检索结果-内蒙古大学图书馆

EFFICIENT MAPPING ALGORITHMS FOR A CLASS OF HIERARCHICAL SYSTEMS

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 1993年第11期4卷 1230-1245页

作者： ZIAVRAS, SG Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

This paper proposes techniques for mapping application algorithms onto a class of hierarchically structured parallel computing systems. Multiprocessors of this type are capable of efficiently solving a variety of scientific problems because they can efficiently implement both local and global operations for data in a two-dimensional array format. Among the set of candidate application domains, low-level and intermediate-level image processing and computer vision (IPCV) are characterized by high-performance requirements. Emphasis is given in this paper to IPCV algorithms. The importance of the mapping techniques stems from the fact that the current technology cannot be used to build cost-effective and efficient systems composed of very large numbers of processors, so the performance of various systems of lower cost should be investigated. Both analytical and simulation results prove the effectiveness and efficiency of the proposed mapping techniques.

关键词： HIERARCHICAL STRUCTURES image processing and computer vision MAPPING TECHNIQUES PROCESS ASSIGNMENT SCHEDULING

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Deformable Detector

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2012年第2期34卷 225-239页

作者： Ali, Karim Fleuret, Francois Hasler, David Fua, Pascal EPFL IC CVLAB Stn 14 CH-1015 Lausanne Switzerland Idiap Res Inst Ctr Parc CH-1920 Martigny Switzerland CSEM SA CH-2002 Neuchatel Switzerland

We propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform based on the signal of interest. We train a detector with a standard AdaBoost procedure by using combinations of pose-indexed features and pose estimators. This allows the learning process to select and combine various estimates of the pose with features able to compensate for variations in pose without the need to label data for training or explore the pose space in testing. We validate our framework on three types of data: hand video sequences, aerial images of cars, and face images. We compare our method to a standard boosting framework, with access to the same ground truth, and show a reduction in the false alarm rate of up to an order of magnitude. Where possible, we compare our method to the state of the art, which requires pose annotations of the training data, and demonstrate comparable performance.

关键词： image processing and computer vision machine learning object detection

来源：评论

学校读者我要写书评

暂无评论

Welcome to the year 2022

引用

VISUAL computer 2022年第1期38卷 27-28页

作者： Magnenat-Thalmann, Nadia Univ Geneva MIRALab CUI Bldg A7 Route Drize CH-1227 Carouge GE Switzerland

Neeharika Adabala, India Florent Lafarge, France Bruno Levy, INRIA, France Liang Lin, Sun Yat-sen University, China Masayuki Nakajima, Japan Bodo Rosenhahn, Leibniz University of Hannover, Germany Jianbin Shen, China Qixiang Ye, Chinese Academy of Sciences, China The editorial board of the Visual computer is renewed regularly. Antonio Agudo, CSIC-UPC, Spain Imon Banerjee, Emory University School of Medicine, USA Sebastiano Battiato, Università di Catania, Italy Tolga Birdal, Stanford University, USA Ladislau Boloni, University of Central Florida, USA Zhonggui Chen, Xiamen University, China Sunghyun Cho, POSTEC, South Korea Jan Egger, Graz University of Technology, Austria Antonino Furnari, University of Catania, Italy Zhenhua Guo, Alibaba Group, China Dakai Jin, PAII Inc., USA Stefano Mattoccia, University of Bologna, Italy Tae-Hyun Oh, POSTECH, South Korea Jinshan Pan, Nanjing University of Science and Technology, China Andrea Prati, Università degli Studi di Parma, Italy Jonathan Roberts, Bangor University, UK Thomas Schultz, University of Bonn, Germany Bernie Tiddeman, Aberystwyth University, UK Zhigang Tu, Wuhan University, China Nannan Wang, Xidian University, Xi'an City, China Mingqiang Wei, Nanjing University of Aeronautics and Astronautics, China Yücel Yemez, Koç University, Turkey During 2021, as usual, the journal published a special issue containing the best papers from the computer Graphics International Conference (CGI’2021) organized by the computer Graphics Society (CGS). Nadia Magnenat Thalmann Editor-in-Chief The Visual computer Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

关键词： computer Graphics computer Science general Artificial Intelligence image processing and computer vision

来源：评论

学校读者我要写书评

暂无评论

BRIEF: Computing a Local Binary Descriptor Very Fast

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2012年第7期34卷 1281-1298页

作者： Calonder, Michael Lepetit, Vincent Oezuysal, Mustafa Trzcinski, Tomasz Strecha, Christoph Fua, Pascal Ecole Polytech Fed Lausanne Comp Vis Lab I&C Fac CH-1015 Lausanne Switzerland

Binary descriptors are becoming increasingly popular as a means to compare feature points very fast while requiring comparatively small amounts of memory. The typical approach to creating them is to first compute floating-point ones, using an algorithm such as SIFT, and then to binarize them. In this paper, we show that we can directly compute a binary descriptor, which we call BRIEF, on the basis of simple intensity difference tests. As a result, BRIEF is very fast both to build and to match. We compare it against SURF and SIFT on standard benchmarks and show that it yields comparable recognition accuracy, while running in an almost vanishing fraction of the time required by either.

