检索结果-内蒙古大学图书馆

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yuhang Xie Lianfang Tian Qiliang Du Ling Yuan School of Automation Science and Engineering South China University of Technology Guangzhou China School of Automation Science and Engineering South China University of Technology Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

The detection of key components in transmission lines faces challenges such as significant variations in object scales, complex backgrounds, and difficulties in detecting small targets, leading to low detection accuracy and missed detections. In this study, we propose an improved YOLOv8 algorithm for detecting key components of transmission lines. First, we incorporate Deformable Convolution (DCNv3) to improve the backbone network's feature extraction capability and mitigate accuracy degradation caused by occlusion and angle variations. Subsequently, we use the Adaptively Spatial Feature Fusion (ASFF) to progressively fuse features of different scales and add same-layer skip connections, enabling efficient feature fusion and strengthening the model's ability to detect small objects. Finally, we replaced the original CIoU with the RIoU to further boost the detection capability for small objects. The modified algorithm achieves an mAP 50 of 96.5%, an mAP 50:95 of 79.2%, representing a 3.1% and 4.8% improvement compared to the original YOLOv8 model.

关键词： Power transmission lines Accuracy Convolution Shape Computational modeling Feature extraction Propagation losses Neck Standards Load modeling

来源：评论

学校读者我要写书评

暂无评论

Rgmef: A Lightweight Multi-Exposure Image Fusion Network Based on Retinex and Gradient Guidance

SSRN

引用

SSRN 2024年

作者： Feng, Yunfei Zhang, Mei Zhu, Jinhui School of Automation Science and Engineering South China University of Technology Guangzhou510641 China School of Software Engineering South China University of Technology Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education Guangzhou510641 China

The goal of the multi-exposure image fusion (MEF) is to create a high dynamic range (HDR) image with balanced exposures and more details by extracting and enhancing valid information from multiple low dynamic range (LDR) images with varied exposures. In recent years, deep learning has provided many solutions for MEF, and they have achieved remarkable effects. However, because of the high network complexity, these approaches often have low efficiency and limit the potential improvement of the effect. In order to fuse valuable information from different images, we introduce a lightweight but robust MEF network, which focus on the image internal characteristics rather than long-distance information. In this study, we first design a decomposed network inspired by Retinex theory to extract the illumination map from an image and obtain the gradient map through Sobel operator. Subsequently, we introduce two lightweight feature extraction modules to extract image features with the guidance of illumination and gradient maps respectively, and then fuse these features to produce an HDR result through three fusion blocks. Furthermore, we design a loss function to obtain a more suitable brightness range for the current scene. Numerous comparative experiments demonstrate the superiority of our method in terms of image texture, pixel intensity, and color retention. Moreover, some ablation studies indicate that our approach has a significant adaptability to source images. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Research of high-efficiency extraction of edges of large complex components in three-dimensional point clouds

Research of high-efficiency extraction of edges of large com...

引用

World Conference on Mechanical Engineering and intelligent Manufacturing (WCMEIM)

作者： Jing Li Jiangchuan Fan Nanyan Shen Hui Qian Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai Fanuc Robot Co. Ltd Shanghai China

ISBN: (纸本)9781665473705

With the rapid development of the automobile manufacturing industry, major automobile manufacturers around the world are stepping up digital transformation to achieve high-flexible, efficient and high-quality automobile production to adapt to the increasingly competitive market situation. robots play an important role in automobile manufacturing. In the process of automobile manufacturing, the performance and quality of the product largely depend on the size accuracy of the parts, so edge information needs to be tested before the product is produced and assembled. At the same time, in the field of path planning, people need to obtain geometric feature information such as the edge of components in advance. However, large components are due to various the accuracy of the error needs to be scanned on the spot, and then processed after obtaining the point cloud. In this paper, a new method for quickly extracting edge contours from large-scale point clouds is studied. In the process of finding edges in two-dimensional images, some optimizations have also been made to make them more suitable for edge extraction of such plane structures. We also demonstrated the application of this method in a bus and compared it with two traditional methods.

关键词： Point cloud compression Three-dimensional displays Trajectory planning Service robots Image edge detection Production Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Hybrid6D: A Dual-Stream Transformer-CNN Approach for 6D Object Pose Estimation from RGB-D Images *

Hybrid6D: A Dual-Stream Transformer-CNN Approach for 6D Obje...

