检索结果-内蒙古大学图书馆

3D image Analysis of Sports Technical Features and Sports Training Methods Based on Artificial Intelligence

JOURNAL OF TESTING AND EVALUATION 2023年第1期51卷 189-200页

作者： Mei, Zhu Shenyang Jianzhu Univ Minist Sports Shenyang 110168 Liaoning Peoples R China

This article studies the three-dimensional (3D) image analysis and sports training methods of sports technical characteristics. This research uses the current sports technology diagnostic 3D video analysis system as a platform to build a database and knowledge base based on athletes' 3D sports information and sports parameters and uses algorithms based on artificial intelligence machine-learning machines to analyze sports data, learn from it, and learn from sports technology. Actions make analytical decisions and predictions. Then, it analyzes the human-motion behavior with the concept of traditional and virtual reality technology. The effectiveness of athletes' technical movements, using mathematical statistics, artificial intelligence, and other research methods, integrates and draws on the research methods of sports biomechanics, graphical imaging, human anatomy, expert systems, and neural networks. A neural network not only inherits certain characteristics of biology but also has its own unique characteristics, such as large-scale parallel processing, strong fault tolerance, and self-learning functions. Neural networks have a wide range of applications in information processing, pattern recognition, optimization, and other issues. By analyzing the application status of artificial intelligence technology in sports, the development prospects of sports training based on artificial intelligence can be inferred. Based on the acquisition of sports-related data, the evaluation of functional action modes, sports techniques, etc., is established. The multi-target feedback training method ultimately helps athletes improve their training level. Experimental data show that for the human body walking toward the camera, the rotation angle between adjacent frames is close to 0 degrees, and the translational position is basically 5 cm. The experimental results show that 3D image analysis and related sports training methods based on specific sports technical characteristics are

关键词： 3D image analysis artificial intelligence sports technical features sports training multi-target feedback training sports data

来源：评论

学校读者我要写书评

暂无评论

Evaluation of parallel processing Employed in Industrial Computed Tomography 1

引用

Conference and Exhibition on Non Destructive Evaluation, NDE 2020

作者： Acharya, Rajesh Kumar, Umesh Patankar, V.H. Kar, Soumitra Dash, Ashutosh Industrial Tomography & Instrumentation Section Radiochemistry & Isotope Group Bhabha Atomic Research Centre Mumbai400085 India Electronics Division Bhabha Atomic Research Centre Mumbai400085 India Security Electronics & Software Systems Division Bhabha Atomic Research Centre Mumbai400085 India Homi Bhabha National Institute Anushakti Nagar Mumbai400094 India

ISBN: (数字)9789811690938

ISBN: (纸本)9789811690921

Industrial computed tomography (ICT) using electromagnetic radiations in the form of gamma or x-rays is a non-destructive technique used in many non-medical applications. Cone-beam CT employing flat panel detectors (FPD) combined with volumetric reconstruction of projections produces three-dimensional representations of a scanned object. The property being represented is the linear attenuation coefficient or an approximate bulk density distribution within the region of interest. The computational cost of such three-dimensional reconstruction is high for computers especially when the projection matrix is larger and more in number. Typically, 2 k × 2 k projections are now common in the industrial domain with a typical pixel size of 200 µm. A 3D volume reconstruction involving approximately 1000 CT slices in such cases may take up to a few hours even on a workstation. The objective of this paper is to compare the performance of volume industrial CT algorithms when executed on GPU. We have implemented algorithms for 3D reconstruction of cone-beam computed tomography (CBCT) data on GPU. Feldkamp-Davis-Kress (FDK) method is used for the 3D reconstruction algorithm where the process of convolution and back-projection is being done on GPU. These two operations are chosen because they are the most time-consuming and repetitive in nature. The performance of the NVIDIA Quadro P6000 is evaluated by comparing execution time and image quality for xeon workstation without GPU and workstation with GPU. We observe that improvement in reconstruction time is up to 53 times (5296%) for volume CT without deterioration of image quality. © 2022, Indian Society for Non-destructive Testing.

