检索结果-内蒙古大学图书馆

21st International Symposium on Applied Reconfigurable Computing, ARC 2025

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031879944

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Versatile Tasks on Integrated Aerial Platforms Using Only Onboard Sensors: Control, Estimation, and Validation

引用

IEEE Transactions on robotics 2025年 41卷 3518-3538页

作者： Wang, Kaidi Lai, Ganghua Yu, Yushu Du, Jianrui Sun, Jiali Xu, Bin Franchi, Antonio Sun, Fuchun Beijing Institute of Technology School of Mechatronical Engineering Beijing100081 China Beijing Institute of Technology School of Mechanical Engineering Beijing100081 China University of Twente Robotics and Mechatronics Lab Faculty of Electrical Engineering Mathematics and Computer Science Enschede7500 AE Netherlands Tsinghua University Department of Computer Science and Technology China

Connecting multiple aerial vehicles to a rigid central platform through passive spherical joints holds the potential to construct a fully-actuated aerial platform. The integration of multiple vehicles enhances efficiency in tasks like mapping and object reconnaissance. This paper proposes a control and state estimation framework for the Integrated Aerial Platform (IAP), enabling it to perform versatile tasks like object reconnaissance and physical interactive tasks with only onboard sensors. In the framework, the 6D motion control serves as the low-level controller, while the high-level controller comprises a 6D admittance filter and a perception-aware attitude correction module. The 6D admittance filter, serving as the interaction controller, is adaptable for aerial interaction tasks. The perception-aware attitude correction algorithm is carefully designed by adopting a geometric Model Predictive Controller (MPC). This algorithm, incorporating both offline and online calculations, proves to be well-suited for the intricate dynamics of an IAP. A 6D direct wrench controller is also developed for the IAP. Notably, both the interaction controller and the direct wrench controller operate without reliance on force/torque sensors. Instead, a wrench observer algorithm is devised, considering external disturbances. Additionally, based on the kinematics constraints of the multiple aerials in the platform, a fusion algorithm for multiple Visual-Inertial Odometry (VIO) and kinematics constraints is developed, providing more accurate localization. A prototype of the IAP is constructed, and its capabilities are demonstrated through experiments including perception-aware object reconnaissance, aerial mapping, aerial peg-in-hole task, and 6D contact wrench generation. All experiments are conducted exclusively with onboard sensors. These tasks exemplify the merits of the proposed IAP and validate the effectiveness of the proposed control framework and fusion algorithm. © 2004-2012

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Specular Region Detection and Covariant Feature Extraction 27th

Specular Region Detection and Covariant Feature Extraction

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Bappy, D.M. Kang, Donghwa Lee, Jinkyu Lee, Youngmoon Koo, Minsuk Baek, Hyeongboo Department of Computer Science and Engineering Incheon National University Incheon Korea Republic of Department of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of Department of Robotics Hanyang University Ansan Korea Republic of Department of Artificial Intelligence University of Seoul Seoul Korea Republic of

ISBN: (纸本)9783031781971

Endoscopy images pose a distinct set of challenges, such as specularity, uniformity, and deformation, which can obstruct surgeons’ observations and decision-making processes. These hurdles complicate feature extraction and may ultimately lead to the failure of a surgical navigation system. To tackle these obstacles, we introduce a Modified Maximal Stable Extremal Region (MMSER) detector that specifically targets fine specular regions. Subsequently, we ingeniously fuse the capabilities of MMSER and saturation region properties to precisely identify specular regions within endoscopy images. Furthermore, our approach harnesses the shared properties of covariant features and endoscopic imaging to detect features in intricate regions, such as low-textured and deformed areas. Surpassing contemporary methods, our proposed technique demonstrates remarkable performance when evaluated on the available CVC-ClinicSpec datasets. Our method has shown improvements in accuracy, recall, f1-score, and Jaccard index by 0.21%,25.42%,7.77% snd 11.77%, respectively, when compared to recent techniques. Owing to its exceptional ability to accurately pinpoint specular regions and extract features from complex areas, our approach holds the potential to significantly advance surgical navigation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Deep Prior Based Limited-Angle Tomography 27th

