检索结果-内蒙古大学图书馆

Rational 3D object placement based on deep learning based plane detection

Multimedia Tools and Applications 2023年第28期82卷 44555-44576页

作者： Yang, Wei-Jong Lu, Li-Yu Chan, Din-Yuen Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung Taiwan Telecommunication Laboratories Chunghwa Telecom Co. Ltd. Internet of Things Laboratory Taoyuan Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi Taiwan

Effective acquisition of 3D planar features from a 2D image for immersive AR applications is challenging without any 3D depth information. In this paper, we present a novel planar object placement (POP) system for rational insertion of 3D objects on plane surfaces and fitting their plane orientations in a given 2D image. The POP system is composed of an adaptive edge extractor (AEE), a vanishing point detector (VPD), a rational fitting transformer (RFT) and a plane normal detection network (PNDnet), which performs the estimation of planar features. With the inputs of the color image and the guided edge map retrieved by the AEE, the PNDnet based on a gating weighted U-Net, whose gating weights are controlled by global cross-level connection (GCC) blocks, can properly extract 3D information including planar pixel-wise normal map, semantic plane-segmented map and plane-wise normal vectors. Simultaneously, with plane-wise normal vectors and the VPD-estimated vanishing points, the RFT can easily induce the best placement position for projecting the AR object on a destination plane with better coherent 3D perspectives. Besides, the POP system allows the users to make the subtle tunes of 3D orientation to the inserted object for personal preferences. Experimental results show that the proposed POP system, which successfully guides the 3D-inserted objects to match up the surfaces and orientations of the planes in the target image, will become an effective AR tool for the insertion of 3D objects in target images and videos in the future. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Vulcan: An Information-Driven Multi-Agent Path Finding Approach

Multi-Agent Vulcan: An Information-Driven Multi-Agent Path F...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jake Olkin Viraj Parimi Brian Williams Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Scientists often search for phenomenon of interest while exploring new environments. Autonomous vehicles are deployed to explore such areas where human-operated vehicles would be costly or dangerous. Online control of autonomous vehicles for information-gathering is called adaptive sampling and can be framed as a Partially Observable Markov Decision Process (POMDPs) that uses information gain as its principal objective. While prior work focuses largely on single-agent scenarios, this paper confronts challenges unique to multi-agent adaptive sampling, such as avoiding redundant observations, preventing vehicle collision, and facilitating path planning under limited communication. We start with Multi-Agent Path Finding (MAPF) methods, which address collision avoidance by decomposing the multi-agent path planning problem into a series of single-agent path planning problems. We present an extension to these methods called information-driven MAPF which addresses multi-agent information gain under limited communication. First, we introduce an admissible heuristic that relaxes mutual information gain to an additive function that can be evaluated as a set of independent single agent path planning problems. Second, we extend our approach to a distributed system that is robust to limited communication. When all agents are in range, the group plans jointly to maximize information. When some agents move out of range, communicating subgroups are formed and the subgroups plan independently. Since redundant observations are less likely when vehicles are far apart, this approach only incurs a small loss in information gain, resulting in an approach that gracefully transitions from full to partial communication. We evaluate our method against other adaptive sampling strategies across various scenarios, including real-world robotic applications. Our method was able to locate up to 200% more unique phenomena in certain scenarios, and each agent located its first unique phenomenon fast

关键词： Additives Markov decision processes Path planning Collision avoidance Autonomous vehicles Mutual information Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

An Approach Based on Knowledge Distillation for Lightweight Defect Classification of Green Plums

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 213-223页

作者： Wang, Jinhai Wang, Wei Liao, Lan Luo, Lufeng Lin, Xuemin Zeng, Xinan Foshan University School of Computer Science and Artificial Intelligence Foshan528000 China Foshan University Department of Food Science Foshan528000 China Foshan University Guangdong Key Laboratory of Intelligent Food Manufacturing Foshan528225 China Foshan University School of Mechatronic Engineering and Automation Foshan528000 China

