检索结果-内蒙古大学图书馆

Unsafe-Net: YOLO v4 and ConvLSTM based computer vision system for real-time detection of unsafe behaviours in workplace

引用

Multimedia Tools and Applications 2024年 1-27页

作者： Önal, Oğuzhan Dandıl, Emre Department of Electronic and Automation Vocational School Bilecik Seyh Edebali University Bilecik Turkey Department of Computer Engineering Faculty of Engineering Bilecik Seyh Edebali University Bilecik Turkey

Unsafe behaviour is a leading cause of death or injury in the workplace, including many accidents. Despite regular safety inspections in workplaces, many accidents occur as a result of breaches of occupational health and safety protocols. In these environments, despite efforts to prevent accidents and losses in hazardous environments, human error cannot be completely eliminated. In particular, in computer-based solutions, automated behaviour detection has low accuracy, is very costly, not real-time and requires a lot of time. In this study, we propose Unsafe-Net, a hybrid computer vision approach using deep learning models for real-time classification of unsafe behaviours in workplace. For the Unsafe-Net, a dataset is first specifically created by capturing 39 days of video footage from a factory. Using this dataset, YOLO v4 and ConvLSTM methods are combined for object detection and video understanding to achieve fast and accurate results. In the experimental studies, the classification accuracy of unsafe behaviours using the proposed Unsafe-Net method is 95.81% and the average time for action recognition from videos is 0.14 s. In addition, the Unsafe-Net has increased the real-time detection speed by reducing the average video duration to 1.87 s. In addition, the system is installed in a real-time working environment in the factory and employees are immediately alerted by the system, both audibly and visually, when unsafe behaviour occurs. As a result of the installation of the system in the factory environment, it has been determined that the recurrence rate of unsafe behaviour has been reduced by approximately 75%. © The Author(s) 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multispectral point cloud superpoint segmentation

引用

Science China(Technological Sciences) 2024年第4期67卷 1270-1281页

作者： WANG QingWang WANG MingYe ZHANG ZiFeng SONG Jian ZENG Kai SHEN Tao GU YanFeng Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Computer Technologies Application Kunming 650500China School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150001China

The multitude of airborne point clouds limits the point cloud processing *** are grouped based on similar points,which can effectively alleviate the demand for computing resources and improve processing ***,existing superpoint segmentation methods focus only on local geometric structures,resulting in inconsistent spectral features of points within a *** feature inconsistencies degrade the performance of subsequent ***,this study proposes a novel Superpoint Segmentation method that jointly utilizes spatial Geometric and Spectral Information for multispectral point cloud superpoint segmentation(GSI-SS).Specifically,a similarity metric that combines spatial geometry and spectral information is proposed to facilitate the consistency of geometric structures and object attributes within segmented *** the formation of the primary superpoints,an intersuperpoint pointexchange mechanism that maximizes feature consistency within the final superpoints is *** are conducted on two real multispectral point cloud datasets,and the proposed method achieved higher recall,precision,F score,and lower global consistency and feature classification *** experimental results demonstrate the superiority of the proposed GSI-SS over several state-of-the-art methods.

关键词： multispectral point cloud superpoint segmentation over-segmentation spatial-spectral joint metric

来源：评论

学校读者我要写书评

暂无评论

Auto-3D-house Design from Structured User Requirements

引用

Machine Intelligence Research 2025年第2期22卷 368-385页

作者： Minkui Tan Qi Chen Zixiong Huang Qi Wu Yuanqing Li Jiaqiu Zhou School of Software Engineering South China University of TechnologyGuangzhou 510006China Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide SA 5005Australia School of Automation Science and Engineering South China University of TechnologyGuangzhou 510006China

We study the task of automated house design,which aims to automatically generate 3D houses from user ***,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user *** address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,*** the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of *** addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary ***,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline ***,we render 3D houses according to the given style requirements in a rule-based *** on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.

关键词： Automated house design user requirements understanding outline processing layout generation graph feature generation.

