Article
Computer Science, Information Systems
Haoxin Wang, Baekgyu Kim, Jiang Xie, Zhu Han
Summary: This paper presents a edge-based energy-aware mobile augmented reality (MAR) system that dynamically adjusts configurations to minimize energy consumption while maintaining performance metrics. It proposes a comprehensive analytical energy model and optimization algorithm, along with an image offloading frequency orchestrator, to improve energy efficiency.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Niloofar Didar, Marco Brocanelli
Summary: Mobile Augmented Reality (MAR) apps may experience short battery life due to high-quality virtual objects, but the proposed eAR framework can significantly reduce energy consumption and storage overhead while maintaining user-perceived quality. The framework utilizes an edge server running offline software to evaluate user-perceived quality based on triangle count and user-object distance. It also includes a lightweight optimization algorithm that dynamically determines the most energy-efficient virtual object triangle count based on energy consumption models and user path prediction. eAR is an autonomous and open-source library that can be easily integrated into existing MAR apps.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Telecommunications
Guangjin Pan, Heng Zhang, Shugong Xu, Shunqing Zhang, Xiaojing Chen
Summary: This paper presents a method for completing video-based AI inference tasks in a mobile edge computing system. By using an alternating optimization algorithm, the problem is decomposed into two sub-problems: resource allocation for devices that complete tasks locally and resource allocation for devices that offload tasks. To further reduce complexity, a distributed algorithm based on alternating direction method of multipliers (ADMM) is proposed. Numerical experiments demonstrate the effectiveness of the proposed algorithms.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2023)
Article
Automation & Control Systems
Zaixing He, Jindong Zhao, Xinyue Zhao, Wuxi Feng, Quanyou Wang, Huilong Jiang
Summary: This paper proposes an object registration method based on multiple edge features, which can effectively register reflective texture-less objects. Experimental results demonstrate its high accuracy, meeting the requirements of augmented reality assembly in the industry.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Computer Science, Theory & Methods
Ning Chen, Siyi Quan, Sheng Zhang, Zhuzhong Qian, Yibo Jin, Jie Wu, Wenzhong Li, Sanglu Lu
Summary: This article introduces a system named Cuttlefish, which uses reinforcement learning to generate video configuration decisions to improve the user experience quality of Augmented Reality (AR) applications. Cuttlefish adaptively selects configurations based on network conditions and video content, without relying on pre-programmed models, achieving a higher QoE compared to other methods.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Abdelhamied A. Ateya, Ammar Muthanna, Andrey Koucheryavy, Yassine Maleh, Ahmed A. Abd El-Latif
Summary: Augmented reality (AR) is a key feature of 5G cellular systems, requiring a total delay of about 5 ms for AR applications. Due to limitations in mobile devices' computing resources, computing tasks for mobile AR applications need to be offloaded to nearby devices with sufficient resources. This paper proposes a system structure based on modified multi-level mobile edge computing system (MM-MEC) for mobile AR and web-based AR applications, along with latency and energy-aware offloading algorithms for efficient execution of AR computing tasks.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Agriculture, Multidisciplinary
Thomas Napier, Ickjai Lee
Summary: Abalone are increasingly popular for consumption, but measuring their number and size distribution in existing farms is challenging. Current methods rely on manual inspection, which is time-consuming and results in mediocre data quality. To address this, we propose a mobile-based tool that combines object detection and augmented reality for real-time counting and measuring of Abalone. Our experimental results showed that the proposed tool outperforms traditional approaches, achieving above 95% accuracy in counting Abalone and reducing measurement time, while maintaining an accuracy within a maximum error range of 2.5% of the Abalone's actual size.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Computer Science, Information Systems
Pei Ren, Ling Liu, Xiuquan Qiao, Junliang Chen
Summary: This paper proposes EARNet, a distributed edge system orchestration approach for mobile Web AR in 5G networks. EARNet manages the edge network dynamics using landmarks and grid index based edge node localization mechanisms, considers both request serving performance and offloading cost, and leverages dynamic hash and max heap mechanisms for efficient Web AR service lookup and AR computations. Additionally, EARNet designs service migration schemes by optimizing several performance factors. Experimental evaluations demonstrate the effectiveness of EARNet compared to several baseline approaches.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Gi Seok Park, Ryeong Hwan Kim, Hwangjun Song
Summary: This paper presents a collaborative virtual 3D object modeling system that leverages mobile edge cloud (MEC) and device-to-device (D2D) communication for low-latency and high-quality augmented reality (AR) streaming services over 5G networks. The system utilizes MEC for computationally intensive tasks and D2D communication for reducing transmission delay. It introduces a part-segment quality selection algorithm to control the quality of each segment based on the user's network condition. The experimental results demonstrate the superior performance of the proposed system in terms of service latency and visual 3D object quality compared to conventional systems.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Review
Computer Science, Interdisciplinary Applications
Yalda Ghasemi, Heejin Jeong, Sung Ho Choi, Kyeong-Beom Park, Jae Yeol Lee
Summary: This paper reviews the integration of augmented/mixed reality and deep learning for object detection over the past decade and analyzes the advantages and limitations of its applications and computations.
COMPUTERS IN INDUSTRY
(2022)
Article
Computer Science, Software Engineering
Wenxiao Zhang, Bo Han, Pan Hui
Summary: This paper presents SEAR, a collaborative framework for Scaling Experiences in multi-user Augmented Reality. SEAR solves the scalability issue in mobile AR through a lightweight collaborative local caching scheme, reducing end-to-end latency and improving object-recognition accuracy.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Computer Science, Information Systems
Tri Nguyen Dang, Kitae Kim, Latif U. Khan, S. M. Ahsan Kazmi, Zhu Han, Choong Seon Hong
Summary: The article discusses the growing demand for augmented reality applications and proposes an incentive mechanism for utilizing user equipment resources for local caching to address the challenge of insufficient MEC server resources.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Giha Yoon, Geun-Yong Kim, Hark Yoo, Sung Chang Kim, Ryangsoo Kim
Summary: In the last decade, deep neural network (DNN)-based object detection technologies have been recognized as a promising solution for image understanding and video analysis on mobile edge devices. However, executing computationally intensive DNN-based object detection workloads on these devices may not meet the accuracy and latency requirements due to limited computation capacity. A proposed offloading framework aims to improve object detection performance by offloading workloads to a remote edge server, but initial results show potential performance degradation in edge computing architectures.
Article
Computer Science, Information Systems
Bin Dai, Fanglin Xu, Yuanyuan Cao, Yang Xu
Summary: The proposed AVR algorithm utilizes computation offloading and resource allocation optimization to improve the efficiency of real-time data processing, achieving cooperative perception with hybrid sensing data fusion.
IEEE SYSTEMS JOURNAL
(2021)
Article
Computer Science, Information Systems
Jiacheng Shang, Si Chen, Jie Wu, Shu Yin
Summary: This paper explores a user location tracking system in augmented reality applications and demonstrates its effectiveness and accuracy through experiments. It also highlights the security threats in current location-based multi-player AR applications and proposes mitigation methods.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)