ABSTRACT
With the rapid economic development and the remote dispatch of materials during the epidemic, transportation is gradually "burnout", which increases the probability of traffic accidents. The main cause of traffic accidents is fatigue driving behavior, so it is extremely necessary to design a fatigue driving detection and early warning system. We can combine face recognition technology with driver's facial features, and embed the 68 feature point detection model of the face generated based on the residual neural network training into this system via transfer learning. This model can be used to extract the real-time state of eyes, mouth and head and transfer it to the Opencv library. By using the EAR-Perclos, MAR-Perclos, Pnp-Hpe, Pitch-Perclos algorithms, we can calculate the fatigue value of the feature point data collected by the Opencv library, extract EAR, MAR, and Pitch changes within 10s to set the fatigue threshold. The real-time data is then compared with the threshold value. If it exceeds the threshold value range, fatigue tendency or fatigue driving activity can be determined. The experimental verification of the system is carried out through the video of fatigue state and non-fatigue state, which confirms the algorithm accuracy in fatigue driving detection.
- Wang Di. Research and application of fatigue detection algorithm based on human eye state. Electronic Science and Technology, 2020.Google Scholar
- K. He,X. Zhang,S. Ren and J. Sun,“Deep Residual LEARning for Image Recognition”,2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR. 2016.90Google ScholarCross Ref
- Wang Xiu, Zhou Fengxiao, Liu Baoluo, Huo Wenyi. Driver fatigue driving detection system based on Dlib library. Internet of Things technology, 2021, 11 (12): 26 – 29.Google Scholar
- He Yanqin, Wu You, Guo Qingfen, Zeng Guinan. Face recognition technology development status and future trend analysis. Wireless Internet Technology, 2021, 18 (13): 80-82.Google Scholar
- Xin Song, Song Ming Da, Wang Zeming, Zhao Gang. Fatigue driving detection method for specific drivers. Safety and Environment Report: 1-8 [2022-05-14].Google Scholar
- Huang Zhichao, Zhao Hongmei, Chen Yixun, Tang Yaosen. Driver fatigue dangerous driving detection system based on facial7recognition. Electromechanical engineering technology, 2021, 50 (12): 143-146.Google Scholar
- Tu Chao, Zhao Bo. Research on driver fatigue detection method based on eye features. Computer and digital engineering, 2021, 49 ( 11 ) : 2200-2203 + 2236.Google Scholar
- Research on eye state fatigue analysis based on N-Range. China University of Science and Technology, 2020.Google Scholar
- The application of Dlib in face recognition technology. Electronic production, 2020, (21): 39-41 + 7.Google Scholar
- Yufa Liu Driver Fatigue Detection Algorithm Based on Improved Yolov4. World Scientific ResEARch Journal, 2022, 8 (1): 58-63.Google Scholar
- Zhang Yimin Driver Fatigue Detection Based On Facial Feature Analysis. International Journal of Pattern Recognition and Artificial Intelligence, 2021, 35 (15)Google Scholar
- Zhao Lin.Research on fatigue driving monitoring method based on face recognition. Changchun University of Technology, 2015.Google Scholar
- Ma Zhaobin. Research on real-time fatigue driving detection technology integrating eye features and head posture. Shandong University, 2016.Google Scholar
Index Terms
- Fatigue driving detection system based on Perclos algorithm optimization
Recommendations
A Real-time Fatigue Driving Detection Method Based on Facial Multi-Feature Fusion
ACAI '21: Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial IntelligenceFatigue driving refers to the imbalance of physiological and psychological functions after driving continuously for a long time, which leads to the objective decline of driving skills. Fatigue driving is one of the main factors leading to traffic ...
Application of Face Recognition Based on CNN in Fatigue Driving Detection
AIAM 2019: Proceedings of the 2019 International Conference on Artificial Intelligence and Advanced ManufacturingFatigue driving detection technology based on the external characteristics of the driver has made some progress in many aspects, but the method of driver facial feature extraction needs to be further improved, and the driver's eye location takes a long ...
Research on Fatigue Driving Detection System Based on Face Recognition
ICAICE '23: Proceedings of the 4th International Conference on Artificial Intelligence and Computer EngineeringThis graduation project aims to deal with the fatigue problem caused by the fast-paced life, and specially focuses on the face recognition algorithm based on ASM model and the facial characteristics determination standard of fatigue driving. First, ...
Comments