检索结果-内蒙古大学图书馆

9th Indian Conference on computer vision, Graphics and Image Processing, ICVGIP 2014

作者： Tapaswi, Makarand Parkhi, Omkar M. Rahtu, Esa Sommerlade, Eric Stiefelhagen, Rainer Zisserman, Andrew Computer Vision for Human Computer Interaction Karlsruhe Institute of Technology Germany Visual Geometry Group Department of Engineering Science University of Oxford United Kingdom Center for Machine Vision Research University of Oulu Finland

ISBN: (纸本)1595930361

The goal of this paper is unsupervised face clustering in edited video material - where face tracks arising from different people are assigned to separate clusters, with one cluster for each person. In particular we explore the extent to which faces can be clustered automatically without making an error. This is a very challenging problem given the variation in pose, lighting and expressions that can occur, and the similarities between different people. The novelty we bring is three fold: first, we show that a form of weak supervision is available from the editing structure of the material - the shots, threads and scenes that are standard in edited video;second, we show that by first clustering within scenes the number of face tracks can be significantly reduced with almost no errors;third, we propose an extension of the clustering method to entire episodes using exemplar SVMs based on the negative training data automatically harvested from the editing structure. The method is demonstrated on multiple episodes from two very different TV series, Scrubs and Buffy. For both series it is shown that we move towards our goal, and also outperform a number of baselines from previous works. Copyright is held by the authors.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Planning for serendipity

Planning for serendipity

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： T. Chakraborti G. Briggs K. Talamadupula Yu Zhang M. Scheutz D. Smith S. Kambhampati Department of Computer Science Arizona State University Tempe AZ USA HRI Laboratory Tufts University Medford MA USA Cognitive Learning Department at IBM Thomas J. Watson Research Center NY USA Tufts University Medford MA US Autonomous Systems & Robotics Intelligent Systems Division NASA Ames Research Center NY USA

Recently there has been a lot of focus on human robot co-habitation issues that are often orthogonal to many aspects of human-robot teaming;e.g. on producing socially acceptable behaviors of robots and de-conflicting plans of robots and humans in shared environments. However, an interesting offshoot of these settings that has largely been overlooked is the problem of planning for serendipity - i.e. planning for stigmergic collaboration without explicit commitments on agents in co-habitation. In this paper we formalize this notion of planning for serendipity for the first time, and provide an Integer Programming based solution for this problem. Further, we illustrate the different modes of this planning technique on a typical Urban Search and Rescue scenario and show a real-life implementation of the ideas on the Nao Robot interacting with a human colleague.

关键词： Planning Robot kinematics Collaboration Context Robot sensing systems Handover

来源：评论

学校读者我要写书评

暂无评论

Integrated management for network virtualization infrastructure

引用

Journal of the National Institute of Information and Communications Technology 2015年第2期62卷 33-43页

作者： Yamada, Kazuhisa Nakao, Akihiro Kanada, Yasusi Saida, Yoshinori Amemiya, Koichiro Future Networking Research Group Media Innovation Laboratory NTT Network Innovation Laboratories Network Japan Interfaculty Initiative in Information Studies Graduate School of Interdisciplinary Information Studies University of Tokyo Network Computer Science Japan Network Research Department Center for Technology Innovation - Information and Telecommunications Network Computer Vision Japan System Integration and Services Technologies Management Division Technological Strategy Planning Department NEC Network Japan Software Laboratory Fujitsu Labratories Ltd. Cloud Computing Network Japan

This paper introduces research and development results of extended functions on our network virtualization infrastructure which achieve advanced network virtualization. Our results achieved to meet five requirements which are resource abstraction, resource isolation, resource elasticity, deep programmability and authentication. In addition, we proposed evolvable architecture and extended network virtualization for edge network and terminals. We also deployed our system on JGN-X testbed.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Surgical robotics beyond enhanced dexterity instrumentation: a survey of machine learning techniques and their role in intelligent and autonomous surgical actions

引用

International journal of computer assisted radiology and surgery 2016年第5期11卷 847页

作者： Yohannes Kassahun Bingbin Yu Abraham Temesgen Tibebu Danail Stoyanov Stamatia Giannarou Jan Hendrik Metzen Emmanuel Vander Poorten Robotics Innovation Center German Research Center for Artificial Intelligence Robert-Hooke-Str. 1 28359 Bremen Germany. yohannes.kassahun@dfki.de. Faculty 3 - Mathematics and Computer Science University of Bremen Robert-Hooke-Str. 1 28359 Bremen Germany. Centre for Medical Image Computing Department of Computer Science University College London London UK. Hamlyn Centre for Robotic Surgery Imperial College London London UK. Department of Mechanical Engineering University of Leuven Celestijnenlaan 300B 3001 Heverlee Belgium.

