检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Elbatel, Marawan Wang, Hualiang Martí, Robert Fu, Huazhu Li, Xiaomeng The Hong Kong University of Science and Technology Hong Kong Computer Vision and Robotics Institute University of Girona Spain Singapore

In the medical field, federated learning commonly deals with highly imbalanced datasets, including skin lesions and gastrointestinal images. Existing federated methods under highly imbalanced datasets primarily focus on optimizing a global model without incorporating the intra-class variations that can arise in medical imaging due to different populations, findings, and scanners. In this paper, we study the inter-client intra-class variations with publicly available self-supervised auxiliary networks. Specifically, we find that employing a shared auxiliary pre-trained model, like MoCo-V2, locally on every client yields consistent divergence measurements. Based on these findings, we derive a dynamic balanced model aggregation via self-supervised priors (MAS) to guide the global model optimization. Fed-MAS can be utilized with different local learning methods for effective model aggregation toward a highly robust and unbiased global model. Our code is available at https://***/xmed-lab/Fed-MAS. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification for Robot Person Following with Online Continual Learning

arXiv

引用

arXiv 2023年

作者： Ye, Hanjing Zhao, Jieting Zhan, Yu Chen, Weinan He, Li Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangdong University of Technology China

Robot person following (RPF) is a crucial capability in human-robot interaction (HRI) applications, allowing a robot to persistently follow a designated person. In practica RPF scenarios, the person can often be occluded by other objects or people. Consequently, it is necessary to re-identify the person when he/she reappears within the robot’s field of view Previous person re-identification (ReID) approaches to person following rely on a fixed feature extractor. Such an approach often fails to generalize to different viewpoints and lighting conditions in practical RPF environments. In other words, it suffers from the so-called domain shift problem where it cannot re-identify the person when his re-appearance is out of the domain modeled by the fixed feature extractor. To mitigate this problem, we propose a ReID framework for RPF where we use a feature extractor that is optimized online with both short-term and long-term experiences (i.e., recently and previously observed samples during RPF) using the online continua learning (OCL) framework. The long-term experiences are maintained by a memory manager to enable OCL to update the feature extractor. Our experiments demonstrate that even in the presence of severe appearance changes and distractions from visually similar people, the proposed method can still re-identify the person more accurately than the state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Distortion Correction of AUV-acquired Side-Scan Sonar Data

Distortion Correction of AUV-acquired Side-Scan Sonar Data

引用

OCEANS

作者： Valerio Franchi Hayat Rajani Rafael Garcia Borja Martinez-Clavel Nuno Gracias Computer Vision and Robotics Research Institute (VICOROB) University of Girona Girona Spain Tecnoambiente (A Tradebe Company) Barcelona Spain

Side scan sonars (SSS) are types of sonars that produce representations of the sea-bed by emitting and receiving acoustic fan-shaped pulses perpendicularly to the motion of the sensor in the water. Generally, SSS are deployed from a towed vehicle pulled from a boat at high speed to avoid oscillatory motions and thus achieve a clean and consistent sea-bed scan. Our approach targets the use of SSSs on small AUVs with limited computing power, and travelling at slow speeds, where the waterfall is directly used for real-time classfication. Due to the increased oscillatory motion, the SSS waterfall tends to have significant distortion, that will preclude the classifier from obtaining correct results. The algorithm described in this paper performs a geometric correction of the sonar scanlines by taking into account the AUV’s change in height, yaw and pitch to calculate correctly their positions on the seabed. The data is mapped into a 2D grid using the scanline intensities to form a mosaic, and the missing mosaic pixels are interpolated using a Gaussian-based kernel. The waterfall is recreated by considering a modified AUV trajectory with smooth changes in heading and a null pitch. The results show a significant improvement in the waterfall output, removing unwanted distortions and displaying the seabed structures with higher geometric consistency. In addition, the concentration of the ping data on the waterfall is constant all around, compared to the varying contribution density in the original one.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LiLO: Lightweight and low-bias LiDAR Odometry method based on spherical range image filtering

arXiv

引用

arXiv 2023年

作者： Velasco-Sánchez, Edison P. Ángel Muñoz-Bañón, Miguel Candelas, Francisco A. Puente, Santiago T. Torres, Fernando The Group of Automation Robotics and Computer Vision AUROVA University of Alicante San Vicente del Raspeig Alicante03690 Spain

