检索结果-内蒙古大学图书馆

Road Crack Acquisition and Analysis System Based on Mobile Robot and Deep Learning 11

Road Crack Acquisition and Analysis System Based on Mobile R...

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Zhu, Guijie Fan, Zhun Ma, Peili Huang, Wenning Ye, Zhihao Huang, Mingwei Li, Jiangli Jiang, Zhicheng Zhong, Zhuwei He, Weiyuan Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou515063 China

ISBN: (纸本)9781665425278

In this paper, a road crack acquisition and analysis system based on mobile robot and deep learning is proposed. First, a virtual reality technology-based omnidirectional mobile robot is developed to remotely collect detailed road crack images. Next, an image dataset including different kinds of crack images collected by the mobile robot is constructed and utilized for training and testing a deep convolutional neural network (DCNN) model. Following this, the trained model is used to identify and segment the crack images acquired from the robot, and to facilitate the inspector to know the road surface condition, crack information (crack length, crack width, and crack area) is obtained using an image processing method. Finally, the proposed system and method are applied to a campus road, which realizes the accurate acquisition and analysis of road crack information, thus demonstrating the feasibility and effectiveness of the proposed system and method. © 2021 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Slimming Convolutional Neural Network Based on Attention Mechanism for Pavement Crack Detection 11

Slimming Convolutional Neural Network Based on Attention Mec...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Huang, Wenning Zhu, Guijie Fan, Zhun Li, Wenji Rong, Yibiao Cai, Yuwei Key Lab of Digital Signal and Image Processing of Guangdong Province College of Engineering Shantou University Shantou515063 China

ISBN: (纸本)9781665425278

In recent years, convolutional neural networks (CNNs) have achieved excellent performance in pavement crack segmentation tasks. However, CNNs usually need high computational cost and large storage. As a result, CNN slimming is important for embedded systems with limited resources. Inspired by the channel attention techniques in CNNs, we propose an effective method to slim CNNs based on attention mechanism. The proposed method first removes the unimportant filters and their connecting feature maps according to their attention scales. The retraining process is then performed on the slimmed model to regain performance. The proposed pruning method is easily embedded in common convolutional layers without any dedicated software libraries. Comprehensive experiments show that the proposed method can prune over 40% parameters of CNNs applied on pavement crack segmentation tasks while the deterioration in performance is slight compared with the original UNet architecture. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Knowledge Augmented Attention Gating Embedding for Link Prediction

Knowledge Augmented Attention Gating Embedding for Link Pred...

引用

Asia-Pacific signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Zewei Chen Shuhong Chen Chen Li Xianwei Zheng Minfan He Xutao Li Department of Electronic Engineering Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou China School of Mathematics Foshan University Foshan China

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

Knowledge graphs (KGs) use graphical representations to illustrate relations between entities, forming a structured knowledge base. However, KGs often suffer from incompleteness, lacking some entities and their interactions. Current link prediction technologies based on KG embeddings primarily focus on learning entity features and relation patterns from existing KGs to address the incompleteness issue. Yet, these methods encounter the inherent sparsity issue in KGs—uneven distribution of entity connections and scarcity of direct links. This complexity challenges models in identifying intricate, potential associations, thereby compromising link prediction accuracy and overall model performance. In this paper, we introduce a innovative Knowledge Augmented Attention-based Gating Embedding (KAAGE) framework for link prediction. Our model augments knowledge by reversing relations and triples, then integrates both original and augmented structural data through gating units. Extensive experiments on three established benchmark datasets demonstrate the superiority of KAAGE over current models. Our implementation code is available at https://***/22zwChen/KAAGE

关键词： Codes Fuses Semantics Knowledge based systems Knowledge graphs Information processing Predictive models Benchmark testing Data models Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search Based on Tabu Search and Evolutionary Algorithm 11

Neural Architecture Search Based on Tabu Search and Evolutio...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Fan, Zhun Long, Zhoubin Li, Wenji Wang, Zhaojun Yang, Zhi Wang, Liu Guangdong Province Engineering College Shantou University Department of Key Lab of Digital Signal and Image Processing GuangdongShantou China

