检索结果-内蒙古大学图书馆

Human action recognition using multiple views: A comparative perspective on recent developments

Human action recognition using multiple views: A comparative...

2011 ACM Multimedia Conference, MM'11 and Co-Located Workshops - 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding, J-HGBU'11

作者： Holte, Michael B. Moeslund, Thomas B. Tran, Cuong Trivedi, Mohan M. Department of Architecture Design and Media Technology Aalborg Universtity Denmark Niels Jernes Vej 14 9220 Aalborg Denmark Computer Vision and Robotic Research Laboratory University of California San Diego 9500 Gilman Drive San Diego CA 92093-0434 United States

ISBN: (纸本)9781450309981

This paper presents a review and comparative study of recent multi-view 2D and 3D approaches for human action recognition. The approaches are reviewed and categorized due to their nature. We report a comparison of the most promising methods using two publicly available datasets: the INRIA Xmas Motion Acquisition Sequences (IXMAS) and the i3DPost Multi-View Human Action and Interaction Dataset. Additionally, we discuss some of the shortcomings of multi-view camera setups and outline our thoughts on future directions of 3D human action recognition. Copyright 2011 ACM.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Online non-feedback image re-ranking via dominant data selection

Online non-feedback image re-ranking via dominant data selec...

引用

20th ACM International Conference on Multimedia, MM 2012

作者： Cao, Chen Chen, Shifeng Li, Yuhong Liu, Jianzhuang Shenzhen Key Laboratory for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Information Engineering Chinese University of Hong Kong Hong Kong Media Lab. Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781450310895

Image re-ranking aims at improving the precision of keyword-based image retrieval, mainly by introducing visual features to re-rank. Many existing approaches require offline training for every keyword, which are unsuitable for online image search. Other real-time approaches demand user interaction, which are inappropriate for large-scale image collection. To improve the accuracy of web image retrieval in a practicable manner, we propose a novel re-ranking algorithm to explore the cluster information of the image set. First, we build spectral graph on images that retrieved bysearch engine, and remove isolated nodes as noisy images. Then, we select positive samples from the most dominant cluster in initial top-ranked images, and the samples are used for semi-supervised learning and ranking. Our algorithm is online and non-feedback. Experiments on two public databases demonstrate that our algorithm outperforms the state-of-the-art approaches. © 2012 ACM.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

3D Human Action Recognition for Multi-view Camera Systems

3D Human Action Recognition for Multi-view Camera Systems

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Michael B. Holte Thomas B. Moeslund Nikos Nikolaidis Ioannis Pitas Computer Vision and Media Technology Laboratory Department of Architecture Design and Media Technology University of Aalborg Denmark Informatics and Telematics Institute Center of Research and Technology Hellas Greece Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece

This paper presents a novel approach for combining optical flow into enhanced 3D motion vector fields for human action recognition. Our approach detects motion of the actors by computing optical flow in video data captured by a multi-view camera setup with an arbitrary number of views. Optical flow is estimated in each view and extended to 3D using 3D reconstructions of the actors and pixel-to-vertex correspondences. The resulting 3D optical flow for each view is combined into a 3D motion vector field by taking the significance of local motion and its reliability into account. 3D Motion Context (3D-MC) and Harmonic Motion Context (HMC) are used to represent the extracted 3D motion vector fields efficiently and in a view-invariant manner, while considering difference in anthropometry of the actors and their movement style variations. The resulting 3D-MC and HMC descriptors are classified into a set of human actions using normalized correlation, taking into account the performing speed variations of different actors. We compare the performance of the 3D-MC and HMC descriptors, and show promising experimental results for the publicly available i3DPost Multi View Human Action Dataset.

关键词： Three dimensional displays Optical imaging Cameras Humans Context Shape Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Low-cost scene modeling using a density function improves segmentation performance

Low-cost scene modeling using a density function improves se...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Vivek Sharma Şule Yildirim-Yayilgan Luc Van Gool Faculty of Computer Science and Media Technology Norwegian University of Science and Technology in Gjovik Gjovik Norway ESAT-PSI VISICS iMinds KU Leuven Leuven Belgium ETH Computer Vision Laboratory Zürich Switzerland

