检索结果-内蒙古大学图书馆

30th IEEE/CVF conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Zunino, Andrea Cavazza, Jacopo Koul, Atesh Cavallo, Andrea Becchio, Cristina Murino, vittorio Ist Italiano Tecnol Pattern Anal & Comp Vis PAVIS Genoa Italy Ist Italiano Tecnol Robot Brain & Cognit Sci Genoa Italy Univ Genoa Elect Elect & Telecommun Engn & Naval Architectur Genoa Italy Univ Turin Psychol Dept Turin Italy Univ Verona Comp Sci Dept Verona Italy

ISBN: (纸本)9781538607336

In computer vision, video-based approaches have been widely explored for the early classification and the prediction of actions or activities. However, it remains unclear whether this modality (as compared to 3D kinematics) can still be reliable for the prediction of human intentions, defined as the overarching goal embedded in an action sequence. Since the same action can be performed with different intentions, this problem is more challenging but yet affordable as proved by quantitative cognitive studies which exploit the 3D kinematics acquired through motion capture systems. In this paper, we bridge cognitive and computer vision studies, by demonstrating the effectiveness of video-based approaches for the prediction of human intentions. Precisely, we propose Intention from Motion, a new paradigm where, without using any contextual information, we consider instantaneous grasping motor acts involving a bottle in order to forecast why the bottle itself has been reached (to pass it or to place in a box, or to pour or to drink the liquid inside). We process only the grasping onsets casting intention prediction as a classification framework. Leveraging on our multimodal acquisition (3D motion capture data and 2D optical videos), we compare the most commonly used 3D descriptors from cognitive studies with state-of-the-art video-based techniques. Since the two analyses achieve an equivalent performance, we demonstrate that computer vision tools are effective in capturing the kinematics and facing the cognitive problem of human intention prediction.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

optical Signal processing of video Surveillance for Recognizing and Measurement Location Railway Infrastructure Elements 14

Optical Signal Processing of Video Surveillance for Recogniz...

引用

14th International conference on optical Technologies for Telecommunications

作者： Diyazitdinov, Rinat R. Vasin, Nikolay N. PSUTI Dept Commun Syst 23 Tolstoy St Samara 443010 Russia

ISBN: (纸本)9781510600485

processing of optical signals, which are received from CCD sensors of video cameras, allows to extend the functionality of video surveillance systems. Traditional video surveillance systems are used for saving, transmitting and preprocessing of the video content from the controlled objects. video signal processing by analytics systems allows to get more information about object's location and movement, the flow of technological processes and to measure other parameters. For example, the signal processing of video surveillance systems, installed on carriage-laboratories, are used for getting information about certain parameters of the railways. Two algorithms for video processing, allowing recognition of pedestrian crossings of the railways, as well as location measurement of the so-called "Anchor Marks" used to control the mechanical stresses of continuous welded rail track are described in this article. The algorithms are based on the principle of determining the region of interest (ROI), and then the analysis of the fragments inside this ROI.

关键词： video surveillance systems optical signal processing diagnostic systems pedestrian crossing railway tracks railways Anchor Marks RANSAC Canny Gaussian impulse the image histogram the region of interest

来源：评论

学校读者我要写书评

暂无评论

Controlling Quantum Correlations in Massively Multichannel optical Networks

Controlling Quantum Correlations in Massively Multichannel O...

引用

conference on Lasers and Electro-Optics Europe

作者： Ravitej Uppu Tom A. W. Wolterink Willem L. Vos Klaus J. Boller Pepijn W. H. Pinkse Complex Photonic Systems (COPS) MESA+ Institute for Nanotechnology University of Twente P.O. Box 217 7500 AE Enschede The Netherlands Laser Physics and Nonlinear Optics (LPNO) MESA+ Institute for Nanotechnology University of Twente P.O. Box 217 7500 AE Enschede The Netherlands

ISBN: (纸本)9781509067374

Quantum optics experiments require ultimate control over the propagation of light in linear optical networks to realize programmable photon correlations [1]. Integrated optics provides a robust and low-loss platform for implementing such linear optical networks. However, to achieve ultimate control on the quantum state of light, it is necessary to program the network [2]. Tuning the network for controlled multiphoton correlations involves optimization algorithms which scale inefficiently with the network size and photon number. Therefore, it is challenging to scale up this approach to massively multichannel networks, which are required for large-scale implementations of quantum information processing and quantum communication.

