Problem
Research questions and friction points this paper is trying to address.
low vision
outdoor navigation
mobile augmented reality
real-world feasibility
assistive technology
NavSight in the Wild: Understanding Real-World Use of a Mobile Augmented Reality Application for People with Low Vision in Outdoor Navigation
🤖 AI Summary
This study addresses the challenges faced by people with low vision in outdoor navigation and the lack of real-world validation in existing AR assistance systems. The authors present NavSight, a mobile AR application that enables safe and independent mobility by detecting critical objects—such as curbs and vehicles—in real time and overlaying visually enhanced cues. For the first time, a seven-day in-the-wild user diary study was conducted to evaluate the system under authentic outdoor conditions. Integrating computer vision and real-time rendering, the research systematically examines how weather, lighting, shadows, and non-standard road markings affect object recognition performance. It further uncovers users’ customization strategies, error-handling behaviors, social acceptability, and context-dependent preferences for visual augmentation, offering crucial design insights for AI-driven outdoor AR assistive technologies.
📝 Abstract
The ability to navigate outdoors safely and independently is crucial yet challenging for people with low vision (PLV). While various augmented reality (AR) systems for low vision have been designed and evaluated in ideal lab environments, no research has investigated their real-world feasibility and challenges. We present NavSight, a mobile AR application that assists PLV in outdoor navigation by recognizing important outdoor objects (e.g., curb, vehicle) and rendering real-time visual augmentations. Through a seven-day diary study with 12 PLV in real-world settings, we characterize the impact of NavSight on scene perception, users' configuration strategies on what objects to augment and how to augment them across scenarios, how users made sense of and responded to recognition errors, and the social acceptability of using NavSight in public. We further identify environmental factors affecting recognition, such as weather conditions, lighting and shadows, and nonstandard road markings and textures, as well as usability issues in daily use. We discuss these real-world challenges and derive design implications for future AI-powered assistive AR systems for outdoor use.
Innovation
Methods, ideas, or system contributions that make the work stand out.
mobile augmented reality
low vision
real-world evaluation
outdoor navigation
AI-powered assistive technology
🔎 Similar Papers
No similar papers found.
