检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wang, Guangming Ren, Shuaiqi Wang, Hesheng The Key Laboratory of System Control and Information Processing of Ministry of Education Department of Automation Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric laws of optical flow based on the insight and detailed definition of non-occlusion. Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric laws of non-occlusion. Specifically, after the occlusion part of the images are masked, the flowing process of pixels is carefully considered and geometric constraints are conducted based on the geometric laws of optical flow. First, neighboring pixels in the first frame will not intersect during the pixel displacement to the second frame. Secondly, when the cluster containing adjacent four pixels in the first frame moves to the second frame, no other pixels will flow into the quadrilateral formed by them. According to the two geometrical constraints, the optical flow non-intersection loss and the optical flow non-blocking loss in the non-occlusion regions are proposed. Two loss functions punish the irregular and inexact optical flows in the non-occlusion regions. The experiments on datasets demonstrated that the proposed unsupervised losses of optical flow based on the geometric laws in non-occlusion regions make the estimated optical flow more refined in detail, and improve the performance of unsupervised learning of optical flow. In addition, the experiments training on synthetic data and evaluating on real data show that the generalization ability of optical flow network is improved by our proposed unsupervised approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Based on Deep Learning and Collaborative Cloud-edge Computation

Surface Defect Detection Based on Deep Learning and Collabor...

引用

International Conference on Computer and Communications (ICCC)

作者： Shunjie He Bo Yang Dafeng Zhu Cheng Li Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai China

ISBN: (纸本)9781665409513

Surface defect detection is a fundamental step of quality management. Nowadays, surface defect detection system based on machine vision technology has made great progress which can gradually replace the human inspector. With the help of convolutional neural networks, the accuracy and stability of the surface defect detection algorithm are improving rapidly. However, it is difficult to process the images which have small defect areas and complex backgrounds. Furthermore, lacking defective samples and limited computation resources are also tough problems. To deal with these problems, a two-stage algorithm combined with object detection and classification networks is proposed. Transform learning and data augmentation are used to deal with the problem of lacking defect samples. Besides, a detection system based on collaborative cloud-edge computation is designed to improve the performance of the algorithm. The result shows that the proposed method has high performance and low requirements of computation resources.

关键词： Training Collaboration Transforms Object detection Classification algorithms Convolutional neural networks Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Model-Free Sliding Mode Iterative Learning control for Cz Silicon Single Crystal Diameter

Model-Free Sliding Mode Iterative Learning Control for Cz Si...

引用

第三十九届中国控制会议

作者： Yin Wan Ding Liu Junchao Ren Congcong Liu Jie Sun National & Local Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology

Aiming at the complex nonlinear dynamic time-varying characteristics for Czochralski（Cz） silicon single crystal growth process and the difficulty in modeling and controlling the crystal diameter by conventional mechanisms, based on the idea of data-driven modeling and control, this paper proposes an improved model-free sliding mode iterative learning control（MFA-SMILC） method. First, a data-driven model of crystal diameter is established using an extreme learning machine（ELM）with actual process data;Then, based on the compact-format dynamic linear（CFDL） data model, a discrete sliding mode control algorithm is used to design a data-driven controller structure for crystal diameters, and the stability of the iterative tracking error is verified by the stability analysis;Finally, the proposed MFA-SMILC controller is applied to silicon single crystal diameter control, and compared with the conventional model-free adaptive iterative learning control（MFA-ILC）, it is found that MFASMILC has faster response speed and convergence speed, which verifies the effectiveness of the proposed control method.

关键词： Cz silicon single crystal growth Crystal diameter Model free iterative learning control Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of Pumping Cell of Nox Sensor - Part Ii: Nox Pumping Cell

SSRN

引用

SSRN 2022年

作者： Wang, Zhen Deng, Zhong-Hua Wang, Jie Lin, Wei-Xun Fu, Xiao-Wei Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Imaging Processing and Intelligent Control Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Guangdong Shenzhen518055 China Lambda Company Jiangsu Changzhou213100 China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China

To improve the performance of the NOx sensor, a combined model based on the electrochemical model and the diffusion model is developed for the NOx pumping cell of the NOx sensor. Considering that a small amount of oxygen enters the third chamber and part of NO is decomposed in the second chamber, the electrochemical model simultaneously considers the reactions of NO and oxygen at cathode, and the diffusion model additionally considers the diffusion of oxygen and the decomposition of NO. To validate the model at different gas concentrations, the sensor is mounted on the designed test rig. Then, the simulation results are compared with experimental data from the test rig and good agreement is obtained. In addition, three key parameters of the model of the NOx pumping cell are analyzed. The values and changing trends of these three parameters are given in the paper. © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