ISBN: (纸本)9781665425278

Most existing optimization methods for neural architecture search (NAS), including evolutionary algorithms, reinforcement learning and gradient-based approaches, have not employed memory strategies explicitly, which may lack of efficiency when searching neural architectures. To solve this issue, we propose a new NAS approach by using an evolutionary algorithm which employs a tabu mechanism to help to improve the search efficiency. To be more specific, the individuals of parent population are selected by tournament selection and tabu list. The tournament selection select parent population according to the accuracy of each individual. And the tabu mechanism builds a tabu list to record the chosen operations in the last previous search process, which employs a search memory mechanism to improve the efficiency explicitly. To confirm the superior performance of our approach, a well-designed surrogate model is used to accelerate the process of performance evaluation on CIFAR-10. The comprehensive experimental results show that the proposed method can reach to 2.48% error rate with about 2 GPU days, which demonstrates the superiority of the suggested method. © 2021 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Neural Networks for Automated Echocardiography View Recognition: A Holistic Approach

arXiv

引用

arXiv 2024年

作者： Thomas, Sarina Tiago, Cristiana Andreassen, Børge Solli Aase, Svein Arne Šprem, Jurica Steen, Erik Solberg, Anne Ben-Yosef, Guy Division of Digital Signal and image processing University of Oslo Oslo Norway GE Vingmed Ultrasound GE Healthcare Horten Norway GE Research NiskayunaNY United States

To facilitate diagnosis on cardiac ultrasound (US), clinical practice has established several standard views of the heart, which serve as reference points for diagnostic measurements and define viewports from which images are acquired. Automatic view recognition involves grouping those images into classes of standard views. Although deep learning techniques have been successful in achieving this, they still struggle with fully verifying the suitability of an image for specific measurements due to factors like the correct location, pose, and potential occlusions of cardiac structures. Our approach goes beyond view classification and incorporates a 3D mesh reconstruction of the heart that enables several more downstream tasks, like segmentation and pose estimation. In this work, we explore learning 3D heart meshes via graph convolutions, using similar techniques to learn 3D meshes in natural images, such as human pose estimation. As the availability of fully annotated 3D images is limited, we generate synthetic US images from 3D meshes by training an adversarial denoising diffusion model. Experiments were conducted on synthetic and clinical cases for view recognition and structure detection. The approach yielded good performance on synthetic images and, despite being exclusively trained on synthetic data, it already showed potential when applied to clinical images. With this proof-of-concept, we aim to demonstrate the benefits of graphs to improve cardiac view recognition that can ultimately lead to better efficiency in cardiac diagnosis. Copyright © 2024, The Authors. All rights reserved.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

Exact power pattern bounds for arrays affected by calibration errors and mutual coupling

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Geréb, Gábor Arnestad, Håvard Kjellmo Lønmo, Tor Inge Birkenes Näsholm, Jan Egil Kirkebø Sven Peter Austeng, Andreas University of Oslo Digital Signal Processing and Image Analysis Group Department of Informatics Oslo0316 Norway Kongsberg Discovery AS Strandpromenaden 50 Horten Norway Verda AI 1 Broadway CIC CambridgeMA02142 United States

Interval methods have become popular for finding reliable bounds on power patterns for arrays affected by bounded errors. Such bounds can be used in the evaluation and design of antenna and transducer arrays, such as, to determine the worst-case sidelobe level and identify detrimental error configurations. The uncertainty of the element responses can be represented as regions in the complex plane. Previous interval arithmetic methods either wrap these complex intervals into simple shapes before summing, or approximate the power pattern bounds directly. The bounds given by these methods are relaxed, which makes the evaluation pessimistic. Tenuti et al. addressed this by introducing the polygon arithmetic that can approximate bounds with arbitrary tightness at the cost of significantly increased computational complexity. In the current work, we show how the exact bounds can be achieved, and how the complexity can be reduced. We introduce a generalization of the polygon by "inflating" the vertices. This generalization is named polyarc and can exactly represent complex intervals bounded by arcs and edges. Compared to the polygon, polyarc offers simultaneously tighter bounds and reduced complexity;thereby increasing the utility of the interval arithmetic tolerance analysis in the fields of communication, sensing, and imaging. © 1963-2012 IEEE.

关键词： digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Adaptive Time-Varying Graph Learning for Traffic Flow Data Based on Anomaly Moment Detection

Adaptive Time-Varying Graph Learning for Traffic Flow Data B...