关键词： Light propagation optical networks Photon correlations Quantum communications Quantum information processing Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Measurement of transparent or translucent objects

Measurement of transparent or translucent objects

引用

International conference on Informatics, Electronics & vision (ICIEV)

作者： Yasushi Yagi OSAKA University Japan

ISBN: (纸本)9781538610244;9781538610237

The studies in our laboratory focus on theory and applications related to computer vision and media processing. Some of the major research projects undertaken in the laboratory involve the creation of novel optical sensing systems including the omni-directional vision system, and the development of algorithms for human sensing, human behavior analysis, gait analysis, geometrical analysis and computational photography. Especially, we have been studying creation of novel optical sensing systems for more than 25 years. Today, I will introduce several special sensing systems for computer vision. Measurement of transparent or translucent objects is an important technology with broad potential applications. In the computer vision field, computational photography approaches that combine optical design and computational algorithms to obtain informative images have been actively developed to enhance and restore images. However, it remains difficult to recover invisible information contained within transparent or translucent objects because light penetrates and scatters inside the object, heavily degrading observed images. Second my talk is about our special sensing system using either spatially or temporally modulated light. This optics, for example, can remove scattering lights from observation, by projecting high frequency patterns. I will show several recent researches on the topics.

关键词： Computer vision optical sensors Photography Informatics Biomedical imaging Media

来源：评论

学校读者我要写书评

暂无评论

2D Non-separable Linear Canonical Transform (2D-NS-LCT) based cryptography 5

2D Non-separable Linear Canonical Transform (2D-NS-LCT) base...

引用

conference on Holography - Advances and Modern Trends V

作者： Zhao, Liang Muniraj, Inbarasan Healy, John J. Malallah, Ra'ed Cui, Xiao-Guang Ryle, James P. Sheridan, John T. Univ Coll Dublin Insight Ctr Data Analyt Dublin 4 Ireland Univ Coll Dublin Sch Elect & Elect Engn Lab IoE2 SFI Strateg Res Cluster Solar Energy Convers Dublin 4 Ireland Univ Basrah Phys Dept Fac Sci Garmat Ali Basrah Iraq Chinese Acad Sci Inst Automat 95East Zhong Guan Cun Rd Beijing 100190 Peoples R China

ISBN: (数字)9781510609686

ISBN: (纸本)9781510609679;9781510609686

The 2D non-separable linear canonical transform (2D-NS-LCT) can describe a variety of paraxial optical systems. Digital algorithms to numerically evaluate the 2D-NS-LCTs are not only important in modeling the light field propagations but also of interest in various signal processing based applications, for instance optical encryption. Therefore, in this paper, for the first time, a 2D-NS-LCT based optical Double-random-Phase- Encryption (DRPE) system is proposed which offers encrypting information in multiple degrees of freedom. Compared with the traditional systems, i.e. (i) Fourier transform (FT);(ii) Fresnel transform (FST);(iii) Fractional Fourier transform (FRT);and (iv) Linear Canonical transform (LCT), based DRPE systems, the proposed system is more secure and robust as it encrypts the data with more degrees of freedom with an augmented key-space.

关键词： ABCD Transform optical security and encryption Numerical approximation and analysis Discrete optical signal processing

来源：评论

学校读者我要写书评

暂无评论

Computer vision on the GPU - Tools, algorithms and Frameworks 20

Computer Vision on the GPU - Tools, Algorithms and Framework...

引用

20th Jubilee IEEE International conference on Intelligent Engineering systems (INES)

作者： Fassold, Hannes JOANNEUM Res DIGITAL Inst Informat & Commun Technol Steyrergasse 17 A-8010 Graz Austria

ISBN: (纸本)9781509012169

In recent years, graphic processing units (GPUs) have emerged as an attractive alternative to CPUs for implementing algorithms in a wide range of applications. The focus of this work is to give an overview about the current state on using GPUs for computer vision. We describe briefly tools like CUDA, OpenCL and OpenACC used for GPU programming and their respective advantages / disadvantages. We give information about the current state of the art for implementing important computer vision algorithms like optical flow, KLT feature point tracking and SIFT descriptor extraction efficiently on the CPU. Finally, we describe open source frameworks which either provide CPU-accelerated computer vision algorithms or which are helpful for porting algorithms to the GPU.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Position Control of a Magnetic Levitation Device Using a Disturbance Observer and Associated Remote Sensing

Position Control of a Magnetic Levitation Device Using a Dis...

引用

IEEE International conference on Advanced Intelligent Mechatronics (AIM)

作者： de langlade, Alexandre Katsura, Seiichiro Keio Univ Dept Integrated Design Engn Yokohama Kanagawa Japan

ISBN: (纸本)9781509060009

This paper presents a method to improve the robustness of the position control of a small permanent magnet within a living organism, such as the human body in microsurgery. So far, position control has been achieved up to 5 Degrees of Freedom with robustness against predicted and modelled disturbance. In order to achieve robust control against non predicted disturbances, the use of a disturbance observer was proved efficient in the past. Disturbance observers require fast and accurate position sensing, which has been achieved so far by optical position sensing. In an effort to extend the operational range of magnetic levitation systems, this paper also considers the use of a position sensor which does not rely on optical sensors, but inductance variation. The models for simulations are based on the Octomag system, which is one of the most up-to-date magnetic levitation devices.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Photonic Implementation of Spike-Timing-Dependent Plasticity and Learning algorithms of Biological Neural systems

