VisiMark: Characterizing and Augmenting Landmarks for People with Low Vision in Augmented Reality to Support Indoor Navigation

2025-02-14

AI Summary

To address the challenge of landmark recognition for visually impaired users in indoor navigation, this study proposes VisiMark. First, it introduces the first cognition-driven landmark taxonomy specifically designed for low-vision users—incorporating dimensions such as spatial region contours and accessibility features—to shift landmark selection from visual salience to cognitive relevance. Second, it designs an augmented reality (AR) navigation interface supporting both spatial overview and on-site augmentation, integrating real-time spatial perception, semantic landmark detection, and multimodal enhancement rendering—including high-contrast visualization, contour accentuation, and spoken feedback. Evaluated with 16 low-vision participants, VisiMark significantly improved target landmark perceptibility, increased landmark identification success rate by 3.2×, and enhanced the reliability and semantic coherence of path-level decision-making.

Technology Category

• Humans and AI: AI for Accessibility
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Landmarks are critical in navigation, supporting self-orientation and mental model development. Similar to sighted people, people with low vision (PLV) frequently look for landmarks via visual cues but face difficulties identifying some important landmarks due to vision loss. We first conducted a formative study with six PLV to characterize their challenges and strategies in landmark selection, identifying their unique landmark categories (e.g., area silhouettes, accessibility-related objects) and preferred landmark augmentations. We then designed VisiMark, an AR interface that supports landmark perception for PLV by providing both overviews of space structures and in-situ landmark augmentations. We evaluated VisiMark with 16 PLV and found that VisiMark enabled PLV to perceive landmarks they preferred but could not easily perceive before, and changed PLV's landmark selection from only visually-salient objects to cognitive landmarks that are more important and meaningful. We further derive design considerations for AR-based landmark augmentation systems for PLV.

Problem

• Enhances landmark perception for low vision
• Supports indoor navigation via AR augmentations
• Transforms landmark selection to cognitive importance

Innovation

• AR interface for low vision
• in-situ landmark augmentations
• cognitive landmarks selection