Titre : | Driver’s Drowsiness and fatigue detection system |
Auteurs : | Hamed LAOUZ, Auteur ; Soheyb Ayad, Directeur de thèse |
Type de document : | Monographie imprimée |
Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2020 |
Format : | 1 vol. (69 p.) / ill. / 29 cm |
Langues: | Anglais |
Mots-clés: | Driver’s drowsiness and fatigue,Driver behavioral measures,eye blink,physiological signals measures,embedded system. |
Résumé : | Traffic accidents always cause great material and human losses. One of the main causes of these accidents is the human factor, which usually results from fatigue or drowsiness. To address this problem, several methods have been proposed to predict the driver's condition. Some solutions are based on measuring the driver’s behavior such as: head movement, blink time, mouth expression note ... etc., while other solutions rely on physiological measurements to obtain information about the driver’s internal condition.This work aims to find a solution to treat this problem by creating a system that can detect driver drowsiness/fatigue in real time using a built-in camera in the car that captures the driver's gestures and movement, so that the system then analyzes the eye's condition to see if the eye is open or not, and the system has also strengthened By monitoring the condition of the mouth, to check whether the driver is yawning, which can help predict sleepiness early. |
Sommaire : |
General introduction ............................................................................................................ 1
Chapter 1: Generalities on machine learning 1.1 Introduction ................................................................................................................ 2 1.2 Machine Learning ...................................................................................................... 3 1.2.1 Definition ............................................................................................................ 3 1.2.2 Types of machine Learning ................................................................................ 3 1.2.2.1 Supervised learning: Learning with a labeled training set ............................. 4 1.2.2.2 Unsupervised learning: Discover patterns in unlabeled data ......................... 4 1.2.2.3 Semi supervised learning ............................................................................... 5 1.2.2.4 Reinforcement learning: learn to act based on feedback/reward ................... 6 1.2.3 Machine learning process ................................................................................... 6 1.2.4 Machine learning models .................................................................................... 7 1.2.4.1 Support vector machine ................................................................................. 7 1.2.4.2 Genetic algorithms ......................................................................................... 8 1.2.4.3 Artificial neural network (ANN) ................................................................... 8 1.2.5 Limitations of machine learning ......................................................................... 8 1.3 Deep learning ............................................................................................................. 9 1.3.1 Definitions ........................................................................................................... 9 1.3.2 Deep learning models ....................................................................................... 10 1.3.2.1 Convolution neural network (CNN) ............................................................ 10 1.3.2.2 Recurrent Neural networks (RNNs) ............................................................. 11 1.3.2.3 Deep Belief networks ................................................................................... 12 1.4 Mobile (On-device) machine learning ..................................................................... 13 1.4.1 Definition of an Edge Device ........................................................................... 13 1.4.2 On device learning definition ............................................................................ 13 1.4.3 On device machine learning improvement approaches .................................... 14 1.5 Why use machine learning on mobile devices: ........................................................ 15 1.6 Conclusion ................................................................................................................ 16 Chapter 2: Related works 2.1 Introduction .............................................................................................................. 17 2.2 Industry ..................................................................................................................... 18 2.2.1 Warden .............................................................................................................. 18 2.2.2 Vigo ................................................................................................................... 18 2.2.3 Stop sleep device ............................................................................................... 18 2.2.4 Leading cars landmarks .................................................................................... 18 Nissan ......................................................................................................................... 19 Mercedes .................................................................................................................... 19 Volvo ......................................................................................................................... 19 2.3 Scientific research works ......................................................................................... 19 2.3.1 Vehicle-Based Measures ................................................................................... 20 2.3.2 Subjective Measures ......................................................................................... 20 2.3.3 Driver’s behavior measures .............................................................................. 20 2.3.4 Driver Physiological Measures ......................................................................... 24 2.3.5 Hybrid measurement ......................................................................................... 27 2.4 Best implementation ................................................................................................. 28 2.5 Conclusion ................................................................................................................ 31 Chapter3: System Design 3.1 Introduction .............................................................................................................. 32 3.2 System architecture .................................................................................................. 32 3.3 System components .................................................................................................. 33 3.3.1 Driver ................................................................................................................ 33 3.3.2 Image capturing module ................................................................................... 33 3.3.3 Drivers’ state prediction module ....................................................................... 33 3.3.3.1 Driver’s state prediction module architecture .............................................. 34 3.3.3.2 Driver’s state prediction module phases ...................................................... 35 3.3.4 Display module ................................................................................................. 43 3.4 Discussion and argumentation ................................................................................. 43 3.5 Conclusion ................................................................................................................ 45 Chapter 4: Implementation and results 4.1 Introduction .............................................................................................................. 46 4.2 System overview ...................................................................................................... 46 4.2.1 Hardware ........................................................................................................... 46 4.2.1.1 Raspberry pi ................................................................................................. 47 4.2.1.2 Pi Camera module ........................................................................................ 47 4.2.1.3 Raspberry pi LCD Touchscreen ................................................................... 47 4.2.2 System characteristics ....................................................................................... 48 4.2.2 Software tools ................................................................................................... 48 4.2.2.1 Python .......................................................................................................... 48 4.2.2.2 TensorFlow .................................................................................................. 49 4.2.2.3 Keras ............................................................................................................ 49 4.2.2.4 OpenCV ....................................................................................................... 49 4.3 Results ...................................................................................................................... 49 4.3.1 Face detection ................................................................................................... 49 4.3.2 Eye state ............................................................................................................ 50 4.3.3 Mouth state ........................................................................................................ 53 4.4 System Interfaces ..................................................................................................... 55 4.4.1 Home page ........................................................................................................ 55 4.4.2 Eye state page ................................................................................................... 56 4.4.3 Mouth state page ............................................................................................... 56 4.4.4 Settings page ..................................................................................................... 57 4.5 Conclusion ................................................................................................................ 57 General Conclusion ............................................................................................................. 58 |
Type de document : | Mémoire master |
Disponibilité (1)
Cote | Support | Localisation | Statut |
---|---|---|---|
MINF/552 | Mémoire master | bibliothèque sciences exactes | Consultable |