AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

TL;DR

AIDE is a comprehensive, multi-view, multi-modal dataset designed for holistic driver monitoring and assistive driving perception, enabling improved safety systems through diverse annotations and tasks.

Contribution

The paper introduces AIDE, a novel dataset with multi-view, multi-modal, multi-task annotations for assistive driving perception, filling a gap in existing datasets.

Findings

Benchmark results demonstrate the effectiveness of multi-modal fusion strategies.

Two fusion strategies improve multi-stream/modal learning.

Systematic analysis validates the dataset's components and benchmarks.

Abstract

Driver distraction has become a significant cause of severe traffic accidents over the past decade. Despite the growing development of vision-driven driver monitoring systems, the lack of comprehensive perception datasets restricts road safety and traffic security. In this paper, we present an AssIstive Driving pErception dataset (AIDE) that considers context information both inside and outside the vehicle in naturalistic scenarios. AIDE facilitates holistic driver monitoring through three distinctive characteristics, including multi-view settings of driver and scene, multi-modal annotations of face, body, posture, and gesture, and four pragmatic task designs for driving understanding. To thoroughly explore AIDE, we provide experimental benchmarks on three kinds of baseline frameworks via extensive methods. Moreover, two fusion strategies are introduced to give new insights into learning effective multi-stream/modal representations. We also systematically investigate the importance and rationality of the key components in AIDE and benchmarks. The project link is https://github.com/ydk122024/AIDE.