检索结果-内蒙古大学图书馆

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： Jiang, Tianjian Fang, Qiu Zhu, Qing Wang, Yaonan Zhou, Zhen Chen, Lin Zhou, Jiaming Luo, Yuefan Wu, Chengzhong National Engineering Research Center for Robot Visual Perception and Control Technology Hunan University Hunan Changsha410082 China Jiangxi Communication Terminal Industry Technology Research Institute China

ISBN: (纸本)9798350300178

Homography estimation is a crucial problem in computer vision, which aims to provide an optimal transformation matrix for aligning images captured from different viewpoints. Current methods extract shallow features from image pairs and introduce learnable mask modules to improve homography estimation performance. However, they struggle to capture long-term dependencies between features and comprehend the global structures of image features. A deep unsupervised homography learning framework is proposed in this paper, consisting of a weight-sharing feature extraction network and a homography estimation network based on the Transformer model. The former extracts the local features of images, while the latter learns the correlation between them and understands the global features of images, enabling the algorithm to better estimate the homography of unaligned images. Experimental results demonstrate that the proposed method outperforms the advanced methods for estimating homography matrices in the CA-Unsupervised dataset. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

HNSRRT∗:A Path Planning Algorithm Based On Heuristic Non-Uniform Sampling Method In Complex Obstacle Environment 42

HNSRRT∗:A Path Planning Algorithm Based On Heuristic Non-Un...

引用

42nd Chinese control Conference, CCC 2023

作者： Xu, Zhiwen Zhang, Hui Chen, Bo Zhou, Xidong Yin, Songtao Yang, Lian College of Electrical and Information Engineering Changsha University of Science and Technology Hunan China College of Robotics Robot Visual Perception and Control Technology National Engineering Research Center Hunan University Hunan China

ISBN: (纸本)9789887581543

The traditional sampling-based algorithm such as Rapidly Random-exploring Tree (RRT) and various varieties have achieved tremendous success in the area of path planning. However, their excessive exploration in the state space leads to long time to find the optimal solution, large memory usage and cannot guarantee the quality of the planned path(generally evaluated by the cost of search time and the length of path) in sophisticated space. In this article, we propose an optimal path planning algorithm based on heuristic non-uniform sampling, namely the HNSRRT∗, which successfully plans path in complex obstacle environments with optimal length and minimum time cost. The HNSRRT∗ utilizes heuristic function to generate non-uniform sampling distribution by Gaussian distribution,and constraints on sampling points can reduce the time wasted and path length increase caused by excessive exploration. We test the proposed HNSRRT∗ in 2D and 3D complex obstacle environment,comparing it with the three traditional sampling-base algorithms. The simulation results indicated that the effectiveness and efficiency of HNSRRT∗ and have an obvious improvement in term of time cost, path length compared with the existing algorithms. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

High Dynamic Range 3d Measurement with Adaptive Projection Pattern Generated from Saturated Image

SSRN

引用

SSRN 2024年

作者： Yu, Hongshan Liang, Xianqiang Yu, Ruiming Xu, Haiqiang Sun, Wei National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Changsha China

Fringe projection profilometry (FPP) shows the advantages of high efficiency and high accuracy in distance sensing. However, it is prone to measurement errors due to fringe saturation in high dynamic range (HDR) scenes. Popular adjust projection intensity (API) based FPP methods have been proposed to reduce the influence of reflectivity variance. Because existing API based FPP method depend on unsaturated images to generate adaptive projection patterns, its measurement time is increased. In this paper, we propose a high dynamic range 3D measurement method with adaptive projection pattern generated from saturated image. Firstly, we establish the reflectance relationship between unsaturated region and saturated region to compute adaptive projection intensity, which removes the dependence of unsaturated images. Secondly, we improve measurement efficiency in computation process by recycling the captured images. In addition, we propose a capture intensity correction method to remove the effect of light propagation distance. Experiments prove that the proposed method has significant advantages in a variety of HDR scenes. Compared with linear-API method, proposed method improves the measurement accuracy by 15.59%. Meanwhile, the number of projection patterns is reduced by 40% compared to the method which based on multiple exposure fusion image (MEFI). © 2024, The Authors. All rights reserved.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

