检索结果-内蒙古大学图书馆

FetchAid: Making Parcel Lockers More Accessible to Blind and Low Vision People With Deep-learning Enhanced Touchscreen Guidance, Error-Recovery Mechanism, and AR-based Search Support

arXiv

引用

arXiv 2024年

作者： Guan, Zhitong Xiong, Zeyu Fan, Mingming Computational Media and Arts Thrust The Hong Kong University of Science and Technology Guangzhou China Division of Integrative Systems and Design Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Parcel lockers have become an increasingly prevalent last-mile delivery method. Yet, a recent study revealed its accessibility challenges to blind and low-vision people (BLV). Informed by the study, we designed FetchAid, a standalone intelligent mobile app assisting BLV in using a parcel locker in real-time by integrating computer vision and augmented reality (AR) technologies. FetchAid first uses a deep network to detect the user's fingertip and relevant buttons on the touch screen of the parcel locker to guide the user to reveal and scan the QR code to open the target compartment door and then guide the user to reach the door safely with AR-based context-aware audio feedback. Moreover, FetchAid provides an error-recovery mechanism and real-time feedback to keep the user on track. We show that FetchAid substantially improved task accomplishment and efficiency, and reduced frustration and overall effort in a study with 12 BLV participants, regardless of their vision conditions and previous experience. © 2024, CC BY-NC-ND.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation

arXiv

引用

arXiv 2024年

作者： Liu, Changkun Chen, Shuai Zhao, Yukun Huang, Huajian Prisacariu, Victor Braud, Tristan Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Division of Integrated Systems Design The Hong Kong University of Science and Technology Hong Kong Active Vision Laboratory Department of Engineering Science University of Oxford United Kingdom

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4% and 15.2% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation

HR-APR: APR-agnostic Framework with Uncertainty Estimation a...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Changkun Liu Shuai Chen Yukun Zhao Huajian Huang Victor Prisacariu Tristan Braud Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Engineering Science Active Vision Laboratory University of Oxford United Kingdom Division of Integrated Systems Design The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

关键词： Training Uncertainty Accuracy Databases Pipelines Estimation Network architecture

来源：评论

学校读者我要写书评

暂无评论

MarineDet: Towards Open-Marine Object Detection

arXiv

引用

arXiv 2023年

作者： Liang, Haixin Zheng, Ziqiang Ma, Zeyu Yeung, Sai-Kit The Division of Integrative Systems and Design Hong Kong University of Science and Technology Hong Kong The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The School of Computer Science and Engineering University of Electronic Science and Technology of China China

Marine object detection has gained prominence in marine research, driven by the pressing need to unravel oceanic mysteries and enhance our understanding of invaluable marine ecosystems. There is a profound requirement to efficiently and accurately identify and localize diverse and unseen marine entities within underwater imagery. The open-marine object detection (OMOD for short) is required to detect diverse and unseen marine objects, performing categorization and localization simultaneously. To achieve OMOD, we present MarineDet. We formulate a joint visual-text semantic space through pre-training and then perform marine-specific training to achieve in-air-to-marine knowledge transfer. Considering there is no specific dataset designed for OMOD, we construct a MarineDet dataset consisting of 821 marine-relative object categories to promote and measure OMOD performance. The experimental results demonstrate the superior performance of MarineDet over existing generalist and specialist object detection algorithms. To the best of our knowledge, we are the first to present OMOD, which holds a more valuable and practical setting for marine ecosystem monitoring and management. Our research not only pushes the boundaries of marine understanding but also offers a standard pipeline for OMOD. © 2023, CC BY-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Real-time deep learning-assisted mechano-acoustic system for respiratory diagnosis and multifunctional classification

