检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Yang, Sen Heng, Wen Liu, Gang Luo, Guozhong Yang, Wankou Yu, Gang School of Automation Southeast University China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Tencent PCG China

In this paper we present a novel method to estimate 3D human pose and shape from monocular videos. This task requires directly recovering pixel-alignment 3D human pose and body shape from monocular images or videos, which is challenging due to its inherent ambiguity. To improve precision, existing methods highly rely on the initialized mean pose and shape as prior estimates and parameter regression with an iterative error feedback manner. In addition, video-based approaches model the overall change over the image-level features to temporally enhance the single-frame feature, but fail to capture the rotational motion at the joint level, and cannot guarantee local temporal consistency. To address these issues, we propose a novel Transformer-based model with a design of independent tokens. First, we introduce three types of tokens independent of the image feature: joint rotation tokens, shape token, and camera token. By progressively interacting with image features through Transformer layers, these tokens learn to encode the prior knowledge of human 3D joint rotations, body shape, and position information from large-scale data, and are updated to estimate SMPL parameters conditioned on a given image. Second, benefiting from the proposed token-based representation, we further use a temporal model to focus on capturing the rotational temporal information of each joint, which is empirically conducive to preventing large jitters in local parts. Despite being conceptually simple, the proposed method attains superior performances on the 3DPW and Human3.6M datasets. Using ResNet-50 and Transformer architectures, it obtains 42.0 mm error on the PA-MPJPE metric of the challenging 3DPW, outperforming state-of-the-art counterparts by a large margin. Code will be publicly available. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Prediction of transmission spectrum from photonic energy band via autoencoder network

引用

IEEE Photonics Technology Letters 2025年第13期37卷 737-740页

作者： Mo, Wenqin Zhu, Yaling Yin, Yuanxing Dong, Kaifeng Jin, Fang Song, Junlei China University of Geosciences School of Automation Wuhan430074 China China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

Optical topological insulators, as an emerging type of photonic material, present substantial benefits for optical communication. The advanced pattern recognition capabilities of deep learning have propelled the inverse design of topological photonic structures into a hot area of research. However, existing methods encounter difficulties with the analysis of intricate band structures. Therefore, we construct a deep learning model capable of handling two-dimensional data of photonic energy band. Utilizing an autoencoder network, our model indirectly trains the photonic energy band and transmission spectrum, by converting them into feature coding. It integrates a transmission spectrum autoencoder and a photonic energy band autoencoder, processing energy band data to predict the corresponding transmission spectrum. The results indicate that compared to convolutional neural network (CNN), our model can accurately predict transmission spectrum, and perform better on both evaluation metrics of RMSE and R2. This work enhances prediction accuracy by leveraging energy band diagrams to constrain optical properties. © 1989-2012 IEEE.

关键词： Topological insulators

来源：评论

学校读者我要写书评

暂无评论

Analysis of light propagation characteristic in the aero-optic flow field of cone-headed vehicle with side window

引用

Optoelectronics Letters 2024年第1期20卷 58-64页

作者： XU Liang ZHOU Liye WANG Luyang ZHAO Shiwei WANG Tao Tianjin Key Laboratory of Complex Control Theory and Application School of Electrical Engineering and AutomationTianjin University of TechnologyTianjin 300384China School of Intelligent Engineering Sun Yat-sen UniversityGuangzhou 510275China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519000China

Aero-optic imaging deviation research is carried out for infrared-guided vehicle with cone-head side window,with a focus on the propagation characteristics of light in an aero-optic flow *** the light entering the aero-optic flow field from the free-stream should be close to the normal,numerous data indicate that the light is refracted away from the *** paper divides the aero-optic flow field into two parts and uses the gas density distribution in the aero-optic flow field to propose the hypothesis that there are two modes of refraction when light propagates through the flow *** results show that light propagates from the optically denser medium to the optically thinner medium after passing through the shock wave and eventually leads to refraction away from the normal when the light enters the aero-optic flow field.

