Facial Expression Recognition in Intelligent Cockpits via Multi-Scale Feature Enhancement and State-Space Models

Automated facial expression recognition (FER) is essential for understanding human emotions and has applications in various fields like human-computer interaction, emotion analysis, and intelligent surveillance. With the development of intelligent vehicles and Advanced Driver Assistance Systems (ADAS), modern vehicles increasingly depend on perception systems integrating environmental awareness and driver state monitoring. Research has primarily concentrated on enhancing environmental perception through technologies like LiDAR and deep learning-based semantic labeling. However, despite its significance in ensuring driving safety and user experience, driver state monitoring, and specifically FER, remains relatively underexplored.