引用

npj Flexible Electronics 2024年第1期8卷 192-203页

作者： Hee Kyu Lee Sang Uk Park Sunga Kong Heyin Ryu Hyun Bin Kim SangHoon Lee Danbee Kang Sun Hye Shin Ki Jun Yu Juhee Cho Joohoon Kang Il Yong Chun Hye Yun Park Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Department of Clinical Research Design and Evaluation SAIHSTSungkyunkwan UniversitySeoulRepublic of Korea Patient-Centered Outcomes Research Institute Samsung Medical CenterSeoulRepublic of Korea Center for Clinical Epidemiology Samsung Medical CenterSeoulRepublic of Korea Division of Pulmonary and Critical Care Medicine Department of MedicineSamsung Medical CenterSungkyunkwan University School of MedicineSeoulRepublic of Korea School of Electrical and Electronic Engineering Yonsei UniversitySeoulRepublic of Korea School of Advanced Materials Science and Engineering Sungkyunkwan UniversitySuwonRepublic of Korea Center for Neuroscience Imaging Research Institute for Basic ScienceSuwonRepublic of Korea

Epidermally mounted sensors using triaxial accelerometers have been previously used to monitor physiological processes with the implementation of machine learning(ML)algorithm *** findings from these previous studies have established a strong foundation for the analysis of highresolution,intricate signals,typically through frequency domain *** this study we integrate a wireless mechano-acoustic sensor with a multi-modal deep learning system for the real-time analysis of signals emitted by the laryngeal prominence area of the thyroid cartilage at frequency ranges up to 1 *** interface provides real-time data visualization and communication with the ML server,creating a system that assesses severity of chronic obstructive pulmonary disease and analyzes the user’s speech patterns.

关键词： system diagnosis mounted

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drone Surveillance with NeRF: Real-World Applications and Simulated Environments

Enhancing Drone Surveillance with NeRF: Real-World Applicati...

引用

Conference on Digital Avionics Systems (DASC)

作者： Joakim Lindén Giovanni Burresi Håkan Forsberg Masoud Daneshtalab Ingemar Söderquis Division of Intelligent Future Technologies School of Innovation Design and Engineering Malardalen University Vasteras Sweden Saab Aeronautics Stockholm Sweden Division of Electronics and Embedded Systems School of Electrical Engineering and Computer Science Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9798350349610

ISBN: (纸本)9798350349627

Machine Learning (ML) systems require representative and diverse datasets to accurately learn the objective task. In supervised learning data needs to be accurately annotated, which is an expensive and error-prone process. We present a method for generating synthetic data tailored to the use-case achieving excellent performance in a real-world usecase. We provide a method for producing automatically annotated synthetic visual data of multi rotor unmanned aerial vehicles (UAV) and other airborne objects in a simulated environment with a high degree of scene diversity, from collection of 3D models to generation of annotated synthetic datasets (synthsets). In our data generation framework SynRender we introduce a novel method of using Neural Radiance Field (NeRF) methods to capture photo-realistic high-fidelity 3D-models of multirotor UAVs in order to automate data generation for an object detection task in diverse environments. By producing data tailored to the real-world setting, our NeRF-derived results show an advantage over generic 3D asset collection-based methods where the domain gap between the simulated and real-world is unacceptably large. In the spirit of keeping research open and accessible to the research community we release our dataset VISER DroneDiversity used in this project, where visual images, annotated boxes, instance segmentation and depth maps are all generated for each image sample.

关键词： Training Visualization Three-dimensional displays Object detection Machine learning Data collection Neural radiance field Autonomous aerial vehicles Data models Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Histopathology-driven prostate cancer identification: A VBIR approach with CLAHE and GLCM insights

引用

computers in Biology and Medicine 2024年 182卷 109213-109213页

作者： Rangaiah, Pramod K.B. Pradeep Kumar, B.P. Augustine, Robin Microwaves in Medical Engineering Group Division of Solid State Electronics Department of Electrical Engineering Uppsala University Box 65 UppsalaSE-751 03 Sweden Department of Computer Science and Design Atria Institute of Technology Bengaluru560024 India