关键词： image processing and computer vision feature matching augmented reality real-time matching

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Recognition of Poorly Resolved Integrated Circuit Elements

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2014年第3期9卷 354-363页

作者： Matlin, Erik Agrawal, Motilal Stoker, David SRI Int Sensor Syst Lab Menlo Pk CA 94025 USA SRI Int Ctr Artificial Intelligence Menlo Pk CA 94025 USA

We present a non-invasive method for recognition of components in a digital CMOS integrated circuit (IC). We use a confocal infrared laser scanning optical microscope to collect multimodal images through the backside of the IC. Individual modes correspond to passive reflectivity measurements or active measurements, such as light-induced voltage alteration. The modes are registered and stored in a multidimensional data cube. We apply a machine learning algorithm using a binary representation to identify a variety of data structures from transistors to entire logic cells. Because of the compact representation, objects can be detected rapidly. We show that by increasing the number of imaging modes used to develop the descriptor, we can significantly increase recognition accuracy. The approach allows recognition of poorly resolved components, whose primary distinguishing features are below traditional optical resolution limits, and is general enough to be applied to multiple design processes. We believe this represents a significant step toward a fully non-invasive IC reverse engineering system.

关键词： image processing and computer vision bag-of-words ensemble learning non-invasive reverse engineering integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Total variation models for variable lighting face recognition

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2006年第9期28卷 1519-1524页

作者： Chen, Terrence Yin, Wotao Zhou, Xiang Sean Comaniciu, Dorin Huang, Thomas S. Univ Illinois Urbana IL 61801 USA Columbia Univ IEOR Dept New York NY 10027 USA Siemens Corp Res Princeton NJ 08540 USA Siemens Med Solut Inc Malvern PA 19355 USA

this paper, we present the logarithmic total variation (LTV) model for face recognition under varying illumination, including natural lighting conditions, where we rarely know the strength, direction, or number of light sources. The proposed LTV model has the ability to factorize a single face image and obtain the illumination invariant facial structure, which is then used for face recognition. Our model is inspired by the SQI model but has better edge-preserving ability and simpler parameter selection. The merit of this model is that neither does it require any lighting assumption nor does it need any training. The LTV model reaches very high recognition rates in the tests using both Yale and CMU PIE face databases as well as a face database containing 765 subjects under outdoor lighting conditions.

关键词： face and gesture recognition signal processing image processing and computer vision pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Rei: A Reconfigurable Interconnection Unit for Array-Based CNN Accelerators

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING 2023年第4期11卷 895-906页

作者： Darbani, Paria Beitollahi, Hakem Lotfi-Kamran, Pejman Iran Univ Sci & Technol Sch Comp Engn Tehran *** Iran Inst Res Fundamental Sci IPM Sch Comp Sci Tehran *** Iran

Convolutional Neural Network (CNN) is used in many real-world applications due to its high accuracy. The rapid growth of modern applications based on learning algorithms has increased the importance of efficient implementation of CNNs. The array-type architecture is a well-known platform for the efficient implementation of CNN models, which takes advantage of parallel computation and data reuse. However, accelerators suffer from restricted hardware resources, whereas CNNs involve considerable communication and computation load. Furthermore, since accelerators execute CNN layer by layer, different shapes and sizes of layers lead to suboptimal resource utilization. This problem prevents the accelerator from reaching maximum performance. The increasing scale and complexity of deep learning applications exacerbate this problem. Therefore, the performance of CNN models depends on the hardware's ability to adapt to different shapes of different layers to increase resource utilization. This work proposes a reconfigurable accelerator that can efficiently execute a wide range of CNNs. The proposed flexible and low-cost reconfigurable interconnect units allow the array to perform CNN faster than fixed-size implementations (by 45.9% for ResNet-18 compared to the baseline). The proposed architecture also reduces the on-chip memory access rate by 36.5% without compromising accuracy.

