检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Retsinas, George Filntisis, Panagiotis P. Daněček, Radek Abrevaya, Victoria F. Roussos, Anastasios Bolkart, Timo Maragos, Petros Institute of Robotics Athena Research Center Maroussi15125 Greece School of Electrical & Computer Engineering National Technical University of Athens Greece MPI for Intelligent Systems Tübingen Germany Greece

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expressive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geometry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between rendering and input image further hinders the learning process. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image. As the neural rendering gets color information from sampled image pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further, it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for diverse expressions. Our qualitative, quantitative and particularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. For our method’s source code, demo video and more, please visit our project webpage: https://***/smirk/. © 2024, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Marine Predators Algorithm with Deep Learning-Based Leukemia Cancer Classification on Medical Images

引用

computer Modeling in engineering & Sciences 2024年第10期141卷 893-916页

作者： Sonali Das Saroja Kumar Rout Sujit Kumar Panda Pradyumna Kumar Mohapatra Abdulaziz S.Almazyad Muhammed Basheer Jasser Guojiang Xiong Ali Wagdy Mohamed Department of Computer Science&Engineering Gandhi Institute for TechnologyBPUTBhubaneswar752054India Department of Information Technology Vardhaman College of Engineering(Autonomous)Hyderabad501218TelanganaIndia Department of Electronic&Communication Engineering Vedang Institute of TechnologyBhubaneswar752010India Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computing and Information Systems School of Engineering and TechnologySunway UniversityJalan UniversitiBandar SunwaySelangor Darul Ehsan47500Malaysia Research Centre for Human-Machine Collaboration(HUMAC) School of Engineering and TechnologySunway UniversityJalan UniversitiBandar SunwaySelangor Darul Ehsan47500Malaysia Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical EngineeringGuizhou UniversityGuiyang550025China Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11931Jordan

In blood or bone marrow,leukemia is a form of cancer.A person with leukemia has an expansion of white blood cells(WBCs).It primarily affects children and rarely affects *** depends on the type of leukemia and the extent to which cancer has established throughout the *** leukemia in the initial stage is vital to providing timely patient *** image-analysis-related approaches grant safer,quicker,and less costly solutions while ignoring the difficulties of these invasive *** can be simple to generalize computer vision(CV)-based and image-processing techniques and eradicate human *** researchers have implemented computer-aided diagnosticmethods andmachine learning(ML)for laboratory image analysis,hopefully overcoming the limitations of late leukemia detection and determining its *** study establishes a Marine Predators Algorithm with Deep Learning Leukemia Cancer Classification(MPADL-LCC)algorithm onMedical *** projectedMPADL-LCC system uses a bilateral filtering(BF)technique to pre-process medical *** MPADL-LCC system uses Faster SqueezeNet withMarine Predators Algorithm(MPA)as a hyperparameter optimizer for feature ***,the denoising autoencoder(DAE)methodology can be executed to accurately detect and classify leukemia *** hyperparameter tuning process using MPA helps enhance leukemia cancer classification *** results are compared with other recent approaches concerning various measurements and the MPADL-LCC algorithm exhibits the best results over other recent approaches.

关键词： Leukemia cancer medical imaging image classification deep learning marine predators algorithm

来源：评论

学校读者我要写书评

暂无评论

Towards Instance Segmentation-Based Litter Collection with Multi-Rotor Aerial Vehicle

Towards Instance Segmentation-Based Litter Collection with M...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Filip Zoric Antonio Franchi Matko Orsag Zdenko Kovacic Chiara Gabellieri Laboratory for Robotics and Intelligent Control Systems (LARICS) at the Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Robotics and Mechatronics Group from the University of Twente Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

This paper presents a novel aerial robotics application of instance segmentation-based floating litter collection with a multi-rotor aerial vehicle (MRAV). In the scope of the paper, we present a review of the available datasets for litter detection and segmentation. The reviewed datasets are used to train a Mask-RCNN neural network for instance segmentation. The neural network is off-board deployed on an edge computing device and used for litter position estimation. Based on the estimated litter position, we plan a path based on a quadratic Bezier curve for the litter pickup. We compare different trajectory generation methods for the object pickup. The system is verified in a laboratory environment. Eventually, we present practical considerations and improvements necessary to enable autonomous litter collection with MRAV.

关键词： Instance segmentation Reviews Neural networks Laboratories Estimation Trajectory Aircraft

来源：评论

学校读者我要写书评

暂无评论

An Investigation into the Accuracy of Blood Oxygen Saturation Measurement using Smart Watch Devices Among Pediatric Users in Saudi Arabia

An Investigation into the Accuracy of Blood Oxygen Saturatio...