来源：评论

学校读者我要写书评

暂无评论

A Simplified-Model Predictive Controller Design for a Four-Wheel Omnidirectional Robot 1

引用

25th International Symposium on Measurement and Control in Robotics, ISMCR 2023

作者： Mocanu, Razvan Achirei, Stefan Dosoftei, Catalin Popovici, Tudor Faculty of Automation Control and Computer Engineering "Gheorghe Asachi" Technical University of Iasi Iasi700050 Romania

ISBN: (数字)9783031510854

ISBN: (纸本)9783031510847

This study introduces a model-based predictive controller to drive an omnidirectional robot to a specific location within a logistic environment. An object map is obtained from a LIDAR sensor. The proposed control structure enhances the safety, optimality, and efficiency of the trajectory of the omnidirectional mobile robot. The study employs simulation techniques of the kinematics and dynamics of the robot to assess the efficacy of a predictive control approach. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Small-Signal and Transient Stability Investigation of Inverter Grid Synchronization 27

Small-Signal and Transient Stability Investigation of Invert...

引用

27th International Conference on Circuits, Systems, Communications and computers, CSCC 2023

作者： Scholey, Alexander Jeinsch, Torsten University of Rostock Institute of Automation Faculty of Computer Science and Electrical Engineering Germany

ISBN: (纸本)9798350337594

Grid synchronisation is essential for grid following inverter control. Typically, a phase-locked loop (PLL) is used to perform the synchronisation, but it is known that the PLL can fail to synchronise with the grid in weak grid scenarios. Although there have been many studies on this topic which relate the grid impedance, the grid voltage and the PLL parameterisation to the grid synchronisation, comprehensive analyses are difficult due to the nonlinear nature of the underlying system. Therefore, the exact relationships remain unclear. This paper investigates the stability of PLL-based grid synchronisation for a grid-side inverter with LC-type output filter and RL-type grid impedance. An analytical steady-state solution is presented, which is used for linearization and evaluation of the small-signal stability. Additionally, the transient stability with consideration of nonlinearities is investigated and a condition for stability of the PLL-based grid synchronization in the transient case is derived. The results are validated by numerical simulations. © 2023 IEEE.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Fast Algorithm for Dynamic Range Expansion of Images in Optoelectronic Measurement Systems 16

Fast Algorithm for Dynamic Range Expansion of Images in Opto...

引用

16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument engineering, APEIE 2023

作者： Guzhov, Vladimir I. Shperling, Vladimir K. Ilinykh, Sergey P. Khaidukov, Dmitry S. Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350330885

The paper proposes a new fast method for increasing the dynamic range of brightness of images projected onto an object and registered by an optoelectronic system. The influence of photon noise on the accuracy of brightness values determination is analyzed. An algorithm realizing the increase of the dynamic range of brightness of images registered by the optoelectronic system is proposed. For this purpose, a three-color RGB image is projected onto an object. Each channel contains encoded information about the brightness field in one of the selected modules of the residual class system. An experimental validation of the proposed algorithm is carried out. The dynamic range extension up to 20 binary digits of digital image digitization is achieved. The speed of data processing was increased several times due to combining several test images into one and using a cascade scheme of their processing. © 2023 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Computational-Heuristic Algorithm for Tomographic Solution of Industrial Flaw Detection Problems 16

Computational-Heuristic Algorithm for Tomographic Solution o...

引用

16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument engineering, APEIE 2023

作者： Peshkov, Alexander V. Zerkal, Sergey M. Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350330885

This paper presents the results of the development and study of the application of a computational heuristic algorithm for industrial tomography based on the use of a reference sample of an industrial product. Thus, based on a priori information about the reference sample of the product, it is possible to build a local tomographic reconstruction from limited initial data due to the selective sensitivity of the object under study to probing radiation. This approach is consistent with the principle of "strong methods", which has recently proven itself well in the field of artificial intelligence. The results obtained form the basis for the development of an appropriate information and computing technology, including algorithmic and software for computer processing and interpretation of measurement data. The paper also presents the designed architecture and software prototype with a graphical interface that implements local tomographic reconstruction based on the proposed algorithms. The presented experimental results testify to the efficiency and speed of the proposed algorithm in comparison with the classical algorithm of computed tomography. The proposed algorithm also makes it possible to detect defects of small thickness, when the classical tomography algorithm cannot cope. From an applied point of view, this study is of interest in the heuristic search for a defect in a product model and allows us to conclude that it is promising in the field of industrial flaw detection. © 2023 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Feasibility of Spine Segmentation in ML-Based Recognition of Vertebrae in X-Ray Images 16

Feasibility of Spine Segmentation in ML-Based Recognition of...

