Adaptive Monocular Visual-Inertial SLAM for Real-Time Augmented Reality Applications in Mobile Devices

Mapping Server Collaboration Architecture Design with OpenVSLAM for Mobile Devices

SLAM technology, which is used for spatial recognition in autonomous driving and robotics, has recently emerged as an important technology to provide high-quality AR contents on mobile devices due to the spread of XR and metaverse technologies. In this paper, we designed, implemented, and verified the SLAM system that can be used on mobile devices. Mobile SLAM is composed of a stand-alone type that directly performs SLAM operation on a mobile device and a mapping server type that additionally configures a mapping server based on FastAPI to perform SLAM operation on the server and transmits data for map visualization to a mobile device. The mobile SLAM system proposed in this paper mixes the two types in order to make SLAM operation and map generation more efficient. The stand-alone type of SLAM system was configured as an Android app by porting the OpenVSLAM library to the Unity engine, and the map generation and performance were evaluated on desktop PCs and mobile devices. The mobile SLAM system in this paper is an open-source project, so it is expected to help develop AR contents based on SLAM in a mobile environment.

An Automated Indoor Localization System for Online Bluetooth Signal Strength Modeling Using Visual-Inertial SLAM

Indoor localization is becoming increasingly important but is not yet widespread because installing the necessary infrastructure is often time-consuming and labor-intensive, which drives up the price. This paper presents an automated indoor localization system that combines all the necessary components to realize low-cost Bluetooth localization with the least data acquisition and network configuration overhead. The proposed system incorporates a sophisticated visual-inertial localization algorithm for a fully automated collection of Bluetooth signal strength data. A suitable collection of measurements can be quickly and easily performed, clearly defining which part of the space is not yet well covered by measurements. The obtained measurements, which can also be collected via the crowdsourcing approach, are used within a constrained nonlinear optimization algorithm. The latter is implemented on a smartphone and allows the online determination of the beacons’ locations and the construction of path loss models, which are validated in real-time using the particle swarm localization algorithm. The proposed system represents an advanced innovation as the application user can quickly find out when there are enough data collected for the expected radiolocation accuracy. In this way, radiolocation becomes much less time-consuming and labor-intensive as the configuration time is reduced by more than half. The experiment results show that the proposed system achieves a good trade-off in terms of network setup complexity and localization accuracy. The developed system for automated data acquisition and online modeling on a smartphone has proved to be very useful, as it can significantly simplify and speed up the installation of the Bluetooth network, especially in wide-area facilities.

Visual-Inertial Odometry of Smartphone under Manhattan World

Based on the hypothesis of the Manhattan world, we propose a tightly-coupled monocular visual-inertial odometry (VIO) system that combines structural features with point features and can run on a mobile phone in real-time. The back-end optimization is based on the sliding window method to improve computing efficiency. As the Manhattan world is abundant in the man-made environment, this regular world can use structural features to encode the orthogonality and parallelism concealed in the building to eliminate the accumulated rotation error. We define a structural feature as an orthogonal basis composed of three orthogonal vanishing points in the Manhattan world. Meanwhile, to extract structural features in real-time on the mobile phone, we propose a fast structural feature extraction method based on the known vertical dominant direction. Our experiments on the public datasets and self-collected dataset show that our system is superior to most existing open-source systems, especially in the situations where the images are texture-less, dark, and blurry.