We propose a low cost and effective way to combine a free simulation software and free CAD models for modeling human-object interaction in order to improve human & object segmentation. It is intended for research scenarios related to safe human-robot collaboration (SHRC) and interaction (SHRI) in the industrial domain. The task of human and object modeling has been used for detecting activity, and for inferring and predicting actions, different from those works, we do human and object modeling in order to learn interactions in RGB-D data for improving segmentation. For this purpose, we define a novel density function to model a three dimensional (3D) scene in a virtual environment (VREP). This density function takes into account various possible configurations of human-object and object-object relationships and interactions governed by their affordances. Using this function, we synthesize a large, realistic and highly varied synthetic RGB-D dataset that we use for training. We train a random forest classifier, and the pixelwise predictions obtained is integrated as a unary term in a pairwise conditional random fields (CRF). Our evaluation shows that modeling these interactions improves segmentation performance by ~7% in mean average precision and recall over state-of-the-art methods that ignore these interactions in real-world data. Our approach is computationally efficient, robust and can run real-time on consumer hardware.

关键词： Solid modeling Density functional theory Data models Three-dimensional displays Robot sensing systems Virtual environments

来源：评论

学校读者我要写书评

暂无评论

A prediction model for differentiating chronic pain patients and healthy subjects based on withdrawal reflex EMG signals

A prediction model for differentiating chronic pain patients...

引用

International IEEE/EMBS Conference on Neural Engineering, CNE

作者： G. P. Nguyen J. A. Biurrun Manresa M. Curatolo T. B. Moeslund O. K. Andersen Center of Sensory-Motor Interaction Department of Health Science and Technology University of Aalborg Denmark University Department of Anaesthesiology and Pain Therapy Inselspital Bern Switzerland Computer Vision and Media Technology Laboratory Department of Architecture Design and Media Technology University of Aalborg Denmark

The nociceptive withdrawal reflex (NWR) has been proven to be a valuable tool in the objective assessment of spinal cord hyperexcitability that is present in chronic pain disorders. However, most of the studies on objective assessment of central sensitisation focus on population differences between patients and healthy individuals and do not provide tools for individual assessment. In this study, a method was developed to objectively assess pain hyperexcitability in individuals using the NWR. Results showed high rate of correct assessment with up to ~80% when differentiating between healthy volunteers and chronic pain patients.

关键词： Training Pain Electromyography Predictive models Probability distribution Electrodes Histograms

来源：评论

学校读者我要写书评

暂无评论

Document Image Coding for Processing and Retrieval

引用

Journal of VLSI Signal Processing Systems for Signal, Image, and Video technology 1998年第1-2期20卷 121-135页

作者： Kia, Omid E. Doermann, David S. Natl. Inst. of Std. and Technology Math. and Compl. Sciences Division Building 820 Gaithersburg MD 20899 United States Lang. and Media Proc. Laboratory Center for Automation Research University of Maryland College Park MD 20742 United States Catholic University of America Washington DC United States University of Illinois Chicago IL United States University of Maryland College Park MD United States Center for Automation Research Lang. and Media Proc. Laboratory University of Maryland United States Natl. Inst. of Std. and Technology United States Bloomsburg University United States University of Maryland United States Computer Vision Laboratory Lab. for Lang. and Media Processing University of Maryland Inst. for Advanced Computer Studies United States

Document images belong to a unique class of images where the information is embedded in the language represented by a series of symbols on the page rather than in the visual objects themselves. Since these symbols tend to appear repeatedly, a domain-specific image coding strategy can be designed to facilitate enhanced compression and retrieval. In this paper we describe a coding methodology that not only exploits component-level redundancy to reduce code length but also supports efficient data access. The approach identifies and organizes symbol patterns which appear repeatedly. Similar components are represented by a single prototype stored in a library and the location of each component instance is coded along with the residual between it and its prototype. A representation is built which provides a natural information index allowing access to individual components. Compression results are competitive and compressed-domain access is superior to competing methods. Applications to network-related problems have been considered, and show promising results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel line verification for multiple instance focused retrieval in document collections

Novel line verification for multiple instance focused retrie...