来源：评论

学校读者我要写书评

暂无评论

Breast masses identification through pixel-based texture classification 1

引用

12th International Workshop on Breast Imaging, IWDM 2014

作者： Torrents-Barrena, Jordina Puig, Domenec Ferre, Maria Melendez, Jaime Diez-Presa, Lorena Arenas, Meritxell Martí, Joan Department of Computer Engineering and Mathematics University Rovira I Virgili Spain Department of Radiology Radboud University Medical Center Netherlands Radiotherapic Oncology Research Group Hospital Universitari Sant Joan de Reus Spain Computer Vision and Robotics Research Institute University of Girona Spain

ISBN: (数字)9783319078878

ISBN: (纸本)9783319078861

Mammographic image analysis plays an important role in computer-aided breast cancer diagnosis. To improve the existing knowledge, this paper proposes a new efficient pixel-based methodology for tumor vs non-tumor classification. The proposed method firstly computes a Gabor feature pool from the mammogram. This feature set is calculated through multi-sized evaluation windows applied to the probabilistic distribution moments, in order to improve the accuracy of the whole system. To deal with a high dimensional data space and a large amount of features, we apply both a linear and non-linear pixel classification stage by using Support Vector Machines (SVMs). The randomness is encoded when training each SVM using randomly sample sets and, in consequence, randomly selected features from the whole feature bank obtained in the first stage. The proposed method has been validated using real mammographic images from well-known databases and its effectiveness is demonstrated in the experimental section. © 2014 Springer International Publishing.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Control Strategies for a Humanoid Robot to Drive and then Egress a Utility Vehicle for Remote Approach

Control Strategies for a Humanoid Robot to Drive and then Eg...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Hyobin Jeong Jaesung Oh Mingeuk Kim Kyungdon Joo In So Kweon Jun-Ho Oh Humanoid Research Center School of Mechanical Aerospace & Systems Engineering Department of Mechanical Engineering Korea Advanced Institute of Science and Technology Robotics and Computer Vision Laboratory School of Mechanical Aerospace & Systems Engineering Department of Electrical Engineering Korea Advanced Institute of Science and Technology Department of Electrical Engineering KAIST

ISBN: (纸本)9781479968862

This paper proposes strategies for the driving and egress of a vehicle with a humanoid robot. To drive the vehicle, the RANSAC method was used to detect obstacles, and the Wagon model was used to control the steering and velocity of the vehicle with only a limited number of sensors which were installed on the humanoid robot. Additionally, a manual teleoperating method was used with the lane projection technique. For the egress motion, gain override and the Cartesian position/force control technique were used to interact with the vehicle structure. To overcome the disadvantages of a highly geared manipulator, a special technique was used that included modelled friction compensation and a non-complementary switching mode. DRC-HUBO+ used the proposed method to perform a vehicle driving and egress task in the DRC finals 2015.

关键词： Humanoid robots EGRESS vehicle Vehicle driving Automobile driving UTILITY VEHICLES control strategy friction compensation DRIVES Steering

来源：评论

学校读者我要写书评

暂无评论

Image-based X-ray visualization techniques for spatial understanding in outdoor augmented reality 14

Image-based X-ray visualization techniques for spatial under...

引用

26th Australian computer-Human Interaction Conference, OzCHI 2014

作者： Zollmann, Stefanie Grasset, Raphael Reitmayr, Gerhard Langlotz, Tobias Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Animation Research Ltd. Dunedin New Zealand Qualcomm Austria Research Center Vienna Austria Department of Information Science University of Otago Dunedin New Zealand

ISBN: (纸本)9781450306539

This paper evaluates different state-of-the-art approaches for implementing an X-ray view in Augmented Reality (AR). Our focus is on approaches supporting a better scene understanding and in particular a better sense of depth order between physical objects and digital objects. One of the main goals of this work is to provide effective X-ray visualization techniques that work in unprepared outdoor environments. In order to achieve this goal, we focus on methods that automatically extract depth cues from video images. The extracted depth cues are combined in ghosting maps that are used to assign each video image pixel a transparency value to control the overlay in the AR view. Within our study, we analyze three different types of ghosting maps, 1) alpha-blending which uses a uniform alpha value within the ghosting map, 2) edge-based ghosting which is based on edge extraction and 3) image-based ghosting which incorporates perceptual grouping, saliency information, edges and texture details. Our study results demonstrate that the latter technique helps the user to understand the subsurface location of virtual objects better than using alpha-blending or the edge-based ghosting. Copyright 2014 ACM.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

All-in-Focus Image Reconstruction from In-Line Holograms of Snowflakes

All-in-Focus Image Reconstruction from In-Line Holograms of ...

