检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ghafoor, Mehwish Mahmood, Arif Bilal, Muhammad Department of Computer Science Information Technology University Lahore Pakistan Center of Excellence in Intelligent Engineering Systems Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D joint observations. This paper introduces a Dual Transformer Fusion (DTF) algorithm, a novel approach to obtain a holistic 3D pose estimation, even in the presence of severe occlusions. Confronting the issue of occlusion-induced missing joint data, we propose a temporal interpolation-based occlusion guidance mechanism. To enable precise 3D Human Pose Estimation, our approach leverages the innovative DTF architecture, which first generates a pair of intermediate views. Each intermediate-view undergoes spatial refinement through a self-refinement schema. Subsequently, these intermediate-views are fused to yield the final 3D human pose estimation. The entire system is end-to-end trainable. Through extensive experiments conducted on the Human3.6M and MPI-INF-3DHP datasets, our method’s performance is rigorously evaluated. Notably, our approach outperforms existing state-of-the-art methods on both datasets, yielding substantial improvements. The code is available here: https://***/MehwishG/DTF. © 2024, CC BY-NC-ND.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

FedATM: Adaptive Trimmed Mean based Federated Learning against Model Poisoning Attacks

FedATM: Adaptive Trimmed Mean based Federated Learning again...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Kenji Nishimoto Yi-Han Chiang Hai Lin Yusheng Ji Department of Electrical and Electronic Systems Engineering Osaka Metropolitan University Osaka Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan

Federated learning (FL) has received explosive research attention in that it enables multiple clients to collaboratively train a global model without sharing raw data in between, thereby facilitating the protection of data privacy. Typically, FL can converge well after a couple of communication rounds, but its convergence is vulnerable to the model poisoning attacks induced by fake clients. Existing works have been devoted to designing various post-processing techniques to alleviate the adverse effects of the model poisoning attacks, they, however, fail to accurately trim off the local models of fake clients while keeping those of benign clients intact during model averaging. In this paper, we investigate the problem of model poisoning attacks in federated learning (FL). To cope with this problem, we design the federated adaptive trimmed mean (FedATM) algorithm, where the clients are sorted in accordance with the distances between local models, and a distance-based threshold is designed to detect the presence of fake clients, thereby preventing the fake local models from destroying the accuracy of model averaging. Simulation results show that the proposed FedATM algorithm is robust to model poisoning attacks as compared to several comparison schemes under various data heterogeneities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Holographic Feedback Controlled Micro-Stereolithography for Constructing Microstructures with Tuned Mechanical Property 7

Holographic Feedback Controlled Micro-Stereolithography for ...

引用

7th International Symposium on Autonomous systems, ISAS 2024

作者： Dong, Xinyi Zhao, Yanfeng Zhang, Qiwen Sun, Letian Wang, Heng Shi, Qing Huang, Qiang Wang, Huaping Beijing Institute of Technology School of Mechatronical Engineering Beijing China Beijing Institute of Technology School of Future Technologies Beijing China Beijing Institute of Technology School of Information and Electronics Beijing China Beijing Institute of Technology Beijing Advanced Innovation Center For Intelligent Robots and Systems Beijing China

ISBN: (纸本)9798350363173

The fabrication of biocompatible scaffolds mimicking the stiffness of real human tissues holds paramount significance in the fields of tissue engineering and cell biology. However, existing stereolithography technologies still face challenges in precise control of the mechanical stiffness distribution of biological microstructures due to the difficulty in real-time monitoring of their mechanical properties during printing. In this study, we propose an innovative projection-based micro-stereolithography control method based on real-time holographic phase feedback to achieve high-precision fabrication of microstructures with region-specific mechanical stiffness distributions. Employing the minimum mean square error method, we calculate the optimal single mapping transformation matrix from holograph to DMD (digital micromirror device) mask for the corresponding calibration. The real-time holographic phase serves as feedback data to correct and modify the dynamic DMD mask. Additionally, adjusting the sampling interval and threshold parameters in feedback control enhances precision. Through this method, we constructed a complex mechanical property distribution of a windmill-shaped hydrogel microstructure. Experimental results demonstrate that our control method reduces the error in mechanical stiffness from 19.2 kPa in the case of no feedback control to 3.68 kPa, representing an 80.8% improvement in accuracy. The novel approach for constructing complex mechanical property distributions of microstructures in vitro has significant potential in tissue engineering in the future. © 2024 IEEE.

关键词： Microstructure

来源：评论

学校读者我要写书评

暂无评论

Design of a Drone System for Large Thermal Power Boiler Inspection

Design of a Drone System for Large Thermal Power Boiler Insp...