In unstructured outdoor environments, robotics requires accurate and efficient odometry with low computational time. Existing low-bias LiDAR odometry methods are often computationally expensive. To address this problem, we present a lightweight LiDAR odometry method that converts unorganized point cloud data into a spherical range image (SRI) and filters out surface, edge, and ground features in the image plane. This substantially reduces computation time and the required features for odometry estimation in LOAM-based algorithms. Our odometry estimation method does not rely on global maps or loop closure algorithms, which further reduces computational costs. Experimental results generate a translation and rotation error of 0.86% and 0.0036°/m on the KITTI dataset with an average runtime of 78ms. In addition, we tested the method with our data, obtaining an average closed-loop error of 0.8m and a runtime of 27ms over eight loops covering 3.5Km. The code is available at: https://***/AUROVA-LAB/applications. © 2023, CC0.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Sequential Transfer with Multi-Objective Genetic Algorithm for Feature Selection of Small, High-Dimensional Datasets

Sequential Transfer with Multi-Objective Genetic Algorithm f...

引用

Congress on Evolutionary Computation

作者： Parth C. Upadhyay G. N. DeSouza John A. Lory Department of Electrical Engineering and Computer Science (EECS) Vision-Guided and Intelligent Robotics (ViGIR) Laboratory Division of Plant Sciences University of Missouri Columbia MO

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Performing feature selection on a small number of instances with high-dimensional datasets poses a needed challenge in preventing over-fitting. To address this issue, this paper proposes a sequential transfer-learning approach combined with a multi-objective genetic algorithm (STMO-GA) for feature selection. Firstly, for the multi-objective component of our method, we employ a Non-dominated Sorting Genetic Algorithm (NSGA-II) to generate a Pareto front. Then, features are ranked based on their number of appearances in the same Pareto front. Next, during the sequential knowledge transfer process, the ranked features are iteratively selected until a predetermined $n$ number of features remains. This feature subspace is further refined by a k-fold cross-validation operation, starting from the rank-one feature, to determine the cut-off of the $n$ features that will remain. Comparative evaluations against both GA-based as well as traditional feature selection methods demonstrate that the proposed method achieves superior classification accuracy, while retaining the smallest number or a comparable number of features.

关键词： Accuracy Evolutionary computation Feature extraction Genetics Linear programming Robustness Optimization

来源：评论

学校读者我要写书评

暂无评论

Reward Planning for Underactuated Robotic Systems: A Study on Pendubot with Parameters Uncertainty

Reward Planning for Underactuated Robotic Systems: A Study o...

引用

School on Dynamics of Complex Networks and their Application in Intellectual robotics (DCNAIR)

作者： Sinan Ibrahim Ramil Khusainov Ali Jnadi S. M. Ahsan Kazmi Institute of Robotics and Computer Vision Innopolis University Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia Computer Science and Creative Technologies University of the West of England (UWE) Bristol United Kingdom

There is a burgeoning interest in the field of Reinforcement Learning (RL) across various domains, including robotics. Traditional control approaches for robotic systems, such as semi-definite programming (SDP) or mixed integer programming (MIP), typically rely on the assumption of a known and deterministic model of the environment. In contrast, this study aims to introduce a novel RL method for planning the reward function specifically tailored for underactuated robotic systems with parameter uncertainty. We propose a method with a single RL agent to address the challenge of swing up and balance of a Pendubot system with uncertain parameters. The ultimate objective is to enhance the system’s ability to adapt and perform reliably in the face of varying uncertainties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression-Aware Masking and Progressive Decoupling for Cross-Database Facial Expression Recognition

Expression-Aware Masking and Progressive Decoupling for Cros...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Tao Zhong Xiaole Xian Zihan Wang Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Cross-database facial expression recognition (CD-FER) has been widely studied due to its promising applicability in real-life situations, while the generalization performance is the main concern in this task. For improving cross-database generalization, current works frequently resort to masked auto encoder (MAE) to learn the expression representation in an unsupervised manner, and disentanglement of expression and domain features. (i) For MAE, current algorithms mainly employ random masking, and leverage the reconstruction of these masked regions to enable networks to learn the expression representation. However, these masked regions are expression-irrelevant, can not well reflect the characteristics of expression, thus are not efficient enough in representation learning. To this end, we propose an expression-aware masking in MAE to improve the learning efficiency of expression representation, by guiding MAE to mask out expression-aware regions during training. (ii) For disentanglement of expression and domain features, current algorithms realize it mainly in the deep layers. However, the coupling of these features in the shallow layers are rarely concerned, which may largely affect the disentanglement performance in deep layers. Thus, we propose a progressive decoupler to disentangle these features block by block, to use the feature disentanglement in shallow layers to facilitate that in deep layers. Extensive quantitative and qualitative results on multiple expression datasets show that our method can largely outperform the state of the arts in terms of cross-database generalization performance.

