Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction

Researchers have developed a gaze-aligned artificial intelligence framework that predicts perceived cycling safety by integrating human eye-tracking data into image analysis. The model, called EG-PCS, uses vision transformers supervised with eye-tracking signals to produce attention maps that more accurately reflect how humans visually assess street safety. The approach enhances both predictive accuracy and interpretability in urban analytics, addressing a key barrier to cycling adoption in cities.

arXiv:2605.24040v1 Announce Type: new Abstract: Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, individuals are less likely to cycle, making perception a key barrier to adoption. Recent work has shown that pairwise comparisons of street-view images provide a scalable way to learn subjective safety judgments. However, existing approaches do not explicitly model human visual attention, which plays a central role in how humans perceive safety. We propose an Eye-Tracking-Guided Perceived Cycling Safety framework EG-PCS that integrates gaze data into a pairwise learning pipeline based on vision transformers. By supervising the model's attention mechanism with eye-tracking signals, we encourage alignment between learned attention maps and human fixation patterns. Experiments show that gaze-guided models achieve similar ranking performance compared to state-of-the-art approaches while producing attention maps that more accurately reflect human visual attention behavior. Our results demonstrate that incorporating eye-tracking information enhances both predictive accuracy and interpretability in perception-based urban analytics.