检索结果-内蒙古大学图书馆

MSF-Net: Multi-Scale Feedback Reconstruction for Guided Depth Map Super-Resolution

IEEE Transactions on Circuits and Systems for Video Technology 2024年第2期34卷 709-723页

作者： Wang, Jin Li, Chenyang Shi, Yunhui Wang, Dan Wu, Mu-En Ling, Nam Yin, Baocai Beijing University of Technology Faculty of Information Technology Beijing100124 China National Taipei University of Technology Department of Information and Finance Management Taipei10608 Taiwan Santa Clara University Department of Computer Science and Engineering Santa ClaraCA95053 United States

Guided depth map super-resolution (GDSR) is one of the mainstream methods in depth map super-resolution, as high-resolution color images can guide the reconstruction of the depth maps and are often easy to obtain. However, how to make full use of extracted guidance information of the color image to improve the depth map reconstruction remains a challenging problem. In this paper, we first design a multi-scale feedback module (MF) that extracts multi-scale features and alleviates the information loss in network propagation. We further propose a novel multi-scale feedback network (MSF-Net) for guided depth map super-resolution, which can better extract and refine the features by sequentially joining MF blocks. Specifically, our MF block uses parallel sampling layers and feedback links between multiple time steps to better learn information at different scales. Moreover, an inter-scale attention module (IA) is proposed to adaptively select and fuse important features at different scales. Meanwhile, depth features and corresponding color features are interacted using cross-domain attention conciliation module (CAC) after each MF block. We evaluate the performance of our proposed method on both synthetic and real captured datasets. Extensive experimental results validate that the proposed method achieves state-of-the-art performance in both objective and subjective quality. © 1991-2012 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Big Data Analysis on Intelligent Traffic Surveillance by Incorporating Sensors and IoT Devices on Roads 7

Big Data Analysis on Intelligent Traffic Surveillance by Inc...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Devi, A. Kapruwan, Akanksha Shrimali, Manish Appalakonda, Vengalapudi Maranan, Ramya Barve, Amit Tamil Nadu Coimbatore641 049 India Graphic Era Deemed To Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Department of Computer Science And It Rajasthan Udaipur313 003 India Department of Artificial Intelligence And Machine Learning Kakinada Andhra Pradesh Surampalem533 437 India SIMATS Saveetha School of Engineering Department of Research And Innovation Tamil Nadu Chennai602105 India Parul University Parul Institute of Technology Faculty of Engineering And Technology Department of Computer Science And Engineering P.O.Limda Gujarat 391760 India

ISBN: (纸本)9798350359299

Rather than relying on public transportation, people are increasingly comfortable driving their automobiles to satisfy their mobility needs. Reasons for this include the automobiles' accessibility and the fact that they can be used whenever needed. Because of this, many cities around the world experience terrible traffic congestion and long wait periods at traffic signals. Smarter and more effective traffic management is possible through the integration of big data, the Internet of Things (IoT), and a cloud platform with a network of linked vehicles and sensors. The objective of this study is to estimate traffic conditions along a route and provide updates to the user. Initially, Deep Learning (DL) models such as YOLO (You Only Look Once) and SSD (Single-Shot Object Detection) are developed and tested to detect vehicles. YOLO produces outstanding performance in vehicle detection, with an 89.5% mean Average Precision (mAP) and an 83.98% Intersection over Union (IoU). This model is then pushed to the cloud. A Global Positioning System (GPS) module is used to determine the user's current location. Based on the user's location, the nearest camera is enabled, and the recorded video is sent to the cloud. The cloud-deployed YOLO model is used to detect and count vehicles. To improve the user experience, this study has created a mobile application. The software contains a navigation map function that allows users to specify the maximum number of vehicles expected along their route. The created system counts the number of vehicles on their path, and if the count exceeds the specified threshold, the mobile app notifies the user about traffic conditions. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Harmonic Impact of EV Charging Station on Prosumer-Rich Distribution Feeders 5

Harmonic Impact of EV Charging Station on Prosumer-Rich Dist...

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Rusan, Marko Fekete, Krešimir Čvek, Kristijan Klaić, Zvonimir Department of Power Engineering Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

This paper presents an analysis of the harmonic influence of an electric vehicle charging station (EVCS) on the harmonic distortion of the voltage in a low-voltage (LV) distribution network. The analysis was performed by simulations of harmonic power flows for different sources of harmonic distortion. In the first case, the source of harmonic distortion is existing non-linear loads in the 0.4 kV network. In the second case, EVCS is added, and in the third case, the photovoltaic power plants are added as another harmonic distortion source. Input data on harmonics for the 0.4 kV network and EVCS were obtained by measurements in the real life and input data for the harmonic influence of the photovoltaic power plants is taken from the literature. The results of the simulations indicate the possibility of deteriorating the power quality when analyzing the joint impact of EVCS and photovoltaics. © 2022 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing’s Effect on Video Games Streaming 2

