检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Junwen Wu M.M. Trivedi Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San Diego CA USA

In this paper a coarse-to-fine system framework for analyzing the head gesture is presented. We discuss several important modules from computer vision aspects, including the pose-invariant face detection, face tracking, pose determination and high-resolution image reconstruction for eye pupils detection. Visual cues using intensity images obtained from in-car cameras are explored. A pose-invariant face detection algorithm is used to get the initial face area; afterwards face tracking and validation step is proposed to segment the face region for pose determination. The algorithm is tested on the drivers images under natural driving conditions. Experimental results show that the algorithm is robust to the head pose changes as well as the illumination changes. In this system framework, we propose that when coarse analysis utilizing the head pose alone is not sufficient for driver's behavior analysis, a finer analysis based on the eye gaze tracking is used, which requires images with sufficient resolution. A novel super-resolution reconstruction algorithm is proposed to help reveal more facial details, so as to facilitate the pupil detection. Experiment on the synthesis data shows the effectiveness of the super-resolution reconstruction algorithm

关键词： Intelligent vehicles Face detection Head Image analysis Reconstruction algorithms computer vision Image reconstruction Cameras Image segmentation Testing

来源：评论

学校读者我要写书评

暂无评论

A Regression Model in TensorPCA Subspace for Face Image Super-resolution Reconstruction

A Regression Model in TensorPCA Subspace for Face Image Supe...

引用

International Conference on Pattern Recognition

作者： Junwen Wu M.M. Trivedi Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San Diego CA USA

ISBN: (纸本)0769525210

A regression model in the tensorPCA subspace is proposed in this paper for face super-resolution reconstruction. An approximate conditional probability model is used for the tensor subspace coefficients and maximum-likelihood estimator gives a linear regression model. The approximation is corrected by adding non-linear component from a RBF-type regressor. Experiments on face images from FERET database validate the algorithm. Although each projection coefficient is estimated by a local estimator, tensorPCA subspace analysis is still a global descriptor, which makes the algorithm have certain ability to deal with partially occluded images

关键词： Image resolution Image reconstruction Tensile stress Spatial resolution Principal component analysis Face detection Image analysis computer vision Robot vision systems Laboratories

来源：评论

学校读者我要写书评

暂无评论

vision-based UAV flight control and obstacle avoidance

Vision-based UAV flight control and obstacle avoidance

引用

2006 American Control Conference

作者： He, Zhihai Iyer, Ram Venkataraman Chandler, Phillip R. Department of Electrical and Computer Engineering University of Missouri Columbia MO 65211 Department of Mathematics and Statistics Texas Tech University Lubbock TX 79409-1042 U.S. Air Force Research Laboratory Wright-Patterson AFB OH 45433-7531

ISBN: (纸本)1424402107

In this work, we explore various ideas and approaches to deal with the inherent uncertainty and image noise in motion analysis, and develop a low-complexity, accurate and reliable scheme to estimate the motion fields from UAV navigation videos. The motion field information allows us to accurately estimate ego-motion parameters of the UAV and refine (or correct) the motion measurements from other sensors. Based on the motion field information, we also compute the range map for objects in the scene. Once we have accurate knowledge about the vehicle motion and its navigation environment (range map), control and guidance laws can be designed to navigate the UAV between way points and avoid obstacles. © 2006 IEEE.

关键词： Flight control systems

来源：评论

学校读者我要写书评

暂无评论

Incorporating spatial information into entropy estimates to improve multimodal image registration

Incorporating spatial information into entropy estimates to ...

引用

IEEE International Symposium on Biomedical Imaging

作者： N.D. Cahill C.M. Williams Shoupu Chen L.A. Ray M.M. Goodgame Research & Development Eastman Kodak (Japan) Limited Rochester NY USA Wolfson Medical Vision Laboratory University of Oxford Oxford UK Department of Electrical and Computer Engineering North Carolina State University Raleigh NC USA

We propose an approach to incorporate spatial information into the estimate of the entropy of an image by partitioning a high-dimensional space into regions over which a one-dimensional histogram can be indexed. This approach obviates the need for the construction of high-dimensional histograms and makes no assumptions on the form of the high-dimensional probability mass function. We use this partitioned estimate of entropy to compute image similarity measures, useful in image registration, and we examine the convergence properties of the registration process

关键词： Entropy Image registration Histograms Mutual information Convergence Noise measurement Size measurement Biomedical imaging Laboratories State estimation

来源：评论

学校读者我要写书评

暂无评论

vision-based UAV flight control and obstacle avoidance

Vision-based UAV flight control and obstacle avoidance

引用

American Control Conference (ACC)

作者： Zhihai He R.V. Iyer P.R. Chandler Department of Electrical and Computer Engineering University of Missouri Columbia MO USA Department of Mathematics and Statistics Texas Tech University Lubbock TX USA U.S. Air Force Research Laboratory Wright Patterson Air Force Base OH USA

关键词： Unmanned aerial vehicles Aerospace control Navigation Motion analysis Motion estimation Videos Parameter estimation Motion measurement Layout Motion control

来源：评论

学校读者我要写书评

暂无评论

A binary tree for probability learning in eye detection

A binary tree for probability learning in eye detection

引用

2005 IEEE computer Society Conference on computer vision and Pattern Recognition, CVPR 2005 - Workshops

作者： Wu, Junwen Trivedi, Mohan M. Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San DiegoCA92037 United States

