检索结果-内蒙古大学图书馆

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Wenbo Zheng Chao Gou Lan Yan Fei-Yue Wang School of Software Engineering Xi'an Jiaotong University The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Intelligent Systems Engineering Sun Yat-sen University School of Artificial Intelligence University of Chinese Academy of Sciences

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Since objects in natural scenarios possess various scales and aspect ratios, learning the rich edge information is very critical for vision-based tasks. Conventional generative adversarial networks (GANs) based methods for edge detection don't perform so well due to model collapse. In order to capture rich edge information and avoid model collapse as much as possible, we consider the learning of GANs as an evolutionary optimization and propose a novel method termed as differential-evolution-based generative adversarial networks (DEGAN) for richer edge detection. In particular, built upon GANs structure, we introduce an improved differential evolutionary algorithm to refine the input of generator, with fitness function evaluated by the discriminator. Experimental results on the well-known BSDS500 and NYUD benchmarks indicate our proposed DEGAN can achieve state-of-the-art performance while retaining a fast speed and validate its simplicity, effectiveness, and efficiency. The high quality of our results on edge detection with proposed DEGAN may promise to make other vision-based tasks work better.

关键词： Image edge detection Generators Gallium nitride Training Generative adversarial networks Evolutionary computation Evolution (biology)

来源：评论

学校读者我要写书评

暂无评论

A survey on fabrication,control,and hydrodynamic function of biomimetic robotic fish

引用

Science China(Technological Sciences) 2017年第9期60卷 1365-1380页

作者： YU JunZhi WEN Li REN ZiYu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences School of Mechanical Engineering and Automation Beihang University

Understanding and replicating the locomotion principles offish are fundamental in the development of artificial fishlike robotic systems,termed robotic *** paper has two objectives:(1) to review biological clues on biomechanics and hydrodynamic flow control offish swimming and(2) to summarize design and control methods for efficient and stable swimming in robotic *** review of state-of-the-art research and future-oriented new directions indicates that fish-inspired biology and engineering interact in mutually beneficial *** strong interaction offers an important insight into the design and control of novel fish-inspired robots that addresses the challenge of environmental uncertainty and competing objectives;in addition,it also facilitates refinement of biological knowledge and robotic strategies for effective and efficient swimming.

关键词： fish swimming robots robotic fish hydrodynamics motion control

来源：评论

学校读者我要写书评

暂无评论

A Brief Research and Lookback of the Development of Iris Recognition

A Brief Research and Lookback of the Development of Iris Rec...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Xiaoshuang Li Shenhua Hu Chengkan Lv Haojun Qin Fenghua Zhu Feiyue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing China School of electrical engineering and aotumation Wuhan University Wuhan China

Personal identification has been used more and more widely in information society. Iris recognition, as one of numerous identification methods, has already been applied in many situations, because the iris patterns have stable, unique and non-invasive features. We analyze the general process of iris recognition in this paper, including image preprocessing, feature extraction, classification and recognition. We also study the progress in iris recognition brought by deep learning method. It is our belief that traditional approaches play a very significant role in iris recognition field, while deep learning methods will make a great difference to iris recognition.

关键词： Iris recognition Feature extraction Iris Image edge detection Wavelet transforms Automation

来源：评论

学校读者我要写书评

暂无评论

Distributed Consensus of Markov Jump Multi-agent systems with Asynchronous Mode-dependent Switching Topology and Communication Delays

Distributed Consensus of Markov Jump Multi-agent Systems wit...

引用

第三十八届中国控制会议

作者： Chao Ma Lihao Jia School of Automation and Electrical Engineering University of Science and Technology Beijing State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Research Center for Brain-inspired Intelligence Institute of Automation Chinese Academy of Sciences

This paper deals with the distributed consensus for Markov jump multi-agent systems(MJMASs) with switching topology. In particular, another different Markov process is adopted to describe the switching topology and mode-dependent transmission delays. By means of model conversion and using Lyapunov-Krasovskii functional method, consensus criterion is first established. The consensus controllers can be further obtained with the aid of matrix transform. The corresponding simulation is presented for showing the validity of the developed method.

