Real Time Driver Somnolence Alert System Using Web Application
R. Lakshmi Devi1, S. Vaishali2, S. Vishalini3
1R. Lakshmi Devi, Assistant Professor, Department of Electronics and Communication Engineering, Sri Sairam Institute of Technology Affiliated to Anna University, Chennai (Tamil Nadu), India.
2S. Vaishali, Department of Electronics and Communication Engineering, Sri Sairam Institute of Technology Affiliated to Anna University, Chennai (Tamil Nadu), India.
3S. Vishalini, Department of Electronics and Communication Engineering, Sri Sairam Institute of Technology Affiliated to Anna University, Chennai (Tamil Nadu), India.
Manuscript received on 23 April 2019 | Revised Manuscript received on 02 May 2019 | Manuscript Published on 08 May 2019 | PP: 191-195 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11360275S19/19©BEIESP
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: The number of accidents that has occurred in India due to driver fatigue has been alarmingly high due to continuous driving, throughout day and night. According to the statistical data of 2017, approximately 80,000 deaths are occurring each year and 1.47 lakhs of passengers with an accuracy of about 80% in a non- real time implementation and intrusive method based detection were found to be drowsy drivers. The aim of our project is to detect the driver’s drowsiness with the help of Computer Vision based technology and to alert the driver through a stimulator and a voice playback system. This project describes an efficient method for drowsiness detection by three well defined phases. These three phases are facial features detection, the eye tracking and yawning detection. Once the face is detected, the system is made illumination invariant by segmenting the skin part alone and considering only the chromatic components to reject most of the non face image backgrounds based on skin colour. The tracking of eyes and yawning detection are done by correlation coefficient template matching and it is processed in the MATLAB using Support Vector Machine Algorithm and the Object Detection library to segregate face and non face regions and disintegration the left eye, right eye and mouth images from the face region to analyze the three different facial parameters separately. If the reference template matches with the current frame in real time then the speed of the engine is reduced automatically and the driver is alerted using the playback system and the vibrator under his seat. In addition to this, the driver’s sleep status will be updated on the travel agent’s personal login. The entire process such as detecting, processing, alerting takes place at the faster rate and the driver is alerted within a second. This method gives an accuracy of about 99% so that the driver fatigue is to be detected accurately. It can be translated into a mobile app to provide additional information to the passengers such as vehicle information, live vehicle tracking, driver details and the time of arrival to reach the destination.
Keywords: Computer Vision, Support Vector Machine Algorithm, Vibrator, Automatic Speed Control, Playback System, Linear Regression, Ada Boosting Algorithm, Facial Adaptive Coding.
Scope of the Article: Internet and Web Applications