GuideTWSI: A Diverse Tactile Walking Surface Indicator Dataset from Synthetic and Real-World Images for Blind and Low-Vision Navigation
🤖 AI Summary
Existing tactile walking surface indicator (TWSI) datasets lack the diversity required for blind navigation, particularly in omitting truncated dome-type TWSIs and robot-relevant viewpoints such as egocentric and top-down perspectives, leading to poor model generalization and frequent missed detections in safety-critical scenarios. To address this gap, this work introduces GuideTWSI, the first large-scale dataset that comprehensively encompasses both Eastern and Western mainstream TWSI types—directional bars and truncated domes—by integrating synthetic and real-world images and incorporating robot-appropriate viewpoints, all accompanied by fine-grained semantic annotations. Experimental results demonstrate that models trained on GuideTWSI achieve significantly improved segmentation performance on cross-regional TWSIs, effectively reducing both missed detections and false-stop incidents.
Application Category
📝 Abstract
Tactile Walking Surface Indicators (TWSIs) are safety-critical landmarks that blind and low-vision (BLV) pedestrians use to locate crossings and hazard zones. From our observation sessions with BLV guide dog handlers, trainers, and an O&M specialist, we confirmed the critical importance of reliable and accurate TWSI segmentation for navigation assistance of BLV individuals. Achieving such reliability requires large-scale annotated data. However, TWSIs are severely underrepresented in existing urban perception datasets, and even existing dedicated paving datasets are limited: they lack robot-relevant viewpoints (e.g., egocentric or top-down) and are geographically biased toward East Asian directional bars - raised parallel strips used for continuous guidance along sidewalks. This narrow focus overlooks truncated domes - rows of round bumps used primarily in North America and Europe as detectable warnings at curbs, crossings, and platform edges. As a result, models trained only on bar-centric data struggle to generalize to dome-based warnings, leading to missed detections and false stops in safety-critical environments.
Problem
Research questions and friction points this paper is trying to address.
Tactile Walking Surface Indicators
dataset bias
geographic bias
truncated domes
accessibility
Innovation
Methods, ideas, or system contributions that make the work stand out.
Tactile Walking Surface Indicators
dataset diversity
cross-regional generalization
egocentric vision
accessibility navigation
🔎 Similar Papers
No similar papers found.
