检索结果-内蒙古大学图书馆

Evaluation of Geometric Data Registration of Small Objects from Non-Invasive Techniques: Applicability to the HBIM Field

引用

SENSORS 2023年第3期23卷 1730-1730页

作者： Moyano, Juan Cabrera-Revuelta, Elena Nieto-Julian, Juan E. Fernandez-Alconchel, Maria Fernandez-Valderrama, Pedro Univ Seville Dept Graph Express & Bldg Engn Ave Reina Mercedes 4A Seville 41012 Spain Univ Cadiz Dept Mech Engn & Ind Design 10 Ave Puerto Real Cadiz 11510 Spain

Reverse engineering and the creation of digital twins are advantageous for documenting, cataloging, and maintenance control tracking in the cultural heritage field. Digital copies of the objects into Building information Models (BIM) add cultural interest to every artistic work. Low-cost 3D sensors, particularly structured-light scanners, have evolved towards multiple uses in the entertainment market but also as data acquisition and processing techniques for research purposes. Nowadays, with the development of structured-light data capture technologies, the geometry of objects can be recorded in high-resolution 3D datasets at a very low cost. On this basis, this research addresses a small artifact with geometric singularities that is representative of small museum objects. For this, the precision of two structured-light scanners is compared with that of the photogrammetric technique based on short-range image capture: a high-cost Artec Spider 3D scanner, and the low-cost Revopoint POP 3D scanner. Data capture accuracy is evaluated through a mathematical algorithm and point set segmentation to verify the spatial resolution. In addition, the precision of the 3D model is studied through a vector analysis in a BIM environment, an unprecedented analysis until now. The work evaluates the accuracy of the devices through algorithms and the study of point density at the submillimeter scale. Although the results of the 3D geometry may vary in a morphometric analysis depending on the device records, the results demonstrate similar accuracies in that submillimeter range. Photogrammetry achieved an accuracy of 0.70 mm versus the Artec Spider and 0.57 mm against the Revopoint POP 3D scanner.

关键词： BIM small object structured-light systems 3D optical scanner point cloud sculpture cultural heritage

来源：评论

学校读者我要写书评

暂无评论

Lightweight YOLOv4 Algorithm for Remote Sensing Image Detection

Lightweight YOLOv4 Algorithm for Remote Sensing Image Detect...

引用

International conference on Signal processing systems, ICSPS

作者： Li Ma Tong He Yong Sun Bin-Bin Hu College of Information Liaoning University Shenyang China

Remote sensing images have the characteristics of complex backgrounds, high resolution, and small targets. Although the existing object detection algorithms can improve the detection accuracy, there are generally problems such as a large number of model parameters, high computational cost, and poor real-time performance. Aiming at the above problems, this paper designs a lightweight object detection algorithm GSC-YOLO based on YOLOv4 to achieve fast and accurate detection of remote sensing images. First, Ghostnet is used as the feature extraction network of GSC-YOLO to reduce the number of parameters and improve the detection speed; Secondly, the improved shuffle attention mechanism is introduced in the prediction head to make the model pay attention to important information and improve the detection accuracy; Finally, the Confidence Propagation Cluster algorithm CP-Cluster is used to post-process the prediction frame to improve the object recognition. Taking the preprocessed DOTA dataset as the experimental object, the experimental results show that the GSC-YOLO algorithm has a detection accuracy of 93.44%, a detection speed of 58 frames per second, and a model size of 43.65MB. Compared with the remote sensing image object detection algorithm based on YOLOv4, the detection accuracy is increased by 3.93%, the detection speed is increased by 1.87 times, and the model size is reduced by 5.62 times, which is more suitable for deployment on devices with limited resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Locally-Adaptive Nonparametric Online Learning 34

Locally-Adaptive Nonparametric Online Learning

引用

34th conference on Neural information processing systems (NeurIPS)

作者： Kuzborskij, Ilja Cesa-Bianchi, Nicolo DeepMind London England Univ Milan Dept Comp Sci Milan Italy Univ Milan DSRC Milan Italy

ISBN: (纸本)9781713829546

One of the main strengths of online algorithms is their ability to adapt to arbitrary data sequences. This is especially important in nonparametric settings, where performance is measured against rich classes of comparator functions that are able to fit complex environments. Although such hard comparators and complex environments may exhibit local regularities, efficient algorithms, which can provably take advantage of these local patterns, are hardly known. We fill this gap by introducing efficient online algorithms (based on a single versatile master algorithm) each adapting to one of the following regularities: (i) local Lipschitzness of the competitor function, (ii) local metric dimension of the instance sequence, (iii) local performance of the predictor across different regions of the instance space. Extending previous approaches, we design algorithms that dynamically grow hierarchical "-nets on the instance space whose prunings correspond to different "locality profiles" for the problem at hand. Using a technique based on tree experts, we simultaneously and efficiently compete against all such prunings, and prove regret bounds each scaling with a quantity associated with a different type of local regularity. When competing against "simple" locality profiles, our technique delivers regret bounds that are significantly better than those proven using the previous approach. On the other hand, the time dependence of our bounds is not worse than that obtained by ignoring any local regularities.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

Saving Energy and Increasing Density in information processing Using Photonics

Saving Energy and Increasing Density in Information Processi...