引用

Automation, Robotics and Computer engineering (ICARCE), International Conference on

作者： Yifan Liu Fu Kang Runjie Shen College of Electronic and Information Engineering Tongji University Shanghai China Sino-German Center of Intelligent Systems and College of Electronic and Information Engineering Tongji University Shanghai China

Drones virtually immune to human survival and physiological limitations and physical injuries, and are capable of performing its intended tasks properly in dangerous, contaminated environments. We propose a drone localization and navigation system in the thermal power boiler. Multiple sensor fusion algorithms, such as UWB, lidar, and IMU, are used to locate and establish maps. The system has outstanding advantages in dusty, dark and vertical feature degradation thermal power boiler drone inspection missions. Moreover, considering that there are no complex and dense obstacles within the boiler, this system only designs a local planner to implement autonomous cruise control within the boiler, which supports initial coordinate system calibration and real-time heading control. Finally, we built a simulation platform to test several performances of the system and compared with traditional localization algorithms. The experimental results verify the feasibility of the multi-sensor fusion algorithm and the reliability of the trajectory planning navigation algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Collaborative Robotics in Top View Surveillance:A Framework for Multiple Object Tracking by Detection Using Deep Learning

引用

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1253-1270页

作者： Imran Ahmed Sadia Din Gwanggil Jeon Francesco Piccialli Giancarlo Fortino the Center of excellence in Information Technology Institute of Management SciencesPeshawar 25000Pakistan the Department of Information and Communication Engineering Yeungnam UniversitySouth Korea the School of Electronic Engineering Xidian UniversityXi’an 710071China the Department of Embedded Systems Engineering Incheon National UniversityIncheon 22012Korea the Department of Mathematics and Applications“R.Caccioppoli” University of Naples Federico IINapoli 80138Italy the Department of Informatics ModelingElectronics and SystemsUniversity of CalabriaRendeCS 87036Italy

Collaborative Robotics is one of the high-interest research topics in the area of academia and *** has been progressively utilized in numerous applications,particularly in intelligent surveillance *** allows the deployment of smart cameras or optical sensors with computer vision techniques,which may serve in several object detection and tracking *** tasks have been considered challenging and high-level perceptual problems,frequently dominated by relative information about the environment,where main concerns such as occlusion,illumination,background,object deformation,and object class variations are *** order to show the importance of top view surveillance,a collaborative robotics framework has been *** can assist in the detection and tracking of multiple objects in top view *** framework consists of a smart robotic camera embedded with the visual processing *** existing pre-trained deep learning models named SSD and YOLO has been adopted for object detection and *** detection models are further combined with different tracking algorithms,including GOTURN,MEDIANFLOW,TLD,KCF,MIL,and *** algorithms,along with detection models,help to track and predict the trajectories of detected *** pre-trained models are employed;therefore,the generalization performance is also investigated through testing the models on various sequences of top view data *** detection models achieved maximum True Detection Rate 93%to 90%with a maximum 0.6%False Detection *** tracking results of different algorithms are nearly identical,with tracking accuracy ranging from 90%to 94%.Furthermore,a discussion has been carried out on output results along with future guidelines.

关键词： Collaborative robotics deep learning object detection and tracking top view video surveillance

来源：评论

学校读者我要写书评

暂无评论

Cohort-based Power Scaling and Gradient Recovery for Over-The-Air Federated Learning

Cohort-based Power Scaling and Gradient Recovery for Over-Th...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Koudai Terai Yi-Han Chiang Hai Lin Yusheng Ji Department of Electrical and Electronic Systems Engineering Osaka Metropolitan University Osaka Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan

Federated learning (FL) enables edge devices (EDs) to collaboratively train a single machine learning (ML) model maintained by an edge server (ES) without sharing their raw data contents, thereby facilitating distributed ML while protecting data privacy. In fact, FL can be implemented in wireless environments by means of the over-the-air (OTA) computation, which takes advantage of the waveform-superposition property of wireless signals to receive local gradients from EDs without the needs of increased bandwidth. Despite the existing works devoted to power control and client selection in OTA-FL systems, they mostly neglect how to construct cohorts (i.e., a subset of EDs that have similar channel coefficients) to elevate the quality of the aggregated local gradients. In this paper, we investigate the problem of gradient aggregation and recovery in OTA-FL systems. To cope with this problem, we propose the cohort-based power scaling and gradient recovery (CRAIC) algorithm, where we first construct cohorts based on uplink channel coefficients, and then we adjust the transmit powers of EDs and recover the aggregated local gradients in a cohort basis. Simulation results show that our proposed solution outperforms several comparison schemes, and we further evaluate how it performs under various parameter settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual Measurement Based on Marking Points Regression and Semantic information

Monocular Visual Measurement Based on Marking Points Regress...