Cloud Computing’s Effect on Video Games Streaming

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Komathi, A. Lenin, J. Asha, S. Suresh, A. Suguna, M. Srinivasan, C. Department of Computer Science Nadar Saraswathi College of Arts and Science College Tamilnadu Theni India Department of ComputerScience and Engineering Alliance College of Engineering and Design Alliance University Karnataka Bengaluru India Department of Information Technology S.A. Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Andhra Pradesh Puttur India Tamil Nadu Salem India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350340235

The disruptive power of cloud computing is altering the gaming industry. Real-time gaming is now feasible because to advancements in streaming algorithms, further blurring the lines between the digital and physical worlds. Understanding the potential of Cloud computing to change the gaming industry is the emphasis which investigates the complicated relationship between numerous technologies. By using cutting-edge streaming protocols and techniques like Adaptive Bitrate Streaming (ABS), buffering, caching, and compression, users may have uninterrupted, high-quality gaming experiences. The study's findings herald a new era of interactive entertainment and shed light on the transformative possibilities of these technologies. Asynchronous Bit-Rate (ABR) encoding, buffering, caching algorithms, video compression standards, and streaming protocols are just few of the numerous digital components that work together to provide uninterrupted data transmission. The rapid progress of ABR algorithms has made it possible to dynamically alter video quality to maximize the user experience across a broad variety of network scenarios. Buffering and caching algorithms play crucial roles by proactively managing data flow and storage to avoid disruptions in the streaming experience. © 2023 IEEE.

关键词： Autism buffering algorithms caching methods Cloud Computing Impact Interactive Entertainment Standards for video compression Streaming Algorithms streaming protocols Video Games

来源：评论

学校读者我要写书评

暂无评论

The Use of Smart Devices for Assessing the User’s Physiological Status 1

引用

8th Future Technologies Conference, FTC 2023

作者： Fodor, Kristián Balogh, Zoltán Molnár, György Department of Computer Science Faculty of Natural Sciences and Informatics Constantine the Philosopher University in Nitra Nitra Slovakia Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary

ISBN: (数字)9783031474576

ISBN: (纸本)9783031474569

Currently, there are various technical solutions as well as methods by which the user’s physiological functions can be obtained. From the point of view of the technical solutions, approaches based on the application of sensors (galvanic skin response, heart rate, temperature, etc.) or the use of a camera for capturing the face and its parts are most often used. The article is devoted to the creation of a system for identifying and classifying the emotional state of the user while maintaining non-invasiveness, which includes an IoT-based (Internet of Things) user interface. It deals with the capture of data about the user and the subsequent evaluation of this data with the help of a web application for visualizing and evaluating the obtained data. The research uses a pulse sensor and a galvanic skin response sensor, which are connected to an Arduino and a computer, for data evaluation. The results of the paper include the design of a portable and affordable device that can be non-invasively attached to the human body and monitor the measured values for a long time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Exploring 2D, 3D and Spatial Audio User Interfaces in VR for Reminiscence Therapy 12

Exploring 2D, 3D and Spatial Audio User Interfaces in VR for...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Uribe-Quevedo, Alvaro Arevalo, Camilo Villegas, Julián Sun, Winnie Ontario Tech University Faculty of Business and It OshawaON Canada University of Aizu Department of Computer Science and Engineering Fukushima Aizuwakamatsu Japan Ontario Tech University Faculty of Health Sciences OshawaON Canada

ISBN: (纸本)9798350340181

Reminiscence Therapy (RT) is a non-pharmacological treatment focused on helping individuals with dementia recollect memories through their senses. Traditionally, RT therapy has relied on multimedia, where caregivers choose videos, pictures, and audio files. Since cross-sensory stimuli play an important role during RT, the adoption of Virtual Reality (VR) has spiked as the technology becomes commonplace. Our previous work has focused on prototyping a VR RT tool through co-design and usability testing, utilizing hand tracking for ease of use. In this research, we aim to further understand usability, presence, and cognitive load effects by comparing a 2D Graphical User Interface (GUI), a radio-style 3D User Interface (3DUI), a curved-style 3DUI, and a spatial audio User Interface UI that allows playing, stopping, and adjusting the volume of an audio file. Our preliminary study indicates that a traditional 2D GUI has higher usability, and lower cognitive load, while a curved-style 3DUI with 3D push buttons and a slider for volume around the user has a higher presence than the radio-style 3DUI and the spatial audio UI. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Multibio Authentication of Online Users in Proctoring and E-Learning 3

