Driver distraction analysis using face pose cues

作者：

Highlights：

• Face pose information is used for driver distraction monitoring.

• A new database is created for driver distraction monitoring with varying conditions.

• An automated (clustered) two layer approach is used for pose estimation.

• Clustered two layer approach accuracy matches convolutional network approach.

摘要

•Face pose information is used for driver distraction monitoring.•A new database is created for driver distraction monitoring with varying conditions.•An automated (clustered) two layer approach is used for pose estimation.•Clustered two layer approach accuracy matches convolutional network approach.

论文关键词：Discriminant analysis,Driver distraction,Manifolds,Multiple subspaces,Pose classification

论文评审过程：Received 20 August 2019, Revised 27 March 2021, Accepted 10 April 2021, Available online 20 April 2021, Version of Record 30 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115036