Motorized two-wheeler riders show distinct gaze patterns by experience
Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian Traffic
Computer Vision and Pattern Recognition
Summary
Motorized two-wheelers are very common on Indian roads, but little was known about how riders look around while driving. The authors analyzed where riders focus their eyes during urban traffic using video and computer vision tools. They found that experienced riders look at multiple objects in a sequence, while beginners tend to keep returning their eyes to the road. This shows experience changes how riders time their attention rather than what they look at.
What this means in practice
- •For vehicle safety system designers: Improve rider monitoring systems by incorporating gaze patterns that distinguish experience levels for better risk assessment in two-wheeler traffic.
- •For driver training program developers: Design training modules that emphasize temporal attention strategies shown to differ between novice and experienced two-wheeler riders in urban environments.
Authors
Prerak Srivastava, Bhaiya Vaibhaw Kumar, Kavita Vemuri
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 \textit{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.