Ltd. All rights reserved.

关键词： Browning computer vision systems Color Apple slices Fractal texture

来源：评论

学校读者我要写书评

暂无评论

Application of computer vision systems to the inspection of contact wire wear

Application of computer vision systems to the inspection of ...

引用

11th International Conference on Urban Transport and the Environment in the 21st Century

作者： Borromeo, S Aparicio, JL Univ Rey Juan Carlos Dept Comp Sci Stat & Telemat Madrid Spain

ISBN: (纸本)184564008X

Measuring systems which automatically detect the degree of wire wear are necessary in order to carry out efficient infrastructure management and maintenance based on contact wire condition. The problem of wear measurement characterized by some important determining factors like rate of sampling and auscultation conditions is studied in detail. This paper describes different developments, based on computer vision, to measure contact wire wear. In general, computer vision in railways contributes towards improved service quality, reduced costs and increased security. This paper concludes with a comparative analysis of different computer vision systems to measure contact wire wear.

关键词： catenary inspection contact wire wear computer vision systems railways

来源：评论

学校读者我要写书评

暂无评论

Determination of senescent spotting in banana (Musa cavendish) using fractal texture Fourier image

引用

JOURNAL OF FOOD ENGINEERING 2008年第4期84卷 509-515页

作者： Quevedo, R. Mendoza, F. Aguilera, J. M. Chanona, J. Gutierrez-Lopez, G. Univ Los Lagos Dept Food Sci & Technol Av Fushlocher 1305 Osorno Chile Pontificia Univ Catolica Chile Dept Chem Engn & Bioproc Santiago Chile Escuela Nacl Ciencias Biol Inst Politecn Nacl Dept Grad & Invest Alimentos Mexico City DF Mexico

The analysis of fractal texture reflects a change in pixel intensity, and this might contain information about the structure of objects since a great change in intensity might usually indicate changes in the object. In the images of banana surfaces, the texture image can, to some extent, reflect changes and thus it can be used as an indicator of the last stage during the ripening process (over-ripening). In this experiment, bananas (Musa cavendish) were stored during 10 days at 20 degrees C. Images of banana surfaces were recorded using a computational vision system. The over-ripening process of bananas was represented by an increment in the fractal value derived from texture fractal Fourier analysis. The result shows that fractal texture derived from the spectral Fourier analysis increased monotonically and it can be used as an indicator of the senescence process also called "senescent spotting" of the banana peel. (c) 2007 Elsevier Ltd. All rights reserved.

关键词： fractal texture computer vision systems senescent spotting bananas

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：