Drowsy Driver Detection and Monitoring System Using Support Vector Machine

Haruna Bassi, Hakeem A. Sulaimon, Muhammad Aminu Ahmad

Abstract


The current methods for detecting a drowsy driver and taking percussive measure in reducing road accidents are subjective. Many researchers have adopted different methods to address how road accident could be reduced. Existing methods such as measuring brainwave activity using electroencephalography (EEG), electrodes wrapped on a drivers scalp will make the driver uncomfortable during driving, wires crossing all over the driver’s body. This paper looks at the use of principal component analysis, local binary pattern and support vector machine to classify the degree of change in the eye lid. These method places a safe and secure way of detecting drowsiness and reducing accidents at minimal cost. To measure these work we loaded a training set and a test set of different faces and feature (the eye)  on Mat lab 8.0 .During the evaluation phase we compared linear, quadratic and polynomial kernels of the support vector machine. The true positive, false negative, true negative and false positive values were placed on a confusion matrix to obtain the giving result. The polynomial support vector machine had the highest accuracy of 99.4%


Full Text:

PDF

References


Alioua N., Amine A., A. Rogozan, A. Bensrhair, and M. Rziza, (2016), “Driver head pose estimation using efficient descriptor fusion,†Eurasip J. Image Video Process

D’Orazio T., Leo, Guaragnella C., and Distante A., (2007), “A visual approach for driver inattention detection,†Pattern Recognit., vol. 40, no. 8, pp. 2341–2355.

Danisman T., Bilasco I. M, Djeraba C., and N. Ihaddadene,( 2010), “Drowsy driver detection system using eye blink patterns,†2010 Int. Conf. Mach. Web Intell. ICMWI 2010 - Proc., pp. 230–233,

Laura Sánchez López (2010) Local Binary Patterns applied to Face Detection and Recognition Directors: Francesc Tarrés Ruiz, Antonio Rama Calvo. Signal Theory & Communication Department.

Mandal B, Li L., Wang G. S., and Lin J., (2017), “Towards Detection of Bus Driver Fatigue Based on Robust Visual Analysis of Eye State,†IEEE Trans. Intell. Transp. Syst., vol. 18, no. 3, pp. 545–557.

Mbouna R. O., Kong S. G., and Chun M. G., (2013), “Visual analysis of eye state and head pose for driver alertness monitoring,†IEEE Trans. Intell. Transp. Syst., vol. 14, no. 3, pp. 1462–1469,

Sacco M. and Farrugia R., (2012), “Driver fatigue monitoring system using support vector machines,†5th Int. Symp. Commun. Control Signal Process.

Saradadevi M. (2008), “Driver Fatigue Detection Using Mouth and Yawning Analysis,†Int. J. Comput. Sci. Netw. Secuirity, vol. 8, no. 6, pp. 183–188,.

.Xie J. F, Xie M., and. Zhu W, (2012), “Driver fatigue detection based on head gesture and PERCLOS,†Int. Conf. Wavelet Act. Media Technol. Inf. Process. ICWAMTIP 2012, pp. 128–131, 2012.

Vega R., Sajed T., Mathewson K. W., Khare K., Pilarski P. M., Greiner R., (2017). Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals. Artif. Intell. Res. 6:37 10.5430/air.v6n1p37 [CrossRef] [Google Scholar]

Vikramaditya Jakkula (2009), Tutorial on Support Vector Machine (SUPPORT VECTOR MACHINE) School of EECS, Washington State University, Pullman 99164. www.intellifaces.com


Refbacks

  • There are currently no refbacks.