检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Yuhui Zou Zhihan Zhu Zhihao Xu Xuefeng Zhou Shixin Mao Hongmin Wu Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Key Laboratory of Modern Control Technology Guangzhou China College of Geological Engineering and Geomatics Chang'an University Xi'an China Biomimetic and Intelligent Robotics Lab (BIRL) Guangdong University of Technology Guangzhou China Jiutian Innovation (Guangdong) Intelligent Technology Co. Ltd Foshan Guangdong China

ISBN: (纸本)9781665481106

Most of the plants are usually roughly assigned categories in previous panoptic segmentation, which cannot meet the demand for autonomous mobile robotic sprayer sys-tems. Only a reasonable allocation of pesticide doses to different kinds of plants can keep them from being harmed by excessive chemicals. Due to the ambiguous boundaries and similar feature distributions between different plants, implementing precise plant segmentation is still a challenging task. To address this challenge, traditional data augmentation methods enhance the feature extraction capability of the model with geometric and color enhancements. However, these methods only augment the data at the image level such that the implicit scale information in the image is ignored. In this paper, we propose a Gaussian pyramid - based multi -scale data augmentation for panoptic segmentation of plants with ambiguous boundaries, named PyrAug. Our methods attempt to hierarchically enhance images at different levels, in which the network can effectively learn different feature distributions among plants and thus predict the respective masks. In addition to this, we present a new panoptic plant segmentation dataset for improving the seg-mentation performance in complex landscapes. In experimental verification, our method is added to the advanced panoptic segmentation network, and results show that our methods outperform the baselines with higher panoptic quality scores.

关键词： Image segmentation Image color analysis Fuses Feature extraction Data models Robustness Resource management

来源：评论

学校读者我要写书评

暂无评论

CB-YOLOv5 Algorithm for Small Target Detection in Aerial Images

CB-YOLOv5 Algorithm for Small Target Detection in Aerial Ima...

引用

Emerging technology (INCET), International Conference for

作者： Yingjie Li Yitian Wang Huaici Zhao College of Information Engineering Shenyang University of Chemical Technology Shenyang China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

Aerial images are often plagued by background interference, and small targets with indistinct features, leading to low accuracy, high false detection rates, and high miss detection rates. To address these challenges, a small target detection algorithm based on YOLOv5, Coordinate-attention and Bidirectional-feature-pyramid-network YOLOv5 (CB-YOLOv5), is proposed in this paper. Considering the small number of pixels occupied by small targets and their indistinct features, a fourth target detection layer is added by concatenating the feature map from quadruple down-sampling during feature extraction with the feature map output from 8-fold up-sampling during feature fusion. Additionally, a coordinate attention mechanism is introduced during the feature extraction stage to improve small target localization and enhance detection accuracy. Finally, the original Path Aggregation Networks (PANet) structure is replaced with a weighted Bidirectional Feature Pyramid Network (BiFPN) structure during the feature fusion stage to improve the network’s ability to fuse feature maps of different scales. The simulation results demonstrate that the CB-YOLOv5 improves mAP 50 by 9.4%, mAP 75 by 9.7%, and mAP50:95 by 7.8% compared to the original YOLOv5s model. Thus, the effectiveness of the CB-YOLOv5 algorithm for detecting small targets in aerial images is validated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single-step precision programming of decoupled multiresponsive soft millirobots

引用

Proceedings of the National Academy of Sciences of the United States of America 2024年第13期121卷 e2320386121页

作者： Zheng, Zhiqiang Han, Jie Shi, Qing Demir, Sinan Ozgun Jiang, Weitao Sitti, Metin Physical Intelligence Department Max Planck Institute for Intelligent Systems Stuttgart 70569 Germany State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong University Xi’an 710054 China School of Mechanical Engineering Xi’an Jiaotong University Xi’an 710054 China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing 100081 China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology) Ministry of Education Beijing 100081 China Institute for Biomedical Engineering ETH Zurich Zurich 8092 Switzerland School of Medicine College of Engineering Koç University Istanbul 34450 Turkey

Stimuli-responsive soft robots offer new capabilities for the fields of medical and rehabilitation robotics, artificial intelligence, and soft electronics. Precisely programming the shape morphing and decoupling the multiresponsiveness of such robots is crucial to enable them with ample degrees of freedom and multifunctionality, while ensuring high fabrication accuracy. However, current designs featuring coupled multiresponsiveness or intricate assembly processes face limitations in executing complex transformations and suffer from a lack of precision. Therefore, we propose a one-stepped strategy to program multistep shape-morphing soft millirobots (MSSMs) in response to decoupled environmental stimuli. Our approach involves employing a multilayered elastomer and laser scanning technology to selectively process the structure of MSSMs, achieving a minimum machining precision of 30 µm. The resulting MSSMs are capable of imitating the shape morphing of plants and hand gestures and resemble kirigami, pop-up, and bistable structures. The decoupled multistimuli responsiveness of the MSSMs allows them to conduct shape morphing during locomotion, perform logic circuit control, and remotely repair circuits in response to humidity, temperature, and magnetic field. This strategy presents a paradigm for the effective design and fabrication of untethered soft miniature robots with physical intelligence, advancing the decoupled multiresponsive materials through modular tailoring of robotic body structures and properties to suit specific applications. Copyright © 2024 the Author(s).