引用

International Conference on Document Analysis and Recognition

作者： Hongxing Gao Marçal Rusiñol Dimosthenis Karatzas Josep Lladós Rajiv Jain David Doermann Hangzhou Hikvision Digital Technology Co. Ltd China Computer Vision Center Univ. Autònoma de Barcelona Spain Language and Media Precessing Laboratory University of Maryland U.S.A

ISBN: (纸本)9781479918065

Spatial verification is typically employed to check the spatial consistency among matched local features and to remove outliers. However, when looking for multiple instances of the query within a target image, RANSAC algorithms which are widely applied in many one-to-one matching applications might fail due to the large proportion of “outliers” - correct matches corresponding to other instances. On the other hand, geometrical verification methods are more robust to outliers but usually suffer from high computational costs. In this paper, we introduce a novel two-step line verification method which is more flexible than existing methods and leads to lower computational complexity especially when multiple instances of a query are sought. We study this approach within an information extraction scenario, where the objective is to locate document structures indicative of certain type of information (e.g. different records on invoices).

关键词： Complexity theory Yttrium Estimation Manuals

来源：评论

学校读者我要写书评

暂无评论

Scalable temporal interest points for abstraction and classification of video events

Scalable temporal interest points for abstraction and classi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Seung-Hoon Han ln-So Kweon Digital Media R&D Center Samsung Electronics Company Limited South Korea Robotics and Computer Vision Laboratory Division of Electrical Engineering Department of EECS Korea Advanced Institute of Science and Technology South Korea

The image sequence of a static scene includes similar or redundant information over time. Hence, motion-discontinuous instants can efficiently characterize a video shot or event. However, such instants (key frames) are differently identified according to the change of velocity and acceleration of motion, and such scales of change might be different on each sequence of the same event. In this paper, we present a scalable video abstraction in which the key frames are obtained by the maximum curvature of camera motion at each temporal scale. The scalability means dealing with the velocity and acceleration change of motion. In the temporal neighborhood determined by the scale, the scene features (motion, color, and edge) can be used to index and classify the video events. Therefore, those key frames provide temporal interest points (TIPs) for the abstraction and classification of video events.

关键词： Layout Acceleration Cameras Humans Research and development Robot vision systems computer vision Laboratories Image sequences Scalability

来源：评论

学校读者我要写书评

暂无评论

Real time head tracking via camera saccade and shape-fitting

引用

2nd International Conference on Image Analysis and Recognition, ICIAR 2005

作者： Zhang, Jason Z. Lu, Ye Wu, Q.M. Jonathan Micro-technology and Sensing Group Institute for Fuel Cell Innovation National Research Council of Canada Vancouver BC V6T 1W5 Canada Vision and Media Laboratory School of Computing Science Simon Fraser University Burnaby BC V5A 1S6 Canada Department of Electrical and Computer Engineering University of Windsor Ont. N9B 3P4 Canada

ISBN: (纸本)3540290699

This paper presents a system that tracks human heads in real-time under unconstrained environments where target occlusion, varying illumination, and cluttered backgrounds exist. Tracking is formulated as an active visual servo problem based on the integration of a saccade and a smooth pursuit processes. The head is modelled as an ellipse computed from the color clusters of candidate targets using a robust least square ellipse fitting algorithm. The Farnsworth Perceptually Uniform Color Model is employed to represent the color information of the visual objects. Kalman filtering is applied to the head ellipse to track the evolution of the position, size, and orientation of the target such that the occlusion of objects with similar color and shape as those of the target are effectively accommodated. Experiments with tracking scenarios demonstrate the effectiveness of the system. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Design sparse features for age estimation using hierarchical face model

Design sparse features for age estimation using hierarchical...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Jinli Suo Tianfu Wu Songchun Zhu Shiguang Shan Xilin Chen Wen Gao Chinese Academy and Sciences China Lotus Hill Institute of Computer Vision and Information Science China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Digital Media Peking University China

A key point in automatic age estimation is to design feature set essential to age perception. To achieve this goal, this paper builds up a hierarchical graphical face model for faces appearing at low, middle and high resolution respectively. Along the hierarchy, a face image is decomposed into detailed parts from coarse to fine. Then four types of features are extracted from this graph representation guided by the priors of aging process embedded in the graphical model: topology, geometry, photometry and configuration. On age estimation, this paper follows the popular regression formulation for mapping feature vectors to its age label. The effectiveness of the presented feature set is justified by testing results on two datasets using different kinds of regression methods. The experimental results in this paper show that designing feature set for age estimation under the guidance of hierarchical face model is a promising method and a flexible framework as well.

关键词： Aging Feature extraction Active appearance model Face detection Spatial databases Skin Hair Content addressable storage computer vision Humans

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：