FHWA-HRT-24-137.pdf (7.01 MB)
Publication Information
Publication Type:
Summary Report
Publication Number:
FHWA-HRT-24-137
Abstract:
This report highlights the research conducted to develop a robust platform that can automatically estimate driver state, address detection challenges in naturalistic driving study (NDS) videos, serve as a repository for models, and enhance current and future NDS data. Deep InSight is a comprehensive artificial intelligence platform for data management, modeling, and enhanced annotations. The platform incorporates recurrent neural network models trained to automatically detect and estimate driving behaviors and deal with challenges, such as when a driver looks to the side or down.
Recommended citation: Federal Highway Administration, Deep InSight: A Driver-State Estimation Platform for Processing Naturalistic Driving Data (Washington, DC: 2024) https://doi.org/10.21949/1521583
Publishing Date:
December 2024
Posting Date:
Digital Object Identifier:
https://doi.org/10.21949/1521583
Author(s):
Publishing Office:
Resource Management Team
FHWA Program(s):
Exploratory Advanced Research
Human Factors
AMRP Program(s):
Research Infrastructure, Technology Transfer, and Partnerships
FHWA Activities:
Human Factors
Subject Area:
Research
Safety and Human Factors