引用

Biomedical Instrumentation and Technology Conference (IBITeC), International

作者： Ahmad F. Turki Electrical and Computer Engineering Department Center of Excellence in Intelligent Engineering Systems King Abdul Aziz University Jeddah Saudi Arabia

Advancements in technology have led to the development and increased use of biomedical wearable devices equipped with various biosensors. This study aimed to evaluate the accuracy of blood oxygen saturation measurements in Saudi pediatric users using the Apple Watch Series 6 and Samsung Galaxy Watch 4. These smartwatches, widely available and relatively affordable fitness trackers, offer the capability to measure blood oxygen saturation and facilitate health monitoring. This paper presents preliminary findings from an investigation into the accuracy of the Apple Watch and Samsung Watch in measuring blood oxygen saturation. Data was collected from a sample of one hundred Saudi pediatric users, comprising 43 females and 57 males, with an average age of 13±3.3 years and a BMI of 21.07±6.3 kg/m 2 . Three measurements of blood oxygen saturation were simultaneously recorded using a hospital-grade pulse oximetry machine, as well as the Apple Watch and the Samsung Watch. Statistical comparisons were conducted using a T-test with a significance level of p=0.05, and the results were visualized using Bland-Altman plots. The T-test results indicated a statistically significant difference between the oximeter readings of the smartwatches and the medical-grade oximeter. Additionally, the calculation of errors revealed discrepancies between the measurements obtained from the smartwatches and the hospital-grade oximeter. It was observed that the errors were generally lower in measurements taken from male subjects compared to female subjects. The Bland-Altman plots, considering data from both the Apple Watch and the Samsung Watch, showed moderate agreement between the smartwatches and the hospital pulse oximetry. These findings suggest that while the Apple Watch and Samsung Watch demonstrate potential for measuring blood oxygen saturation, there are discrepancies compared to the accuracy of the hospital-grade oximeter. Further research and refinement may be necessary to improve the

关键词：

来源：评论

学校读者我要写书评

暂无评论

TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems

arXiv

引用

arXiv 2024年

作者： Sidrane, Chelsea Tumova, Jana The Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden

Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show that the system is generally functioning as desired, but a formal tool like reachability analysis can provide a guarantee of correctness. For linear systems, reachability analysis is straightforward and fast, but as more complex components are added to the control system such as nonlinear dynamics or a neural network controller, reachability analysis may slow down or become overly conservative. To address these challenges, much literature has focused on spatial refinement, e.g., tuning the discretization of the input sets and intermediate reachable sets. However, this paper addresses a different dimension: temporal refinement. The basic idea of temporal refinement is to automatically choose when along the horizon of the reachability problem to execute slow symbolic queries which incur less approximation error versus fast concrete queries which incur more approximation error. Temporal refinement can be combined with other refinement approaches and offers an additional "tuning knob" with which to trade off tractability and tightness in approximate reachable set computation. Here, we introduce an automatic framework for performing temporal refinement and we demonstrate the effectiveness of this technique on computing approximate reachable sets for nonlinear systems with neural network control policies. We demonstrate the calculation of reachable sets of varying approximation error under varying computational budget and show that our algorithm is able to generate approximate reachable sets with a similar amount of error to the baseline approach in 20-70% less time. © 2024, CC BY.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation

KGNet: Knowledge-Guided Networks for Category-Level 6D Objec...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Qiwei Meng Jason Gu Shiqiang Zhu Jianfeng Liao Tianlei Jin Fangtai Guo Wen Wang Wei Song Zhejiang Lab Research Center for Intelligent Robotics Research Institute of Interdis-ciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

Despite the giant leap made in object 6D pose estimation and robotic grasping under structured scenarios, most approaches depend heavily on the exact CAD models of target objects beforehand, thereby limiting their wide applications. To address this, we propose a novel knowledge-guided network - KGNet to estimate the pose and size of category-level unseen objects. This network includes three primary innovations: knowledge-guided categorical model generation, pointwise deformation probability matrix and synergetic RGBD feature fusion, with the former two leveraging categorical object knowledge for unseen object reconstruction and the latter one facilitating pose-sensitive feature extraction. Exten-sive experiments on CAMERA25 and REAL275 verify their effectiveness, and KGNet achieves the SOTA performance on these two acknowledged benchmarks. Additionally, a real-world robotic grasping experiment is conducted, and its results further qualitatively prove the practicability and robustness of KGNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Experiment of a Four-Fingered Robotic Hand for T-FLoW 4.0 humanoid robot

Design and Experiment of a Four-Fingered Robotic Hand for T-...

