检索结果-内蒙古大学图书馆

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

Segmentation of Retina Vessels in 2D OCT-Reconstructed Fundus Images with 3D UNet

Segmentation of Retina Vessels in 2D OCT-Reconstructed Fundu...

引用

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

作者： Tomasz Marciniak Agnieszka Stankiewicz Przemysław Zaradzki Department of Control Robotics and Electrical Engineering Division of Electronic Systems and Signal Processing Institute of Automatic Control and Robotics Poznan University of Technology Poznan Poland

This paper presents an analysis of the effectiveness of blood vessel segmentation in human retinal images. The segmentation process was carried out for three-dimensional optical coherence tomography (OCT) scans using the author’s publicly available CAVRI-C database. A 3D version of the U-Net artificial neural network was used. Various dimensions of the input blocks were investigated to determine their influence on the segmentation process. The effectiveness of the proposed solutions was evaluated using various metrics and the results obtained were compared with the 2D solution, also based on neural networks. The use of the proposed solutions allowed us to improve the segmentation even by 15% (in the case of the F1-score).

关键词：

来源：评论

学校读者我要写书评

暂无评论

PointNetPGAP-SLC: A 3D LiDAR-based Place Recognition Approach with Segment-level Consistency Training for Mobile Robots in Horticulture

arXiv

引用

arXiv 2024年

作者： Barros, T. Garrote, L. Conde, P. Coombes, M.J. Liu, C. Premebida, C. Nunes, U.J. University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Portugal Dept. of Aeronautical and Automotive Engineering LUCAS Lab Loughborough University United Kingdom

3D LiDAR-based place recognition remains largely underexplored in horticultural environments, which present unique challenges due to their semi-permeable nature to laser beams. This characteristic often results in highly similar LiDAR scans from adjacent rows, leading to descriptor ambiguity and, consequently, compromised retrieval performance. In this work, we address the challenges of 3D LiDAR place recognition in horticultural environments, particularly focusing on inter-row ambiguity by introducing three key contributions: (i) a novel model, PointNetPGAP, which combines the outputs of two statistically-inspired aggregators into a single descriptor;(ii) a Segment-Level Consistency (SLC) model, used exclusively during training to enhance descriptor robustness;and (iii) the HORTO-3DLM dataset, comprising LiDAR sequences from orchards and strawberry fields. Experimental evaluations conducted on the HORTO-3DLM and KITTI Odometry datasets demonstrate that PointNetPGAP outperforms state-of-the-art models, including OverlapTransformer and PointNetVLAD, particularly when the SLC model is applied. These results underscore the model’s superiority, especially in horticultural environments, by significantly improving retrieval performance in segments with higher ambiguity. The dataset and the code will be made publicly available at https://***/Cybonic/*** © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Methodology for Assessing the Economic Viability of EV Charging Infrastructure in Brazil

A Comprehensive Methodology for Assessing the Economic Viabi...

引用

Smart Power & Internet Energy systems (SPIES), International Conference on

作者： Daywes Pinheiro Neto António Paulo Coimbra Aníbal T. De Almeida Tony R. Almeida Pedro Moura Letícia C. Ucker Raphael A. Gomes Alana S. Magalhães Center for Experimental and Technological Research and Studies Federal Institute of Goiás Brazil Dpt. of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal

ISBN: (数字)9798350368864

ISBN: (纸本)9798350368871

This study proposes a comprehensive methodology to assess the economic viability of electric vehicle (EV) charging infrastructure projects in Brazil, specifically targeting connections with a capacity of up to 112.5 kW, which are subject to flat electricity tariffs. The methodology employs a novel EV energy consumption model, integrates the regulatory framework of net metering and relevant tax considerations, explores the potential cost-saving benefits of photovoltaic (PV) system integration, and utilizes key economic indicators like Net Present Value and Discounted Payback Time to quantify project profitability. By accounting for a set of EV demand scenarios (low, moderate, and high), the methodology provides a multifaceted assessment of project viability. A case study demonstrates the methodology's application, highlighting the potential economic benefits of such investments. The results suggest that the minimum charging service fee required for economic viability ranges from 0.17 to 0.29 USD/kWh, with a clear cost advantage associated with PV integration observed across all scenarios.