Deep Prior Based Limited-Angle Tomography

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Bappy, D.M. Kang, Donghwa Lee, Jinkyu Lee, Youngmoon Baek, Hyeongboo Department of Computer Science and Engineering Incheon National University Incheon Korea Republic of Department of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of Department of Robotics Hanyang University Ansan Korea Republic of Department of Artificial Intelligence University of Seoul Seoul Korea Republic of

ISBN: (纸本)9783031781940

In the process of reconstructing images from data acquired within a limited angular range, we encounter what is termed limited-angle tomography. The deficiency of complete data in this context results in artifacts, commonly appearing as streaks or missing structures, which can significantly compromise the quality of the reconstructed slice. This degradation gives rise to issues such as boundary distortion, blurred edges, and intensity bias, potentially leading to misinterpretation of the images. Hence, addressing artifacts in limited-angle tomography is crucial for clinical applications. Although deep learning-based reconstruction has shown impressive results in recent times, concerns about its robustness persist. To bolster the robustness of our proposed technique, we integrate prior information from a modified U-net with preprocessed input into the Relative Variation - Simultaneous Algebraic Reconstruction Technique (RV-SART) to provide insights into unmeasured data. Subsequently, the method extracts structure from the initially reconstructed slice through structure-texture decomposition. This process facilitates the reconstruction of high-quality CT images while suppressing pattern-like artifacts. Extensive experiments demonstrate that our approach surpasses both traditional and state-of-the-art learning techniques in terms of reconstruction quality and preservation of fine structures in noisy limited-angle reconstruction problems. Our technique provides improvements over the recent LRIP-net for a 90-degree scanning range in quantitative metrics such as PSNR by 17.48%, RMSE by 46.36%, and SSIM by 6.18%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Advanced Endoscopy Imaging with Automatic Feedback 27th

Advanced Endoscopy Imaging with Automatic Feedback

引用

27th International Conference on Pattern Recognition, ICPR 2024

ISBN: (纸本)9783031781940

As we move towards a future where minimally invasive methods become the norm for surgeries and diagnostic procedures, it is increasingly vital to improve our strategies for viewing the organs and complex structures within our bodies. Image stitching presents an enticing solution, expanding our field of view by seamlessly weaving together a sequence of images. While existing stitching techniques do lean on the capabilities of endoscopy imaging, they, unfortunately, overlook the critical need for automated feedback when grappling with the complexities and challenges innate to endoscopy imaging. these methods struggle to stand firm against deformations and regions with low texture. In this paper, we introduce a robust endoscopic image-stitching algorithm designed to thrive in adversity. Its unique resilience to deformations and low-texture regions is reinforced by the inclusion of a radial basis function weighting that is paired harmoniously with location-dependent homography based on the corresponding locations of the strong features extracted by affine shape-adapted Hessian-Laplace detector. Crucially, this algorithm is steered by a sophisticated automatic feedback mechanism. This feedback system makes astute evaluations based on an image quality metric and the structural comparison between the sequences of endoscopy images. We have thoroughly validated the efficacy of our new approach using two public datasets, namely EndoSLAM and EndoAbS, under demanding conditions. The results eloquently illustrate the superior benefits of our technique. Our proposed method surpasses commonly employed techniques, delivering superior performance in quantitative metrics, including precision at 30.07%, recall at 114.89%, F1-score at 84.62%, and TRE at 46.07%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

ViT-SENet-Tom: machine learning-based novel hybrid squeeze–excitation network and vision transformer framework for tomato fruits classification

引用

Neural Computing and Applications 2025年第9期37卷 6583-6600页

作者： Swapno, S M Masfequier Rahman Nobel, S. M. Nuruzzaman Islam, Md Babul Bhattacharya, Pronaya Mattar, Ebrahim A. Department of CSE Bangladesh University of Business and Technology Dhaka1216 Bangladesh Department of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Department of Computer Science and Engineering Amity School of Engineering and Technology and Research and Innovation Cell Amity University West Bengal Kolkata India Robotics - Cybernetic College of Engineering University of Bahrain Manama Bahrain

