Methodology for in-the-Wild Driver Monitoring Dataset Formation

Proceedings of the XXth Conference of Open Innovations Association FRUCT

Alexey Kashevnik¹  Alexandr Bulygin² 

[1] SPC RAS, Russia;St. Petersburg Institute for Informatics and Automation RAS, Russia;

关键词: driver dataset;    driver monitoring;    fatigue detection;   

DOI  :  10.23919/FRUCT54823.2022.9770925

来源: DOAJ

【 摘 要 】

Driver distraction and fatigue have become one of the leading causes of severe traffic accidents. Hence, the systems that implement driver monitoring systems are crucial. Usually such systems used a monocular camera to recognize driver behavior. Even with the growing development of advanced driver assistance systems and the introduction of third-level autonomous vehicles, this task is still trending and complex due to challenges such as in-cabin illumination change and the dynamic background. To reliably compare and validate driver inattention monitoring methods a limited number of public datasets are available. The paper proposes a methodology for in-the-wild dataset creation of vehicle driver for recording an oculomotor activity, a video images of a driver as well as relevant smartphone sensors that track vehicle movement. Based on the methodology we plan to conduct in-the-wild experiments.

【 授权许可】

Unknown