A Lightweight Driver Drowsiness Detection System Using 3DCNN With LSTM

作     者：Sara A.Alameen Areej M.Alhothali 

作者机构：Department of Computer ScienceKing Abdulaziz UniversityJeddah21589Kingdom of Saudi Arabia 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第44卷第1期

页      面：895-912页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors received no specific funding for this study 

主　　题：3D-CNN deep learning driver drowsiness detection LSTM spatiotemporal features 

摘      要：Today,fatalities,physical injuries,and significant economic losses occur due to car *** the leading causes of car accidents is drowsiness behind the wheel,which can affect any *** and sleepiness often have associated indicators that researchers can use to identify and promptly warn drowsy drivers to avoid potential *** paper proposes a spatiotemporal model for monitoring drowsiness visual indicators from *** model depends on integrating a 3D convolutional neural network(3D-CNN)and long short-term memory(LSTM).The 3DCNN-LSTM can analyze long sequences by applying the 3D-CNN to extract spatiotemporal features within adjacent *** learned features are then used as the input of the LSTM component for modeling high-level temporal *** addition,we investigate how the training of the proposed model can be affected by changing the position of the batch normalization(BN)layers in the 3D-CNN *** BN layer is examined in two different placement settings:before the non-linear activation function and after the non-linear activation *** study was conducted on two publicly available drowsy drivers datasets named 3MDAD and YawDD.3MDAD is mainly composed of two synchronized datasets recorded from the frontal and side views of the *** show that the position of the BN layers increases the convergence speed and reduces overfitting on one dataset but not the *** a result,the model achieves a test detection accuracy of 96%,93%,and 90%on YawDD,Side-3MDAD,and Front-3MDAD,respectively.