关键词： Computed tomography reconstruction FDK algorithm GPU parallel processing

来源：评论

学校读者我要写书评

暂无评论

PLSAV: parallel loop searching and verifying for loop closure detection

引用

IET INTELLIGENT TRANSPORT systems 2021年第5期15卷 683-698页

作者： Yang, Zhe Pan, Yun Deng, Lei xie, Yuan Huan, Ruohong Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou Peoples R China Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou Peoples R China

Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long-term navigation without loop closure detection. Recently, deep neural networks (DNNs) are leveraged to achieve high accuracy for loop closure detection, however the execution time is much slower than those employing handcrafted visual features. In this paper, a parallel loop searching and verifying method for loop closure detection with both high accuracy and high speed, which combines two parallel tasks using handcrafted and DNN features, respectively, is proposed. A fast loop searching is proposed to link the bag-of-words features and histogram for higher accuracy, and it splits the images into multiple grids for high parallelism;meanwhile, a DNN feature extractor is utilized for further verification. A loop state control method based on a finite state machine to control these tasks is designed, wherein the loop closure detection is described as a context-related procedure. The framework is implemented on a real machine, and the top-2 best accuracy and fastest execution time of 80-543 frames per second (min: 1.84ms, and max: 12.45ms) are achieved on several public benchmarks compared with some existing algorithms.

关键词： image recognition Mobile robots Automata theory Computer vision and image processing techniques Machine learning (artificial intelligence) Neural nets

来源：评论

学校读者我要写书评

暂无评论

Improving the efficiency of graph algorithm executions on high-performance computing

引用

CONCURRENCY AND COMPUTATION-PRACTICE & ExPERIENCE 2023年第18期35卷

作者： Moori, Marcelo K. Rocha, Hiago Mayk G. de A. Schwarzrock, Janaina Lorenzon, Arthur F. Beck, Antonio Carlos S. Univ Fed Rio Grande do Sul Inst Informat Porto Alegre RS Brazil Fed Univ Pampa Optimizat Syst Lab Alegrete RS Brazil

The growing need for extracting information from large graphs has been pushing the development of parallel graph algorithms. However, the highly irregular structure of the real-world graphs limits the performance and energy improvements of graph applications. In this paper, we show that, in most cases, using all the available cores of the multiprocessor is not the best option in terms of the aforementioned non-functional requirements. Based on that, we propose GraphKat, a framework that enables the simultaneous processing of several algorithms/graphs instead of executing them serially (i.e., one after another), increasing efficiency in terms of performance and energy. GraphKat works in two steps: (i) it characterizes the graph applications with a specific number of threads based on their efficiency levels;and (ii) it defines the execution order of all graph applications in the target system. Experimental results on three multicore processors (Intel and AMD) show that GraphKat improves the overall system's efficiency related to performance (up to 434.26x$$ 434.26\times $$) and energy-saving (up to 245.21x$$ \times $$), and reduces the graph applications' execution time (up to 17.70x$$ 17.70\times $$) and energy consumption (up to 6.64x$$ \times $$) compared to the default execution of parallel applications on HPC systems.

关键词： graph analytics parallel graph processing multiprogramming system efficiency energy-saving

来源：评论

学校读者我要写书评

暂无评论

Highly parallel Vector Radix FFT for High Throughput Video applications

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-ExPRESS BRIEFS 2020年第10期67卷 2114-2118页

作者： Unnikrishnan, Supriya Sreelekha, G. Natl Inst Technol Dept Elect & Commun Kozhikode 673601 India

The Vector Radix Fast Fourier Transform, with the inherent amenity for parallel implementation is very favourable for high throughput video processing applications. The conventional implementation of two-dimensional Fast Fourier Transform as one dimensional transforms of rows and columns can be replaced with this approach. This brief presents a novel Single Instruction Multiple Data architecture for the 8 x 8 vector radix Fast Fourier Transform implemented in Field-Programmable Gate Array with Digital Signal processing Slice as the processing element. The performance metrics of the design is compared to the two dimensional Fast Fourier Transform implemented using one dimensional Fast Fourier Transform Intellectual Property from xilinx. The analysis demonstrates the dominance of the design for high throughput low latency video applications.

关键词： Throughput Arrays Field programmable gate arrays Signal processing algorithms parallel processing Process control FFT vector radix SIMD

来源：评论

学校读者我要写书评

暂无评论

Feluca: A Two-Stage Graph Coloring Algorithm With Color-Centric Paradigm on GPU

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED systems 2021年第1期32卷 160-173页

作者： Zheng, Zhigao Shi, xuanhua He, Ligang Jin, Hai Wei, Shuo Dai, Hulin Peng, xuan Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Serv Comp Technol & Syst Lab Wuhan 430074 Peoples R China Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England