During the cultivation and growth of green plums, various defects frequently occur, potentially affecting their overall quality and economic value. Accurate classification and identification of these defects have become essential components of the harvesting process, particularly when employing smart agricultural equipment. These defects pose significant challenges to the yield and quality of green plums, making their precise detection crucial for ensuring optimal output and economic efficiency. However, most contemporary research on fruit defect classification and grading using artificial intelligence techniques primarily focuses on accuracy, often neglecting the constraints imposed by limited resources. This study addresses the aforementioned challenges by employing knowledge distillation techniques to optimize the performance of a lightweight model. Specifically, during the knowledge distillation process, the vision transformer model, known for its robust recognition capabilities, was selected as the teacher model. The lightweight MobileNetv3 model, chosen for its ease of deployment, served as the student model and was trained using the Lion optimizer. In addition, the dual guidance learning module was designed to enhance knowledge transfer between the teacher and student models, thereby improving the overall capability of the student model. Experimental validation demonstrated that the proposed method excels in the green plum defect recognition task, with the student model, MobileNetv3, achieving an accuracy of 99.17% and exhibiting high performance in key metrics such as precision, recall, and F1-score. Notably, MobileNetv3 not only delivers exceptional performance but also features a low parameter count and computational complexity, facilitating its efficient deployment in practical applications. This study provides an effective and practical solution for the automatic identification and sorting of green plum defects, significantly advancing the development an

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Absorbing Interface Conditions for the Simulation of Wave Propagation on Non-Uniform Meshes

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 433-452页

作者： Changshi Li Yuhui Liu Fengru Wang Jerry Zhijian Yang Cheng Yuan Institute of Artificial Intelligence School of Computer ScienceWuhan UniversityWuhan 430072P.R.China School of Mathematics and Statistics Wuhan UniversityWuhan 430072P.R.China Hubei Key Laboratory of Computational Science Wuhan UniversityWuhan 430072P.R.China

We proposed absorbing interface conditions for the simulation of linear wave propagation on non-uniform *** on the superposition principle of second-order linear wave equations,we decompose the interface condition problem into two subproblems around the interface:for the first one the conventional artificial absorbing boundary conditions is applied,while for the second one,the local analytic solutions can be *** proposed interface conditions permit a two-way transmission of low-frequency waves across mesh interfaces which can be supported by both coarse and fine meshes,and perform a one-way absorption of high-frequency waves which can only be supported by fine meshes when they travel from fine mesh regions to coarse *** examples are presented to illustrate the efficiency of the proposed absorbing interface conditions.

关键词： Local time step non-uniform mesh absorbing interface condition

来源：评论

学校读者我要写书评

暂无评论

NOT ALL TASKS ARE BORN EQUAL: UNDERSTANDING ZERO-SHOT GENERALIZATION 11

NOT ALL TASKS ARE BORN EQUAL: UNDERSTANDING ZERO-SHOT GENERA...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhou, Jing Lin, Zongyu Zheng, Yanan Li, Jian Yang, Zhilin Tsinghua University China Department of Computer Science and Technology Tsinghua University China Shanghai Artificial Intelligence Laboratory China Shanghai Qi Zhi Institute China

Recent work has achieved remarkable zero-shot performance with multi-task prompted pretraining, but little has been understood. For the first time, we show that training on a small number of key tasks beats using all the training tasks, while removing these key tasks substantially hurts performance. We also find that these key tasks are mostly question answering (QA) tasks. These novel findings combined deepen our understanding about zero-shot generalization-training on certain tasks such as QA encodes general knowledge transferable to a wide range of tasks. In addition, to automate this procedure, we devise a method that (1) identifies key training tasks without observing the test tasks by examining the pairwise generalization results and (2) resamples training tasks for better data distribution. Empirically, our approach achieves improved results across various model scales and tasks. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel High-Efficiency Transaction Verification Scheme for Blockchain Systems

引用

computer Modeling in Engineering & sciences 2024年第5期139卷 1613-1633页

作者： Jingyu Zhang Pian Zhou Jin Wang Osama Alfarraj Saurabh Singh Min Zhu School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410015China Science and Technology on Information Systems Engineering Laboratory School of Systems EngineeringNational University of Defense TechnologyChangsha410073China Computer Science Department King Saud UniversityRiyadh11437Saudi Arabia Department of Artificial Intelligence and Big Data Woosong UniversityDaejeon34606South Korea College of Information Science and Technology Zhejiang Shuren UniversityHangzhou310015China

