100-Driver: A Large-Scale, Diverse Dataset for Distracted Driver Classification

Abstract

Distracted driver classification () plays an important role in ensuring driving safety. Although many datasets are introduced to support the study of, most of them are small in data size and are short of diversity in environmental variations. This largely limits the development of since many practical problems such as the cross-modality setting cannot be fully studied. In this paper, we introduce, a large-scale, diverse posture-based distracted diver dataset, with more than 470K images taken by 4 cameras observing 100 drivers over 79 hours from 5 vehicles. involves different types of variations that closely meet real-world applications, including changes in the vehicle, person, camera view, lighting, and modality. We provide a detailed analysis of and present 4 settings for investigating practical problems of, including the traditional setting without domain shift and 3 challenging settings ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , cross-modality, cross-view, and cross-vehicle) with domain shifts. We conduct comprehensive experiments on these 4 settings with state-the-of-art techniques and show several insights to the future study of . Our will be publicly available offering new opportunities to advance the development of . The 100-driver dataset, source code, and evaluation protocols are available at https://100-driver.github.io.