Article
Robotics
Sylvie Naudet-Collette, Kathia Melbouci, Vincent Gay-Bellile, Omar Ait-Aider, Michel Dhome
Summary: This paper introduces a new RGBD-SLAM system that combines visual and depth data to improve localization accuracy and takes advantage of scene knowledge enhancement. The system has been evaluated in real environments and public datasets and can be used for localization of lightweight robots, UAVs, and VR helmets.
Article
Automation & Control Systems
Hae Min Cho, HyungGi Jo, Euntai Kim
Summary: In this article, a novel SP-SLAM method using surfels as features for both high and low texture environments is proposed, with new objective functions to simultaneously optimize points, surfels, and cameras, demonstrating better performance and lower memory usage compared to previous feature-based visual SLAM methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Automation & Control Systems
Hae Min Cho, HyungGi Jo, Euntai Kim
Summary: This article proposes a novel SLAM method named SP-SLAM using surfels as features to handle both high texture and low texture environments. The method can represent spacious environments with relatively small memory usage and achieves better performance in both types of environments compared to previous feature-based visual SLAM methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Chemistry, Analytical
Jehn-Ruey Jiang, Hanas Subakti
Summary: This paper proposes an indoor location-based augmented reality framework (ILARF) for the development of indoor AR systems. ILARF integrates an indoor localization unit, a secure context-aware message exchange unit, and an AR visualization and interaction unit. The ILARF prototype app, GAR, helps gym users locate equipment, provides usage instructions, and enables socialization. It outperforms other AR systems by offering more information and desirable properties such as secure communication and a 3D graphical user interface.
Article
Environmental Sciences
Lu Jie, Zhi Jin, Jinping Wang, Letian Zhang, Xiaojun Tan
Summary: This paper presents a versatile and velocity-aware LiDAR-based odometry and mapping (VLOM) system, which uses a spherical projection-based feature extraction method to process raw point clouds from various LiDARs and improve feature representation. Bundle adjustment is adopted to jointly estimate poses and velocities, improving velocity estimation accuracy and compensating for point cloud distortions. Experimental results demonstrate the superiority of VLOM in terms of accuracy and robustness.
Article
Computer Science, Software Engineering
Lewis Baker, Jonathan Ventura, Tobias Langlotz, Shazia Gul, Steven Mills, Stefanie Zollmann
Summary: In augmented reality applications, knowing the user's position and orientation is crucial. However, existing methods for visual tracking through SLAM have limitations in global localization and reconstruction for stationary applications. In this paper, we propose an extended approach for spherical localization and tracking, addressing relocalization after tracking failure, global localization in large shared environments, and optimization for mobile hardware. Our system is evaluated with state-of-the-art localization methods and demonstrates effectiveness in real-life scenarios.
Article
Computer Science, Software Engineering
Lasse H. Hansen, Philipp Fleck, Marco Stranner, Dieter Schmalstieg, Clemens Arth
Summary: The research revisited the field of subsurface utility engineering, presented new methods to tackle unresolved issues, and demonstrated new technologies to solve outdoor localization problems and improve outdoor data visualization.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Jinyu Li, Xin Zhou, Bangbang Yang, Guofeng Zhang, Xun Wang, Hujun Bao
Summary: In this paper, we propose a robust and lightweight monocular visual-inertial odometry system using multiplane priors. The system utilizes planes extracted from the point cloud for fast localization and expands the planes robustly to counteract depth errors. The computational cost is further reduced by optimized algorithms and a modified marginalization strategy. Additionally, the system improves tracking robustness by constraining landmark depths using the planes during degenerated motion. Tested on various datasets, our system achieves competitive accuracy and works robustly even on challenging sequences.
COMPUTER ANIMATION AND VIRTUAL WORLDS
(2023)
Article
Computer Science, Software Engineering
Sara Romano, Enricoandrea Laviola, Michele Gattullo, Michele Fiorentino, Antonio Emmanuele Uva
Summary: This article addresses the challenges of content creation and management in Augmented Reality by providing design guidelines for the localization of in-view and not occluded components. Two user studies were conducted to validate the effectiveness of designing optimized auxiliary models based on the component shapes.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Chemistry, Multidisciplinary
Fangfang Lu, Hao Zhou, Lingling Guo, Jingjing Chen, Licheng Pei
Summary: The paper introduces an ARCore-based augmented reality campus navigation system, which utilizes AR technology and visual inertial ranging algorithm to achieve real-time positioning of 3D information and map generation, enhancing user navigation experience. Experimental results demonstrate the effectiveness and usability of the system for campus learning.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Shaojun Yue
Summary: This paper introduces AR technology and human motion feature extraction and descriptor algorithms tailored for intelligent terminals, including feature point detection and positioning methods and recursive tracking algorithms. The recursive tracking scheme outperforms the detection tracking scheme in terms of time and precision.
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2021)
Article
Engineering, Electrical & Electronic
Weijun Lin, Shijie Ding, Zheng Li, Ning Yang
Summary: In this study, a three-step calibration method is proposed to automatically obtain the rough initial value of the sensor pose. By rotating the system and using a strong magnet, the initial sensor orientation and position can be obtained. Bundle adjustment is then used to further optimize the sensor accuracy.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Oncology
Pedro Filipe Pereira Gouveia, Rogelio Luna, Francisco Fontes, David Pinto, Carlos Mavioso, Joao Anacleto, Rafaela Timoteo, Joao Santinha, Tiago Marques, Fatima Cardoso, Maria Joao Cardoso
Summary: Augmented Reality (AR) has the potential to bring numerous benefits and educational applications in the virtual health ecosystem. This paper focuses on the future applications of AR in breast surgery education, specifically discussing two potential use cases and the technical requirements to make them possible.
Article
Business
William Fritz, Rhonda Hadi, Andrew Stephen
Summary: Augmented reality technology has been adopted by the food and beverage sector to improve customer experience. Research shows that by visually simulating the consumption of food items in real-time environments, AR increases consumers' desire for the products and their likelihood to make a purchase. This increased mental simulation is influenced by the consumers' personal relevance of the food items.
JOURNAL OF THE ACADEMY OF MARKETING SCIENCE
(2023)
Article
Oncology
Chengqiang Li, Anqi Ji, Zheng Jian, Yuyan Zheng, Xijia Feng, Wei Guo, Toni Lerut, Jules Lin, Hecheng Li
Summary: This study aimed to evaluate the safety and feasibility of a newly developed augmented reality navigation technology for intraoperative localization of small pulmonary nodules. The augmented reality system successfully guided the localization procedure in 70% of cases, with an average localization time of 9.4 minutes and average operation time of 172.9 minutes. No complications were observed during the entire process.
TRANSLATIONAL LUNG CANCER RESEARCH
(2023)