关键词： Training Representation learning Couplings Face recognition Gesture recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Quantum Annealing for the Mechanics of Robot Inspectors on Electrical Transmission Lines' Conductors

Quantum Annealing for the Mechanics of Robot Inspectors on E...

引用

Control, robotics and Informatics (ICCRI), International Conference on

作者： Hadi Salloum Mohammad Reza Bahrami Artem Matevosian Sofia Gamershmidt Ali Jnadi Manuel Mazzara Faculty of Computer Science and Engineering Innopolis University Innopolis Russia Cyber-physical systems lab Innopolis University Innopolis Russia Institute of Robotics and Computer Vision Innopolis University Innopolis Russia

ISBN: (数字)9798350380309

ISBN: (纸本)9798350380316

This paper explores the integration of quantum computing, specifically quantum annealing, into robotics for inspecting electrical transmission lines. By using quantum annealing's computational power, we address the dynamics of robot inspectors on transmission line conductors, enhancing the computational efficiency of managing the movements of robot inspectors on transmission line conductors. The use of these robots is crucial for performing efficient and safe inspections. We discuss the mathematical foundations of quantum annealing, transforming differential equations governing robot dynamics into Ising model Hamiltonians suitable for quantum annealing devices. Through experiments using D-Wave's ‘Advantage’ quantum annealer, we demonstrate the viability of quantum annealing in solving complex robotics problems, paving the way for advanced applications in the field.

关键词： Annealing Power transmission lines Computational modeling Quantum mechanics Differential equations Inspection Quantum annealing Conductors Mathematical models Robots

来源：评论

学校读者我要写书评

暂无评论

Complexity based investigation in collaborative assembly scenarios via non intrusive techniques

引用

Procedia computer Science 2023年 217卷 478-485页

作者： Sotirios Panagou Monica Sileo Konstantinos Papoutsakis Fabio Fruggiero Ammar Qammaz Antonis Argyros School of Engineering University of Basilicata 85100 Potenza Italy Computational Vision and Robotics Laboratory Institute of Computer Science Foundation for Research and Technology – Hellas 70013 Heraklion Greece

Human and robot collaboration in assembly tasks is an integral part in modern manufactories. Robots provide advantages in both process and productivity with their repeatability and usability in different tasks, while human operators provide flexibility and can act as safeguards. However, process complexity increases which can lower the overall quality. Increased complexity can negatively influence decision making due to cognitive load on human operators, which can lead to lower quality, be it product, process or human work. Moreover, it can lead to safety risks, human-system error and accidents. In this work, we present the preliminary results on an experiment performed with student-participants, based on an assembly task. The experiment was set up to emulate an industrial assembly, and data collection was performed through qualitative and non-intrusive quantitative methods. Questionnaires were used to assess perceptual task complexity and cognitive load, while a stereo camera provided recordings for after-task analysis on process errors and human work quality based on a 3D skeleton-based human pose estimation and tracking method. The aim of the study is to investigate causes of errors and implications on quality. Future direction of the work is discussed.

关键词： collaboration assembly task complexity cognitive load human pose estimation tracking

来源：评论

学校读者我要写书评

暂无评论

Human Orientation Estimation Under Partial Observation

Human Orientation Estimation Under Partial Observation

引用

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

作者： Jieting Zhao Hanjing Ye Yu Zhan Hao Luan Hong Zhang Department of Electronic and Electrical Engineering SUSTech Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology (SUSTech) Department of Computer Science School of Computing National University of Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under full observation. However, the existing methods easily make a wrong prediction under partial observation and give it an unexpectedly high confidence. To solve the above problems, this study first develops a method called Part-HOE that estimates orientation from the visible joints of a target person so that it is able to handle partial observation. Subsequently, we introduce a confidence-aware orientation estimation method, enabling more accurate orientation estimation and reasonable confidence estimation under partial observation. The effectiveness of our method is validated on both public and custom-built datasets, and it shows great accuracy and reliability improvement in partial observation scenarios. In particular, we show in real experiments that our method can benefit the robustness and consistency of the Robot Person Following (RPF) task.

关键词： Accuracy Filtering Estimation Robustness Autonomous agents Intelligent robots

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：