关键词： Mode-dependent consensus Markov jump multi-agent systems asynchronous mode-dependent switching topology mode-dependent communication delays

来源：评论

学校读者我要写书评

暂无评论

Training and Testing Object Detectors With Virtual Images

引用

IEEE/CAA Journal of Automatica Sinica 2018年第2期5卷 539-546页

作者： Yonglin Tian Xuan Li Kunfeng Wang Fei-Yue Wang Department of Automation University of Science and Technology of China Hefei 230027 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijirtg 100190 China School of Automation Beijing Institute of Technology Beijing 100081. China Qingdao Academy of Intelligent Industries Qingdao 266000 China Research Center for Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha 410073 China IEEE

In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations.A virtual dataset named Parallel Eye is built, which can be used for several computer vision tasks. Then, by training the DPM(Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining Parallel Eye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors.

关键词： Index Terms--Deep learning object detection parallel vision virtual dataset

来源：评论

学校读者我要写书评

暂无评论

A Face Recognition Method Based on Broad Learning of Feature Block

A Face Recognition Method Based on Broad Learning of Feature...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Dan Zhang He Yang Philip Chen Teishan Li Innovation and Entrepreneurship Education College Dalian Minzu University Dalian China Navigation College Dalian Maritime University Dalian China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Recently, deep learning methods are widely used in face recognition, but the model training time is long, and the problem of global optimal solution cannot be guaranteed. In order to solve the problem of high time cost in face recognition training, this paper applies Broad Learning System (BLS) to face recognition. At the same time, BLS is sensitive to the input features, and the occlusion and illumination problems in the recognition process are considered. The idea of feature block is introduced to BLS. Final weighted facial features and face recognition. Experiments were carried out on ORL and Yale-B datasets, and compared with BLS, PCA and improved deep learning algorithm. The results show that our method is not affected by the number of features on the face dataset with strong illumination and occlusion, maintaining a high recognition accuracy.

关键词： Face recognition Face Machine learning Training Learning systems Lighting Nose

来源：评论

学校读者我要写书评

暂无评论

Accelerating minibatch stochastic gradient descent using typicality sampling

arXiv

引用

arXiv 2019年

作者： Peng, Xinyu Li, Li Wang, Fei-Yue Department of Automation Tsinghua University Beijing100084 China Department of Automation Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing100084 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Minibatch SGD is one of the most popular stochastic optimization method in training deep networks, it shows a slow convergence rate due to the large noise in gradient approximation. In this paper, we attempt to remedy this problem by building more efficient batch selection method based on typicality sampling, which reduces error of gradient estimation in conventional Minibatch SGD. We analyze convergence rate of the resulting typical batch SGD algorithm, and compare convergence properties between Minibatch SGD and the algorithm. Experimental results demonstrate that our batch selection scheme works well and more complex Minibatch SGD variants can benefit from the proposed batch selection strategy. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Two-level Adaptive Target Recognition and Tracking Method Based on Vision for Multi-robot System

A Two-level Adaptive Target Recognition and Tracking Method ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Liang Ren Zhiqiang Cao Min Tan Peng Zhao Xuechao Chen State Key Laboratory of Management and Control for Complex Systems University of Chinese Academy of Sciences Beijing China The 21st Research Institute of China Electronics Technology Group Corporation Shanghai China Beijing Advanced Innovation Center for Intelligent Robots and Systems BIT Beijing China

The vision-based target recognition and tracking have received much attention in the field of robotics. Existing methods mainly focus on the vision perception of individual robot with a single view, however, the performance is susceptible to illumination and occlusion. Multi-robot collaborative perception provides a potential solution to deal with the limitation of single-view observation, however, the challenging of environmental adaptability for multi-robot collaborative decision still remains unsolved. To solve this problem, this paper proposes a two-level adaptive target recognition and tracking method based on vision for multi-robot system. The problem of multi-robot target recognition and tracking is solved under a two-level framework, which contains the features fusion level of individual robot and the cooperation level of multi-robot system. In the first level, the features measuring results that influence the visual perception of individual robot are fused, while the second level combines the voting of each robot together to determine the target for multi-robot system. Both the features measuring weights and robots voting weights are adaptively updated according to their evaluation, which lead to a beneficial result where the features and robots with higher accuracy play major roles in the first and second levels, respectively. Therefore, a good adaptability to the environments can be guaranteed. The experimental results show that the proposed approach can realize the coordination of multi-robot system in target recognition and tracking with an effective performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SmartPV-AIoT: an AIoT-integrated framework for fault diagnosis and remote monitoring in photovoltaic systems

