Multi-feature fatigue driving detection based on computer vision. (November 2020)

• Record Type: Journal Article
• Authors: Huang, Juan; Lin, Zihui
• Is Part Of: Journal of physics. Volume 1651(2020)
• Publication Date: 2020-11
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1651/1/012188
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Fatigue driving is one of the main causes of traffic accidents. This paper proposes a fatigue detection method based on computer vision. The first is the introduction of an optimized algorithm, based on AdaBoost, to detect the face area, and then the ERT algorithm is used to achieve precise localization of the facial landmarks. Finally, a variety of fatigue features of eyes and mouth state associated with driving fatigue are extracted, and after the fusion of all these features, the fatigue driving detection is performed. The experimental results show that multi-feature detection is more accurate than single feature detection.