引用

16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument engineering, APEIE 2023

作者： Bakaev, Maxim A. Kobzev, Denis A. Piletskii, Dmitry K. Yakimenko, Alexander A. Gladkov, Alexander V. Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350330885

Medicine remains one of the data-scarce domains, with typical datasets size not exceeding hundreds of thousands items. Correspondingly, straightforward application of end-to-end Deep Learning (ML) methods for Medical Imaging is often problematic. Carefully constructed pipelines that involve filter-based enhancement of raw images allow better outcome and leave more room for feasible data augmentation. In our paper, we explore and develop computer Vision approaches for vertebrae recognition on a limited dataset of X-ray images of human spine. In particular, we test several pre-processing filters, of which Adaptive Histogram Equalization demonstrates the highest accuracy of 85.8% in a naïve model using the popular U-Net architecture. Further, we put forward the mechanism for the automated spine area cropping based on brightness cut-off. This additional step in the pipeline allowed improving the accuracy to 89.9%, which is comparable with the accuracy obtained for MRI images of higher quality. We plan to further increase the prediction quality of the model via spine segmentation into about 20 individual vertebrae and 8-fold data augmentation. The ultimate goal is improving the identification of the vertebrae corners, which currently has the relative error of 4.36%. Our intermediate results reported in the current paper might be of interest to ML engineers who pick the steps for X-ray spine images processing pipelines. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

On the Use of Quality Flags for Digital Transformers in the Sampled Values Protocol IEC 61850 25

On the Use of Quality Flags for Digital Transformers in the ...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Plotnikov, Igor V. Ponomarev, Stanislav V. Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia Faculty of Radio Engineering and Electronics Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350389234

This work is devoted to a detailed description of the quality flags of the Sampled Values protocol of the IEC 61850 standard for digital current and voltage transformers. The relevance of this article is due to the fact that the quality flags are not strictly and in detail described in the standard itself, therefore, manufacturers of equipment for digital current and voltage transformers fill in the quality flags if there are problems with data or device at their own discretion. The first part provides information on the structure of interaction between elements of a digital measuring system, describes the advantages of using quality flags in digital data transmission protocols relative to traditional transformers. In the second part, special attention is paid to the interpretation of quality flags in the IEC 61850 standard and the lack of a clear formulation of their applicability in real devices. The third part offers new interpretation of these quality flags with an example of use based on the developed measuring system. At the end of the article, evidence of the correct operation of the described quality flags is provided using a test bench and equipment for analyzing the Sampled Values protocol. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Development of a Software Complex for Energy Facilities Based on an Embedded Linux System 25

Development of a Software Complex for Energy Facilities Base...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Osyko, Georgii S. Ponomarev, Stanislav V. Faculty of Automation and Computer Engineering Novosibirsk State Technical University Novosibirsk Russia Faculty of Radio Engineering and Electronics Novosibirsk State Technical University Novosibirsk Russia

ISBN: (纸本)9798350389234

Supervisory Control and Data Acquisition is the main and currently remains the most promising method of automated control of complex dynamic systems. In this article the development of a software package installed on embedded Linux-based systems for managing and monitoring energy facilities is discussed. The main part of the article consists of 3 sections. The first section describes the structural diagrams of the entire software package. The UML diagrams of individual software modules designed for processing and transferring data to other devices are presented. The second section describes the structure and appearance of the web interface, describes possible scenarios for user interaction with the interface. At the end, the results of testing performed using a specially created test bench are presented. The entire software base of the developed complex was implemented by the authors of this article. The developed software package has unique characteristics in terms of functionality in conditions of limited resources, and therefore is fully suitable for managing energy facilities based on embedded systems. © 2024 IEEE.

关键词： Embedded software

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：