检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Qi Li Ziyi Shen Qian Li Dean C Barratt Thomas Dowrick Matthew J Clarkson Tom Vercauteren Yipeng Hu Department of Medical Physics and Biomedical Engineering Centre for Medical Image Computing Wellcome/EPSRC Centre for Interventional and Surgical Sciences University College London London U.K. State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China School of Biomedical Engineering & Imaging Sciences King’s College London London U.K.

Three-dimensional (3D) freehand ultrasound (US) reconstruction without a tracker can be advantageous over its two-dimensional or tracked counterparts in many clinical applications. In this paper, we propose to estimate 3D spatial transformation between US frames from both past and future 2D images, using feed-forward and recurrent neural networks (RNNs). With the temporally available frames, a further multi-task learning algorithm is proposed to utilise a large number of auxiliary transformation-predicting tasks between them. Using more than 40,000 US frames acquired from 228 scans on 38 forearms of 19 volunteers in a volunteer study, the hold-out test performance is quantified by frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, based on ground-truth from an optical tracker. The results show the importance of modelling the temporal-spatially correlated input frames as well as output transformations, with further improvement owing to additional past and/or future frames. The best performing model was associated with predicting transformation between moderately-spaced frames, with an interval of less than ten frames at 20 frames per second (fps). Little benefit was observed by adding frames more than one second away from the predicted transformation, with or without LSTM-based RNNs. Interestingly, with the proposed approach, explicit within-sequence loss that encourages consistency in composing transformations or minimises accumulated error may no longer be required. The implementation code and volunteer data 1 will be made publicly available ensuring reproducibility and further research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of real-time digital twin model of autonomous field robot for prediction of vehicle stability

引用

Journal of institute of Control, robotics and systems 2021年第3期27卷 109-196页

作者： Han, Jong-Boo Kim, Sung-Soo Song, Ha-Jun Ocean System Engineering Research Division Korea Research Institute of Ships & Ocean Engineering Korea Republic of Department of Mechanics Engineering Chungnam National University Korea Republic of Intelligent Robotics Research Center Korea Electronics Technology Institute Korea Republic of

This study aimed to develop a real-time digital twin model for an autonomous field robot. Autonomous control involves controlling vehicle stability parameters such as angular and translational velocities. However, stability is lost when a vehicle run over rough terrain. Therefore, it is necessary to accurately predict vehicle stability in real time using a digital twin model. In this study, we developed the digital twin model for an autonomous driving robot using real-time multibody dynamics. To verify the accuracy, we carried out real road tests on a flat road, and roads with symmetric and asymmetric bumps. We regulated the dynamic parameters such as the position of the center of gravity and coefficients of force elements in the built digital twin model and evaluated its efficiency as well. © ICROS 2021.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

BAN: A Universal Paradigm for Cross-Scene Classification Under Noisy Annotations From RGB and Hyperspectral Remote Sensing Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Chen, Wentang Wen, Yibin Zheng, Juepeng Huang, Jianxi Fu, Haohuan Sun Yat-sen University School of Artificial Intelligence Zhuhai519082 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering Robotics Institute Hangzhou310027 China Southwest Jiaotong University Faculty of Geosciences and Engineering Chengdu610032 China China Agricultural University College of Land Science and Technology Beijing100107 China Ministry of Agriculture and Rural Affairs Key Laboratory of Remote Sensing for Agri-Hazards Beijing100125 China Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518071 China Tsinghua University Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Beijing100190 China National Supercomputer Center in Shenzhen Shenzhen518071 China

While domain adaptation (DA) methods have made significant strides in remote sensing community, most current works assume that the source domain labels are accurate. However, limited emphasis has been placed on the scenario where source data are mislabeled with noisy annotations, which is more common in real applications and referred to as noisy DA (NDA). This article formulates remote sensing cross-scene classification on NDA scenarios and proposes a novel network called bilateral adaptation network (BAN), which consists of two parts: 1) forward learning (FL), which utilizes a model learning from the noisy source domain and transfers knowledge to target domain;and 2) backward learning (BL), which utilizes a dual model to acquire knowledge from the target domain and transfer it to source domain. We conduct two parts alternately and adopt a symmetrical Kullback-Leibler (KL) loss to align predictions of the model and its dual model in the same domain. This interactive strategy is able to explore bilateral relationships between domains, implicitly reducing label noise in the source domain. In addition, BAN could serve as a universal paradigm to not only improve the existing NDA methods but also enhance recent DA approaches. Comprehensive evaluations on three publicly available RGB-band remote sensing datasets and two hyperspectral datasets validate the superior effectiveness of our proposed BAN. BAN improves the average accuracy by 6.70%-15.70% on RGB datasets and overall accuracy (OA) by 1.36%-3.14% on hyperspectral datasets with flip-20% noise compared to other state-of-the-art DA and NDA approaches. Promising results indicate the potential of our approach in tackling more general and practical problems with noisy source domain. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Estimation of Deformation for Self-balancing Lower Limb Exoskeleton Only Using Force/Torque Sensors

Estimation of Deformation for Self-balancing Lower Limb Exos...