FreeDriveRF: Monocular RGB Dynamic NeRF without Poses for Autonomous Driving via Point-Level Dynamic-Static Decoupling

arXiv

引用

arXiv 2025年

作者： Wen, Yue Song, Liang Liu, Yijia Zhu, Siting Miao, Yanzi Han, Lijun Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Dimanshen Technology Co. Ltd. China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China

Dynamic scene reconstruction for autonomous driving enables vehicles to perceive and interpret complex scene changes more precisely. Dynamic Neural Radiance Fields (NeRFs) have recently shown promising capability in scene modeling. However, many existing methods rely heavily on accurate poses inputs and multi-sensor data, leading to increased system complexity. To address this, we propose FreeDriveRF, which reconstructs dynamic driving scenes using only sequential RGB images without requiring poses inputs. We innovatively decouple dynamic and static parts at the early sampling level using semantic supervision, mitigating image blurring and artifacts. To overcome the challenges posed by object motion and occlusion in monocular camera, we introduce a warped ray-guided dynamic object rendering consistency loss, utilizing optical flow to better constrain the dynamic modeling process. Additionally, we incorporate estimated dynamic flow to constrain the pose optimization process, improving the stability and accuracy of unbounded scene reconstruction. Extensive experiments conducted on the KITTI and Waymo datasets demonstrate the superior performance of our method in dynamic scene modeling for autonomous driving. Our implementation will be available at https://***/IRMVLab/FreeDriveRF. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

fMRI-based Brain Disease Diagnosis: A Graph Network Approach

TechRxiv

引用

TechRxiv 2023年

作者： Chen, Qi-Qi Gao, Yubing Tong, Wei Li, Ping Wu, Edmond Q. The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Nanjing University of Science and Technology Jiangsu210008 China The School of Biological Science and Medical Engineering Beihang University Beijing100191 China The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

As a non-invasive brain imaging technology, functional magnetic resonance imaging (fMRI) provides a basic tool for brain functional network modeling and brain disease diagnosis. Problems, such as large number of parameters, low training efficiency, and poor interpretability, are encountered in mainstream models because of the high complexity of fMRI and brain networks. To solve these problems, a novel structure feature combined graph neural network (SFC-GNN) with a low number of parameters is proposed. In particular, SFC-GNN is composed of 1) the graph convolution layer of the brain region perception and 2) the node pooling layer of the graph structure feature (GSF). It also receives the sparse brain graph modeled by each subject’s fMRI as input. Especially, the GSF layer can select brain regions that are important for classification, thereby localizing all active regions related to brain disease. Moreover, a group network is constructed according to the correlation among subjects, and SFC-GNN can be extended further to a node classification model to achieve better diagnosis performance. The proposed method has been validated on the ABIDE and ADNI datasets, thereby showing the effectiveness of our proposed method in various experiments. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Collision Detection, Localization and Force Estimation for a Soft Cable-driven Robot Manipulator

Towards Collision Detection, Localization and Force Estimati...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yuxin Wang Hesheng Wang Fan Xu Junzhi Yu Weidong Chen Yun-Hui Liu Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Institute of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai China College of Engineering Peking University Beijing China The Chinese University of Hong Kong Hong Kong

Soft robots have been applied widely to various constrained scenarios due to the advantages over traditional rigid manipulators such as softness, deformability and adaptability to constrained surroundings. To make full use of this merit, this paper proposes a method that integrates collision detection, localization and force estimation for a cable-driven soft manipulator without any prior geometrical knowledge of its surroundings. First of all, a collision detection algorithm is presented based upon Cosserat-rod statics by a threshold method through using the cable tension and the shape information, which are obtained by the load cells and the Vicon system, respectively. Secondly, a collision localization and force estimation method is proposed through optimizing the discrepancy between the actual and the theoretical shapes. Finally, experiments are carried out to validate these algorithms. The experimental results demonstrate that the site, the magnitude as well as the direction can be estimated.

关键词： Location awareness Shape Conferences Force Estimation Soft robotics Manipulators

来源：评论

学校读者我要写书评

暂无评论

Power Loss Analysis of Three-Phase Four-leg Four-Wire Inverter Using SiC/Si HyS 2

Power Loss Analysis of Three-Phase Four-leg Four-Wire Invert...