关键词： environmental response miniature robot soft electronics soft robotics

来源：评论

学校读者我要写书评

暂无评论

An Assembly Sequence Planning Method Using Ant Colony Algorithm for Arbitrary Placed Workpieces

An Assembly Sequence Planning Method Using Ant Colony Algori...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Ruiming Hou Sheng Xu Chenguang Yang Bing Zhu Jianghua Duan Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Science Beijing China Shandong Institute of Advanced Technology CAS Shandong China College of Automation Science and Engineering South China University of Technology Guangzhou China Department of Mechanical and Aerospace Engineering Hong Kong University of Science and Technology Hong Kong

This paper proposes a particular and effective online sequence planning method to help manipulators complete complex assembly tasks. In many existing studies, the workpiece is constrained to be placed at a particular initial position. To overcome this drawback, we combine the ant colony algorithm with a target detection algorithm, which could get the positions of the workpieces in real time for online sequence planning. In addition, the constraint and obstacle avoidance of different workpieces in the assembly process is also considered. According to the experiment results, an observation is found that the new method is superior to the general way in terms of efficiency and cost function value. Furthermore, the proposed method effectively solves different practical and feasible assembly sequence planning problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

arXiv

引用

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous microstructure and mechanical behaviour of Al-8.3Fe-1.3V-1.8Si alloy produced by laser powder bed fusion

引用

Virtual and Physical Prototyping 2023年第1期18卷 Article: e2155197页

作者： Yu, S.J. Wang, P. Li, H.C. Setchi, R. Wu, M.W. Liu, Z.Y. Chen, Z.W. Waqar, S. Zhang, L.C. Additive Manufacturing Institute Shenzhen University Shenzhen China Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robotics College of Mechatronics and Control Engineering Shenzhen University Shenzhen China School of Materials Science and Engineering Shanghai University of Engineering Science Shanghai China Cardiff School of Engineering Cardiff University Cardiff United Kingdom Department of Materials and Mineral Resources Engineering National Taipei University of Technology Taipei Taiwan Department of Mechanical Engineering Institute of Space Technology Islamabad Pakistan School of Engineering Edith Cowan University Perth Australia

The relationship between processing parameters, microstructure, and mechanical properties of Al-8.3Fe-1.3V-1.8Si alloy processed by laser powder bed fusion is seldom studied. Therefore, fully dense alloys with two parameters were selected to investigate this key issue. The results show that the alloy with low power and scanning speed (S200) shows fan-shell-shaped melt pools and laser tracks while another (S350) shows a deeper and wider melt pool. Both alloys obtain a heterogeneous microstructure without a secondary phase in melt pool (MP) and a nano-sized phase in melt pool boundary (MPB). The difference between solid-solution strengthening and Orowan strengthening in MP and MPB contributes to the difference in compressive yield strength (S200: 380 ± 14 MPa and S350: 705 ± 16 MPa), and heterogeneous nano-hardness results in different crack behaviours and failure strains. This work indicates that adjusting processing parameters is an effective method to control microstructure and mechanical properties of this alloy. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Aluminum alloys

来源：评论

学校读者我要写书评

暂无评论

Low-Friction Soft Robots for Targeted Bacterial Infection Treatment in Gastrointestinal Tract

引用

Cyborg and Bionic Systems 2024年第1期5卷 162-176页

作者： Ben Wang Yunrui Chen Zhicheng Ye Haidong Yu Kai Fung Chan Tiantian Xu Zhiguang Guo Weimin Liu Li Zhang College of Chemistry and Environmental Engineering Shenzhen UniversityShenzhen 518060China Guangxi Key Laboratory of Processing for Non-Ferrous Metals and Featured Materials School of ResourceEnvironments and MaterialsGuangxi UniversityNanning 530004China Chow Yuk Ho Technology Centre for Innovative Medicine The Chinese University of Hong KongShatinNew TerritoriesHong Kong SARChina Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Key Laboratory of Biomedical Imaging Science and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Hubei Collaborative Innovation Centre for Advanced Organic Chemical Materials and Ministry of Education Key Laboratory for the Green Preparation and Application of Functional Materials Hubei UniversityWuhan 430062China State Key Laboratory of Solid Lubrication Lanzhou Institute of Chemical PhysicsChinese Academy of ScienceLanzhou 730000China Department of Mechanical and Automation Engineering The Chinese University of Hong KongShatinNew TerritoriesHong Kong SARChina Multi-Scale Medical Robotics Center Hong Kong Science ParkShatinNew TerritoriesHong Kong SARChina

