An integrated framework for multi-state driver monitoring using heterogeneous loss and attention-based feature decoupling

• Main Authors: Hu, Zhongxu, Zhang, Yiran, Xing, Yang, Li, Qinghua, Lv, Chen
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Mechanical engineering; Driver State; Feature Decoupling
• Online Access: https://hdl.handle.net/10356/167025
• Institution: Nanyang Technological University

Multi-state driver monitoring is a key technique in building human-centric intelligent driving systems. This paper presents an integrated visual-based multi-state driver monitoring framework that incorporates head rotation, gaze, blinking, and yawning. To solve the challenge of head pose and gaze es...