Multibio Authentication of Online Users in Proctoring and E-...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Ajitha, P. Sadish Sendi, M. Navaneethakrishnan, Sundara Rajulu Sivasangari, A. Surendran, R. Sathyabama Institue of Science and Technology School of Computing Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology School of Computing Chennai India Dhanalakshmi Srinivasan University Trichy Department of Computer Science and Engineering Samayapuram Campus Tiruchirappalli India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350369083

online courses have become more liked recently as a brand-new method of instructing students in remoteness literacy environment. However, as request grows, educational accademies were faced with difficulty of determining how to verify that online scholars are the persons they say they are throughout learning ventures, particularly examinations. Mortal monitoring is an un-scalable method that calls for someone to oversee every student ever. On the computraized supervisors frequently focus on a certain kind of gadget and confirm the students' attendance without taking into account their interactions with the distance learning platform. In this study, present a multi- ralistic authentication system that is device/commerce independent and aims to constantly and translucent validate both existance and commerce. Through the use of a score-position emulsion of several realistic authentication response suc as facial, voice, touch based on the gadget. The system is suitable to certify to the scholars's identification all over the literacy occurrance depending on how it is used and the commerce that is conducted with it. Our donation has a fair chance of providing workable and dependable carry on a wider range of online system tests when compared to existing alternatives. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study on Healthcare Applications for Remote Patients

An Exploratory Study on Healthcare Applications for Remote P...

引用

2023 International Conference on Artificial Intelligence Robotics, Signal and Image Processing, AIRoSIP 2023

作者： Deekshith, Servepalli Moushmi Niharika, Kandepu Sri Karthika, Adapa Akanksha Deepika, Gunji Bhattacharjya, Aniruddha Koneru Lakshmaiah Education Foundation Department of Cse Andhra Pradesh Guntur522502 India Sgt University Faculty of Engineering & Technology Department of Computer Science Engineering Gurugram India

ISBN: (纸本)9798350327472

Healthcare has experienced massive changes as a result of the development of technologies. It is a basic requirement for human life. Nowadays online platforms are continuously growing in the field of healthcare and helping millions in the world. The innovative technologies such as Virtual reality, artificial intelligence, data analysis, Blockchain and mixed reality are not only interesting but they are increasingly applied in the field of healthcare. The objective of this research is to study healthcare applications that are suitable for patients who reside far away. The aim of this research is to explore the advantages and challenges of implementing healthcare applications for people living in remote places, looking at the variables that influence the adoption of these applications, and offer suggestions for improving these applications more. A qualitative research methodology was used to conduct the study. The Virtual developments in healthcare can reduce the overall global healthcare spending and they are very much hassle-free to use for patients. These developments will cause major changes in the healthcare in upcoming decades. The study has found that remote patients can certainly benefit from healthcare applications, including improved treatment accessibility, cost savings, and convenience. Unfortunately, a variety of challenges, including technological problems, privacy issues, and a lack of understanding, prevent the broader use of these applications. These healthcare applications provide authentications and scalable structures. © 2023 IEEE.

关键词： challenges Healthcare healthcare applications remote patients technology

来源：评论

学校读者我要写书评

暂无评论

Impact of Different Noise Distributions in the Application of Kalman Filter in Sensor Fusion 5

Impact of Different Noise Distributions in the Application o...

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Čvek, Kristijan Mostarac, Marija Miličević, Kruno Department of Power Engineering Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

This paper explains the concept of the Kalman filter as an estimator of the system state based on measurements in the presence of noise. Sensor fusion allows for the measurement of factors that are not immediately measurable as well as the creation of more accurate data. The theoretical underpinning for the definition of a filter and Kalman-based sensor fusion, and filter and sensor fusion algorithms are explained and implemented in simulation. The application of the filter for sensor fusion is presented, and in the end, simulation results are obtained for different types of noise distribution – normal as the usual one for physical quantities and uniform as dominant in digitized values. © 2022 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification Using Siamese Triplet Network 4

Person Re-Identification Using Siamese Triplet Network

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Menon, Aparna Yashwanthika, R. Shreya, J.V. Somasundaram, K. Thangavel, Senthil Kumar Asawa, Shreeya Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India Amrita School of Physical Sciences Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Due to the increasing demand for public safety and the rapid development of intelligent surveillance networks, the re-identification of individuals (Re-ID) has become one of the most important research topics in computer vision. Person re-identification (Re-ID) has a wide range of applications, which increases its popularity in recent studies. The main goal of person re-identification (Re-ID) is to retrieve people with the same identity from different cameras. In the open world, there are still some challenges. First, existing re-ID research usually assumes that only one-factor variable (view, clothing, pedestrian pose, pedestrian occlusion, image resolution, RGB/IR modality) changes, and ignores the complexity of multi-factor variables in the open world. Second, existing ID methods are overly dependent on clothing color and other obvious pedestrian features that can be easily obscured or changed. In addition, the lack of benchmark datasets that include multifactor variables hinders the practical application of ID in the open world. The proposed model uses a Deep learning model -Siamese triplet network to extract the features, and a similarity measure to re-identify the individual. The evaluation metrics used are cumulative matching features (CMC) and mean average precision (mAP). Preliminary results show that the model performs well in comparison to existing methods, and future work will focus on improving robustness under varying environmental conditions. © 2025 IEEE.

关键词： Reamers

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：