Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes

TL;DR

This paper introduces RAID, a large-scale dataset for driver risk perception, and proposes a weakly supervised framework to identify risk sources and analyze pedestrian attention, advancing understanding of driver behavior in diverse traffic scenarios.

Contribution

The paper presents RAID, a new dataset for driver risk perception, and a weakly supervised method to identify risk sources and assess pedestrian attention in driving scenes.

Findings

Achieved 20.6% performance improvement on RAID dataset.

Achieved 23.1% performance improvement on HDDS dataset.

Demonstrated the importance of pedestrian attention in risk estimation.

Abstract

Achieving zero-collision mobility remains a key objective for intelligent vehicle systems, which requires understanding driver risk perception-a complex cognitive process shaped by voluntary response of the driver to external stimuli and the attentiveness of surrounding road users towards the ego-vehicle. To support progress in this area, we introduce RAID (Risk Assessment In Driving scenes)-a large-scale dataset specifically curated for research on driver risk perception and contextual risk assessment. RAID comprises 4,691 annotated video clips, covering diverse traffic scenarios with labels for driver's intended maneuver, road topology, risk situations (e.g., crossing pedestrians), driver responses, and pedestrian attentiveness. Leveraging RAID, we propose a weakly supervised risk object identification framework that models the relationship between driver's intended maneuver and responses to identify potential risk sources. Additionally, we analyze the role of pedestrian attention in estimating risk and demonstrate the value of the proposed dataset. Experimental evaluations demonstrate that our method achieves 20.6% and 23.1% performance gains over prior state-of-the-art approaches on the RAID and HDDS datasets, respectively.