There are great challenges in performing graph coloring on GPU in general. First, the long-tail problem exists in the recursion algorithm because the conflict (i.e., different threads assign the adjacent nodes to the same color) becomes more likely to occur as the number of iterations increases. Second, it is hard to parallelize the sequential spread algorithm because the color allocation depends on the adjoining iteration. Third, the atomic operation is widely used on GPU to maintain the color list, which can greatly reduce the efficiency of GPU threads. In this article, we propose a two-stage high-performance graph coloring algorithm, called Feluca, aiming to address the above challenges. Feluca combines the recursion-based method with the sequential spread-based method. In the first stage, Feluca uses a recursive routine to color a majority of vertices in the graph. Then, it switches to the sequential spread method to color the remaining vertices in order to avoid the conflicts of the recursive algorithm. Moreover, the following techniques are proposed to further improve the graph coloring performance. i) A new method is proposed to eliminate the cycles in the graph;ii) a top-down scheme is developed to avoid the atomic operation originally required for color selection;and iii) a novel color-centric coloring paradigm is designed to improve the degree of parallelism for the sequential spread part. All these newly developed techniques, together with further GPU-specific optimizations such as coalesced memory access, comprise an efficient parallel graph coloring solution in Feluca. We have conducted extensive experiments on NVIDIA GPU. The results show that Feluca can achieve 1.19 - 8.39x speedup over the state-of-the-art algorithms.

关键词： Color Graphics processing units image color analysis Task analysis parallel processing Computational modeling Synchronization Graph coloring GPGPU parallelism color-centric paradigm pipeline

来源：评论

学校读者我要写书评

暂无评论

Automatic optical inspection platform for real-time surface defects detection on plane optical components based on semantic segmentation

引用

APPLIED OPTICS 2021年第19期60卷 5496-5506页

作者： Karangwa, Jules Kong, Linghua Yi, Dingrong Zheng, Jishi Fujian Univ Technol Internet Things Lab Dept Mech Engn Fac Mech Engn Fuzhou 350000 Peoples R China Huaqiao Univ Coll Mech Engn & Automat Xiamen 361021 Peoples R China Fujian Univ Technol Coll Informat Sci & Engn Fuzhou 350000 Peoples R China

The tendency to increase the accuracy and quality of optical parts inspection can be observed all over the world. The imperfection of manufacturing techniques can cause different defects on the optical component surface, making surface defects inspection a crucial part of the manufacturing of optical components. Currently, the inspection of lenses, filters, mirrors, and other optical components is performed by human inspectors. However, human-based inspections are time-consuming, subjective, and incompatible with a highly efficient high-quality digital workflow. Moreover, they cannot meet the complex criteria of ISO 10110-7 for the quality pass and fail optical element samples. To meet the high demand for high-quality products, intelligent visual inspection systems are being used in many manufacturing processes. Automated surface imperfection detection based on machine learning has become a fascinating and promising area of research, with a great direct impact on different visual inspection applications. In this paper, an optical inspection platform combining parallel deep learning-based image-processing approaches with a high-resolution optomechanical module was developed to detect surface defects on optical plane components. The system involves the mechanical modules, the illumination and imaging modules, and the machine vision algorithm. Dark-field images were acquired using a 2448 x 2048-pixel line-scanning CMOS camera with 3.45 mu m per-pixel resolution. Convolutional neural networks and semantic segmentation were used for a machine vision algorithm to detect and classify defects on captured images of optical bandpass filters. The experimental results on different bandpass filter samples have shown the best performance compared to traditional methods by reaching an impressive detection speed of 0.07 s per image and an overall detection pixel accuracy of 0.923. (C) 2021 Optical Society of America

关键词： Bandpass filters CMOS cameras Complementary metal oxide semiconductors image processing Optical components Optical elements

来源：评论

学校读者我要写书评

暂无评论

Algorithm for the automated determination of heating areas during metal processing with numerically controlled machines 10

Algorithm for the automated determination of heating areas d...

