Fatigue driving behavior recognition based on attention mechanism and dual flow network

被引：0

作者：

Gong L.N. ^{[1
]}

机构：

[1] College of Electronic Information Engineering, Xi'an Siyuan University, Shaanxi, Xi'an

来源：

Advances in Transportation Studies | 2024年 / 1卷 / Speical issue期

关键词：

attention mechanism; characteristics of fatigue behavior; dual stream network; facenet network; fatigue driving;

D O I：

10.53136/979122181230512

中图分类号：

学科分类号：

摘要：

Aiming at the problems of low accuracy and poor consistency in fatigue driving behavior recognition, this paper proposes a fatigue driving behavior recognition method using attention mechanism and dual flow network. Firstly, this method processes facial images through a FaceNet network, where the channel attention module within the attention mechanism is used to accurately identify key regions for feature detection. Then, extract fatigue behavior characteristics based on the angles of eye closure and head posture changes. Finally, based on the characteristics of fatigue behavior, a fatigue recognition model combining attention mechanism and dual stream network was developed. The test results indicate that provided method successfully maintains the mean square error (MSE) below 3.5. In addition, it also achieved high Pearson correlation coefficient (PCC) and consistency correlation coefficient. © 2024, Aracne Editrice. All rights reserved.

引用

页码：125 / 138

页数：13

共 18 条

[1]

An F., Liu J.E., Bai L., Pedestrian Reidentification Algorithm Based on Deconvolution Network Feature Extraction-Multilayer Attention Mechanism Convolutional Neural Network, Journal of Sensors, 32, 19, pp. 1-12, (2021)

[2]

Beauty3DFaceNet: Deep Geometry and Texture Fusion for 3D Facial Attractiveness Prediction, Computers & Graphics, 98, 8, pp. 11-18, (2021)

[3]

Billal S., Boukebbab S., Boulahlib M.S., Hand position on steering wheel during fatigue and sleepiness case: Driving simulator, Journal of Advanced Transportation, 45, 6, pp. 68-84, (2021)

[4]

Chen J., Yang G., Ding X., Robust detection of dehazed image via dual-stream CNNs with adaptive feature fusion, Computer Vision and Image Understanding, 54, 8, (2022)

[5]

Chu Y.X., Zhang J., Yang L., Risk identification method of dangerous driving behavior based on sliding window feature fusion, Advances in Transportation Studies, 4, 53, (2022)

[6]

Huang A.C., Yuan C., Meng S.H., Design of Fatigue Driving Behavior Detection Based on Circle Hough Transform, Big Data, 11, 1, pp. 1-17, (2023)

[7]

Jin H., Bao Z., Chang X., Semantic segmentation of remote sensing images based on dilated convolution and spatial-channel attention mechanism, Journal of Applied Remote Sensing, 17, 1, pp. 1-17, (2023)

[8]

Lokku G., Reddy G.H., Prasad M.N.G., OPFaceNet: OPtimized Face Recognition Network for noise and occlusion affected face images using Hyperparameters tuned Convolutional Neural Network, Applied Soft Computing, 117, 65, pp. 11-16, (2022)

[9]

Ming S., Rong G.Z., Cheng W.J., Analysis of HAZMAT truck driver fatigue and distracted driving with warning-based data and association rules mining, Journal of Traffic and Transportation Engineering, 10, 1, pp. 132-142, (2023)

[10]

Peng Z., Rong J., Wu Y., Exploring the Different Patterns for Generation Process of Driving Fatigue Based on Individual Driving Behavior Parameters, Transportation Research Record, 2675, 8, pp. 408-421, (2021)

← 1 2 →