关键词： Economics Photovoltaic systems Costs Finance Transportation Tariffs System integration Charging stations Electric vehicle charging Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Bilateral-Head Region-Based Convolutional Neural Networks: A Unified Approach for Incremental Few-Shot Object Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4376-4390页

作者： Li, Yiting Zhu, Haiyue Tian, Sichao Ma, Jun Xiang, Cheng Vadakkepat, Prahlad National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research 138634 Singapore Peking Union Medical College Institute of Medicinal Plant Development Chinese Academy of Medical Sciences Beijing100193 China Robotics and Autonomous Systems Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong SAR Hong Kong Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen Futian518045 China

Practical object detection systems are highly desired to be open-ended for learning on frequently evolved datasets. Moreover, learning with little supervision further adds flexibility for real-world applications such as autonomous driving and robotics, where large-scale datasets could be prohibitive or expensive to obtain. However, continual adaption with small training examples often results in catastrophic forgetting and dramatic overfitting. To address such issues, a compositional learning system is proposed to enable effective incremental object detection from nonstationary and few-shot data streams. First of all, a novel bilateral-head framework is proposed to decouple the representation learning of base (pretrained) and novel (few-shot) classes into separate embedding spaces, which takes care of novel concept integration and base knowledge retention simultaneously. Moreover, to enhance learning stability, a robust parameter updating rule, i.e., recall and progress mechanism, is carried out to constrain the optimization trajectory of sequential model adaption. Beyond that, to enforce intertask class discrimination with little memory burden, we present a between-class regularization method that expands the decision space of few-shot classes for constructing unbiased feature representation. Final, we deeply investigate the incomplete annotation issue considering the realistic scenario of incremental few-shot object detection (iFSOD) and propose a semisupervised object labeling mechanism to accurately recover the missing annotations for previously encountered classes, which further enhances the robustness of the target detector to counteract catastrophic forgetting. Extensive experiments conducted on both Pascal visual object classes dataset (VOC) and microsoft common objects in context dataset (MS-COCO) datasets demonstrate the effectiveness of our method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CUPREDS: Multi-sensor Point Cloud Mapping for Local Navigation

CUPREDS: Multi-sensor Point Cloud Mapping for Local Navigati...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Carlos Tojal Luis Conde Bento Paulo Peixoto Institute of Systems and Robotics University of Coimbra Coimbra Portugal ESTG Polytechnic Institute of Leiria Leiria Portugal Department of Electrical and Computer Engineering University of Coimbra Coimbra Portugal

ISBN: (数字)9798350352344

ISBN: (纸本)9798350352351

Robot mapping usually benefits from the combination of several sensors. However, most algorithms for Simultaneous Localization And Mapping using point clouds only consider a single point cloud as input. There are also scenarios where SLAM is not needed and a simple local map representation without probabilities is preferred, for example due to throughput requirements. For these scenarios, software is needed that combines multiple point clouds into a unified, short-lived, robot-centric representation. Mapping software is only one tool in the software stack and should not compromise other components, which is why its performance-oriented design is of utmost importance. CUPREDS presents a ROS package for local mapping that prioritizes robustness and performance, with minimal overhead for its internal mechanisms.

关键词： Point cloud compression Simultaneous localization and mapping Navigation Software architecture Software algorithms Throughput Software

来源：评论

学校读者我要写书评

暂无评论

Exploring Continuous Awareness Modelling for Improving Worker Safety and Trust*

Exploring Continuous Awareness Modelling for Improving Worke...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Andrey Solovov Mohammad Zarei Vishal Gautam Bruno Ferreira Gustavo Assunção Antonio Marin-Hernandez Paulo Menezes Department of Electrical and Computer Engineering University of Coimbra Coimbra Portugal Institute of Systems and Robotics University of Coimbra Coimbra Portugal Universidad Veracruzana Xalapa Mexico

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

The Industry 5.0 Human-Robot Interaction (HRI) goals have the potential for significantly reducing production costs, but require factory workers to trust that robots will not cause them physical harm when sharing the workspace in order to be achieved. To this end, we propose a model that adjusts the robot’s actions to an estimate of the workers’ awareness of its behavior. Its premise is that mutual awareness should be continuous, and if no recent visual contact has been established, then the robot should adapt its range of motion and speed in order to minimize the intersection between the robot’s space and the worker’s space. On the other hand, if the worker steadily establishes visual contact from times to times, the robot operates under a normal or a faster configuration. After a period of habituation, this awareness model can be further tweaked to continuously improve production times, while improving worker’s safety and trust. We present preliminary results of a pilot study with 32 participants, to asses if the existence of this awareness model impacts the outcomes of the combined task. The obtained tepidly optimistic results are the key to build upon in future designs.

