检索结果-内蒙古大学图书馆

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Filip Zorić Ana Milas Tamara Petrović Zdenko Kovačić Matko Orsag Faculty of Electrical Engineering and Computing LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Zagreb Croatia

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

Roads, bridges, tunnels, railways and canals are crucial for the transportation of goods and people in modern society. Modern infrastructure is subject to damage and requires therefore regular inspection and maintenance to remain safe and functional. While this can be done manually, large parts of the mentioned infrastructure are hardly accessible, which is a main motivational factor for the use of multi-rotor aerial vehicles (MAV s) for inspection and maintenance tasks. MAV s, paired with novel deep learning computer vision techniques, such as instance segmentation, are emerging as an obvious choice for automating certain parts of structural health monitoring (SHM). In this manuscript, we provide an overview of available SHM datasets and how they can be utilized for the task of autonomous crack detection. We use available datasets to train and compare two neural network architectures for instance segmentation. The segmented crack instances are then localized in a global coordinate frame to perform autonomous mapping of the potentially dangerous infrastructure defects. Experimental studies demonstrate the effectiveness of the proposed SHM approach, which results in precisely localized infrastructure defects marked on the global map.

关键词： Instance segmentation Irrigation Structural panels Neural networks Transportation Inspection Rail transportation

来源：评论

学校读者我要写书评

暂无评论

Camera-based light source localization for precise luminous intensity measurement of airport lamps

Camera-based light source localization for precise luminous ...

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Kacper Podbucki Tomasz Marciniak Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Jana Pawła II 24 Poznan University of Technology Poznań Poland

ISBN: (数字)9788362065486

ISBN: (纸本)9798350373806

Measuring luminous intensity using electronic sensors requires their precise positioning. In the case of mobile measurement platforms, it is important to detect the light source and thus determine the correct direction of movement of the measuring device. This article presents research on a solution for the initial detection of glowing airport lamps based on camera images. The impact of the selection of parameters and image processing methods on the prepared data set was assessed. The histogram filtration method was introduced to improve the effectiveness of airport lamp localization. The proposed solution was investigated in different weather and daytime conditions. The overall accuracy of the proposed solution is more than ${9 0 \%}$.

关键词： Location awareness Histograms Accuracy Filtration Signal processing algorithms Airports Sensors Meteorology Light sources Erosion

来源：评论

学校读者我要写书评

暂无评论

Foreign Object Debris detection at aerodromes using YOLOv5

Foreign Object Debris detection at aerodromes using YOLOv5

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Jakub Suder Tomasz Marciniak Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Jana Pawła II 24 Poznan University of Technology Poznań Poland

ISBN: (数字)9788362065486

ISBN: (纸本)9798350373806

The latest EASA recommendations from 2024 indicate the possibility of using machine learning techniques in aerodrome monitoring. The aim of the work was to analyze solutions and prepare FOD (Foreign Object Debris) object detection software on aerodromes. In order to implement the issue, a dataset of photos and video recordings for testing algorithms was developed. The dataset consists of 1480 photos showing FOD at aerodromes and photos of the runway itself, according to EASA and FAA recommendations. FOD detection was implemented using a classical, k-means method and effective YOLOv5.

关键词： YOLO Reviews Neural networks Software algorithms Signal processing algorithms Software Real-time systems Video recording Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Improving the Efficiency of Mechatronic systems Based on Optimization Principles

Improving the Efficiency of Mechatronic Systems Based on Opt...

引用

2021 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", T and QM and IS 2021

作者： Marusina, Maria Ya. Silaev, Alexei A. ITMO University Faculty of Control Systems and Robotics St. Petersburg Russia

ISBN: (纸本)9781665433020

A method of increasing the efficiency of various robotic and mechatronic systems based on the method of analysis and optimization synthesis is presented. The proposed method is implemented by the example of improving the efficiency of the functioning of individual components that are part of various mechatronic systems. In particular, the article presents the results of modeling the magnetic field of an electric motor using the finite element analysis program FEMM. Maintaining a high efficiency of the electric motor in an extended range of rotation speeds is ensured by turning the rotor magnets and introducing an angle of advance of the current supply to the stator windings. © 2021 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks for Early Prediction of Alzheimer's Diseases

Convolutional Neural Networks for Early Prediction of Alzhei...

引用

2021 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", T and QM and IS 2021

作者： Marusina, Maria Ya. Bukhalov, Alexei D. ITMO University Faculty of Control Systems and Robotics St. Petersburg Russia

ISBN: (纸本)9781665433020

It has now been confirmed that the main cause of dementia is Alzheimer's disease. It is characterized as neurodegenerative, chronic, progressive, and belonging to the category of incurable. The clinical picture of the disease's manifestation includes cognitive dysfunction, amnesia, gradual loss of multiple brain functions and the lack independence in daily functioning. To reduce the risk of its occurrence, it is necessary to identify the MCI in advance. In our work, we aim to describe a method that helps to detect signs of early onset of AD with the help of CNN. Sagittal, axial, and coronary MRI slices were used to train CNN models for a number of classification tasks;then these CNN models were combined into one group. The paper also discusses image and dataset preprocessing. The method can find its application in medicine for the delivery of a diagnosis at stages when the changes in the brain are so small that a medical expert cannot yet detect them. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning Method for Selection of Cascade PLI Filter in Design of a Computerized ECG Signal Processing System

Application of Machine Learning Method for Selection of Casc...