Efficient extraction and analysis of histopathological images are crucial for accurate medical diagnoses, particularly for prostate cancer. This research enhances histopathological image reclamation by integrating Visual-Based Image Reclamation (VBIR) techniques with contrast-limited adaptive Histogram Equalization (CLAHE) and the Gray-Level Co-occurrence Matrix (GLCM) algorithm. The proposed method leverages CLAHE to improve image contrast and visibility, crucial for regions with varying illumination, and employs a non-linear Support Vector Machine (SVM) to incorporate GLCM features. Our approach achieved a notable success rate of 89.6%, demonstrating significant improvement in image analysis. The average execution time for matched tissues was 41.23 s (standard deviation 36.87 s), and for unmatched tissues, 21.22 s (standard deviation 29.18 s). These results underscore the method's efficiency and reliability in processing histopathological images. The findings from this study highlight the potential of our method to enhance image reclamation processes, paving the way for further research and advancements in medical image analysis. The superior performance of our approach signifies its capability to significantly improve histopathological image analysis, contributing to more accurate and efficient diagnostic practices. © 2024 The Authors

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Largest Unit Rectangles Inscribed in a Convex Polygon

SSRN

引用

SSRN 2023年

作者： Chung, Jaehoon Bae, Sang Won Shin, Chan-Su Yoon, Sang Duk Ahn, Hee-Kap Department of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of Division of Computer Science and Engineering Kyonggi University Suwon Korea Republic of Division of Computer Engineering Hankuk University of Foreign Studies Seoul Korea Republic of Department of Service and Design Engineering SungShin Women’s University Seoul Korea Republic of Graduate School of Artificial Intelligence Department of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of

We consider an optimization problem of inscribing a unit rectangle in a convex polygon. An axis-aligned unit rectangle is an axis-aligned rectangle whose horizontal sides are of length 1. A unit rectangle of orientation θ is a copy of an axis-aligned unit rectangle rotated by θ in counterclockwise direction. The goal is to find a largest unit rectangle inscribed in a convex polygon over all orientations in [0, π). This optimization problem belongs to shape analysis, classification, and simplification, and they have applications in various cost-optimization problems. © 2023, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Refinement for Package Substrate Routing

Deep Learning based Refinement for Package Substrate Routing

引用

Electronic Components and Technology Conference (ECTC)

作者： Peng-Tai Huang Tsubasa Koyama Keng-Tuan Chang Chih-Yi Huang Chen-Chao Wang Tsung-Yi Ho Department of Computer Science National Tsing Hua University Taiwan Product Design Division Advanced Semiconductor Engineering (ASE) Inc. Taiwan Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Heterogeneous integration packaging has become increasingly important due to recent rapid technological advancements. In these designs, substrate routing is a critical factor in terms of time to market. While there are some existing works and automatic routing tools available to help designers solve routing problems, they often result in poor performance due to the complex constraints and specifications of industrial designs. Manual revision of these results is time-consuming and can take weeks. In this work, we propose a deep learning approach to improving the area distribution and reducing detours in the auto-routing results of industrial Flip-Chip Ball Grid Array (FCBGA) substrate designs, with the goal of reducing the time needed for manual modification. Experimental results show that our proposed methods can effectively refine both detours and area distribution in auto-routing results, producing results that are similar to manual routing. We also successfully reduce the modification time compared to manual one.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure-by-Construction Controller Synthesis via Control Barrier Functions

引用

IFAC-PapersOnLine 2023年第2期56卷 239-245页

作者： Bingzhuo Zhong Siyuan Liu Marco Caccamo Majid Zamani TUM School of Engineering and Design Technical University of Munich Germany Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Computer Science CU Boulder USA

In this paper, we propose a secure-by-construction scheme for synthesizing controllers to enforce safety and security properties simultaneously over control systems. As a key insight, we establish a bridge between the desired safety and security properties by leveraging notions of (augmented) control barrier functions. Based on these functions, we show that one can synthesize secure-by-construction controllers for control systems with continuous state and input sets. Additionally, we provide sum-of-square (SOS) conditions under which the desired (augmented) control barrier functions can be constructed. Finally, we demonstrate the applicability of our results on a case study.

关键词： Secure-by-Construction Controller Synthesis Safety Opacity Control Barrier Function Security

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：