Search for: All records

Augmented reality (AR) platforms now support persistent, markerless experiences, in which virtual content appears in the same place relative to the real world, across multiple devices and sessions. However, optimizing environments for these experiences remains challenging; virtual content stability is determined by the performance of device pose tracking, which depends on recognizable environment features, but environment texture can impair human perception of virtual content. Low-contrast 'invisible textures' have recently been proposed as a solution, but may result in poor tracking performance when combined with dynamic device motion. Here, we examine the use of invisible textures in detail, starting with the first evaluation in a realistic AR scenario. We then consider scenarios with more dynamic device motion, and conduct extensive game engine-based experiments to develop a method for optimizing invisible textures. For texture optimization in real environments, we introduce MoMAR, the first system to analyze motion data from multiple AR users, which generates guidance using situated visualizations. We show that MoMAR can be deployed while maintaining an average frame rate > 59fps, for five different devices. We demonstrate the use of MoMAR in a realistic case study; our optimized environment texture allowed users to complete a task significantly faster (p=0.003) than a complex texture. 

3D object detection (OD) is a crucial element in scene understanding. However, most existing 3D OD models have been tailored to work with light detection and ranging (LiDAR) and RGB-D point cloud data, leaving their performance on commonly available visual-inertial simultaneous localization and mapping (VI-SLAM) point clouds unexamined. In this paper, we create and release two datasets: VIP500, 4772 VI-SLAM point clouds covering 500 different object and environment configurations, and VIP500-D, an accompanying set of 20 RGB-D point clouds for the object classes and shapes in VIP500. We then use these datasets to quantify the differences between VI-SLAM point clouds and dense RGB-D point clouds, as well as the discrepancies between VI-SLAM point clouds generated with different object and environment characteristics. Finally, we evaluate the performance of three leading OD models on the diverse data in our VIP500 dataset, revealing the promise of OD models trained on VI-SLAM data; we examine the extent to which both object and environment characteristics impact performance, along with the underlying causes. 

Mobile augmented reality (AR) has a wide range of promising applications, but its efficacy is subject to the impact of environment texture on both machine and human perception. Performance of the machine perception algorithm underlying accurate positioning of virtual content, visual-inertial SLAM (VI-SLAM), is known to degrade in low-texture conditions, but there is a lack of data in realistic scenarios. We address this through extensive experiments using a game engine-based emulator, with 112 textures and over 5000 trials. Conversely, human task performance and response times in AR have been shown to increase in environments perceived as textured. We investigate and provide encouraging evidence for invisible textures, which result in good VI-SLAM performance with minimal impact on human perception of virtual content. This arises from fundamental differences between VI-SLAM-based machine perception, and human perception as described by the contrast sensitivity function. Our insights open up exciting possibilities for deploying ambient IoT devices that display invisible textures, as part of systems which automatically optimize AR environments. 

Virtual content instability caused by device pose tracking error remains a prevalent issue in markerless augmented reality (AR), especially on smartphones and tablets. However, when examining environments which will host AR experiences, it is challenging to determine where those instability artifacts will occur; we rarely have access to ground truth pose to measure pose error, and even if pose error is available, traditional visualizations do not connect that data with the real environment, limiting their usefulness. To address these issues we present SiTAR (Situated Trajectory Analysis for Augmented Reality), the first situated trajectory analysis system for AR that incorporates estimates of pose tracking error. We start by developing the first uncertainty-based pose error estimation method for visual-inertial simultaneous localization and mapping (VI-SLAM), which allows us to obtain pose error estimates without ground truth; we achieve an average accuracy of up to 96.1% and an average FI score of up to 0.77 in our evaluations on four VI-SLAM datasets. Next, we present our SiTAR system, implemented for ARCore devices, combining a backend that supplies uncertainty-based pose error estimates with a frontend that generates situated trajectory visualizations. Finally, we evaluate the efficacy of SiTAR in realistic conditions by testing three visualization techniques in an in-the-wild study with 15 users and 13 diverse environments; this study reveals the impact both environment scale and the properties of surfaces present can have on user experience and task performance. 