引用

Chinese Automation Congress (CAC)

作者： Dingliang Huang Junzhu Chen Yanchao Chen Shuwen Hang Chenyang Sun Junrui Zhang Quanxi Zhan Runjie Shen College of Electronics and Information Engineering Tongji University Shanghai China College of Electronics and Information Engineering Sino-German Center of Intelligent Systems Tongji University Shanghai China

This paper studies the visual measurement problem in the intelligent warehouse stocktaking task and designs a set of monocular visual measurement methods that can be used in the UAV-AGV collaborative autonomous warehouse stocktaking system. Monocular visual measurement attempts to complete the measurement task of the target through the information of a single image. Such methods are usually applied to the size estimation of human bodies or small objects and lack practice in large-scale industrial scenes. Compared with the traditional monocular visual measurement algorithm, our method extracts and utilizes the structured information and semantic information in the image. We design the BoxMPR network to undertake the regression task of upper corners in cargo and use LEDNet [1] to identify the semantic information of shelves. Based on the understanding of the scene in an image, we join the real size of the shelf as prior information to measure the target. We systematically evaluate the proposed BoxMPR neural network and our measurement method, which can realize the centimeter-level measurement of the target area in the warehouse scene.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Consistent Extension of Networks of Digital Representations of Production System Assets

Consistent Extension of Networks of Digital Representations ...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Arndt Lüder David Hoffmann Kristof Meixner Paula Hünecke Stefan Biffl Otto-von-Guericke University Magdeburg Germany Austrian Center of Digital Production Vienna Austria CDL-SQI TU Wien Information Systems Engineering CDL-SQI TU Wien Information Systems Engineering Austrian Center of Digital Production Vienna Austria

Industry 4.0 use case on products along the production lifecycle require an extensible representation of PPR dependencies, which are distributed on PLM, CRM, and production system assets. This paper introduces the PPRplus modeling method to facilitate the digital representation of a product along the product lifecycle, including PPR dependencies, and knowledge about performance indicators. We initially evaluated the feasibility and effectiveness of the PPRplus modeling method with two use cases on work lines for metal processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved subarray coherence factor beamformer for ultrasound plane-wave imaging

Improved subarray coherence factor beamformer for ultrasound...

引用

2023 International Congress on Ultrasonics, ICU Beijing 2023

作者： Guan, Huchang Jiang, Chen Xu, Kailiang Ta, Dean Department of Biomedical Engineering School of Information Science and Technology Fudan University Shanghai200438 China State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai201203 China Micro-nano System Center School of Information Science and Technology Fudan University Shanghai200438 China State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Fudan University China

Coherent plane-wave compounding (CPWC) has gained significant traction in medical ultrasound imaging. The coherence factor (CF) weighting algorithm, a classical adaptive beamforming strategy, aims to enhance the CPWC imaging lateral resolution, but it also noticeably compromises the speckle patterns, *** a low signal-to-noise ratio (SNR). Delay multiply and sum (DMAS) has been proposed to reduce side lobes. However, the reconstructed image quality with DMAS is limited in terms of resolution and speckle level. In the present study, an improved subarray coherence factor (ISCF) algorithm is introduced by combining CF with DMAS strategies, aiming to improve the contrast and resolution while preserving the speckle level. The performance of the proposed algorithm is evaluated using simulation and phantom datasets. Results indicate that the resolution and the contrast of ISCF can be improved by 41.6% and 79.4%, respectively;compared with delay and sum (DAS) algorithm. Additionally, the resolution and the speckle level of ISCF can be improved by 10.6% and 35.7% compared with CF algorithm, respectively. The proposed ISCF algorithm outperforms CF in terms of resolution, contrast, and speckle preservation. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

High Resolution of City-Level Climate Simulation by GPU with Multi-physical Phenomena 18th

High Resolution of City-Level Climate Simulation by GPU with...

引用

18th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2021

作者： Watanabe, Koei Kikuchi, Kohei Boku, Taisuke Sato, Takuto Kusaka, Hiroyuki Master’s Program in Computer Science Graduate School of Systems and Information Engineering University of Tsukuba Tsukubashi Japan Center for Computational Sciences University of Tsukuba Tsukubashi Tennodi Japan

ISBN: (纸本)9783030935702

In this paper, we describe the Graphics Processing Unit (GPU) implementation of our City-LES code on detailed large eddy simulations, including the multi-physical phenomena on fluid dynamics, heat absorption and reflection by surface and building materials, cloud effects, and even sunlight effect. Because a detailed simulation involving these phenomena is required for analyses at the street level and several meters of resolution, the computation amount is enormous, and ordinary CPU computation cannot provide sufficient performance. Therefore, we implemented the entire code on GPU clusters with large-scale computing. We applied OpenACC coding to incrementally implement relatively easy programming and eliminate data transfers between the CPU and GPU memories. Based on this research, we determined that the elimination of data transfers is effective, even in the case where a part of the code execution on the GPU is slower than the CPU, owing to the absence of spatial parallelism. The objective of this study is to perform a complete climate simulation on a few square-kilometers field around the Tokyo Station, considering the finest resolution of the original highlighted area of the Marathon race in the Olympic Games Tokyo 2020. We successfully transferred the entire code to the GPU to provide approximately eight times the performance of CPU-only computation on multi-GPU per node with a large scale cluster. © 2022, IFIP International Federation for information Processing.

关键词： Graphics processing unit

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：