ISBN: (纸本)0769526608

In this paper we proposed to solve the eye detection and localization problem under a general statistical model based object detection framework. A binary tree representation is used to discover the objects' underlying statistical structure. Tree structures enable us to describe the object local statistical structure in a coarse-to-fine fashion. Each subtree explains the statistics for certain local *** tree is built in a top-down fashion. Subsets with negligible conditional independency are found by k-means clustering using mutual information. The conditionally independent features are separated into different subtrees, while more dependent features are tended to appear close in the tree. The distribution of the object can be learned accordingly. Gaussian mixture in the independent component analysis (ICA) subspace is used to model the distribution of each high dependent feature subset, where each independent component explains the local substructure. The use of tree structure enables us to learn the distribution recursively by applying Bayesian criterion. Substantial experiments were done to evaluate the performance over the eyes detection accuracy as well as the localization ability. Experimental results show a better detection accuracy than the Viisage system with a reasonable localization ability, which validate the algorithm. © 2005 IEEE computer Society. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multiperspective thermal IR and video arrays for 3D body tracking and driver activity analysis

Multiperspective thermal IR and video arrays for 3D body tra...

引用

2005 IEEE computer Society Conference on computer vision and Pattern Recognition, CVPR 2005 - Workshops

作者： Cheng, Shinko Y. Park, Sangho Trivedi, Mohan M. Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San Diego San DiegoCA United States

ISBN: (纸本)0769526608

This paper presents a multi-perspective (i.e., four camera views) multi-modal (i.e., thermal infrared and color) video based system for robust and real-time 3D tracking of important body *** multi-perspective characteristics of the system provides 3Dtrajectory of the body parts, while the multi-modal characteristics of the system provides robustness and reliability of feature detection and tracking. The application context for this research is that of intelligent vehicles and driver assistance systems. Experimental results demonstrate effectiveness of the proposed system. © 2005 IEEE computer Society. All rights reserved.

关键词： Automobile drivers

来源：评论

学校读者我要写书评

暂无评论

Dynamic gait pattern generation with reinforcement learning

Dynamic gait pattern generation with reinforcement learning

引用

作者： Erden, Mustafa Suphi Leblebicioglu, Kemal Computer Vision and Intelligent Systems Research Laboratory Department of Electrical and Electronics Engineering Middle East Technical University 06531 Ankara Turkey

ISBN: (纸本)008045108X

This paper presents the gait pattern generation work performed for the sixlegged robot EA308 developed in our laboratory. The aim is to achieve a dynamically developing gait pattern generation structure using reinforcement learning. For the six legged robot a simplified simulative model is constructed. The algorithm constructs a radial basis function neural network (RBFNN) to command proper leg configurations to the simulative robot. The weights of the RBFNN are learned using reinforcement learning. The developed structure succeeded in learning gait patterns compatible with different speeds of the robot. Copyright © 2005 IFAC.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Binary Tree for Probability Learning in Eye Detection

A Binary Tree for Probability Learning in Eye Detection

引用

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

作者： Junwen Wu M.M. Trivedi Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San Diego CA USA

In this paper we proposed to solve the eye detection and localization problem under a general statistical model based object detection framework. A binary tree representation is used to discover the objects’ underlying statistical structure. Tree structures enable us to describe the object local statistical structure in a coarse-to-fine fashion. Each subtree explains the statistics for certain local substructure. The tree is built in a top-down fashion. Subsets with negligible conditional independency are found by k-means clustering using mutual information. The conditionally independent features are separated into different subtrees, while more dependent features are tended to appear close in the tree. The distribution of the object can be learned accordingly. Gaussian mixture in the independent component analysis (ICA) subspace is used to model the distribution of each high dependent feature subset, where each independent component explains the local substructure. The use of tree structure enables us to learn the distribution recursively by applying Bayesian criterion. Substantial experiments were done to evaluate the performance over the eyes detection accuracy as well as the localization ability. Experimental results show a better detection accuracy than the Viisage system with a reasonable localization ability, which validate the algorithm.

关键词： Binary trees Object detection Bayesian methods computer vision Eyes Tree data structures Probability Statistical distributions Independent component analysis Face detection

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC GAIT PATTERN GENERATION WITH REINFORCEMENT LEARNING

引用

IFAC Proceedings Volumes 2005年第1期38卷 151-156页

作者： Mustafa Suphi Erden Kemal Leblebicioĝlu Department of Electrical & Electronics Engineering Computer Vision and Intelligent Systems Research Laboratory Middle East Technical University 06531 Ankara Turkey

This paper presents the gait pattern generation work performed for the six-legged robot EA308 developed in our laboratory. The aim is to achieve a dynamically developing gait pattern generation structure using reinforcement learning. For the six legged robot a simplified simulative model is constructed. The algorithm constructs a radial basis function neural network (RBFNN) to command proper leg configurations to the simulative robot. The weights of the RBFNN are learned using reinforcement learning. The developed structure succeeded in learning gait patterns compatible with different speeds of the robot.

关键词： Six-legged robot walking gait pattern reinforcement learning radial basis function neural network

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：