Blockchain can realize the reliable storage of a large amount of data that is chronologically related and verifiable within the *** technology has been widely used and has developed rapidly in big data systems across various *** increasing number of users are participating in application systems that use blockchain as their underlying *** the number of transactions and the capital involved in blockchain grow,ensuring information security becomes *** the verification of transactional information security and privacy has emerged as a critical ***-based verification methods can effectively eliminate the need for centralized third-party ***,the efficiency of nodes in storing and verifying blockchain data faces unprecedented *** address this issue,this paper introduces an efficient verification scheme for transaction ***,it presents a node evaluation module to estimate the activity level of user nodes participating in transactions,accompanied by a probabilistic analysis for all ***,this paper optimizes the conventional transaction organization form,introduces a heterogeneous Merkle tree storage structure,and designs algorithms for constructing these heterogeneous *** analyses and simulation experiments conclusively demonstrate the superior performance of this *** verifying the same number of transactions,the heterogeneous Merkle tree transmits less data and is more efficient than traditional *** findings indicate that the heterogeneous Merkle tree structure is suitable for various blockchain applications,including the Internet of *** scheme can markedly enhance the efficiency of information verification and bolster the security of distributed systems.

关键词： Blockchain architecture transaction verification information security heterogeneous Merkle tree distributed systems

来源：评论

学校读者我要写书评

暂无评论

DMFVAE:miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

引用

Frontiers of computer science 2024年第6期18卷 259-270页

作者： Pijing WEI Qianqian WANG Zhen GAO Ruifen CAO Chunhou ZHENG Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China

MicroRNAs(miRNAs)are closely related to numerous complex human diseases,therefore,exploring miRNA-disease associations(MDAs)can help people gain a better understanding of complex disease *** increasing number of computational methods have been developed to predict ***,the sparsity of the MDAs may hinder the performance of many *** addition,many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor *** this study,we propose a deep matrix factorization model with variational autoencoder(DMFVAE)to predict potential *** first decomposes the original association matrix and the enhanced association matrix,in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method,to obtain sparse vectors and dense vectors,***,the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors,and meanwhile,node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense ***,sample features are acquired by combining the latent vectors and network structure embedding vectors,and the final prediction is implemented by convolutional neural network with channel *** evaluate the performance of DMFVAE,we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs ***,case studies on lung neoplasms,colon neoplasms,and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

关键词： miRNA-disease association deep matrix factorization self-adjusted nearest neighbor variational encoder network structure

来源：评论

学校读者我要写书评

暂无评论

Computing Challenges of UAV Networks: A Comprehensive Survey

引用

computers, Materials & Continua 2024年第11期81卷 1999-2051页

作者： Altaf Hussain Shuaiyong Li Tariq Hussain Xianxuan Lin Farman Ali Ahmad Ali AlZubi School of Computer Science&Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of EducationChongqing University of Posts and TelecommunicationsChongqing400065China School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China School of Artificial Intelligence Nanjing University of Information Science&TechnologyNanjing210044China Department of Computer Science and Engineering School of ConvergenceCollege of Computing and InformaticsSungkyunkwan UniversitySeoul03063Republic of Korea Department of Computer Science Community CollegeKing Saud UniversityRiyadh11495Saudi Arabia

Devices and networks constantly upgrade,leading to rapid technological ***-dimensional(3D)point cloud transmission plays a crucial role in aerial computing terminology,facilitating information *** network types,including sensor networks and 5G mobile networks,support this ***,Flying Ad hoc Networks(FANETs)utilize Unmanned Aerial Vehicles(UAVs)as nodes,operating in a 3D environment with Six Degrees of Freedom(6DoF).This study comprehensively surveys UAV networks,focusing on models for Light Detection and Ranging(LiDAR)3D point cloud compression/*** topics covered include autonomous navigation,challenges in video streaming infrastructure,motivations for Quality of Experience(QoE)enhancement,and avenues for future ***,the paper conducts an extensive review of UAVs,encompassing current wireless technologies,applications across various sectors,routing protocols,design considerations,security measures,blockchain applications in UAVs,contributions to healthcare systems,and integration with the Internet of Things(IoT),artificial intelligence(AI),Machine Learning(ML),and Deep Learning(DL).Furthermore,the paper thoroughly discusses the core contributions of LiDAR 3D point clouds in UAV systems and their future prediction along with mobility *** also explores the prospects of UAV systems and presents state-of-the-art solutions.