关键词： flow propagation light

来源：评论

学校读者我要写书评

暂无评论

Pattern Matching of Industrial Alarm Floods Using Word Embedding and Dynamic Time Warping

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1096-1098页

作者： Wenkai Hu Xiangxiang Zhang Jiandong Wang Guang Yang Yuxin Cai School of Automation China University of GeosciencesWuhan 430074Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex SystemsWuhan 430074 Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan 430074China College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China

Dear Editor,This letter proposes a new pattern matching method based on word embedding and dynamic time warping(DTW)to identify groups of similar alarm ***,alarm messages are transformed into numeric values that represent alarms and also reflect the relationships between alarm ***,similarities between numerically encoded alarm flood sequences are calculated by DTW and groups of similar floods are identified via *** effectiveness of the proposed method is demonstrated by a case study with alarm&event data obtained from a public industrial simulation model.

关键词： Word Alarm DTW

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Coverage Path Planning Method Based on Improved Particle Swarm Optimization

Multi-UAV Coverage Path Planning Method Based on Improved Pa...

引用

2024 China automation Congress, CAC 2024

作者： Zhou, Yan Xiong, Yonghua School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9798350368604

The widespread application of unmanned aerial vehicle (UAV) has made the coverage path planning problem for multiple UAV systems a research hotspot. In this paper, we propose a multi-UAV solution to achieve complete coverage of multi-region. Based on this solution, we present an improved particle swarm optimization (PSO) algorithm that combines PSO algorithm, greedy strategy, and back-and-forth (BAF) algorithm. Its purpose is to plan the optimal paths for multi-UAV while achieving the shortest total distance and the highest UAV cooperation efficiency with the minimum number of UAVs, thereby enhancing the multi-UAV coverage cooperation and path optimization capabilities. Simulation results demonstrate the feasibility and superiority of this algorithm. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Simulation and optimization of inchworm-like pneumatic crawling actuator based on ABAQUS software 7

Simulation and optimization of inchworm-like pneumatic crawl...

引用

7th International Conference on Robotics, control and automation engineering, RCAE 2024

作者： Mu, Junqi Zong, Xiaofeng Wei, Yiyang Hou, Xuping China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation Wuhan430074 China

ISBN: (纸本)9798350355642

The actuator, serving as the fundamental power source of a soft robot, functions as its central component. The field of soft robotics has garnered increasing research attention since its inception. Pneumatic crawling robots, being an essential branch within the realm of soft robotics, possess notable characteristics such as rapid response time, cost-effectiveness, and human-computer interaction safety. Consequently, they hold significant research value. Among various types of crawling robots that have garnered considerable interest from researchers is the inchworm crawling robot. This paper aims to address the design and development aspects pertaining to inchworm actuators. By utilizing ABAQUS simulation software and taking displacement as the reference parameter, an analysis was conducted to investigate the impact of various geometric parameters on actuator displacement. Additionally, optimization of these geometric parameters was performed. The values of aspect ratio, length-to-width ratio, vertex angle and gap depth suitable for inchworm-like actuator are obtained. These findings are presented for the first time in the field of crawling soft robots and provide a theoretical basis for the development of pneumatic inchworm-like actuators. © 2024 IEEE.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

keypoints-guided Lightweight Network for Single-view 3D Human Reconstruction

Keypoints-guided Lightweight Network for Single-view 3D Huma...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Yuhang Chen Chenxing Wang School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Single-view 3D human reconstruction has been a hot topic due to the potential of wide applications. To achieve high accuracy, existing works usually take computationally intensive models as backbone for exhaustive underlying features and then directly estimate human mesh vertices. These factors lead to redundant parameters, large calculations and low efficiency, while lightweight solutions to address these challenges are relatively scarce. In this work, based on the problems studied above, we propose a keypoints-guided lightweight network with an encoding-decoding framework. As the input is an image, a lightweight backbone named multi-stage and global feature enhanced network is designed for 2D encoding, where some operations of multi-scale fusion and frequency domain filtering are performed to extract more informative but low-resolution features. As the output is mesh of human body, we construct a keypoints-based 3D human template, with which the 2D low-resolution features can be mapped to 3D space to guide the 3D decoding with high efficiency and high accuracy. Extensive experiments on popular benchmarks 3DPW and Human3.6M illustrate the favorable trade-off between the accuracy and complexity of our method. Our code is publicly available at https://***/ChrisChenYh/***.