引用

Energy Conversion and management: X 2025年

作者： Ehtisham Lodhi Xiaoli Liu Gang Xiong M. Adil Khan Zeeshan Lodhi Tahir Nawaz Adil Dilawar Sasu Tarkoma Feiyue Wang Zhejiang University-University of Illinois Urbana-Champaign Institute International Campus Haining 314400 China The SKL for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Computer Science University of Helsinki Helsinki 00560 Finland School of Transportation Fujian University of Technology Fuzhou China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Computer Science COMSATS University Islamabad Abbottabad Campus 22060 Pakistan Department of Electronics Technology University of Technology Nowshera 24100 Pakistan Department of Mechatronics Engineering National University of Sciences and Technology H-12 Islamabad 44000 Pakistan The SKL of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing 100101 China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China

This paper presents SmartPV-AIoT, a cost-effective and edge-computing-based framework for real-time fault detection and environmental monitoring in photovoltaic (PV) systems. Addressing the challenges faced in remote or intermittently connected environments, the proposed system integrates electrical and environmental sensor data using a Raspberry Pi 4 and NodeMCU microcontroller. A lightweight Res-BiLSTM model, combining residual learning and bidirectional long short-term memory (BiLSTM) layers, is deployed at the edge to perform local fault classification by analyzing seven key parameters derived from I to V curve measurements and ambient conditions. Additionally, the framework employs multi-sensor data fusion by integrating voltage, current, irradiance, and temperature measurements to support comprehensive fault detection and predictive maintenance. The framework was validated on a 4.56  kW PV installation using a dataset of 2400 labeled samples representing normal operation, open-circuit, short-circuit, and partial shading conditions. The classifier achieved a fault detection accuracy of 96.67 %, with a maximum inference latency of 290  ms and low power overhead, making it suitable for real-time, on-site diagnostics. The system supports offline operation with automatic data synchronization upon connectivity restoration and includes mobile-based monitoring for remote accessibility. The proposed framework is designed for modular deployment and scales linearly with array size. Overall, SmartPV-AIoT offers a scalable, resilient, and practical solution for intelligent PV monitoring, particularly in resource-constrained or off-grid environments.

关键词： Photovoltaic (PV) Artificial Intelligence of Things (AIoT) Green energy resources Deep learning Fault detection Fault classification Monitoring system Edge intelligence

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Path Planning and Trajectory Smoothing

Multi-robot Path Planning and Trajectory Smoothing

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Hub Ali Gang Xiong Huaiyu Wu Bin Hu Zhen Shen Hongxing Bai School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China Hubei Jointown Technology Co. Ltd Artificial Intelligence Research Institute Wuhan China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

In this paper we consider a problem in task execution for multi-robot trajectory planning with collision avoidance in a shared working environment. Consider two or more robots generating trajectories towards their respective goal positions. The collision may occur if their trajectory coordinates are intersecting at a point or follow the same path segment simultaneously. The central planner is introduced to control robot motion in the collision state and to reduce the complexity of the multi-robot path planning system. The global path for every robot is generated by the $\mathrm{A}^{*}$ algorithm in a grid-based environment. The path has presented a sequence of optimal grid numbers and later transformed into Cartesian coordinates for smooth trajectory generation. The central planner takes an optimal grid sequence for every robot to analyze the collision state according to its cost value. It regenerates the trajectories to minimize the complexity cost value and replaces the previous trajectory based on minimum cost value. In the collision state, the central planner allows one robot at a time to pass along the conflict path segment and hold others in queue at a safety offset distance until the previous robot passes safely. The algorithm has been applied to robots working in a shared environment in complex maps and the simulations is performed with MATLAB to calculate the efficiency of this approach for handling collision states in a multi-robot path planning system.

关键词： Robot kinematics Trajectory Collision avoidance Task analysis Resource management

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：