关键词： Visualization Adaptation models Costs Service robots Human-robot interaction Production facilities Safety Motion control Fifth Industrial Revolution

来源：评论

学校读者我要写书评

暂无评论

Instantaneous Center of Rotation Trajectory Tracking of A Novel Five-bar Robotic Exoskeleton for Knee Rehabilitation

Instantaneous Center of Rotation Trajectory Tracking of A No...

引用

International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

作者： Ahmad Abdullah Jaideep Thattamparambil Jayachandran Sheng Quan Xie Aiqin Liu School of Biomedical Sciences University of Leeds Leeds UK Institute of Robotics and Autonomous Systems School of Electronic and Electrical Engineering University of Leeds Leeds UK

ISBN: (数字)9798350391916

ISBN: (纸本)9798350391923

Knee Exoskeletons provide a way to restore the quality of life in people with knee disorders or after injury. One of the major limitations of these exoskeletons is to mimic the natural polycentric knee joint motion. The design and performance analysis of a novel five-bar mechanism is proposed in this study which can be used in a knee exoskeleton. The purpose of this study was to analyze the instantaneous center of rotation trajectory of the five-bar mechanism mimicking the natural knee center of rotation trajectory during sit to stand motion and compare it with similar existing mechanisms. The position analysis of the mechanism in a simplified configuration and the actual hardware configuration was performed for analyzing the center of rotation trajectory, both theoretically and using a dedicated tool respectively. The motion and the center of rotation trajectory of five-bar mechanism was validated, and the results of the study are presented which show the successful tracking of the reference Instantaneous center of rotation with an error as low as 0.14mm for the simplified configuration and 0.24mm for the actual configuration. These results were then compared with different bar mechanisms showing that our five-bar mechanism had better tracking performance among the available rigid mechanisms.

关键词： Torque Mechatronics Trajectory tracking Exoskeletons Hardware Motion capture Trajectory Performance analysis Robots Bars

来源：评论

学校读者我要写书评

暂无评论

Combined Locomotion and Direction Control of Ferrofluidic Robots*

Combined Locomotion and Direction Control of Ferrofluidic Ro...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Qinkai Chen Haozhe Feng Xinjian Fan Lining Sun Zhan Yang Hui Xie School of Mechanical and Electrical Engineering Soochow University Suzhou China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Yikuang Harbin China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

As the characteristics of low invasiveness, good controllability and deformability, ferrofluid robots have enormous potential for technological applications in the medical field. With the volume of ferromagnetic fluid robots increases, a motion control strategy coupled with magnetic moment and gradient force is usually adopted which makes it impossible for the robot to perform complex movements and limits the application of the ferrofluid robot. By designing a control system that decouples magnetic torque and magnetic gradient force, joint control of the locomotion and direction of a ferrofluid robot has been achieved. The results indicate that the miniature ferrofluid robot (MFR) has achieved directional controllable trajectory motion and ultimately achieved autonomous path selection. These extended functions can further promote the medical application of micro robots in closed and complex environments such as human blood vessels.

关键词： Ferrofluid Targeted drug delivery Torque Three-dimensional displays Force Blood vessels Trajectory Motion control Robots Tumors

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Convolutional Neural Network Inference on Low-Power Edge Devices

Benchmarking Convolutional Neural Network Inference on Low-P...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Oscar Ferraz Helder Araujo Vitor Silva Gabriel Falcao Instituto de Telecomunicações Dept. of Electrical and Computer Engineering University of Coimbra Portugal Institute of Systems and Robotics

The massive adoption of IoT devices, the recent developments in the efficiency of AI systems, and the increase of edge computational power, accelerated the deployment of edge AI systems. The implementation of these systems through the use of low-power embedded devices scattered across the edges of a network allows for reduced latency and cost, compared to traditional cloud-based AI computing systems. As a result of the low-complexity AI models and the available low-power embedded systems on the market, this paper provides a comparative study on the inference performance of convolutional neural networks for different edge devices, by exploiting low-power GPUs and dedicated AI hardware. The benchmark results were able to achieve 864 inferences/s for the Jetson AGX Xavier board on a pre-trained SqueezeNet, while reaching a high power efficiency of 52.6 inferences/s per Watt. For the dedicated Movidius neural stick, the system requires only 1.5 W for processing 24.2 inferences/s.

关键词： Performance evaluation Benchmark testing Signal processing Throughput Hardware Convolutional neural networks Internet of Things

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：