Keywords
Support vector machine (SVM)
Dlib algorithm (facial feature)
Driving safety
Submitted : 2025-07-08
Accepted : 2025-07-23
Published : 2025-08-07
Abstract
Abnormal driving behavior includes driving distraction, fatigue, road anger, phone use, and an exceptionally happy mood. Detecting abnormal driving behavior in advance can avoid traffic accidents and reduce the risk of traffic conflicts. Traditional methods of detecting abnormal driving behavior include using wearable devices to monitor blood pressure, pulse, heart rate, blood oxygen, and other vital signs, and using eye trackers to monitor eye activity (such as eye closure, blinking frequency, etc.) to estimate whether the driver is excited, anxious, or distracted. Traditional monitoring methods can detect abnormal driving behavior to a certain extent, but they will affect the driver’s normal driving state, thereby introducing additional driving risks. This research uses the combined method of support vector machine and dlib algorithm to extract 68 facial feature points from the human face, and uses an SVM model as a strong classifier to classify different abnormal driving statuses. The combined method reaches high accuracy in detecting road anger and fatigue status and can be used in an intelligent vehicle cabin to improve the driving safety level.
References
Qu W, Ge Y, Jiang C, et al., 2014, The Dula Dangerous Driving Index in China: An Investigation of Reliability and Validity. Accident Analysis Prevention, 64: 62–68.
Underwood G, Chapman P, Wright S, et al., 1999, Anger While Driving. Transportation Research Part F Traffic Psychology & Behaviour, 2(1): 55–68.
Gao H, Yuce A, Thiran J, 2014, Detecting Emotional Stress from Facial Expressions for Driving Safety, IEEE International Conference on Image Processing (ICIP), Paris, France, 5961–5965.
Wan P, Wu C, Lin Y, et al., 2019, Driving Anger States Detection Based on Incremental Association Markov Blanket and Least Square Support Vector Machine. Discrete Dynamics in Nature and Society, 7: 1–17.
Huang Y, Yang J, Liu S, et al., 2019, Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition. Future Internet, 11: 105–117.
Zhang L, et al., 2021, EEG-Based Fatigue Detection During Simulated Driving: A Spectral Entropy Analysis. Transportation Research Part F, 78: 156–167.
European Transport Safety Council, 2022, Regulating Fatigue in Professional Drivers: A Policy Review, ETSC, Brussels.
World Health Organization, 2023, Global Status Report on Road Safety 2023, WHO Press, Geneva.
Ministry of Transport, 2023, Annual Report on China’s Motor Vehicle Ownership, People’s Communications Press, Beijing.
Li D, Zhang X, Liu X, et al., 2023, Driver Fatigue Detection Based on Comprehensive Facial Features and Gated Recurrent Unit. J Real-Time Image Proc, 20(19).
Wang C, Dai Y, Zhou W, et al., 2020, A Vision-Based Video Crash Detection Framework for Mixed Traffic Flow Environment Considering Low-Visibility Condition. Journal of Advanced Transportation, 9194028.
Chen X, Wang Y, 2023, Evaluation of Commercial Fatigue Monitoring Devices: A Meta-Analysis. IEEE Transactions on Intelligent Transportation Systems, 24(5): 1–12.
International Transport Forum, 2024, Impact Report: 2021–23, ITF, Paris, viewed May 15, 2025.
Kumari J, Rajesh R, Kumar A, 2016, Fusion of Features for the Effective Facial Expression Recognition. International Conference on Communication and Signal Processing, April 6–8, 2016, India.
Guo X, Li S, Yu J, et al., 2019, PFLD: A Practical Facial Landmark Detector. Computer Vision and Pattern Recognition. arXiv:1902.10859.
Hjorland B, 2009, The Foundation of the Concept of Relevance. Journal of the American Society for Information Science and Technology. 61(2): 217–237.