引用

IEEE International Conference on robotics and Biomimetics

作者： Ziqiang Chen Ming Yang Feng Li Wentao Li Jinke Li Dingkui Tian Jianquan Sun Yong He Xinyu Wu Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Science and Technology of China Hefei China China Construction Third Bureau First Engineering MEP Co. Ltd. Shenzhen China

This paper presents a general estimation method of deformation for the self-balancing lower limb exoskeleton (SBLLE). In particular, we propose a Bi-LSTM deformation estimator (BLDE) to predict and compensate for the deformation of SBLLE based on the current force and torque data measured by force/torque (F/T) sensors. First, we choose four movements including squatting down and up, waist twisting, left foot lifting, and right foot lifting to mimic the constituent action of walking motion. The deformation data set is obtained through the motion capture analysis system and offline planning trajectories, and the relative F/T data set is obtained by the F/T sensors embedded in the feet of SBLLE. Second, the BiLSTM network is trained to learn the relationship between the deformation and F/T and verified on the test set. After that, BLDE is added to the control system of SBLLE to estimate and compensate for the deformation. Finally, four same movements and the walking experiment are conducted on the exoskeleton AutoLEE-G2 with BLDE. The experimental results have proven that BLDE can predict and compensate for deformation by only using F/T sensors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structural design and analysis of a permanent-magnet wheeled pipe robot with pipe diameter adaption capability

Structural design and analysis of a permanent-magnet wheeled...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zechao Wang Mingyuan Wang Jianjun Yuan Shiqiang Wang Liang Du Sheng Bao Weiwei Wan Shanghai Robotics Institute Shanghai University Shanghai China Safety Environment Quality Surveillance and Inspection Research Institute of CNPC Chuanqing Drilling & Exploration Guanghan Sichuan China Department of System Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan

ISBN: (纸本)9781665481106

Pipe robots can replace workers to work in harsh environments. Generally, most of the existing pipe robots can only move in pipes with constant diameters, but cannot move in pipes with variable diameters. To this end, we propose a permanent-magnet wheeled pipe robot. We introduce a differential mechanism as well as a slide block and slide rail structure so that the robot can move on the pipe with variable diameters. Firstly, the CAD model is established by SOLIDWORKS, the self-adaptive diameter-variable mechanism of the robot is analyzed, and the applicable pipe diameter range is obtained. Then we use MATLAB to carry out numerical analysis and obtain the relationship of the attraction force of the magnetic wheel. Finally, the MAXWELL module in the ANSYS ELECTRONICS software is used to simulate the magnetic wheel. Through simulation, we obtain the curve of magnetic field strength and the attraction force of the magnetic wheel. The hypothesis of our theory is tested.

关键词： Legged locomotion Solid modeling Force Wheels Software Numerical models Magnetic analysis

来源：评论

学校读者我要写书评

暂无评论

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A Study on Giant Magnetostrictive Actuator for Interior Sound Control system of the Ultra-Compact Mobility: Fundamental Consideration on Formation of the Giant Magnetostrictive Phases Depending on Heat Treatment Condition 27

A Study on Giant Magnetostrictive Actuator for Interior Soun...

引用

27th International Conference on Electrical Machines and systems, ICEMS 2024

作者： Kato, Taro Naganuma, Ryusei Bando, Koki Sawada, Kentaro Wenbao, Wu Kobayashi, Ikkei Kuroda, Jumpei Uchino, Daigo Ogawa, Kazuki Ikeda, Keigo Endo, Ayato Kato, Hideaki Narita, Takayoshi Furui, Mitusaki Tokyo University of Technology Department of Mechanical Engineering 1404-1 Katakura Hachioji-shi Tokyo192-0982 Japan Sustainable Engineering Program Graduate School of Engineering Tokyo University of Technology 1404-1 Katakura Hachioji-shi Tokyo192-0982 Japan Tokai University Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan Tokai University Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan Numazu College Department of Mechanical Engineering Ohoka 3600 Shizuoka Numazu-shi410-0022 Japan Aichi University of Technology Department of Electronic Robotics 50-2 Manori Nishisako-machi Aichi Gamagori-shi443-0047 Japan Hokkaido University of Science Department of Mechanical Engineering 7-Jo 15-4-1 Maeda Teine Hokkaido Sapporo006-8585 Japan Fukuoka Institute of Technology Department of Electrical Engineering Wajiro Higashi 3-30-1 Higashi-ku Fukuoka Fukuoka-shi811-0295 Japan Tokai University Department of Mechanical System Engineering Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan

ISBN: (纸本)9784886864406

An active noise control system using giant magnetostrictive actuator has been proposed as a countermeasure for interior noise of the ultra-compact mobilities, which is a new transportation tools. In this paper, as basic research toward the development of the proposed giant magnetostrictive actuator for active noise control, we conduct experiments on the material properties when terbium, dysprosium, and iron powder, which make up the giant magnetostrictive material, are mixed and the heat treatment conditions are changed. In this study, the heat treatment temperature was varied from 800°C to 1100°C in 100°C incrementsbased on the equilibrium state temperature of each material, and the heat treatment time was set in 30-minute increments from 1 hour to 3 hours. As a result, TbFe2 was confirmed after heat treatment at an electric furnace temperature of 1000°C for 3 hours, although its strength was insufficient. © 2024 The institute of Electrical Engineers of Japan.

关键词： Active noise control

来源：评论

学校读者我要写书评

暂无评论

A Study on Giant Magnetostrictive Actuator for Interior Soun...

引用

International Conference on Electrical Machines and systems (ICEMS)

作者： Taro Kato Ryusei Naganuma Koki Bando Kentaro Sawada Wu Wenbao Ikkei Kobayashi Jumpei Kuroda Daigo Uchino Kazuki Ogawa Keigo Ikeda Ayato Endo Hideaki Kato Takayoshi Narita Mitusaki Furui Department of Mechanical Engineering Tokyo University of Technology Hachioji-shi Tokyo Japan Sustainable Engineering Program Graduate School of Engineering Tokyo University of Technology Hachioji-shi Tokyo Japan Course of Mechanical Engineering Tokai University Hiratsuka-shi Kanagawa Japan Course of Science and Technology Tokai University Hiratsuka-shi Kanagawa Japan Department of Mechanical Engineering National Institute of Technology (KOSEN) Numazu College Numazu-shi Shizuoka Japan Department of Electronic Robotics Aichi University of Technology Gamagori-shi Aichi Japan Department of Mechanical Engineering Hokkaido University of Science Sapporo Hokkaido Japan Department of Electrical Engineering Fukuoka Institute of Technology Fukuoka-shi Fukuoka Japan Department of Mechanical System Engineering Tokai University Hiratsuka-shi Kanagawa Japan

ISBN: (数字)9784886864406

ISBN: (纸本)9798350379105

An active noise control system using giant magnetostrictive actuator has been proposed as a countermeasure for interior noise of the ultra-compact mobilities, which is a new transportation tools. In this paper, as basic research toward the development of the proposed giant magnetostrictive actuator for active noise control, we conduct experiments on the material properties when terbium, dysprosium, and iron powder, which make up the giant magnetostrictive material, are mixed and the heat treatment conditions are changed. In this study, the heat treatment temperature was varied from $800^{\circ}\mathrm{C}$ to $1100^{\circ}\mathrm{C}$ in $100^{\circ}\mathrm{C}$ incrementsbased on the equilibrium state temperature of each material, and the heat treatment time was set in 30-minute increments from 1 hour to 3 hours. As a result, TbFe2 was confirmed after heat treatment at an electric furnace temperature of $1000^{\circ}\mathrm{C}$ for 3 hours, although its strength was insufficient.

关键词： Actuators Heat treatment Powders Temperature Magnetostriction Noise Terbium Iron Resistance heating Material properties

来源：评论

学校读者我要写书评

暂无评论

High-density Baropodometry Platform Based on Vision Based Tactile Sensing

High-density Baropodometry Platform Based on Vision Based Ta...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yueshi Dong Jieji Ren Ningbin Zhang Weijing Zhao Jian Zhou Guoying Gu School of Mechanical Engineering The State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University University School of Medicine Shanghai China Department of Endocrinology and Metabolism Sixth People’s Hospital Shanghai Jiao Tong University School of Medicine Shanghai China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Plantar pressure distribution measurement is significant for healthy monitoring and disease diagnosis. However, existing equipment lack of high-density resolution and may lead under-diagnosed of small abnormal regions. To address problem, we propose a special high resolution and low cost Baropodometry based on vision based tactile sensing (VBTS). Specially, we design a measurement platform with larger-scale sensing range (280 mm x 150 mm) and high-density resolution (440 ppi). To achieve the homogeneous illumination for the measure area, we also propose normally distributed light sources around the platform, and delicately adjust the incident angle to optimize the reconstruction performance. Besides, we design a example-based method to calibrate the platform and build a look-up table to reconstruct the plantar geometry from observed image. Experiments show the high lateral resolution that can discriminate the details (<2 mm), and the depth measurement accuracy is 68.5%. The experiments of reconstruction of plantar pressure depth map and identification of tumours show its’ advantage for providing adaptive high-resolution plantar topography and pressure measurement.

关键词： Performance evaluation Sensors Pressure measurement Surface topography Table lookup Object recognition Surface cracks Monitoring Image reconstruction Tumors

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：