Untethered and self-transformable miniature robots are capable of performing reconfigurable deformation and on-demand locomotion,which aid the traversal toward various lumens,and bring revolutionary changes for targeted delivery in gastrointestinal(GI)***,the viscous non-Newtonian liquid environment and plicae gastricae obstacles severely hamper high-precision actuation and payload ***,we developed a low-friction soft robot by assembly of densely arranged cone structures and grafting of hydrophobic *** magnetic orientation encoded robot can move in multiple modes,with a substantially reduced drag,terrain adaptability,and improved motion velocity across the non-Newtonian ***,the robot stiffness can be reversibly controlled with magnetically induced hardening,enabling on-site scratching and destruction of antibiotic-ineradicable polymeric matrix in biofilms with a low-frequency magnetic ***,the magnetocaloric effect can be utilized to eradicate the bacteria by magnetocaloric effect under high-frequency alternating *** verify the potential applications inside the body,the clinical imaging-guided actuation platforms were developed for vision-based control and delivery of the *** developed low-friction robots and clinical imaging-guided actuation platforms show their high potential to perform bacterial infection therapy in various lumens inside the body.

关键词： gastrointestinal tract reconfigurable deformation targeted bacterial infection treatment low friction soft robots plicae gastricae obstacles assembly densely arranged cone structures targeted delivery grafting hy

来源：评论

学校读者我要写书评

暂无评论

Machine vision inspection of roughness defects in opaque board surface

Machine vision inspection of roughness defects in opaque boa...

引用

12th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering (QR2MSE 2022)

作者： J.- X. Song Y.- X. Xu F.- Z. Bai P. Li College of Mechanical Engineering Inner Mongolia University of Technology Hohhot People's Republic of China College of Mechanical Engineering Inner Mongolia University of Technology Inner Mongolia Key Laboratory of Special Service Intelligent Robotics Hohhot People's Republic of China Beijing Polytechnic College Beijing People's Republic of China

A machine visual method is introduced to inspect roughness defects from the opaque board surface. The new method uses the line-structured light technology with direct triangulation structure to obtain three-dimensional (3D) information. The captured light stripe image modulated by the board surface is processed firstly with the Steger algorithm to extract the center line of the light strip with sub-pixel level. The key parameter used in the Steger algorithm is obtained by estimating the width of light strip. Furthermore, the Zhang Zhengyou's method is used to calibrate the camera parameters, and the 3D depth information is calibrated through the light plane fitting method combining with the principal component analysis (PCA). As a result, the 3D coordinate information corresponding to the center line of the light stripe on the measured surface can be obtained. Finally, the average deviation of profile arithmetic ( R a index) is employed to evaluate the roughness defect of board surface. The experimental results indicate that the method proposed in the paper can achieve a detecting accuracy of 0.02mm ( R a ), which can meet the needs of high-quality wooden board for roughness defect inspection. Compared with the traditional contact detecting method and manual method, the proposed method has high detecting efficiency, low cost, reliable detecting result, and holds a good engineering application prospect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

D2NT: A High-Performing Depth-to-Normal Translator

D2NT: A High-Performing Depth-to-Normal Translator

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yi Feng Bohuan Xue Ming Liu Qijun Chen Rui Fan Robotics & Artificial Intelligence Laboratory (RAIL) the State Key Laboratory of Intelligent Autonomous Systems and Frontiers Science Center for Intelligent Autonomous Systems the College of Electronic & Information Engineering Tongji University Shanghai P. R. China Department of Computer Science & Engineering the Hong Kong University of Science and Technology (Guangzhou) Hong Kong SAR P. R. China Robotics & Autonomous Systems Thrust of the Systems Hub the Hong Kong University of Science and Technol-ogy (Guangzhou) Nansha Guangzhou P. R. China

Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this dilemma, this paper first presents a superfast depth-to-normal translator (D2NT), which can directly translate depth images into surface normal maps without calculating 3D coordinates. We then propose a discontinuity-aware gradient (DAG) filter, which adaptively generates gradient convolution kernels to improve depth gradient estimation. Finally, we propose a surface normal refinement module that can easily be integrated into any depth-to-normal SNEs, substantially improving the surface normal estimation accuracy. Our proposed algorithm demonstrates the best accuracy among all other existing real-time SNEs and achieves the SoTA trade-off between efficiency and accuracy.

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：