Abstract

Drowsiness is one of the underlying causes of driving accidents leading to serious injuries and deaths annually. According to the experts has mentioned that almost 30% of all traffic accidents have been caused by drowsiness. In avoiding these traffic accidents, a proper system is required to prevent the driver from falling asleep. This study proposes a real-time image processing-based system for recognizing the drowsiness face expression of the vehicle driver. The method of this study, detecting the exact position facial landmarks and both left and right eyes using dlib and eye aspect ratio algorithm. This system, after detecting drowsiness eye, give audible alert the vehicle driver to stay awake throughout the driving journey.

References

[1] Fletcher, L., Petersson, L., Zelinsky, A.: Driver assistance systems based on vision in and out of vehicles. In: IEEE Proceedings of Intelligent Vehicles Symposium, pp. 322–327 (2003)

[2] WHO (2009). Global Status Report on Road Safety Geneva, Switzerland. https://afro.who.int/sites/default/files/201706/vid_global_status_report_en.pdf [PubMed]

[3] SKL Lal and A. Craig, "A critical review of the psychophysiology of driver fatigue", Biological psychology, vol. 55, no. 3, pp. 173-194, 2021.

[4] AF Abate, M Nappi, D Piccio and G. Sabatino, "2D and 3D face recognition: a survey", Pattern recognition letters 2007, vol. 28, pp. 1885-906.

[5] M Kim, D Lee and KY. Kim, "System Architecture for Real-Time Face Detection on Analog Video Camera", International Journal of Distributed Sensor Networks 2015, pp. 11

[6] G. D. Brito Moncayo y and W. L. Lépesz Romero, "Sistema de control del estado de somnolencia en conductores de vehículos", Universidad Técnica de Ambato Ambato, 2016.

[7] K. Saldaña Altamirano y and R. Rodríguez Urquiaga, "Detección de la somnolencia usando maquinas de soporte vectorial a partir de" in Universidad Nacional De Trujillo, Trujillo, 2014.

[8] Understanding the “eye aspect ratio” (EAR) https://www.pyimagesearch.com/2017/04/24/eye-blink-detection-opencv-python-dlib/, 2021

[9] A. Picot, S. Charbonnier, A. Caplier and N.-S. Vu, "Using retina modelling to characterize blinking: Comparison between EOG and video analysis", Mach. Vis. Appl., vol. 23, no. 6, pp. 1195-1208, Nov. 2012.

[10] Y. Zhang and C. Hua, "Driver fatigue recognition based on facial expression analysis using local binary patterns", Optik, vol. 126, no. 23, pp. 4501-4505, Dec. 2015.

[11] Xue Liu, Xiaoyang Tan, Songcan Chen, " Eye Closeness Detection Using Appearance Based Methods," Intelligent Information Processing, volume 385 of IFIP Advances in Information, Communication Technology, pp. 398-408, 2012.