关键词： Autonomous vehicles UAV systems UAV transmission UAV in healthcare future of UAV system security measures

来源：评论

学校读者我要写书评

暂无评论

Using Deep Learning for 2D Primitive Perception with a Noisy Robotic LiDAR

Using Deep Learning for 2D Primitive Perception with a Noisy...

引用

Iberian Robotics Conference (ROBOT)

作者： Antónia Brito Pedro Sousa Ana Couto Gonçalo Leão Luís Paulo Reis Armando Sousa FEUP - Faculty of Engineering University of Porto Portugal FCUP - Faculty of Sciences University of Porto Portugal LIACC - Artificial Intelligence and Computer Science Laboratory Portugal INESC TEC - INESC Technology and Science Portugal

ISBN: (数字)9798350376364

ISBN: (纸本)9798350376371

Effective navigation in mobile robotics relies on precise environmental mapping, including the detection of complex objects as geometric primitives. This work introduces a deep learning model that determines the pose, type, and dimensions of 2D primitives using a mobile robot equipped with a noisy LiDAR sensor. Simulated experiments conducted in Webots involved randomly placed primitives, with the robot capturing point clouds which were used to progressively build a map of the environment. Two mapping techniques were considered, a deterministic and probabilistic (Bayesian) mapping, and different levels of noise for the LiDAR were compared. The maps were used as input to a YOLOv5 network that detected the position and type of the primitives. A cropped image of each primitive was then fed to a Convolutional Neural Network (CNN) that determined the dimensions and orientation of a given primitive. Results show that the primitive classification a chieved a n a ccuracy o f 95% in low noise, dropping to 85% under higher noise conditions, while the prediction of the shapes' dimensions had error rates from 5% to 12%, as the noise increased. The probabilistic mapping approach improved accuracy by 10-15% compared to deterministic methods, showcasing robustness to noise levels up to 0.1. Therefore, these findings h ighlight t he e ffectiveness of probabilistic mapping in enhancing detection accuracy for mobile robot perception in noisy environments.

关键词： YOLO Deep learning Laser radar Accuracy Noise Robot sensing systems Probabilistic logic Noise measurement Convolutional neural networks Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Estimation of Human Motion Intention and Time-Varying Arm Stiffness for Enhanced Human-Robot Interaction

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期17卷 510-524页

作者： Wu, Huayang Zhu, Chengzhi Cheng, Long Yang, Chenguang Li, Yanan University of Sussex Department of Engineering and Design BrightonBN1 9RH United Kingdom South China University of Technology Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering Guangzhou510640 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China University of Liverpool Department of Computer Science LiverpoolL69 3BX United Kingdom

Recent advances in physiological human motor control research indicate that human endpoint stiffness magnitude increases linearly with grasp force. Based on these findings, a scheme was proposed in this paper to integrate the linear quadratic estimation (LQE) filter with the stiffness model inferred from grasp force, which can simultaneously estimate the human arm's stiffness and motion intention. Then, an online variable impedance controller (VIC) was designed based on previous estimations for physical human-robot interaction (pHRI). The proposed stiffness model and estimation method were validated through experiments using a planar robotic interface. In order to assess its performance in practical pHRI tasks, the implementation of human arm stiffness and intention estimation combining with VIC was extended to a teleoperation peg-in-hole and robot-assisted rehabilitation tasks. The experimental results demonstrate that the proposed method can effectively estimate human motion intention and arm stiffness simultaneously. Compared to existing methods, the proposed VIC enhances pHRI in terms of increased flexibility, effective guidance, and reduced human effort. © 2016 IEEE.

关键词： Human robot interaction

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：