Tomatoes are essential fruits in numerous nations for their vast demand. It is very important to maintain the freshness of tomatoes. One of the primary challenges in the recent culinary landscape is accurately identifying healthy tomatoes while effectively eliminating damaged or rejected ones. Existing approaches employ various strategies for categorizing tomato fruit, but they often suffer from inaccuracies, slow detection, and suboptimal performance. Thus, motivated by this gap, in this paper, we propose a novel machine learning (ML) framework, ViT-SENet-Tom, which is a hybrid vision transformer (ViT) model with squeeze and excitation (SENet) block network for fast, accurate, and efficient tomato fruit classification. The framework works on three tomato classes, respectively, the ripe, unripe, and reject. In developing the proposed model, we utilized advanced and newly designed layers and functions. This integration created a more complex and sophisticated neural network, significantly enhancing efficiency and contributing to the model’s novelty. Our chosen dataset was small initially, but we implemented augmentation techniques to increase its size. This approach made our system more reliable, efficient, and effective. The hybrid ViT-SENet framework employs encoders and self-attention networks with squeeze and excitation channel functions to allow precise, robust, fast, and efficient tomato classification. In simulation, the framework achieves a training accuracy of 99.87% and validation accuracy of 93.87%, indicating the precise classification of tomatoes. Besides, this work tests accuracy using fivefold cross-validation. The highest accuracy seen at fold-5 is 99.90%. These testing results demonstrate the efficacy of the proposed framework in real-deployment scenarios. The implementation has the potential to provide enhanced and more sustainable food security and safety in future. © The Author(s) 2025.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Scanning the Issue - May 2025

引用

IEEE Transactions on Intelligent Transportation Systems 2025年第5期26卷 5627-5648页

作者： Simona Sacone Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genova Genova Italy

来源：评论

学校读者我要写书评

暂无评论

Scanning the Issue

引用

IEEE Transactions on Intelligent Transportation Systems 2025年第1期26卷 3-21页

作者： Simona Sacone Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genova Genova Italy

“Scanning the Issue.“

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based FOD Detection For Runway Health Monitoring 1

Deep Learning Based FOD Detection For Runway Health Monitori...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Kumar, Amarjeet Mittal, Aanya Dixit, Abhishek Agrawal, Pooja School of Robotics Defence Institute of Advanced Technology Pune India Manipal University Jaipur Department of Computer Science Rajasthan India Defence Institute of Advanced Technology Department of Aerospace Pune India

ISBN: (纸本)9798350355611

This paper focuses on the safety of airport runways, which is crucial for aviation industries. Foreign Object Debris (FOD) i.e. objects like nails or bolts can cause significant harm to aircraft and potentially lead to catastrophic incidents and fatalities. This study delves into detecting objects on runways by using versions of the YOLO (You Only Look Once) model. Further, it also presents the differences in detecting objects and comparing the accuracy across a range of objects, paying attention to their ability to identify even the smallest things that have a potential danger. In order to identify the model variation and enable real-time runway surveillance, the proposed methodology considers the trade-off between detection speed and precision. The results illustrate the effectiveness of the latest YOLO model in object recognition over existing models, this can support the improvement of runway safety and the development of automated systems that monitor runway conditions. © 2025 IEEE.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

Exploring Children’s Strategies in Response to Robot’s Advice During a Group Task with iCub and Nao 16th

Exploring Children’s Strategies in Response to Robot’s A...

引用

16th International Conference on Social robotics, ICSR + AI 2024

作者： Pusceddu, Giulia Sangineto, Mariapia Cocchella, Francesca Bogliolo, Michela Belgiovine, Giulia Lastrico, Linda Casadio, Maura Rea, Francesco Gena, Cristina Sciutti, Alessandra Robotics Brain and Cognitive Science Department Italian Institute of Technology Genoa Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Computer Science University of Turin Turin Italy Cognitive Architecture for Collaborative Technologies Unit Italian Institute of Technology Genoa Italy Scuola di Robotica Genoa Italy

ISBN: (纸本)9789819635184

This study investigates children’s trust in two humanoid robots, Nao and iCub, through a cooperative game designed to elicit spontaneous behaviors and group dynamics. We investigate whether participants change their choices after hearing advice from a robot, considering rounds where the advice is correct or incorrect, with the robot apologizing for its mistakes. Results reveal that, in most cases, participants prefer not to change their moves after the robot’s advice. Additionally, after the robots made mistakes, participants are less likely to actively follow their advice and more likely to reject it. No significant differences in strategies among the iCub and Nao samples are evidenced. Furthermore, we examine the influence of group dynamics, identifying "Proactive Players" who consistently initiated moves. A significant association between the strategies of this player and their teammates is found, suggesting potential influence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

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：