引用

IEEE International Instrumentation and Measurement Technology Conference

作者： Sami Varjo Ville Kaikkonen Jari Hannuksela Anssi Makynen The Center for Machine Vision Research Department of Computer Science and Engineering University of Oulu Oulu Finland Unit for Measurement Technology CEMIS-Oulu University of Oulu Kajaani Finland Optoelectronics and Measurement Techniques Laboratory University of Oulu Oulu Finland

ISBN: (纸本)9781479961153

In-line holography enables particle measurements in large imaging volumes with an extended depth of field compared with conventional imaging systems. Accurate measurements of the structural details of the particles are practically possible only if the measured details are brought in focus. In order to extract in-focus images of objects recorded into a digital hologram from a large set of holograms in a feasible manner, automated focusing and segmentation are needed. The twin image present inheritently in the in-line holography data leads to extra noise that makes this a challenging problem. We propose a new depth estimation method for in-line holography, where the stack of reconstructed intensity images is analyzed. First rough object locations are estimated where the object depths are estimated with a wavelet based focus measure. Clusters of depth estimates are used with plane fitting to approximate the object orientation in the 3D volume to obtain the final all-in-focus images. We show that the proposed method can be used to obtain sharp images of planar objects, such as snowflakes.

关键词： Image reconstruction Holography Particle measurements Frequency measurement Atmospheric measurements Noise

来源：评论

学校读者我要写书评

暂无评论

User customizable interaction in coexistence space

User customizable interaction in coexistence space

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： KangGeon Kim Myoung Soo Park Jung-Min Park Computer Science Department University of Southern California USA Interaction and Robotics Research Center Korea Institute of Science and Technology Seoul Korea

ISBN: (纸本)9781479953349

This paper proposes a user customizable interface for user-centered interaction in a space where the real, virtual and remote world is unified and indistinguishable through a combination of humans, artifacts and a virtual world. We have developed a new user customizable interface, which is a set according to the preferences of users and is intuitive and natural to minimize inconvenience of using the dedicated interface. We have executed several experiments using user gestural expression as user customizable interface such as: various devices control, object handling, environmental interaction, and command transmission in the space. The results of the demonstration have shown that effective interaction with a user customizable interface is possible among the real, virtual and remote worlds.

关键词： User interfaces Aerospace electronics Robot sensing systems Gesture recognition Real-time systems Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Extended local binary pattern fusion for face recognition

Extended local binary pattern fusion for face recognition

引用

作者： Liu, Li Fieguth, Paul Zhao, Guoying Pietikainen, Matti School of Information System and Management National University of Defense Technology Changsha410073 China Department of Systems Design Engineering University of Waterloo WaterlooN2L 3G1 Canada Center for Machine Vision Research Department of Computer Science and Engineering University of Oulu Oulu90014 Finland

ISBN: (纸本)9781479957514

This paper presents a simple, novel, yet highly effective approach for robust face recognition. Given LBP-like descriptors based on local accumulated pixel differences, Angular Differences (AD) and Radial Differences (RD), the local differences are decomposed into complementary components of signs and magnitudes. The proposed descriptors have desirable features: (1) robustness to lighting, pose, and expression;(2) computation efficiency;(3) encoding of both microstructures and macrostructures;(4) consistent in form with traditional LBP, thus inheriting the merits of LBP;and (5) no required training, improving generalizability. From a given face image, we obtain six histogram features, each of which is obtained by concatenating spatial histograms extracted from nonoverlapping subregions. The Whitened PCA technique is used for dimensionality reduction, followed by Nearest Neighbor classification. We have evaluated the effectiveness of the proposed method on the Extended Yale B and CAS-PEAL-R1 databases. The proposed method impressively outperforms other well known systems, including what we believe to be the best reported performance for the the CAS-PEAL-R1 lighting probe set with a recognition rate of 72.3%. © 2014 IEEE.

关键词： Local binary pattern

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：