FedGAI: Federated Style Learning with Cloud-Edge Collaboration for Generative AI in Fashion Design

arXiv

引用

arXiv 2025年

作者： Wu, Mingzhu Jiang, Jianan Li, Xinglin Deng, Hanhui Wu, Di National Engineering Research Center for Robot Visual Perception and Control Technology Hunan University Changsha China

Collaboration can amalgamate diverse ideas, styles, and visual elements, fostering creativity and innovation among different designers. In collaborative design, sketches play a pivotal role as a means of expressing design creativity. However, designers often tend to not openly share these meticulously crafted sketches. This phenomenon of data island in the design area hinders its digital transformation under the third wave of AI. In this paper, we introduce a Federated Generative Artificial Intelligence Clothing system, namely FedGAI, employing federated learning to aid in sketch design. FedGAI is committed to establishing an ecosystem wherein designers can exchange sketch styles among themselves. Through FedGAI, designers can generate sketches that incorporate various designers’ styles from their peers, drawing inspiration from collaboration without the need for data disclosure or upload. Extensive performance evaluations indicate that our FedGAI system can produce multi-styled sketches of comparable quality to human-designed ones while significantly enhancing efficiency compared to hand-drawn sketches. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Tightly-Coupled LiDAR-visual SLAM Based on Geometric Features for Mobile Agents

Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Feature...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Cao, Ke Liu, Ruiping Wang, Ze Peng, Kunyu Zhang, Jiaming Zheng, Junwei Teng, Zhifeng Yang, Kailun Stiefelhagen, Rainer Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics Germany Hunan University School of Robotics China Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology China

ISBN: (纸本)9798350325706

The mobile robot relies on SLAM (Simultaneous Localization and Mapping) to provide autonomous navigation and task execution in complex and unknown environments. However, it is hard to develop a dedicated algorithm for mobile robots due to dynamic and challenging situations, such as poor lighting conditions and motion blur. To tackle this issue, we propose a tightly-coupled LiDAR-visual SLAM based on geometric features, which includes two sub-systems (LiDAR and monocular visual SLAM) and a fusion framework. The fusion framework associates the depth and semantics of the multi-modal geometric features to complement the visual line landmarks and to add direction optimization in Bundle Adjustment (BA). This further constrains visual odometry. On the other hand, the entire line segment detected by the visual subsystem overcomes the limitation of the LiDAR subsystem, which can only perform the local calculation for geometric features. It adjusts the direction of linear feature points and filters out outliers, leading to a higher accurate odometry system. Finally, we employ a module to detect the subsystem's operation, providing the LiDAR subsystem's output as a complementary trajectory to our system while visual subsystem tracking fails. The evaluation results on the public dataset M2DGR, gathered from ground robots across various indoor and outdoor scenarios, show that our system achieves more accurate and robust pose estimation compared to current state-of-the-art multi-modal methods. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-World Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5776-5790页

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model’s robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： Adaptation models Transformers Data models Correlation Circuits and systems Electronic mail Robustness Uncertainty Training Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv7 Based on Transformer for Object Detection in UAV-Captured Images

Improved YOLOv7 Based on Transformer for Object Detection in...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Luo, Yuefan Zhu, Qing Zhou, Zhen Chen, Lin Zhou, Jiaming Jiang, Tianjian Li, Yijiang Wang, Danwei Wang, Yaonan Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology Hunan Changsha410082 China School of Electrical and Electrical Engineering Nanyang Technological University Singapore639798 Singapore

ISBN: (纸本)9798350337020

As the drone captures image targets at different flying altitudes, their scales may vary significantly, which can pose challenges for the object detection model to accurately detect them. Additionally, tiny objects in the image contain minimal information, making them difficult to distinguish from the background. To overcome these two challenges, we proposed a network architecture that aims to improve the accuracy of tiny object detection in drone images. Specially, we designed a tiny object detector(TOD) that can effectively extract features of tiny objects and distinguish between tiny object features and image background. Furthermore, this TOD module contains a Convolutional visual Attention Network (CVAN) to better focus on the regions of tiny objects. Experimental results demonstrate that the proposed method achieves mAP@.5 accuracy of 53.9% on the VisDrone2021-test-dev dataset and improves by 2.8 % compared to YOLOv7. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Safety control of a Constrained Uncertain robotic System 8

Adaptive Safety Control of a Constrained Uncertain Robotic S...

