A Contextual Analysis of Driver-Facing and Dual-View Video Inputs for Distraction Detection in Naturalistic Driving Environments

TL;DR

This study evaluates how incorporating road-facing views with driver-facing footage affects distraction detection accuracy in naturalistic driving, revealing that architecture design critically influences the benefits of contextual inputs.

Contribution

It provides a systematic comparison of single- and dual-view distraction detection models using real-world data, highlighting architecture-dependent performance impacts.

Findings

SlowOnly improved by 9.8% with dual-view inputs.

SlowFast experienced a 7.2% accuracy drop with dual-view inputs.

Architecture design determines whether contextual inputs enhance or hinder detection.

Abstract

Despite increasing interest in computer vision-based distracted driving detection, most existing models rely exclusively on driver-facing views and overlook crucial environmental context that influences driving behavior. This study investigates whether incorporating road-facing views alongside driver-facing footage improves distraction detection accuracy in naturalistic driving conditions. Using synchronized dual-camera recordings from real-world driving, we benchmark three leading spatiotemporal action recognition architectures: SlowFast-R50, X3D-M, and SlowOnly-R50. Each model is evaluated under two input configurations: driver-only and stacked dual-view. Results show that while contextual inputs can improve detection in certain models, performance gains depend strongly on the underlying architecture. The single-pathway SlowOnly model achieved a 9.8 percent improvement with dual-view inputs, while the dual-pathway SlowFast model experienced a 7.2 percent drop in accuracy due to representational conflicts. These findings suggest that simply adding visual context is not sufficient and may lead to interference unless the architecture is specifically designed to support multi-view integration. This study presents one of the first systematic comparisons of single- and dual-view distraction detection models using naturalistic driving data and underscores the importance of fusion-aware design for future multimodal driver monitoring systems.