引用

IEEE International Conference on robotics and Biomimetics

作者： Songhao Fu Qiang Zhang Xueying Sun Mingmin Liu Zhiwei Fan College of Automation Jiangsu University of Science and Technology Zhenjiang China Central Research Institute SIASUN Robot & Automation CO. Ltd. Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

Estimating the 6D pose presents a formidable challenge due to the intricate nature of world objects and the myriad of issues encountered when acquiring data from real-world scenes. This task is compounded by occlusions, fluctuating lighting conditions, and data noise. The conventional CNN or Transformer architectures primarily focus on either local or global information, and relying solely on RGB or depth maps proves inadequate for extracting the most robust features. To address these challenges, we introduce Hybird6D, a dual-stream fusion deep learning approach that leverages a Transformer-CNN structure and attention mechanism to regress the 6D pose of objects using RGB-D images as input. Our methodology capitalizes on the strengths of both Transformers and CNNs, incorporating global attention and local attention, while simultaneously harnessing both appearance and geometric information. This comprehensive approach enhances robustness to noise and occlusions. Experimental evaluation on the YCB-Video dataset demonstrates that our method outperforms existing Transformer-based approaches and surpasses advanced CNN-based methods. Moreover, our approach exhibits superior performance on symmetry objects, textureless objects, and small objects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plate Contour Recognized Algorithm Based on Depth Histogram Threshold Segmentation 15

Plate Contour Recognized Algorithm Based on Depth Histogram ...

引用

15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2022

作者： Liu, Zhenyu Liu, Yaoqi Su, Meng Guo, Haibing Li, Pengchao Shenyang University of Technology Central Campus Shenyang China Tianjin Siasun Robot and Automationo. Ltd Tianjin China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (数字)9781665488877

ISBN: (纸本)9781665488877

In this paper, a method of extracting board contour from depth image is proposed, the method has very important practicability in the complex scenes of the current industry, such as uneven illumination and burst noise. The traditional single threshold segmentation methods consider all pixels, the effect of image segmentation in complex scenes is poor and loses more details. Therefore, an algorithm is proposed to automatically select the optimal threshold value according to the features provided by the depth histogram: draw the depth histogram according to the image, the histogram is optimized to reduce the interference information and preserve the image features to the greatest extent. According to the background and the detection target of the frequency distribution in the depth histogram, the optimal threshold can be quickly and accurately determined automatically. The algorithm extracts information from the image depth histogram, optimizes the depth histogram, and eliminates the problem of low robustness of fixed thresholds in complex scenes. The method has been verified on the data set, and the results prove the practicability of the algorithm. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Mechanism of SOC Balancing for Battery Energy Storage System

Dynamic Event-Triggered Mechanism of SOC Balancing for Batte...

引用

Chinese automation Congress (CAC)

作者： Haitao Jia Zhiyong Zhu Yiliu Zhang Shikai Wu Annan Zheng Xiaohan Fang Yuan Fan Wendian College Anhui University Hefei China Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Anhui University Hefei China

This paper studies the state of charge (SOC) balancing control for distributed battery energy storage systems (BESS). SOC gives the information of holding capacity when the battery is charged or discharged. A dynamic event triggering coordination consensus algorithm is proposed under an undirected topology by introducing internal dynamic variables. Multi-agent consensus theory is utilized to achieve SOC balance. Lyapunov function is constructed to illustrate the battery management system asymptotically stable. Compared with the conventional event-triggered mechanism (ETM), the introduction of dynamic ETM can reduce more consumption of communication. Finally, Simulation is presented to show the validity and effectiveness of the dynamic ETM.