关键词： Adaptable architectures array and vector processors image processing and computer vision parallel processors reconfigurable hardware special-purpose and application-based systems

来源：评论

学校读者我要写书评

暂无评论

Cost-benefit analysis of virtual reality-based training for emergency rescue workers: a socio-technical systems approach

引用

VIRTUAL REALITY 2021年第4期25卷 1071-1086页

作者： Pedram, Shiva Ogie, Robert Palmisano, Stephen Farrelly, Matthew Perez, Pascal Univ Wollongong Fac Engn & Informat Sci Smart Infrastruct Facil Wollongong NSW Australia Univ Wollongong Fac Social Sci Sch Psychol Wollongong NSW Australia Coal Serv Pty Ltd Mines Rescue Sydney NSW Australia

Virtual reality (VR) is widely recognised as a promising technology for training emergency first responders and other safety-critical workers. It is uniquely able to immerse trainees in extreme situations that are too risky or dangerous to be examined in traditional real-world safety training. Most organisations seeking to implement VR safety training often limit their decisions to financial and technological factors. However, in this paper, we argue that a socio-technical systems approach is required to better appreciate the social costs and benefits of VR training, which are important for a successful implementation. The paper also reports our own research on a real-world implementation of VR safety training for the Mine Rescue Brigades in New South Wales, Australia. The training-conducted in both fully immersive (360 VR) and non-immersive (Desktop VR) virtual reality-involved a search and rescue operation which was necessitated by an underground fire at the bottom of the transport drift in a coal mine. Following this training, the 368 trainees not only completed a post-training questionnaire, but also were interviewed, to assess their training experiences in the VR environment. The findings provide a comprehensive account of the social costs and benefits of adopting VR as a safety training tool. Overall, the trainees perceived the benefits to far outweigh the costs, with an overall high inclination to recommend the VR training to other colleagues. Desktop VR was found to be as fit for delivering successful training as the more immersive 360 VR. However, this Desktop VR generated considerably less motion sickness in trainees. These findings should help organisations and training providers decide on: (1) whether or not to invest in VR safety training solutions;(2) which type technology/method of delivery to use.

关键词： computer Graphics Artificial Intelligence image processing and computer vision User Interfaces and Human computer Interaction

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection and Tracking for Augmented Reality on Mobile Phones

引用

IEEE TRANSACTIONS ON VISUALIZATION AND computer GRAPHICS 2010年第3期16卷 355-368页

作者： Wagner, Daniel Reitmayr, Gerhard Mulloni, Alessandro Drummond, Tom Schmalstieg, Dieter Graz Univ Technol Inst Comp Graph & Vis A-8010 Graz Austria Univ Cambridge Dept Engn Cambridge CB2 1PZ England

In this paper, we present three techniques for 6DOF natural feature tracking in real time on mobile phones. We achieve interactive frame rates of up to 30 Hz for natural feature tracking from textured planar targets on current generation phones. We use an approach based on heavily modified state-of-the-art feature descriptors, namely SIFT and Ferns plus a template-matching-based tracker. While SIFT is known to be a strong, but computationally expensive feature descriptor, Ferns classification is fast, but requires large amounts of memory. This renders both original designs unsuitable for mobile phones. We give detailed descriptions on how we modified both approaches to make them suitable for mobile phones. The template-based tracker further increases the performance and robustness of the SIFT- and Ferns-based approaches. We present evaluations on robustness and performance and discuss their appropriateness for Augmented Reality applications.

关键词： Information interfaces and presentation multimedia information systems artificial augmented and virtual realities image processing and computer vision scene analysis tracking

来源：评论

学校读者我要写书评

暂无评论

Dynamic Load Balancing of Parallel SURF with Vertical Partitioning

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2015年第12期26卷 3358-3370页

作者： Kim, Deokho Kim, Minwoo Kim, Kyungah Sung, Minyong Ro, Won Woo Yonsei Univ Sch Elect & Elect Engn Seoul 120749 South Korea

The demand for real-time processing of robust feature detection is one of the major issues in the computer vision field. In order to comply with the requirements, in this paper a parallelization and optimization method to effectively accelerate SURF is proposed. The proposed parallelization method is developed based on a workload analysis of SURF in terms of various aspects, focusing in particular on the load balancing problem. First, the average parallel workload is divided into identical portions using the vertical partitioning method. Then, the load imbalance problem is further resolved using the dynamic partition balancing method. In addition, an optimization method is proposed together with the parallelization method to find and exclude redundant operations in SURF, thus effectively accelerating the feature detection operation when the proposed parallelization method is applied. The proposed method shows a maximum speedup of 19.21 compared to the single threaded performance on a 24-core system, achieving a maximum of 83.80 fps in a real-machine experiment, enabling real-time processing.

关键词： image processing and computer vision edge and feature detection SURF parallel computing multithreading

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：