检索结果-内蒙古大学图书馆

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Lu, Le Dai, Xiang-Tian Hager, Gregory Computational Interaction and Robotics Lab Computer Science Department Johns Hopkins University BaltimoreMD21218 United States

Particle filtering is a very popular technique for sequential state estimation problem. However its convergence greatly depends on the balance between the number of particles/hypotheses and the fitness of the dynamic model. In particular, in cases where the dynamics are complex or poorly modeled, thousands of particles are usually required for real applications. This paper presents a hybrid sampling solution that combines the sampling in the image feature space and in the state space via RANSAC and particle filtering, respectively. We show that the number of particles can be reduced to dozens for a full 3D tracking problem which contains considerable noise of different types. For unexpected motions, a specific set of dynamics may not exist, but it is avoided in our algorithm. The theoretical convergence proof [1, 3] for particle filtering when integrating RANSAC is difficult, but we address this problem by analyzing the likelihood distribution of particles from a real tracking example. The sampling efficiency (on the more likely areas) is much higher by the use of RANSAC. We also discuss the tracking quality measurement in the sense of entropy or statistical testing. The algorithm has been applied to the problem of 3D face pose tracking with changing moderate or intense expressions. We demonstrate the validity of our approach with several video sequences acquired in an unstructured environment. © 2004 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Integrating region and boundary information for improved spatial coherencein object tracking

Integrating region and boundary information for improved spa...

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Chung, Desmond MacLean, W. James Dickinson, Sven Department of Electrical and Computer Engineering University of Toronto 10 King's College Road TorontoM5S 3G4 Canada Department of Computer Science University of Toronto 10 King's College Road TorontoM5S 3G4 Canada

This paper describes a novel method for performing spatially coherent motion estimation by integrating region and boundary information. The method begins with a layered, parametric flow model. Since the resulting flow estimates are typically sparse, we use the computed motion in a novel way to compare intensity values between images, thereby providing improved spatial coherence of a moving region. This dense set of intensity constraints is then used to initialize an active contour, which is influenced by both motion and intensity data to track the object's boundary. The active contour, in turn, provides additional spatial coherence by identifying motion constraints within the object boundary and using them exclusively in subsequent motion estimation for that object. The active contour is therefore automatically initialized once and, in subsequent frames, is warped forward based on the motion model. The spatial coherence constraints provided by both the motion and the boundary information act together to overcome their individual limitations. Furthermore, the approach is general, and makes no assumptions about a static background and/or a static camera. We apply the method to image sequences in which both the object and the background are moving. © 2004 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Visual hand tracking using nonparametric belief propagation

Visual hand tracking using nonparametric belief propagation

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Sudderth, Erik B. Mandel, Michael I. Freeman, William T. Willsky, Alan S. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States

This paper develops probabilistic methods for visual tracking of a three-dimensional geometric hand model from monocular image sequences. We consider a redundant representation in which each model component is described by its position and orientation in the world coordinate frame. A prior model is then defined which enforces the kinematic constraints implied by the model's joints. We show that this prior has a local structure, and is in fact a pairwise Markov random field. Furthermore, our redundant representation allows color and edge-based likelihood measures, such as the Chamfer distance, to be similarly decomposed in cases where there is no self-occlusion. Given this graphical model of hand kinematics, we may track the hand's motion using the recently proposed nonparametric belief propagation (NBP) algorithm. Like particle filters, NBP approximates the posterior distribution over hand configurations as a collection of samples. However, NBP uses the graphical structure to greatly reduce the dimensionality of these distributions, providing improved robustness. Several methods are used to improve NBP's computational efficiency, including a novel KD-tree based method for fast Chamfer distance evaluation. We provide simulations showing that NBP may be used to refine inaccurate model initializations, as well as track hand motion through extended image sequences. © 2004 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A hierarchical framework for high resolution facial expression tracking

A hierarchical framework for high resolution facial expressi...

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Huang, Xiaolei Zhang, Song Wang, Yang Metaxas, Dimitris Samaras, Dimitris Computer Science Department Rutgers University New BrunswickNJ United States Mechanical Engineering Department State University of New York Stony BrookNY United States Computer Science Department State University of New York Stony BrookNY United States

We present a novel hierarchical framework for high resolution, nonrigid facial expression tracking. The high quality dense point clouds of facial geometry moving at video speeds are acquired using a phase-shifting based structured light ranging technique. To use such data for temporal study of the subtle dynamics in expressions and for face recognition, an efficient nonrigid facial tracking algorithm is needed to establish intra-frame correspondences. In this paper, we propose such an algorithmic framework that uses a multi-resolution 3D deformable face model, and a hierarchical tracking scheme. This framework can not only track global facial motion that is caused by muscle action, but fit to subtler expression details that are generated by highly local skin deformations. Tracking of global deformations is performed efficiently on the coarse level of our face model with one thousand nodes, to recover the changes in a few intuitive parameters that control the motion of several deformable regions. In order to capture the complementary highly local deformations, we use a variational algorithm for non-rigid shape registration based on the integration of an implicit shape representation and the Free Form Deformations (FFD). Due to the strong implicit and explicit smoothness constraints imposed by the algorithm, the resulting registration/deformation field is smooth, continuous and gives dense one-to-one intra-frame correspondences. User-input sparse facial feature correspondences can also be incorporated as hard constraints in the optimization process, in order to guarantee high accuracy of the established correspondences. Extensive tracking experiments using the dynamic facial scan of five different subjects demonstrate the accuracy and efficiency of our proposed framework. © 2004 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Automated registration of high resolution images from slide presentation and whiteboard handwriting via a video camera

Automated registration of high resolution images from slide ...

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Li, Weihong Tang, Hao Zhu, Zhigang Dept. of Computer Science Graduate Center City University of New York New YorkNY10016 United States Dept. of Computer Science City College City University of New York New YorkNY10031 United States Dept. of Computer Science City College and Graduate Center City University of New York New YorkNY10031 United States

A PowerPoint © (PPT) slide presentation and a whiteboard handwriting capture system, when used together, could provide a better means to present a lecture in a classroom and later to deliver more effective e-lectures for off-campus students. When the PPT slides are projected on the whiteboard where the instructor annotates, modifies, or expands the PPT presentation, geometrically registering high-resolution images from the two sources yields high quality digital presentations. Since the two sources do not share the same materials, one with printing notes and the other with handwriting notes, we use a low-cost digital camera as a bridge to align the two sources. We present a hybrid registration approach to align the PPT and handwriting images. We use domain knowledge in a classroom presentation (i.e., the illumination of the slide projection, the timing information for both slide changes and handwriting page creation) to align the camera views with the digital slides and to extract handwriting contents from clustered video scenes. We propose a coarse-to-fine content matching method to register handwriting contents captured by the video camera and the whiteboard capture system. Experimental results are presented to validate our approach. © 2004 IEEE.

关键词： Video cameras

来源：评论

学校读者我要写书评

暂无评论

Preface: GMBV 2004

IEEE Computer Society Conference on Computer Vision and Patt...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops 2004年第JANUARY期2004-January卷 176-176页

作者： Pece, Arthur E.C. Heimdall Vision Bjørnsonsvej 29 Valby2500 Denmark Dept. of Computer Science University of Copenhagen Denmark

来源：评论

学校读者我要写书评

暂无评论

Combining top-down and bottom-up segmentation

Combining top-down and bottom-up segmentation

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Borenstein, Eran Sharon, Eitan Ullman, Shimon Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot76100 Israel Division of Applied Mathematics Brown University ProvidenceRI02912 United States

In this work we show how to combine bottom-up and top-down approaches into a single figure-ground segmentation process. This process provides accurate delineation of object boundaries that cannot be achieved by either the top-down or bottom-up approach alone. The top-down approach uses object representation learned from examples to detect an object in a given input image and provide an approximation to its figure-ground segmentation. The bottom-up approach uses image-based criteria to define coherent groups of pixels that are likely to belong together to either the figure or the background part. The combination provides a final segmentation that draws on the relative merits of both approaches: The result is as close as possible to the top-down approximation, but is also constrained by the bottom-up process to be consistent with significant image discontinuities. We construct a global cost function that represents these top-down and bottom-up requirements. We then show how the global minimum of this function can be efficiently found by applying the sum-product algorithm. This algorithm also provides a confidence map that can be used to identify image regions where additional top-down or bottom-up information may further improve the segmentation. Our experiments show that the results derived from the algorithm are superior to results given by a pure top-down or pure bottom-up approach. The scheme has broad applicability, enabling the combined use of a range of existing bottom-up and top-down segmentations. © 2004 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Hybrid image registration based on configural matching of scale-invariant salient region features

Hybrid image registration based on configural matching of sc...

引用

2004 IEEE computer Society conference on computer vision and pattern recognition workshops, CVPRW 2004

作者： Huang, Xiaolei Sun, Yiyong Metaxas, Dimitris Sauer, Frank Xu, Chenyang Division of Computer and Information Sciences Rutgers University PiscatawayNJ United States Imaging and Visualization Department Siemens Corporate Research PrincetonNJ United States

We present a novel method for aligning images under arbitrary poses, based on finding correspondences between image region features. In contrast with using purely feature-based or intensity-based methods, we adopt a hybrid method that integrates the merits of both approaches. Our method uses a small number of automatically extracted scale-invariant salient region features, whose interior intensities can be matched using robust similarity measures. While previous techniques have primarily focused on finding correspondences between individual features, we emphasize the importance of geometric configural constraints in preserving global consistency of individual matches and thus eliminating false feature matches. Our matching algorithm consists of two steps: region component matching (RCPM) and region configural matching (RCFM), respectively. The first step finds correspondences between individual region features. The second step detects a joint correspondence between multiple pairs of salient region features using a generalized Expectation-Maximization framework. The resulting joint correspondence is then used to recover the optimal transformation parameters. We applied our method to registering a pair of aerial images and several pairs of single and multiple modality medical images with promising results. The preliminary results, in particular, showed that the proposed method has excellent robustness to image noise, intensity change and inhomogeneity, appearance and disappearance of structures, as well as partial matching. © 2004 IEEE.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Program Chairs' Introduction to the 2004 IEEE Workshop on Real-Time vision for Human-computer Interaction at the 2004 IEEE CVPR conference,Washington, D.C.

IEEE Computer Society Conference on Computer Vision and Patt...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops 2004年第JANUARY期2004-January卷

作者： Kisačanin, Branislav Pavlović, Vladimir Huang, Thomas S. Delphi Corporation KokomoIN46904 United States Dept. of Computer Science Rutgers University PiscatawayNJ08854 United States Beckman Institute University of Illinois UrbanaIL61801 United States

来源：评论

学校读者我要写书评

暂无评论

IEEE Workshop Learning in computer vision and pattern recognition

IEEE Workshop Learning in Computer Vision and Pattern Recogn...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： B. Bhanu Jing Peng B. Draper University of California Riverside

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：