检索结果-内蒙古大学图书馆

International Conference on Neural Networks

作者： Y.V. Venkatesh N. Rishikesh Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India

We propose a new technique, based on self-organization, for localizing salient contours in an image, with applications to, for instance, object and character recognition, stereopsis and motion tracking. A neuronal network which is isomorphic to the template/initial contour is created. This network acts as an active contour, which, using self-organization, undergoes deformation in an attempt to cling on to the nearest salient contour in the test image. The application areas of the model proposed are similar to "snake", but distinct from it both in the underlying mathematics and implementation. The new technique is illustrated with some examples.

关键词： Active contours Neural networks Humans Image edge detection artificial intelligence Shape Character recognition Object recognition Prototypes Spline

来源：评论

学校读者我要写书评

暂无评论

Determining the skeletal description of sparse shapes

Determining the skeletal description of sparse shapes

引用

IEEE International Symposium on Computational intelligence in robotics and Automation (CIRA)

作者： R. Singh V. Cherkassky N.P. Papanikolopoulos Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science University of Minnesota Minneapolis MN USA Department of Electrical Engineering University of Minnesota Minneapolis MN USA

A variety of techniques in machine vision involve representation of objects by using their shape skeleton. In this paper we present a method to obtain the skeletal shape of binary images in the presence of both boundary noise and noise occurring inside object regions. We propose to obtain the skeletal shape of such images by a modified version of the Kohonen self-organizing map, implemented in a batch processing mode. The modifications allow the map to adapt to the input shape distribution. At each iteration, a competitive Hebbian rule is used to progressively compute the Delaunay triangulation of the shape. Information from the triangulation augments the map topology to yield the final skeletal shape. The batch mode implementation of the self-organizing process, allows our approach to compare very favourably, in terms of computational time, with the traditional flowthrough implementations. Encouraging experimental performance has been obtained on a variety of shapes under varying signal to noise ratios.

关键词： Shape Noise shaping Skeleton Intelligent robots Machine vision computer vision Noise level Noise figure Machine intelligence Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

An invariant pulse-coder for 2-D shape recognition

An invariant pulse-coder for 2-D shape recognition

引用

International Conference on Information, Communications and Signal Processing

作者： N. Rishikesh Y.V. Venkatesh Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India

We present some novel schemes for (i) pulse coding for invariant representation of shape; and (ii) a neural architecture for recognizing the encoded shape. The proposed shape encoder utilizes the properties of complex logarithmic mapping (CLM) which transforms rotation and scaling (in its domain) to shifts (in its range). In order to handle this shift, in an attempt to provide increased speed of operation, the encoder converts the CLM output to a sequence of pulses. These pulses are fed to a novel multilayered neural recognizer which (i) invokes template matching with a distinct architecture; and (ii) achieves robustness (to noise and shape deformation) by virtue of its overlapping strategy for code classification. The proposed encoder-recognizer system, which is hardware implementable by a high-speed electronic switching circuit, and can add new shapes on-line to the existing ones, is illustrated by examples.

关键词： Pulse shaping methods Shape Pattern recognition Encoding Fires computer vision artificial intelligence Laboratories computer architecture Noise robustness

来源：评论

学校读者我要写书评

暂无评论

Some applications of active contours using ANNs isomorphic to boundaries

Some applications of active contours using ANNs isomorphic t...

引用

International Conference on Information, Communications and Signal Processing

作者： Y.V. Venkatesh N. Rishikesh Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India Indian Institute of Science Bangalore Karnataka IN

We present a few applications of the neural active contour model described by Venkatesh Rishikesh (see International Conference on Neural Networks (ICNN-97), Houston, Texas, USA, 1997). The model, which is a neural network based on the principles of self-organization, exploits the principles of spatial isomorphism and self-organization in order to create flexible contours for characterizing shapes in images. We illustrate the versatility of the model by presenting its applications to the problems of boundary extraction, stereo vision, biomedical image analysis and digital image libraries. Only the essential ideas are described.

关键词： Active contours Image edge detection Shape Deformable models Application software computer vision artificial neural networks Stereo vision Image motion analysis Tracking

来源：评论

学校读者我要写书评

暂无评论

A generalized Hermite pyramid for ultrasonic image analysis .2. Gallstone

引用

ULTRASONIC IMAGING 1996年第4期18卷 305-327页

作者： Venkatesh, YV Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science

This paper deals with the problem of extracting information regarding the chemical composition of stones in the human gallbladder from in vitro and in vivo B-scan ultrasonic images. The images are subjected to the Hermite pyramid decomposition technique described in Part I (Venkatesh, Y. V., Ultrasonic Imaging, 18, 261-301, 1996). In an attempt to determine the chemical composition of the gallstones, the gradients of the decomposed images are input to an unsupervised classifier. The outputs of the classifier exhibit some interesting patterns that appear to be related to the chemical composition of the gallstones contained in these images. (C) 1996 Academic Press.

