Browse Publications Technical Papers 2020-01-5159
2020-12-30

A Driving Fatigue Identification Method Based on HMM 2020-01-5159

Driving fatigue has typical temporal characteristic, and the acquisition of related features and its state evaluation have an important impact on the development of vehicle detection systems. This paper proposes a driving fatigue recognition method based on hidden Markov process to achieve reliable detection of fatigue state. Among them, in view of the difference in fatigue state level, based on the fuzzy C-means clustering algorithm (FCM), the optimal fatigue state classification number is determined by using mixed F statistics; the Deep Alignment Network (DAN) method is used to reliably detect the key facial features reflecting the fatigue state. Finally, combined with the strong timing characteristics of driving fatigue, a HMM model for driving fatigue detection is constructed. The results show that the driving fatigue detection model proposed in this paper can realize the effective recognition of the fatigue state, and the state recognition rate is over 82%.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Members save up to 18% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.
X