引用

2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021

作者： Jing, Zhengting Fu, Yongsheng Chen, Jianfei Ren, Haipeng Xi'An Technological University School of Electrical Information Engineering Xi'an710021 China Xi'An Technological University School of Mechatronic Engineering And the School of Electrical Information Engineering Xi'an710021 China University of Maryland Department of Electrical and Computer Engineering College ParkMD20742 United States Xi'An Technological University School of Mechatronic Engineering Xi'an710021 China Shaanxi Key Laboratory of Comple System Control and Intelligent Information Xi an University of Technology Xi'an710048 China

ISBN: (纸本)9781665400640

Three-phase four-leg four-wire voltage source inverter (3P4L4W VSI) attracts more attention in many power electronics applications due to its flexibility for both balanced and unbalanced loads, where the power efficiency is a critical point. Conventional Si semiconductor devices suffer from large switching loss due to large parasitic capacitances and thus limit its switching frequency. As a result, it further limits the power density and efficiency improvement. The SiC/Si hybrid switch formed by SiC-MOSFET and Si-IGBT in parallel (SiC/Si HyS) can improve the switching frequency with high efficiency and low cost, which helps to design a power converter with high power density and high efficiency. However, the application of SiC/Si HyS in 3P4L4W faces some challenges, such as the drive circuit design, the proper delay selection, etc.. In this paper, a SiC/Si HyS based 3P4L4W VSI is introduced and the optimal turn-off time delay selection for the SiC/Si HyS used in 3P4L4W VSI is analyzed. A systematical way to calculate the power loss in the SiC/Si HyS is presented. A 5-kW/50kHz 3P4L4W VSI is taken as an example for validating the theory and method. It is found the peak efficiency of the 3P4L4W VSI is 97.5%, and the unbalanced phase load leads to more power loss and degrade the efficiency. The work in this paper provides practical guidance for a SiC/Si HyS based 3P4L4W VSI inverter design. © 2021 IEEE.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Zeng, Honghao Wang, Ziliang Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FD United Kingdom

Real-time 3D human pose estimation is crucial for human-computer interaction. It is cheap and practical to estimate 3D human pose only from monocular video. However, recent bone splicing based 3D human pose estimation method brings about the problem of cumulative error. In this paper, the concept of virtual bones is proposed to solve such a challenge. The virtual bones are imaginary bones between non-adjacent joints. They do not exist in reality, but they bring new loop constraints for the estimation of 3D human joints. The proposed network in this paper predicts real bones and virtual bones, simultaneously. The final length of real bones is constrained and learned by the loop constructed by the predicted real bones and virtual bones. Besides, the motion constraints of joints in consecutive frames are considered. The consistency between the 2D projected position displacement predicted by the network and the captured real 2D displacement by the camera is proposed as a new projection consistency loss for the learning of 3D human pose. The experiments on the Human3.6M dataset demonstrate the good performance of the proposed method. Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints. Copyright © 2021, The Authors. All rights reserved.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Utility-Oriented Underwater Image Quality Assessment Based on Transfer Learning

arXiv

引用

arXiv 2022年

作者： Chen, Weiling Lin, Rongfu Liao, Honggang Zhao, Tiesong Gu, Ke Le Callet, Patrick Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou350108 China Peng Cheng Laboratory Shenzhen518000 China The Faculty of Information Technology Beijing University of Technology Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Équipe Image Perception et Interaction Laboratoire des Sciences du Numérique de Nantes Université de Nantes France

The widespread image applications have greatly promoted the vision-based tasks, in which the Image Quality Assessment (IQA) technique has become an increasingly significant issue. For user enjoyment in multimedia systems, the IQA exploits image fidelity and aesthetics to characterize user experience;while for other tasks such as popular object recognition, there exists a low correlation between utilities and perceptions. In such cases, the fidelity-based and aesthetics-based IQA methods cannot be directly applied. To address this issue, this paper proposes a utility-oriented IQA in object recognition. In particular, we initialize our research in the scenario of underwater fish detection, which is a critical task that has not yet been perfectly addressed. Based on this task, we build an Underwater Image Utility Database (UIUD) and a learning-based Underwater Image Utility Measure (UIUM). Inspired by the top-down design of fidelity-based IQA, we exploit the deep models of object recognition and transfer their features to our UIUM. Experiments validate that the proposed transfer-learning-based UIUM achieves promising performance in the recognition task. We envision our research provides insights to bridge the researches of IQA and computer vision. Copyright © 2022, The Authors. All rights reserved.

关键词： Multimedia systems

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：