引用

Conference on Dimensional Optical Metrology and Inspection for Practical applications x

作者： Semenishchev, E. Voronin, V. Agaian, S. Alepko, A. Zelensky, A. Moscow State Technol Univ STANKIN 1a Vadkovsky Moscow 127055 Russia CUNY Dept Comp Sci New York NY 10314 USA

ISBN: (纸本)9781510643024

The article developed an approach to automated analysis images obtained in the visible and thermal imaging range by a system consisting of two separate cameras. For the generated images, a technique is proposed for the parallel application of algorithms for primary data processing (filtering and blur restoration method), searching for communication elements between data and performing geometric transformations over them, necessary for their combination. To identify elements with elevated temperatures, a primary (normal) thermal gradient mask is created. For simplicity, the resulting mask image is simplified. The simplification method is based on a nonlinear change in the image's bitness by analyzing histograms of color gradients. Next, a mask of threshold values for objects recorded by the optical system is formed. The paper proposes an algorithm for the averaged comparison of the received data and identifying areas where the values are exceeded. The advantage of the developed approach is its versatility. The use of one tuned system makes it possible to signal the cutting tool's wear, the presence of inclusions (inhomogeneities) in the workpiece part, wear of the bearings or elements of the robotic complex (machine tool). The set of test data provides an example of applying the proposed approach for analyzing the production process of cutting metal using a waterjet machine and milling a part on a numerically controlled machine.

关键词： local features thermal images IR denoising

来源：评论

学校读者我要写书评

暂无评论

High Performance Spatial and Spatio-Temporal Big Data processing

High Performance Spatial and Spatio-Temporal Big Data Proces...

引用

作者： Baig, Furqan State University of New York at Stony Brook

学位级别：Ph.D.

This dissertation presents our research and development works to address the challenges for delivering effective, scalable, and high performance methods and systems for managing, and querying complex spatial and spatio-temporal big data at multiple dimensions. This is driven mainly by big data problems emerging from geospatial applications, medical image analysis, satellite imaging, weather analytics, and collaborative spatial data collection. Managing and analyzing such data poses major challenges, including explosion of data volume, an unprecedented rate of data generation, and high complexity of handling spatial and/or temporal dynamics. Traditional spatial data processing algorithms and data structures have been developed mostly for linear processing. Despite the need, these are not optimized for modern requirements of big data processing. To this end, we present strategies for adapting spatial and spatio-temporal principles and methods to the parallel and distributed domain. In particular, we approached the problem from three different aspects. In distributed domain, recent attempts have proposed Hadoop based strategies to accelerate big spatial data processing. Hadoop based systems, however, rely on disk IO, fairly limiting system performance. Apache Spark, on the other hand, is a widely popular framework, based on similar distributed principles, providing iterative in-memory processing. Despite their efficiency, Spark based systems are oblivious to spatial characteristics and provide limited memory optimizations catering to spatial data. To address these, we designed and implemented SparkGIS; which not only provid in-memory spatial querying capabilities but also introduce a novel resource-aware dynamic query re-writing mechanism to efficiently manage distributed resources for large spatial workloads. Spatial processing is inherently compute intensive due to its complexity and multi-dimensional properties. While SparkGIS addresses in-memory aspects of spatial

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid FPGA-GPU-based Hardware Accelerator for High Throughput 2D Electrical Impedance Tomography

TechRxiv

引用

TechRxiv 2023年

作者： Tiwari, Varun Kumar Meribout, Mahmoud Peña Herrera, Juan Pablo Najeeb, Asma Baobaid, Mahfoudh Awadh Adeyemi, Idowu Khalifa University United Arab Emirates

A high-resolution two-dimensional (2D) electrical impedance tomography (EIT) system requires a larger number of electrodes and a finer mesh than its traditional counterpart. This increases the required number of measurements and, in turn, the amount of computation for the image reconstruction. Given the inverse and ill-posed nature of the EIT systems, they require a high signal-to-noise ratio (SNR) acquisition system as well as a high-precision hardware accelerator platform. In this paper, we present a field programmable gate array (FPGA)-based acquisition system with a tunable single-frequency current source that can reach an acquisition speed of more than 500 and 2400 frames per second (fps) for an excitation signal frequency of 500 kHz using 32 and 16 electrodes, respectively. The data processing and reconstruction are carried out using the most recent embedded Graphical processing Unit (GPU, Nvidia Jetson Orin) by utilizing multiple Cuda cores to perform parallel high-speed 2D image reconstruction. Five different algorithms, namely linear back projection (LBP), Tikhonov regularization (TK), one-step Gauss Newton (GN), Landweber (LW), and iterative Tikhonov (ITK), were used for investigation. A gain in speed-up of at least 4 times was observed over the traditional implementations on recent general-purpose computers (PCs). Extensive experiments indicate that the proposed system can yield a throughput of more than 2500 fps for a 16-electrode system with around 8192 mesh elements. This paves the way for EIT systems to be potentially used in high-speed imaging applications as well as in 3D EIT applications which involve even larger amount of mesh elements. © 2023, CC BY.

关键词： Graphics processing unit

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：