myEye2Wheeler: A Two-Wheeler Indian Driver Real-World Eye-Tracking Dataset

TL;DR

The paper introduces myEye2Wheeler, a real-world gaze dataset for Indian two-wheeler drivers navigating chaotic traffic, addressing a gap left by Western, four-wheeler–focused datasets. Data were collected from 40 participants using the Tobii Pro Glasses 2 over a 3.9 km urban route in Hyderabad, yielding 261,073 frames with ground-truth AOIs annotated via YOLOv5 and gaze overlays provided in raw and preprocessed formats. A preliminary saliency evaluation using TASED-Net shows a notable domain gap: 84% accuracy on the DR(Eye)VE dataset versus 61% on myEye2Wheeler, underscoring the need for context-specific models tailored to Indian traffic. The dataset advances two-wheeler safety research and paves the way for designing domain-relevant saliency predictors and driver-assistance systems in heterogeneous, high-density traffic environments.

Abstract

This paper presents the myEye2Wheeler dataset, a unique resource of real-world gaze behaviour of two-wheeler drivers navigating complex Indian traffic. Most datasets are from four-wheeler drivers on well-planned roads and homogeneous traffic. Our dataset offers a critical lens into the unique visual attention patterns and insights into the decision-making of Indian two-wheeler drivers. The analysis demonstrates that existing saliency models, like TASED-Net, perform less effectively on the myEye-2Wheeler dataset compared to when applied on the European 4-wheeler eye tracking datasets (DR(Eye)VE), highlighting the need for models specifically tailored to the traffic conditions. By introducing the dataset, we not only fill a significant gap in two-wheeler driver behaviour research in India but also emphasise the critical need for developing context-specific saliency models. The larger aim is to improve road safety for two-wheeler users and lane-planning to support a cost-effective mode of transport.

Figures (6)

• Figure 1: Flowchart representing the key steps in this study
• Figure 2: In clockwise order from top-left: (a) Participant wearing the eye tracker inside his helmet and, (b) Experiment setup while on the road and, (c) Point G on the route, and (d) Top view of the route described where arrows denote the direction of traffic
• Figure 3: The data will be classified into Experienced and Novice, and each participant's age, two-wheeler driving experience and gender will provided in the folder's name containing that respective participant's data.
• Figure 4: Some frames from the dataset
• Figure 5: (a) Ground Truth (On/off-road) vs (b) Prediction (Vehicle in this case)