关键词： gallstones Hermite polynomials image decomposition medical imaging multiscale image analysis ultrasonic image analysis unsupervised classification

来源：评论

学校读者我要写书评

暂无评论

vision-guided robotic grasping: issues and experiments

Vision-guided robotic grasping: issues and experiments

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： C.E. Smith N.P. Papanikolopoulos Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science University of Minnesota Minneapolis MN USA

Many researchers have turned to sensing, and in particular computer vision, to create more flexible robotic systems. computer vision is often required to provide data for the grasping of a target. Using a vision system for grasping presents several issues with respect to sensing, control, and system configuration. This paper presents some of these issues in concert with the options available to the researcher and the trade-offs to be expected when integrating a vision system with a robotic system for the purpose of grasping objects. The paper includes experimental results from a particular configuration that characterize the type and frequency of errors encountered while performing various vision-guided grasping tasks. These error classes and their frequency of occurrence lend insight into the problems encountered during visual grasping and into the possible solution of these problems.

关键词： Robot vision systems Robot sensing systems Control systems Robot kinematics Intelligent robots computer vision Machine vision Frequency Sensor systems Cameras

来源：评论

学校读者我要写书评

暂无评论

Automatic selection of control points for deformable-model-based target tracking

Automatic selection of control points for deformable-model-b...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： I. Pavlidis N.P. Papanikolopoulos Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science University of Minnesota Minneapolis MN USA

A novel curve segmentation algorithm for determining control points for deformable-model-based target tracking is proposed. The algorithm is parameterless enabling a fully-fledged automated tracking regardless of the shape of the object being tracked. Compared with other curve segmentation algorithms, it selects a minimal number of control points that yet deliver a superior shape description. The algorithm is comparatively tested with other curve segmentation algorithms in a variety of characteristic target outlines.

关键词： Automatic control Target tracking Deformable models Shape control Intelligent robots Testing artificial intelligence Robot vision systems robotics and automation Laboratories

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT CLASSIFICATION BY NEURAL NETWORKS USING ENCODED PATTERNS

引用

ELECTRONICS LETTERS 1995年第12期31卷 988-989页

作者： MURTHY, CNSG VENKATESH, YV Department of Electrical Engineering Computer Vision and Artificial Intelligence Laboratory Indian Institute of Science Bangalore India

The corners and the middle points, which are extracted as features from the line approximation of a given pattern, are overlaid on a radial grid to form the input array for training a backpropagation network for classification. The proposed method is shown to be simple and robust by extensive testing of its performance on patterns both with and without noise.

关键词： NEURAL NETWORKS PATTERN CLASSIFICATION

来源：评论

学校读者我要写书评

暂无评论

vision-based intelligent control of transportation systems

Vision-based intelligent control of transportation systems

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： C.A. Richards C.E. Smith N.P. Papanikolopoulos Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science University of Minnesota Minneapolis MN USA

In response to the overcrowding of transportation systems, there has been an increase in the emphasis placed upon intelligent vehicle/highway systems (IVHS). Whether the application is keeping a safe distance between vehicles on highways or allowing a pedestrian to safely cross a street, environmental sensing and control play a crucial role in IVHS applications. In this paper we present robust visual detection and tracking techniques for IVHS applications, where computer vision may be the only sensor used or a part of a larger multi-sensor system. We have selected the application of pedestrian detection and tracking to demonstrate that the controlled active vision framework can provide precisely the type of information required to effectively manage traffic situations.

关键词： Intelligent control Intelligent transportation systems Application software Road transportation Intelligent vehicles Road vehicles Vehicle safety Robustness computer vision Sensor systems and applications

来源：评论

学校读者我要写书评

暂无评论

Grasping of static and moving objects using a vision-based control approach

Grasping of static and moving objects using a vision-based c...

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： C.E. Smith N.P. Papanikolopoulos Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science University of Minnesota Minneapolis MN USA

Recent work combining robotics with vision has emphasized an active vision paradigm where the system changes the pose of the camera to improve environmental knowledge or to establish and presence a desired relationship between the robot and objects in the environment. Much of this work has concentrated upon the active observation of objects by the robotic agent. In this paper we present extensions to the controlled active vision framework that focus upon the autonomous grasping of a moving or static object in the manipulator's workspace. Our work extends the capabilities of an eye-in-hand system beyond those as a "pointer" or a "camera orienter" to provide the flexibility required to robustly interact with the environment in the presence of uncertainty. The proposed work is experimentally verified using the Minnesota robotic visual tracker to automatically select object features, to derive estimates of unknown environmental parameters, and to supply a control vector based upon these estimates to guide the manipulator in the grasping of a moving or static object.

关键词： Robot sensing systems Robot vision systems Cameras Manipulators Intelligent robots Grippers Charge-coupled image sensors artificial intelligence Laboratories computer science

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：