引用

optical Fiber Communications conference and Exposition (OFC)

作者： Miller, David A. B. Ginzton Lab Spilker Bldg348 Via Pueblo Mall Stanford CA 94305 USA

We argue energy and interconnect density in information processing can be improved by orders of magnitude using parallel free-space optical channels inside and between racks, enabled by integrated waveguide photonics,... 详细信息

ISBN: (数字)9781943580712

ISBN: (纸本)9781943580712

关键词： Guided waves Light beams optical devices optical interconnects optical systems

来源：评论

学校读者我要写书评

暂无评论

The Integration of Stream Data Models in Modern Transportation Networks

The Integration of Stream Data Models in Modern Transportati...

引用

International conference on ICT in Business Industry & Government (ICTBIG)

作者： Preeti Naval Sandeep Kumar Jain K. Gopala Krishna Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Electrical Engineering Vivekananda Global University Jaipur India Department of Electronics and Communication Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Karnataka

The study proposal proposes an innovative strategy for managing modern transport networks, with an emphasis on the coordinated use of analytics, real-time data processing, and dynamic decision-making utilizing stream data models. To create a solid infrastructure for real-time data analysis, it is required to use a diverse set of data sources, such as sensors, GPS devices, traffic cameras, and mobile application software. A strategy for reaching this goal is described below. The real-time system that integrates transportation models, artificial intelligence, and data mining is at the core of this strategy. In addition to monitoring and assessment, one of the key responsibilities of this system is to develop the transportation network. Without this framework as a foundation, the method would be worthless. This collaborative effort provides proactive traffic control, efficient route planning, and event prediction in real time. The application of machine learning in predictive analytics and traffic analysis, which together give solid traffic forecasts, prompts the creation of tactics that cut wait times and enhance productivity. Event detection algorithms are critical for ensuring commuter safety and reducing wait times in the event of an emergency. Using cloud-hosted data processing technologies, the idea manages massive amounts of real-time data. This is critical for data collection, processing, and storage methods. Finally, we believe that the development of an intelligent transportation network—one that can continually learn, adapt, and drive itself—will result in less traffic, more safety, shorter travel times, and environmentally friendly legislation and practices. To address the ever-increasing demands placed on dynamic urban settings, it is believed that the technique developed would transform current transport networks into more responsive, user-friendly, and efficient systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Introduction to the JSTQE Issue on Advanced Photonic Modulation: devices, systems & Techniques

引用

IEEE Journal of Selected Topics in Quantum Electronics 2021年第3期27卷

作者： Vivien, Laurent Takenaka, Mitsuru Thomson, David Tsang, Hon Ki Witzens, Jeremy Cnrs and University Paris-Saclay Palaiseau France University of Tokyo Tokyo Japan University of Southampton Southampton United Kingdom Department of Electronic Engineering Chinese University of Hong Kong Hong Kong Institute of Integrated Photonics Rwth Aachen University Aachen Germany

The twenty-one papers in this special section focus on advanced photonic modulation devices, systems, and techniques. Integrated light modulation in the low- or high-speed frequency regimes is central to most photonic applications, including optical telecommunications, datacom, quantum information processing, artificial intelligence, high-speed information processing such as optically enabled data converters or microwave photonics, Lidars, and sensing.

关键词： Special issues and sections Photonics Modulation optical modulation optical variables control optical sensors High-speed optical techniques

来源：评论

学校读者我要写书评

暂无评论

Advanced Ultra Low-Power Deep Learning Applications with Neuromorphic Computing

Advanced Ultra Low-Power Deep Learning Applications with Neu...

