A New System for Driver Drowsiness and Distraction Detection
محل انتشار: بیستمین کنفرانس مهندسی برق ایران
سال انتشار: 1391
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,959
فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE20_279
تاریخ نمایه سازی: 14 مرداد 1391
چکیده مقاله:
Drowsiness especially in long distance journeys is a key factor in traffic accidents. In this paper a new module for automatic driver drowsiness detection based on visual informationand Artificial Intelligence is presented. The aim of this system is to locate, track and analyze both the driver’s face and eyes tocompute a drowsiness index to prevent accidents. Both face and eye detection is performed by Haar-like features and AdaBoost classifiers. In order to achieve better accuracy in face tracking,we propose a new method which is combination of detection and object tracking. Proposed face tracking method, also hascapability to self correction. After eye region is found, Local Binary Pattern (LBP) is employed to extract eye characteristics.Using these features, an SVM classifier was trained to perform eye state analysis. To evaluate the effectiveness of proposed method, a drowsy person was pictured, while his EEG signalswere taken. In this video we were able to track face by an accuracy of 100% and detecting eye blink by accuracy of 98.4%.Also we can calculate face orientation and tilt using eye position which is valuable knowledge about driver concentration. Finally,we can make a decision about drowsiness and distraction of the driver. Experimental results show high accuracy in each sectionwhich makes this system reliable for driver drowsiness detection
کلیدواژه ها:
نویسندگان
Mehrdad Sabet
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
Khosro Sadeghniiat-Haghighi
Tehran University of Medical Sciences, Center For Research on Occupational Medicine
Maryam Sabbaghian
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :