检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： M.E. Nilsback B. Caputo Department of Numerical Analysis and Computer Science Computational Vision and Active Perception Laboratory (CVAP) KTH Stockholm Sweden

Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme, which extends the idea of cue accumulation to discriminative classifiers. We derive and test the scheme for support vector machines (SVMs), but we also show that it is easily extendible to any large margin classifier. In the case of one-class SVMs the scheme can be interpreted as a new class of Mercer kernels for multiple cues. Experimental comparison with a probabilistic accumulation scheme is favorable to our method. Comparison with voting scheme shows that our method may suffer as the number of object classes increases. Based on these results, we propose a recognition algorithm consisting of a decision tree where decisions at each node are taken using our accumulation scheme. Results obtained using this new algorithm compare very favorably to accumulation (both probabilistic and discriminative) and voting scheme.

关键词： Voting Object recognition Robustness computer vision Histograms Humans Laboratories numerical analysis computer science Testing

来源：评论

学校读者我要写书评

暂无评论

Velocity adaptation of space-time interest points

Velocity adaptation of space-time interest points

引用

International Conference on Pattern Recognition

作者： I. Laptev T. Lindeberg Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computer Science KTH Royal Institute of Technology Stockholm Sweden

The notion of local features in space-time has recently been proposed to capture and describe local events in video. When computing space-time descriptors, however, the result may strongly depend on the relative motion between the object and the camera. To compensate for this variation, we present a method that automatically adapts the features to the local velocity of the image pattern and, hence, results in a video representation that is stable with respect to different amounts of camera motion. Experimentally we show that the use of velocity adaptation substantially increases the repeatability of interest points as well as the stability of their associated descriptors. Moreover, for an application to human action recognition we demonstrate how velocity-adapted features enable recognition of human actions in situations with unknown camera motion and complex, non-stationary backgrounds.

关键词： Cameras Humans Image motion analysis Pattern recognition Motion measurement Optical recording Covariance matrix computer vision Laboratories numerical analysis

来源：评论

学校读者我要写书评

暂无评论

Recognizing human actions: a local SVM approach

Recognizing human actions: a local SVM approach

引用

International Conference on Pattern Recognition

作者： C. Schuldt I. Laptev B. Caputo Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition.

关键词： Humans Support vector machines computer vision Pattern recognition Support vector machine classification Cameras Frequency Spatial databases Performance evaluation Image recognition

来源：评论

学校读者我要写书评

暂无评论

Galilean-diagonalized spatio-temporal interest operators

Galilean-diagonalized spatio-temporal interest operators

引用

International Conference on Pattern Recognition

作者： T. Lindeberg A. Akbarzadeh I. Laptev Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computer Science KTH Royal Institute of Technology Stockholm Sweden

This paper presents a set of image operators for detecting regions in space-time where interesting events occur. To define such regions of interest, we compute a spatio-temporal second-moment matrix from a spatio-temporal scale-space representation, and diagonalize this matrix locally, using a local Galilean transformation in space-time, optionally combined with a spatial rotation, so as to make the Galilean invariant degrees of freedom explicit. From the Galilean-diagonalized descriptor so obtained, we then formulate different types of space-time interest operators, and illustrate their properties on different types of image sequences.

关键词： Cameras Covariance matrix computer vision Laboratories numerical analysis computer science Image sequences Layout Councils Filters

来源：评论

学校读者我要写书评

暂无评论

Harmonie broadcasting is optimal 13

Harmonie broadcasting is optimal

引用

13th Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2002

作者： Engebretsen, Lars Sudan, Madhu Department of Numerical Analysis and Computer Science Royal Institute of Technology StockholmSE-100 44 Sweden MIT Laboratory for Computer Science 200 Technology Square NE43-307 CambridgeMA02139-3594 United States

ISBN: (纸本)089871513X

Harmonic broadcasting was introduced by Juhn and Tseng as a way to reduce the bandwidth requirements required for video-on-demand broadcasting. In this paper, we note that harmonic broadcasting is actually a special case of the priority encoded transmission scheme introduced by Albanese et al. and prove-using an information theoretic argument-that it is impossible to achieve the design goals of harmonic broadcasting using a shorter encoding.