关键词： Asymptotic stability Costs Heuristic algorithms Microgrids Dynamic scheduling Stability analysis Batteries

来源：评论

学校读者我要写书评

暂无评论

Design of a Flexible robot for Inspection in Confined Spaces

Design of a Flexible Robot for Inspection in Confined Spaces

引用

IEEE International Conference on robotics and Biomimetics

作者： Jie Li Ji Shen Chongyang Wang Dingjia Li Junlin Cui Hao Liu school of mechanical engineering Shenyang Jianzhu University Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory of Minimally Invasive Surgical Robot Liaoning Province Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

The complex shape of aircraft engine blades, combined with their location in confined spaces, poses significant challenges for inspection tasks. These confined spaces not only limit the operational range of inspection equipment, making the task more difficult, but also hinder traditional rigid robots from flexibly adapting to complex paths. Additionally, manual inspection methods often require disassembling the engine, which is both costly and inefficient. To address these challenges, this paper presents a flexible robot designed for use in confined spaces. The robot features a hinge-joint design, with a continuum flexible arm at the proximal end, allowing it to adapt flexibly to narrow environments, and a jointed flexible arm at the distal end, providing high load-bearing capacity. Furthermore, coordinated movement and pose decoupling of the two-segment continuum are achieved through fixed tendons at both ends. Experimental results demonstrate that this robot exhibits high flexibility and load capacity during blade inspection, significantly improving inspection efficiency and showing great potential for applications in confined-space inspections.

关键词： Service robots Deformation robot kinematics Blades Wires Inspection Arms Manipulators Aircraft propulsion Tendons

来源：评论

学校读者我要写书评

暂无评论

Application of Lenze 9400 servo in dynamic splicing of bobbin paper

Application of Lenze 9400 servo in dynamic splicing of bobbi...

引用

2021 IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2021

作者： Xu, Hongqing Tian, Junmin Li, Chengpeng Zhao, Qian Yang, Xu Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Tobacco Shaanxi Industrial Company Limited Xi'an710065 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Shenyang110179 China SIASUN Robot & Automation Co. Ltd. Shenyang110169 China

ISBN: (纸本)9781665432511

In the process of cigarette, the dynamic splicing of running bobbin paper and spare bobbin paper plays a very important role in the continuous operation of Cigarette Making and Filter Assembling Group. However, at present, the dynamic splicing system of some domestic Cigarette Making and Filter Assembling Group mostly adopts magnetic particle clutch. After using the magnetic particle clutch for a period of time, it will not rotate or rotate too slowly due to wear and tear. It is easy to cause the rotation speed of spare bobbin paper and running bobbin paper to be inconsistent when splicing, resulting in relative speed, resulting in failure of splicing. Therefore, a dynamic splicing system based on Lenze 9400 servo controller is proposed. The system can guarantee the smooth splicing of the running and spare bobbin paper, reduce The Times of maintenance and improve the production efficiency. ©2021 IEEE.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Distributed Continuous Time Optimization Algorithms over Unbalanced Graphs

Distributed Continuous Time Optimization Algorithms over Unb...

引用

第33届中国控制与决策会议

作者： Songsong Cheng Yuan Fan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui University

This paper investigates two distributed optimization schemes with or without feasible set constraints over unbalanced graphs,*** overcome the inaccuracy convergence problem of unbalanced graphs,we propose two continuous time algorithms with an inexact gradient tracking *** first one is a distributed optimization algorithm without feasible set constraints and the second one is improved from the first one with feasible set ***,we provide the convergence analyses for the two optimization algorithms.

关键词： Distributed optimization Continuous time algorithms Unbalanced graphs Feasible set constraint Convergence

来源：评论

学校读者我要写书评

暂无评论

A Fast Method to Sparse Reconstruction for Near-infrared Spectroscopy

A Fast Method to Sparse Reconstruction for Near-infrared Spe...

引用

第32届中国过程控制会议(CPCC2021)

作者： Chao Wu Tianhong Pan Anhui Engineering Laboratory of Human-Robot Collaboration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui University

Sparse reconstruction is widely popular in many *** Bayesian learning(SBL) approach has been applied to capture and recover the spectra variables via a small number of ***,the computational cost of the reconstruction is high because an inverse of large matrix needs to be calculated in each *** this paper,a fast method to sparse reconstruction for near-infrared(NIR) spectra is proposed based on block sparse Bayesian learning ***,the minimum cost function obtained the optimal hyper-parameters is taken by using the fast marginalized likelihood maximization method,which is greatly helpful to reduce the computational ***,a real NIR spectra is used to verified the proposed method by comparing with full-spectral based PLS and SBL+PLS *** experimental results explained that the proposed method has better performance than other two methods.

关键词： Sparse Bayesian Learning Block Sparse Bayesian Learning Fast Marginalized Likelihood Maximization

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：