The traditional freehand placement of an external ventricular drain (EVD) relies on empirical craniometric landmarks to guide the craniostomy and subsequent passage of the EVD catheter. The diameter and trajectory of the craniostomy physically limit the possible trajectories that can be achieved during the passage of the catheter. In this study, the authors implemented a mixed reality–guided craniostomy procedure to evaluate the benefit of an optimally drilled craniostomy to the accurate placement of the catheter. Optical marker–based tracking using an OptiTrack system was used to register the brain ventricular hologram and drilling guidance for craniostomy using a HoloLens 2 mixed reality headset. A patient-specific 3D-printed skull phantom embedded with intracranial camera sensors was developed to automatically calculate the EVD accuracy for evaluation. User trials consisted of one blind and one mixed reality–assisted craniostomy followed by a routine, unguided EVD catheter placement for each of two different drill bit sizes. A total of 49 participants were included in the study (mean age 23.4 years, 59.2% female). The mean distance from the catheter target improved from 18.6 ± 12.5 mm to 12.7 ± 11.3 mm (p = 0.0008) using mixed reality guidance for trials with a large drill bit and from 19.3 ± 12.7 mm to 10.1 ± 8.4 mm with a small drill bit (p < 0.0001). Accuracy using mixed reality was improved using a smaller diameter drill bit compared with a larger bit (p = 0.039). Overall, the majority of the participants were positive about the helpfulness of mixed reality guidance and the overall mixed reality experience. Appropriate indications and use cases for the application of mixed reality guidance to neurosurgical procedures remain an area of active inquiry. While prior studies have demonstrated the benefit of mixed reality–guided catheter placement using predrilled craniostomies, the authors demonstrate that real-time quantitative and visual feedback of a mixed reality–guided craniostomy procedure can independently improve procedural accuracy and represents an important tool for trainee education and eventual clinical implementation. 

Edge computing is increasingly proposed as a solution for reducing resource consumption of mobile devices running simultaneous localization and mapping (SLAM) algorithms, with most edge-assisted SLAM systems assuming the communication resources between the mobile device and the edge server to be unlimited, or relying on heuristics to choose the information to be transmitted to the edge. This paper presents AdaptSLAM, an edge-assisted visual (V) and visual-inertial (VI) SLAM system that adapts to the available communication and computation resources, based on a theoretically grounded method we developed to select the subset of keyframes (the representative frames) for constructing the best local and global maps in the mobile device and the edge server under resource constraints. We implemented AdaptSLAM to work with the state-of-the-art open-source V-and VI-SLAM ORB-SLAM3 framework, and demonstrated that, under constrained network bandwidth, AdaptSLAM reduces the tracking error by 62% compared to the best baseline method. 

External ventricular drain (EVD) is a common, yet challenging neurosurgical procedure of placing a catheter into the brain ventricular system that requires prolonged training for surgeons to improve the catheter placement accuracy. In this paper, we introduce NeuroLens, an Augmented Reality (AR) system that provides neurosurgeons with guidance that aides them in completing an EVD catheter placement. NeuroLens builds on prior work in AR-assisted EVD to present a registered hologram of a patient’s ventricles to the surgeons, and uniquely incorporates guidance on the EVD catheter’s trajectory, angle of insertion, and distance to the target. The guidance is enabled by tracking the EVD catheter. We evaluate NeuroLens via a study with 33 medical students, in which we analyzed students’ EVD catheter insertion accuracy and completion time, eye gaze patterns, and qualitative responses. Our study, in which NeuroLens was used to aid students in inserting an EVD catheter into a realistic phantom model of a human head, demonstrated the potential of NeuroLens as a tool that will aid and educate novice neurosurgeons. On average, the use of NeuroLens improved the EVD placement accuracy of year 1 students by 39.4% and of the year 2−4 students by 45.7%. Furthermore, students who focused more on NeuroLens-provided contextual guidance achieved better results. 

Demand is growing for markerless augmented reality (AR) experiences, but designers of the real-world spaces that host them still have to rely on inexact, qualitative guidelines on the visual environment to try and facilitate accurate pose tracking. Furthermore, the need for visual texture to support markerless AR is often at odds with human aesthetic preferences, and understanding how to balance these competing requirements is challenging due to the siloed nature of the relevant research areas. To address this, we present an integrated design methodology for AR spaces, that incorporates both tracking and human factors into the design process. On the tracking side, we develop the first VI-SLAM evaluation technique that combines the flexibility and control of virtual environments with real inertial data. We use it to perform systematic, quantitative experiments on the effect of visual texture on pose estimation accuracy; through 2000 trials in 20 environments, we reveal the impact of both texture complexity and edge strength. On the human side, we show how virtual reality (VR) can be used to evaluate user satisfaction with environments, and highlight how this can be tailored to AR research and use cases. Finally, we demonstrate our integrated design methodology with a case study on AR museum design, in which we conduct both VI-SLAM evaluations and a VR-based user study of four different museum environments.