引用

2021 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", T and QM and IS 2021

作者： Altay, Yeldos A. ITMO University Faculty Control Systems and Robotics St. Petersburg Russia

ISBN: (纸本)9781665433020

This article presents the results of the study of cascade PLI filters to justify the selection damping coefficient in order to increase the noise resistance system and create a software complex for ECG signal processing. To justify the selection of this coefficient, it is proposed to apply the supervised machine learning method. Theoretically significant analytical dependences processing system indicators on the selection damping coefficient of cascade PLI filters are obtained. It was found that at low values of this coefficient, the selectivity of narrow-band cascade PLI filters improves, and the quality indicators of ECG signal processing increase. Based on the analysis characteristics synthesized cascade PLI filter and the analysis of the processing results, the damping value of system xi=0.1 is justified and selected to create a software package. To confirm the practical significance of the improved processing approach, the performance software package, which combines the PLI filtration system, has been demonstrated. It is shown that the improved (developed) approach allows filtering natural power line interference with harmonics at frequencies of 50 Hz and 100 Hz and opens up new possibilities for ECG signal processing. © 2021 IEEE.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Programming by Demonstration Methods: Kinesthetic Teaching vs Human Demonstration

arXiv

引用

arXiv 2024年

作者： Maric, Bruno Zoric, Filip Petric, Frano Orsag, Matko The LARICS Laboratory for Robotics and Intelligent Control Systems University of Zagreb Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

Programming by demonstration (PbD) is a simple and efficient way to program robots without explicit robot programming. PbD enables unskilled operators to easily demonstrate and guide different robots to execute task. In this paper we present comparison of demonstration methods with comprehensive user study. Each participant had to demonstrate drawing simple pattern with human demonstration using virtual marker and kinesthetic teaching with robot manipulator. To evaluate differences between demonstration methods, we conducted user study with 24 participants which filled out NASA raw task load index (rTLX) and system usability scale (SUS). We also evaluated similarity of the executed trajectories to measure difference between demonstrated and ideal trajectory. We concluded study with finding that human demonstration using a virtual marker is on average 8 times faster, superior in terms of quality and imposes 2 times less overall workload than kinesthetic teaching. © 2024, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Automated Suckering of Vines with a Mobile Robot and a Torque-controlled Suckering Tool 5

Automated Suckering of Vines with a Mobile Robot and a Torqu...

引用

5th IEEE International Conference on Smart systems and Technologies, SST 2022

作者： Stuhne, Dario Vatavuk, Ivo Hrabar, Ivan Vasiljević, Goran Kovačić, Zdenko University of Zagreb Faculty of EE&C Zagreb Croatia University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

The research presented in this paper focuses on the development of fully automated and autonomous vine suckering, a seasonal viticulture activity required to remove all unwanted shoots from the vine trunks. This requires human workers to do a lot of strenuous work, often using only their hands or tools such as clippers or shears. The suckering is done during the early growing season (usually April-May) to provide more energy, water, and nutrients to the main shoots. Commercially available suckering machines appear to be a large-scale solution. However, their performance varies between 10% and 85% and their purely mechanical nature can easily cause damage to the vines. In this paper, we present a concept for autonomous suckering using a mobile robot equipped with a special suckering tool driven by a torque-controlled DC motor that protects the vine from damage. The proposed suckering system was designed, analysed and experimentally validated in a real vineyard. The results showed that the system was able to remove about two thirds of the unwanted shoots, reaching a suckering rate of more than 86 vines per hour. © 2022 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Procedural Generation of Synthetic Dataset for Robotic Applications in Sweet Pepper Cultivation 5

Procedural Generation of Synthetic Dataset for Robotic Appli...

引用

5th IEEE International Conference on Smart systems and Technologies, SST 2022

作者： Vuletić, Jelena Polić, Marsela Orsag, Matko University of Zagreb Faculty of EE&C Zagreb Croatia University of Zagreb LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing Zagreb10000 Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

In this paper, a deep learning based object detection model is developed for robotic applications in structured agricultural cultivation of sweet peppers (Capsicum annuum). We propose a realistic simulation based method for procedural generation of a labeled sweet pepper dataset. Realistic 3D models of fruit, leaves, and other relevant plant body parts are generated through photogrammetry, enabling generation of a large and relevant dataset. The dataset is labeled for both object detection and semantic segmentation by scene rendering in multiple layers and using artificial depth information. Smart augmentation techniques are deployed in procedural generation, as well as label filtering techniques for more realistic dataset labels. A MobileNet-SSD based deep learning model is trained through transfer learning on the generated dataset. The trained model is tested both in simulated environment, as well as on a relevant real-world setup. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Fast Prototyping of In-Pavement Airport Navigation Lamp Prism Classification

Fast Prototyping of In-Pavement Airport Navigation Lamp Pris...

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Jakub Suder Tomasz Marciniak Division of Electronic Systems and Signal Processing Poznan University of Technology Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Poznań Poland

The paper presents an analysis of fast selection of neural network for the purpose of visual analysis of mechanical wear on prism lenses of in-pavement airport navigational lighting systems. This issue is particularly important in terms of aviation safety and navigational lighting control, regulated by EASA and ICAO. The article is the next stage of the development of the system for the vision control of lamps, in which the concept of using a different neural network with an increased data set prepared by the authors is presented. The Deep Network Designer tool included in the Matlab 2022b environment was used. The solution using the GoogLeNet neural network allows for the classification of lamps with an accuracy of 88.37%.

关键词：

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：