引用

8th International Conference on Automation, control and robotics engineering, CACRE 2023

作者： Wang, Haijing Peng, Jinzhu Zhang, Fangfang Wang, Yaonan School of Electrical and Information Engineering Zhengzhou University Zhengzhou China National Engineering Laboratory for Robot Visual Perception and Control Hunan University Changsha China College of Electrical and Information Engineering Hunan University Changsha China

ISBN: (纸本)9798350302776

The safety control problem of a constrained uncertain robotic system is investigated in this paper. First, the high-order control barrier functions (HoCBFs) are introduced to deal with the output constraints for he system. And to solve the uncertain problem and revisit the HoCBF-based framework, an adaptive approach is proposed to updating the unknown parameters online. In this way, the system safety can be achieved adaptively by keeping the system output within the predefined constrained region even in the presence of parametric uncertainty. Finally, simulation tests are carried out to verify the validity of the proposed controller. © 2023 IEEE.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Boundary Gap Based Reactive Navigation in Unknown Environments

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 468-477页

作者： Zhao Gao Jiahu Qin Shuai Wang Yaonan Wang the Department of Automation University of Science and Technology of ChinaHefei 230027China the College of Electrical and Information Engineering Hunan UniversityChangsha 410082 the National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha 410082China

Due to the requirements for mobile robots to search or rescue in unknown environments,reactive navigation which plays an essential role in these applications has attracted increasing ***,most existing reactive methods are vulnerable to local minima in the absence of prior knowledge about the *** paper aims to address the local minimum problem by employing the proposed boundary gap(BG)based reactive navigation ***,the narrowest gap extraction algorithm(NGEA)is proposed to eliminate the improper ***,we present a new concept called boundary gap which enables the robot to follow the obstacle boundary and then get rid of local ***,in order to enhance the smoothness of generated trajectories,we take the robot dynamics into consideration by using the modified dynamic window approach(DWA).Simulation and experimental results show the superiority of our method in avoiding local minima and improving the smoothness.

关键词： Boundary gap local minima reactive navigation unknown environments

来源：评论

学校读者我要写书评

暂无评论

Humanoid robot technology and Industry Development

引用

Strategic Study of CAE 2025年第1期27卷 150-167页

作者： Chenghao, Xu Yaonan, Wang Yang, Mo Qing, Zhu College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Research Center of Robot Visual Perception and Control Technology Changsha410082 China

With the continuous breakthroughs in technologies such as artificial intelligence, advanced manufacturing, and new materials, China’s humanoid robot industry is experiencing explosive growth. Technological innovation and supportive policies have fostered a diversified and competitive landscape. However, China’s humanoid robot industry still faces significant challenges, including lagging core technologies, high difficulty in mass production, and obstacles to commercialization. This study explores the major subfields and technological frontiers of humanoid robotics, offering an in-depth analysis of global trends in policies, technologies, and industrial development. It examines the current state of humanoid robotics in China and identifies key opportunities and challenges. Furthermore, the study proposes strategic recommendations to address these challenges, focusing on technological innovation, pilot demonstration, improvement in laws and regulations, and policy support. Specifically, the research recommends encouraging breakthroughs in core technologies, strengthening industrial layout, building humanoid robot infrastructure, and implementing demonstrative projects. These efforts aim to help China’s humanoid robot industry overcome technical challenges, improve its industrial ecosystem, and achieve large-scale production and commercialization, thereby enhancing the global competitiveness of the industry. © 2025 Beijing Zhongguo Gongcheng Kexue Zazhishe. All rights reserved.

关键词： Anthropomorphic 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

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

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：