A Method of Generating a Composite Dataset for Monitoring of Non-Driving Related Tasks

2024-01-2640

04/09/2024

Features
Event
WCX SAE World Congress Experience
Authors Abstract
Content
Recently, several datasets have become available for occupant monitoring algorithm development, including real and synthetic datasets. However, real data acquisition is expensive and labeling is complex, while virtual data may not accurately reflect actual human physiology. To address these issues and obtain high-fidelity data for training intelligent driving monitoring systems, we have constructed a hybrid dataset that combines real driving image data with corresponding virtual data generated from 3D driving scenarios. We have also taken into account individual anthropometric measures and driving postures. Our approach not only greatly enriches the dataset by using virtual data to augment the sample size, but it also saves the need for extensive annotation efforts. Besides, we can enhance the authenticity of the virtual data by applying ergonomics techniques based on RAMSIS, which is crucial in dataset construction. This paper presents the process and content of generating a hybrid dataset for the monitoring of driver’s high risk NDRTs monitoring, serving as a potential alternative to existing datasets and addressing their limitations.
Meta TagsDetails
DOI
https://doi.org/10.4271/2024-01-2640
Pages
7
Citation
Wu, X., Gou, J., and Shao, J., "A Method of Generating a Composite Dataset for Monitoring of Non-Driving Related Tasks," SAE Technical Paper 2024-01-2640, 2024, https://doi.org/10.4271/2024-01-2640.
Additional Details
Publisher
Published
Apr 09
Product Code
2024-01-2640
Content Type
Technical Paper
Language
English