Problem
Research questions and friction points this paper is trying to address.
motorized two-wheelers
gaze behavior
naturalistic driving
rider experience
attention allocation
Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian Traffic
🤖 AI Summary
This study addresses the limited research on motorcycle rider gaze behavior in Indian urban traffic by conducting the first large-scale analysis of two-wheeler gaze patterns in naturalistic driving scenarios, utilizing the myEye2Wheeler dataset. Methodologically, a semantic segmentation pipeline integrating YOLOv11 and SAM2 is constructed to extract object-level gaze metrics. The findings reveal that riding experience primarily optimizes the temporal rhythm of gaze allocation rather than its spatial distribution strategy. Furthermore, the work elucidates the functional division between central vision monitoring and direct gaze sampling mechanisms. These insights provide a critical theoretical foundation for the design of intelligent riding safety systems.
📝 Abstract
Motorized two-wheelers (MTW) dominate Indian roads but remain underrepresented in driver behavior research. This study presents the first large-scale analysis of MTW driver gaze behavior in naturalistic, heterogeneous urban traffic, using the myEye2Wheeler dataset. A semantic segmentation pipeline (YOLOv11 + SAM2) was used to extract object-level gaze metrics under two attention modes: direct gaze (foveal overlap) and central vision (parafoveal monitoring). Results reveal a functional division: central vision supports broad monitoring, while direct gaze enables brief, selective sampling. Novice riders exhibit road-anchored scanning, returning to the road between object fixations, while experienced riders form longer chains of attention across multiple objects. The findings suggest that experience primarily refines temporal rhythm rather than altering allocation strategy and reduces object-class effects in gaze patterns. These findings offer new insight into MTW attention structures and inform future work on behavior modeling and safety systems.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Motorized two-wheelers
Gaze behavior
Semantic segmentation
YOLOv11
SAM2
🔎 Similar Papers
No similar papers found.