关键词： Broadcasting

来源：评论

学校读者我要写书评

暂无评论

γ-Brass Crystallization in a Simple Monotomic Liquid

引用

MRS Online Proceedings Library 2001年第1期643卷 951-956页

作者： Zetterling, Fredrik H. M. Dzugutov, Mikhail Lidin, Sven Department of Numerical Analysis and Computer Science Royal Institute of Technology Stockholm Sweden Department of Inogranic Chemistry Arrhenius Laboratory Stockholm University Stockhlom Sweden

We present a molecular dynamics simulation investigating the crystallization pattern of a simple monatomic liquid model which utilize an interatomic interaction potential. The shape of the potential imitates effective interionic interaction in metallic systems. The potentials is constructed to favour icosahedral arrangement in the first coordination shell. We observe that, the system forms a thermodynamically stable solid phase exhibiting cubic symmetry. Its diffraction pattern can be identified as that of γ-brass phase, a terahedrally packed crystalline structure with 52 atoms in the unit cell. We conclude that the monatomic version of γ-brass structure generated in this simultion can be regarded as a new archetype for the γ-base structures observed in many intemetllic compounds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retaining body language in subjective virtual environments using artifact-centred coordinate systems

Retaining body language in subjective virtual environments u...

引用

Annual Hawaii International Conference on System sciences (HICSS)

作者： K.-M. Jaa-Aro D. Snowdon Interaction and Presentation Laboratory Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden Communications Research Group Department of Computer Science University of Nottingham Nottingham UK

Embodiment and subjectivity are important research issues for collaborative virtual environments. The authors claim that the direction and distance of an embodiment are the most important indicators of the relation between a user and surrounding objects or other users. In an objective view of a virtual environment embodiment motion is unambiguous since all users will see all other users and all artifacts in the same positions. However there are many reasons to present different views of the same basic data set to different users. If objects end up in different positions in different views, one cannot retain a common coordinate system for the embodiments, since directions and distances are distorted. They present an implementation of artifact-centred coordinate mappings by which the positions of the artifacts that the user is interacting with govern how that user is represented to other users of the system.

关键词： Virtual environment Collaborative work numerical analysis Collaboration computer science Protocols Resumes Visualization Topology Context

来源：评论

学校读者我要写书评

暂无评论

Integrating task-directed plaiming with reactive object recognition 12

Integrating task-directed plaiming with reactive object reco...

引用

Intelligent Robots and computer Vision XII: Algorithms and Techniques 1993

作者： Dickinson, Sven Stevenson, Suzanne Amdur, Eugene Tsotsos, John Olsson, Lars Department of Computer Science University of Toronto 6 King's College Rd. TorontoONM5S1A4 Canada Computational Vision and Active Perception Laboratory Dept. of Numerical Analysis and Computing Science Royal Institute of Tecimology StockholmS-10044 Sweden

We describe a robot vision system that achieves complex object recognition with two layers of behaviors, performing the tasks of planning and object recognition, respectively. The recognition layer is a pipeline in which successive stages take in images from a stereo head, recover relevant features, build intermediate representations, and deposit 3-D objects into a world model. Each stage is an independent process that reacts automatically to output from the previous stage. This reactive system operates continuously and autonomously to construct the robot's 3-D model of the environment. Sitting above the recognition pipeline is the planner which is responsible for populating the world model with objects that satisfy the high-level goals of the system. For example, upon examination of the world model, the planner can decide to direct the head to another location, gating new images into the recognition pipeline, causing new objects to be deposited into the world model. Alternatively, the planner can alter the recognition behavior of the pipeline so that objects of a certain type or at a certain location appear in the world model. © 1993 SPIE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

The MultiG research programme: distributed multimedia applications on Gigabit networks 93

The MultiG research programme: distributed multimedia applic...

引用

Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems

作者： Björn Pehrson Yngve Sundblad Distributed Systems Laboratory Swedish Institute for Computer Science S-164 28 STOCKHOLM-KISTA Sweden Interaction and Presentation Laboratory Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 STOCKHOLM Sweden

No abstract available.

ISBN: (纸本)9780897915755

No abstract available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convected activation profiles and the measurement of visual motion

Convected activation profiles and the measurement of visual ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： A.M. Waxman J. Wu F. Bergholm Laboratory for Sensory Robotics College of Engineering Boston University Boston MA USA Computer Vision and Graphics Laboratory Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

A method is developed for the measurement of short-range visual motion in image sequences, making use of the motion of image features such as edges and points. Each feature generates a Gaussian activation profile in a spatiotemporal neighborhood of specified scale around the feature itself; this profile is then convected with motion of the feature. The authors show that image velocity estimates can be obtained from such dynamic activation profiles using a modification of familiar gradient techniques. The resulting estimators can be formulated in terms of simple ratios of spatiotemporal filters (i.e. receptive fields) convolved with image feature maps. A family of activation profiles of varying scale must be utilized to cover a range of possible image velocities. They suggest a characteristic speed normalization of the estimate obtained from each filter in order to decide which estimate is to be accepted. They formulate the velocity estimators for dynamic edges in 1-D and 2-D image sequences, as well as that for dynamic feature points in 2-D image sequences.< >

关键词： Motion measurement Image sequences Motion analysis Filters Laboratories computer vision Robot sensing systems Educational institutions computer graphics numerical analysis

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：