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2016年第2期34卷 470-476页

作者： Toole, Ryan Tait, Alexander N. de Lima, Thomas Ferreira Nahmias, Mitchell A. Shastri, Bhavin J. Prucnal, Paul R. Fok, Mable P. Univ Georgia Lightwave & Microwave Photon Lab Coll Engn Athens GA 30602 USA Princeton Univ Dept Elect Engn Lightwave Commun Lab Princeton NJ 08544 USA

The neurobiological learning algorithm, spike-timing-dependent plasticity (STDP), is demonstrated in a simple photonic system using the cooperative nonlinear effects of cross gain modulation and nonlinear polarization rotation, and supervised and unsupervised learning using photonic neuron principles are examined. An STDP-based supervised learning scheme is presented which is capable of mimicking a desirable spike pattern through learning and adaptation. Furthermore, unsupervised learning is illustrated by a principal component analysis system operating under similar learning rules. Finally, a photonic-distributed processing network capable of STDP-based unsupervised learning is theoretically explored.

关键词： Feedback circuits information theory neural networks nonlinear optics optical signal processing

来源：评论

学校读者我要写书评

暂无评论

Detection of Face Position and Orientation Using Depth Data

引用

8th International conference on Image processing and Communications (IP and C)

作者： Szwoch, Mariusz Pieniazek, Pawel Gdansk Univ Technol Gdansk Poland

ISBN: (纸本)9783319238142;9783319238135

In this paper an original approach is presented for real-time detection of user's face position and orientation based only on depth channel from a Microsoft Kinect sensor which can be used in facial analysis on scenes with poor lighting conditions where traditional algorithms based on optical channel may have failed. Thus the proposed approach can support, or even replace, algorithms based on optical channel or based on skeleton or face tracking information. The accuracy of proposed algorithms is 91% and was verified on Facial Expressions and Emotions Database using 169 recordings of 25 persons. As the processing time is below 20 ms per frame on a standard PC, the proposed algorithms can be used in real-life applications. The presented algorithms were validated in a prototype application for user emotion recognition based on depth channel information only.

关键词： Face detection Depth image processing Kinect sensor

来源：评论

学校读者我要写书评

暂无评论

Hessian-Assisted Supervoxel: Structure-Oriented Voxel Clustering and Application to Mediastinal Lymph Node Detection from CT Volumes

Hessian-Assisted Supervoxel: Structure-Oriented Voxel Cluste...

引用

conference on Medical Imaging - Computer-Aided Diagnosis

作者： Oda, Hirosha Bhatia, Kanwal K. Oda, Masahiro Kitasaka, Takayuki Iwano, Shingo Homma, Hirotoshi Takabatake, Hirotsugu Mori, Masaki Natori, Hiroshi Schnabel, Julia A. Mori, Kensaku Nagoya Univ Grad Sch Informat Sci Nagoya Aichi Japan Kings Coll London Div Imaging Sci & Biomed Engn London England Nagoya Univ Strategy Off Informat & Commun Nagoya Aichi Japan Aichi Inst Technol Fac Informat Sci Toyota Japan Nagoya Univ Grad Sch Med Nagoya Aichi Japan Sapporo Kosei Gen Hosp Sapporo Hokkaido Japan Sapporo Minami Sanjo Hosp Sapporo Hokkaido Japan Keiwakai Nishioka Hosp Nagoya Aichi Japan

ISBN: (纸本)9781510607132;9781510607149

In this paper, we propose a novel supervoxel segmentation method designed for mediastinal lymph node by embedding Hessian-based feature extraction. Starting from a popular supervoxel segmentation method, SLIC, which computes supervoxels by minimising differences of intensity and distance, we overcome this method's limitation of merging neighboring regions with similar intensity by introducing Hessian-based feature analysis into the supervoxel formation. We call this structure-oriented voxel clustering, which allows more accurate division into distinct regions having blob-, line- or sheet-like structures. This way, different tissue types in chest CT volumes can be segmented individually, even if neighboring tissues have similar intensity or are of non- spherical extent. We demonstrate the performance of the Hessian-assisted supervoxel technique by applying it to mediastinal lymph node detection in 47 chest CT volumes, resulting in false positive reductions from lymph node candidate regions. 89 % of lymph nodes whose short axis is at least 10 mm could be detected with 5.9 false positives per case using our method, compared to our previous method having 83 % of detection rate with 6.4 false positives per case. © (2017) COPYRIGHT Society of Photo-optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

关键词： Lymphatic system Image segmentation Blood vessels Chest Esophagus Feature extraction Target detection Computer aided diagnosis and therapy information science Computer-aided diagnosis Image processing algorithms and systems Lung Lung cancer

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：