Drowsiness Detection using Eye-Blink Frequency and Yawn Count for Driver Alert
Maganti Manasa1, Vikas B2, K. Subhadra3
1M. Manasa, UG Student, Department of CSE, GITAM University, Visakhapatnam (Andhra Pradesh), India.
2Vikas B, Assistant Professor, GITAM University, Visakhapatnam (Andhra Pradesh), India.
3Dr. K. Subhadra, Assistant Professor, GITAM University, Visakhapatnam (Andhra Pradesh), India.
Manuscript received on 24 November 2019 | Revised Manuscript received on 12 December 2019 | Manuscript Published on 30 December 2019 | PP: 314-317 | Volume-9 Issue-2S3 December 2019 | Retrieval Number: B10541292S319/2019©BEIESP | DOI: 10.35940/ijitee.B1054.1292S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Several reasons can be sighted for the cause of these road accidents. Few of them include lack of sleep, drunk driving, violation of traffic rules, etc. Amongst them, the state of drowsiness and drunk driving alone contributes to 36% of accidents. Though a number of national schemes and traffic rules have been implemented to avoid these road accidents, it could only bring down the accident rate by 10%. As car accidents are one of the major issues of concern, this paper will be discussing mainly on Drunk driving or drowsiness. In these recent years, various methods have been proposed to implement drowsiness detection based on Hough transforms. Here, in this paper, we have determined a technique to detect drowsiness among car drivers and alert them whenever they tend to sleep. The algorithm is based on eye-blink and yawn frequency. It deals with an eye blink yawn frequency algorithm that uses eye coordinates to keep track of person and determine the open or closed state of the eye and generate an alarm if the driver is drowsy. The yawn count is determined by checking the frequency of yawn count with a minimum threshold value.
Keywords: Drowsiness Detection, Eye-blink Frequency, Eye-Aspect-ratio, Euclidean Distance, PERCLOS.
Scope of the Article: Frequency Selective Surface