A Novel Approach of Driver Facial Expression Recognition Based on Improved Swin Transformer
作者单位：School of Mechatronic EngineeringChina University of Mining and Technology
会议名称：《第43届中国控制会议》
会议日期：1000年
学科分类：082304[工学-载运工具运用工程] 08[工学] 080203[工学-机械设计及理论] 080204[工学-车辆工程] 0802[工学-机械工程] 0823[工学-交通运输工程]
关 键 词：Driver facial expression recognition Swin Transformer Structural re-parameterization Attention mechanism
摘 要：Driver facial expression recognition(FER) is a fundamental yet challenging task for the perception system of intelligent *** is difficult for the current recognition model to achieve high accuracy and fast *** overcome the above issue,we propose a novel driver facial expression recognition method based on an improved Swin ***,shallow features of facial images are extracted through CNNs to reduce the patch of image sequences and lower the computational complexity of self-attention ***,the residual coordinate attention mechanism is designed to focus on crucial facial features and suppress environmental ***,the structural re-parameterization method is employed to accelerate the model while maintaining recognition *** are conducted on three widely used expression datasets,and the results demonstrate that our approach is competitive to several state-of-the-art methods in FER *** experimental results evidence the practicality of the RCST,and the overall accuracy reaches 95.04% on the HDER dataset.