关键词： Three-dimensional displays Accuracy Image coding Frequency-domain analysis Estimation Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Distributed Finite-Time Anti-Disturbance Secondary Voltage Regulation for Islanded Alternating-Current Microgrids 41

Distributed Finite-Time Anti-Disturbance Secondary Voltage R...

引用

第41届中国控制会议

作者： Xuechao Qiu Guanjun Li Xiangyu Wang School of Automation Southeast Universityand Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education China Electric Power Research Institude Company Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,a distributed finite-time anti-disturbance secondary voltage regulation problem is investigated for islanded alternating-current(AC) microgrids with unmeasurable states and *** combining the integral-type nonsingular terminal sliding-mode control and finite-time extended-state observer technique together,distributed finite-time anti-disturbance secondary voltage regulation protocols are *** order to estimate the unmeasurable states and disturbances,some finite-time extended-state observers are constructed at ***,according to the estimates of disturbances and unmeasurable states,some integral-type nonsingular terminal sliding-mode surfaces are designed for the ***,secondary voltage regulation protocols are proposed based on the *** the islanded AC microgrid system,these protocols achieve the output voltage consensus in finite *** demonstrate the effectiveness of the proposed secondary voltage regulation protocols.

关键词： Islanded Alternating-Current Microgrids Disturbance Rejection control Secondary Voltage Regulation Output-Feedback control

来源：评论

学校读者我要写书评

暂无评论

Context-Aided Semantic-Aware Self-Alignment for Video-Based Person Re-Identification

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Ran, Zhidan Xiao, Zhiyao Lu, Xiaobo Wei, Xuan Liu, Wei Southeast University School of Automation Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China

Video-based person re-identification (Re-ID) aims at associating the video sequences of the identical person across multiple cameras. The ubiquitous appearance misalignment poses a major obstacle for video person Re-ID. Existing alignment-based methods generally rely on off-the-shelf semantic parsing models to locate visible human parts, which ignore identifiable personal belongings and cannot handle various interferences (e.g., pedestrian detection errors and occlusions) in video clips. In this work, we propose a novel framework termed Context-Aided Semantic-Aware Self-Alignment (CSSA) for video-based person Re-ID. First, we propose to jointly learn pixel-level part-aligned representations and semantic-aligned global-level representations in an end-to-end manner. Unlike most existing approaches that depend on prior information in terms of pose for part estimation, CSSA can locate different body parts and achieve the pixel-level semantic alignment without extra human topology semantics. Second, a Context-Aided Region Enhancement (CARE) module is proposed to efficiently highlight macro-visual patterns associated with the target pedestrian and suppress noise caused by factors like background clutters and occlusions. Third, we propose a Semantic-Aware Global Feature Alignment (SGFA) method for generating pair-wise semantic-aligned global representations, which play an essential role in both the training and inference phases. Extensive experimental results on multiple challenging benchmarks indicate the superiority and effectiveness of the proposed CSSA. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Leader-Following Consensus of Multiagent systems under DoS Attacks 43

Dynamic Event-Triggered Leader-Following Consensus of Multia...

引用

43rd Chinese control Conference, CCC 2024

作者： Ma, Ji Chen, Xiangyong Wu, Yue Sun, Ji Liu, Jianhua Linyi University The Key Laboratory of Complex Systems and Intelligent Computing in Universities of Shandong School of Automation and Electrical Engineering Linyi276005 China

ISBN: (纸本)9789887581581

In this paper, the leader-following consensus of multi-agent systems (MASs) under denial-of-service (DoS) attacks over undirected networks is studies. First, introduce an estimator under DoS attacks to design a dynamic event-triggered communication protocol, which avoids continuous communication between agents. Then, with the presence of the estimator between the triggering instants can reduce the state shift. In contrast to the conventional method, the existence of dynamic threshold need fewer triggering times. Under this control strategy, the systems only need the states in triggering instants according to estimated states. Finally, verify the effectiveness of the proposed approach by a simulation example. © 2024 Technical Committee on control Theory, Chinese Association of automation.

关键词： Denial-of-service attack

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：