引用

International Electronics Symposium (IES)

作者： Kevin Ilham Apriandy Bima Sena Bayu Dewantara Raden Sanggar Dewanto Dadet Pramadihanto Catoer Ryando Dept. of Informatics and Computer Engineering Robotics and Intelligent Systems Center (RoISC) Politeknik Elektronika Negeri Surabaya (PENS) Dept. of Mechanical and Energy Engineering Robotics and Intelligent Systems Center (RoISC) Politeknik Elektronika Negeri Surabaya (PENS) Dept. of Electrical Engineering Politeknik Elektronika Negeri Surabaya (PENS)

In this research study, we present a novel design of a four-fingered robotic hand for T-FLoW 4.0 humanoid robot along with its experiments to validate its grasping performance. Our proposed robotic hand designed with four fingers and five Degree-of-Freedom (DoF), with a configuration of a thumb, index, middle, and ring fingers to remain within the criteria of an anthropomorphic type robot hand. Our hand is built with a modular design on each finger and its mechanism, allowing for easy assembly and achieving a compact hand result. Main controller Arduino Mega implement the system for grasping movement, and then PCA9685 PWM controller get the hand movement instructions from it and generates the required PWM signal for the servo motors. The process of manufacturing the hand involves 3D printing technology to produce hands with a realistic appearance, and use PLA filament material achieve lightweight, affordable, and easy-to-maintain outcomes. The grasping experimental results show that our proposed robotic hand could perform basic grasping movements on household objects. With the use of Cini’s taxonomy of grasp as the hand functionality standard, we achieved a success rate of 8 out of 14 tests conducted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TReR: A Lightweight Transformer Re-Ranking Approach for 3D LiDAR Place Recognition

TReR: A Lightweight Transformer Re-Ranking Approach for 3D L...

引用

International Conference on intelligent Transportation

作者： Tiago Barros Luís Garrote Martin Aleksandrov Cristiano Premebida Urbano J. Nunes Department of Electrical and Computer Engineering University of Coimbra Institute of Systems and Robotics Portugal Dahlem Center for Machine Learning and Robotics Freie Universität Berlin Berlin

Autonomous driving systems often require reliable loop closure detection to guarantee reduced localization drift. Recently, 3D LiDAR-based localization methods have used retrieval-based place recognition to find revisited places efficiently. However, when deployed in challenging real-world scenarios, the place recognition models become more complex, which comes at the cost of high computational demand. This work tackles this problem from an information-retrieval perspective, adopting a first-retrieve-then-re-ranking paradigm, where an initial loop candidate ranking, generated from a 3D place recognition model, is re-ordered by a proposed lightweight transformer-based re-ranking approach (TReR). The proposed approach relies on global descriptors only, being agnostic to the place recognition model. The experimental evaluation, conducted on the KITTI Odometry dataset, where we compared TReR with s.o.t.a. re-ranking approaches such as αQE and SGV, indicate the robustness and efficiency when compared to αQE while offering a good trade-off between robustness and efficiency when compared to SGV.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Worst-Case Integrity Attacks and Resilient State Estimation With Partially Secured Measurements

引用

IEEE Transactions on Control of Network systems 2025年

作者： Zhou, Jing Shang, Jun Chen, Tongwen University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China

This paper examines the problem of optimal deception attacks against state estimation with partially secured measurements, where smart sensors transmit innovation sequences to the remote end for information fusion. Due to resource limitations or defensive countermeasures, the adversary can only modify data packets transmitted through unreliable channels. Meanwhile, the attack should be synthesized with sophistication to deceive an anomaly detector. To investigate the vulnerabilities of such estimation systems without feedback links and enhance security performance, the optimal attack policy is derived by formulating and explicitly solving a convex optimization problem, with the goal of maximizing the sum of estimation errors. Subsequently, a novel attack detection and resilient state estimation algorithm is proposed to ensure an acceptable level of estimation accuracy. The theoretical performance metrics, including false alarm rates for the proposed detector, are provided. Finally, the effectiveness of the results is confirmed through numerical examples. © 2014 IEEE.

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Real-time Architecture for Audio-Visual Active Speaker Detection

Real-time Architecture for Audio-Visual Active Speaker Detec...

引用

IEEE International Conference on robotics and Biomimetics

作者： Min Huang Wen Wang Zheyuan Lin Fiseha B. Tesema Shanshan Ji Jason Gu Minhong Wan Wei Song Te Li Shiqiang Zhu Intelligent Robotics Research Center Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical And Computer Engineering Dalhousie University Canada

ISBN: (纸本)9781665481106

Continuously measuring the speaking state of users with robot in a human-robot Interaction(HRI) system improves metrics of interaction quality. Meanwhile, mainstream active speaker detection (ASD) algorithms emphasize achieving high AUCs at frame level in the AVA-Active Speaker dataset and pay less attention to get real-time performance in robotic systems. In this paper, we propose a model named FSDNet to keep a high AUC score in the AVA-Active Speaker dataset while reducing time cost, our model increase AUC score by 0.1% compared with the State-Of-The-Art and need only 75% running time. Furthermore, we put forward an architecture with a time-related prediction function to make our algorithm more effective and generative in interactive robotic systems. The code is released at https://***/huangmin9966/FSDNet_RealTimeArch.

关键词： Measurement Visualization Costs Codes Biological system modeling Transformers Feature extraction

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：