引用

IEEE conference on High Performance Extreme Computing (HPEC)

作者： Mark Barnell Courtney Raymond Lisa Loomis Darrek Isereau Daniel Brown Francesca Vidal Steven Smiley Air Force Research Laboratory Information Directorate Rome NY USA Defense Systems & Solutions SRC Inc. North Syracuse NY USA

The latest Intel neuromorphic processor, Loihi 2, provides a breakthrough in Artificial Intelligence (AI) for computing at the edge, where sensor information is collected. The computing architecture does this by leveraging computations at the transistor level in a fashion analogous to the human brain's biological neural networks (vs. a Von Neumann compute architecture). The Loihi 2's high performance, small form factor, and low-power consumption makes it a unique capability that is well suited for use in devices. Our technical approach and findings support extreme computing needs for the internet of things (IoT) and various airborne platforms' applications. The recently released Loihi 2 and the novel research completed on this effort were combined to accelerate development and demonstration of a new concept of operation for machine learning at the edge. This research included the development of spiking neural networks (SNN) on sensor data representative of information sources from a small research platform. Our concept uses the representative sensor data to predict the platform mode through machine learning. Importantly, our technical approach allowed us to rapidly scale from IBM's TrueNorth Corelet framework to the Lava framework, which Intel's Loihi 2 neuromorphic processor utilizes. The use of the Lava framework demonstrates the art-of-the-possible in edge computing by demonstrating capabilities on small airborne platform sensor data and wide extensibility to other domains that can use this neuromorphic compute hardware. In summary, this research included the use of new compute frameworks, novel processing algorithms, and a unique concept of operation. This technical approach resulted in the classification of the platform mode given the sensor information with accuracies up to 97.6%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hardware Acceleration of Statistical Data processing Based on FPGAs in Corporate information systems 2

Hardware Acceleration of Statistical Data Processing Based o...

引用

2nd International conference on Control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2020

作者： Andrianova, Elena Sovietov, Peter Tarasov, Ilya Russian Technological University Mirea Institute of Information Technology Moscow Russia

ISBN: (纸本)9781728188409

The article discusses the architecture of the FPGA-based computing subsystem to accelerate the statistical processing of data in corporate information systems. To implement these algorithms, you can use a network of processor devices placed on an FPGA chip of medium or large logical volume. It is proposed to use specialized processor cores, the development of which is carried out as part of the hardware software co-design approach, in order to create a device optimized for typical algorithms of a target set of tasks. © 2020 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

7th International conference on Signal and information processing, Networking and Computers, ICSINC 2020

7th International Conference on Signal and Information Proce...

引用

7th International conference on Signal and information processing, Networking and Computers, ICSINC 2020

ISBN: (纸本)9789813341012

The proceedings contain 129 papers. The special focus in this conference is on Signal and information processing, Networking and Computers. The topics include: The introduction and prospect of extended range forecasting in 11~30 days at the national meteorological center in china;cross-screen tracking method based on user behavior data;a virtual optical network mapping algorithm based on machine learning;big data ecological platform architecture design and construction practice in telecommunication operators;an evaluation model of user lifetime value based on improved rfm and ahp method;sharing c-band frequency between satellite and terrestrial 5g communication systems;architecture and technology of multi-source heterogeneous data system for telecom operator;intelligent detection of network coverage problems based on the clustering algorithm;exploration and practice of China unicom multi-scene capability construction and open platform for large-scale heterogeneous data;poc testing analysis of big data products;the next generation identity platform for digital era based on blockchain;research on rulebase metamodel construction and management;kubernetes realizes the cloud & network cooperation based on hardware sdn controller;data visualization of 5g speed test platform using tableau;intelligent mobile communication network plan for 5g based on insight big data;research and application of precision marketing algorithms for etc credit card based on telecom big data;lunar observation research on low-orbit remote sensing satellites;soc design and implementation of can 2.0 protocol toward satellite applications;remote sensing satellite rapid response technology based on orbit maneuver;angular momentum management design and on orbit verification of geo navigation satellite;preface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Handwritten Text Recognition using Deep Learning algorithms

Handwritten Text Recognition using Deep Learning Algorithms

引用

Artificial Intelligence and Speech Technology (AIST), International conference on

作者： Arbaj Ansari Baljinder Kaur Manik Rakhra Arun Singh Dalwinder Singh Department of Computer Science and Engineering Lovely Professional University Phagwara India Computer Science and Engineering Lovely Professional University Phagwara India

Since a pen is more convenient than a keyboard, most scripts are now produced by hand; this often leads to mistakes due to the illegibility of human handwriting. To combat this issue, handwriting recognition has rapidly emerged as a top research priority. Computer vision algorithms involving optical character recognition were previously employed in traditional handwriting recognition systems. It is a challenging undertaking to train an optical character recognition (OCR) system with these constraints in mind. The OCR method has many problems. In this study, we employ Convolutional Neural Networks (CNNs), Long Short-Term Memories (LSTMs) built on Recurrent Neural Network (RNN) architecture, and Connectionist Temporal Classification (CTC) to recognise handwritten text (CTC). To train and evaluate the network, we use the information Acquisition MNIST dataset, which includes an English language handwriting test. Here, image processing is handled by OpenCV, while word recognition and training are handled by TensorFlow. Python is used throughout the development of this system, with the console serving as the final destination for the output.

关键词： Training Handwriting recognition Recurrent neural networks Text recognition optical character recognition Speech recognition Writing

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：