引用

Asia-Pacific signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Shuhong Chen Zewei Chen Chen Li Xianwei Zheng Minfan He Xutao Li Department of Electronic Engineering Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou China School of Mathematics and Big Data Foshan University Foshan China

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

This paper proposes an adaptive time-varying graph structure construction strategy for traffic flow data based on anomaly moment detection, which is capable of identifying anomaly moments within traffic flow signals and adaptively dividing the temporal dimension to construct corresponding graph representations for distinct traffic patterns. Specifically, we leverage a threshold determination method that incorporates the smoothness and energy of temporal difference traffic flow signals to identify anomaly moments in the traffic flow. Upon detecting these anomaly moments, we utilize them as segmentation boundaries along the timeline, adaptively partitioning the continuous time series into multiple dynamic and relatively stable subsequences. Within each subsequence, we apply a time-varying graph learning method to independently construct a graph structure that reflects the traffic flow characteristics of that specific period, thereby achieving an adaptive time-varying property in the traffic flow graph structure. Experimental results demonstrate that the proposed method exhibits reliable performance in detecting anomaly moments in traffic flow, and the adaptive time-varying graph structures accurately reflect the varying characteristics of traffic flow across different time periods.

关键词： Learning systems Time series analysis Asia Information processing Traffic control Data models Reliability Flow graphs Anomaly detection Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Vision-based Distributed Multi-UAV Collision Avoidance via Deep Reinforcement Learning for Navigation

arXiv

引用

arXiv 2022年

作者： Huang, Huaxing Zhu, Guijie Fan, Zhun Zhai, Hao Cai, Yuwei Shi, Ze Dong, Zhaohui Hao, Zhifeng Key Lab of Digital Signal and Image Processing of Guangdong Province College of Engineering Shantou University China

Online path planning for multiple unmanned aerial vehicle (multi-UAV) systems is considered a challenging task. It needs to ensure collision-free path planning in real-time, especially when the multi-UAV systems can become very crowded on certain occasions. In this paper, we presented a vision-based decentralized collision-avoidance policy for multi-UAV systems, which takes depth images and inertial measurements as sensory inputs and outputs UAV’s steering commands. The policy is trained together with the latent representation of depth images using a policy gradient-based reinforcement learning algorithm and autoencoder in the multi-UAV three-dimensional workspaces. Each UAV follows the same trained policy and acts independently to reach the goal without colliding or communicating with other UAVs. We validate our policy in various simulated scenarios. The experimental results show that our learned policy can guarantee fully autonomous collision-free navigation for multi-UAV in the three-dimensional workspaces with good robustness and scalability. Copyright © 2022, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer Based Fault-Tolerant Predictive Control for a Four-Mecanum Wheels Mobile Robot 14

Extended State Observer Based Fault-Tolerant Predictive Cont...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Yang, Binghao Wang, Dongliang Wen, Ziling Wei, Wu Li, Wenji Fan, Zhun Shantou University Key Lab of Digital Signal and Image Processing of Guangdong Province Guangdong 515063 China Shantou University School of Department of Electronic and Information Engineering Guangdong 515063 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangdong Guangzhou510640 China School of Automation Science and Engineering South China University of Technology Guangdong Guangzhou510641 China

ISBN: (纸本)9798331506056

The application of unmanned vehicles in industrial cargo transportation is becoming increasingly widespread, particularly playing a significant role in transporting heavy-duty goods. However, when performing such tasks, whether in single-vehicle transportation or multi-vehicle collaborative transportation, the occurrence of wheel failures can potentially lead to serious safety accidents. Therefore, this paper proposes a fault-tolerant control scheme, establishing a kinematic model considering disturbances and failures, and adopts model predictive control for trajectory tracking. Additionally, an extended state observer is introduced to observe system states and counteract disturbances. To address potential failure issues, a controller reconstruction strategy is proposed. Finally, the effectiveness and superiority of the controller is validated through numerical simulation and comparative experiment. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Resilient Formation Tracking Control of Multiple Nonholonomic Mobile Robots with Communication Link Attacks

Finite-Time Resilient Formation Tracking Control of Multiple...

引用

International Conference on Cybernetics, Robotics and Control (CRC)

作者： Yani Wang Minyin Lu Xinran Yu An-Min Zou Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou China

ISBN: (纸本)9781665473071

In this paper, we address the issue of distributed finite-time resilient formation control for multiple nonholonomic mobile robots with unknown communication link attacks. First, we design a distributed finite-time resilient state observer to estimate the leader's information. Second, we propose a finite-time resilient formation control law by use of the observers and the input-output feedback linearization technique. Theoretical analysis is presented to show that all follower robots can track a leader robot and maintain a desired geometric formation simultaneously in finite time. Finally, the performance of the derived resilient formation control protocol is illustrated by numerical simulation.

关键词： Protocols Observers Numerical simulation Formation control Feedback linearization Nuclear magnetic resonance Mobile robots

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：