Word Files
Reference for Downloading Educational Files
  2. Computer Engineering
  3. Designing the driver's face monitoring system to detect fatigue and lack of concentration

Designing the driver's face monitoring system to detect fatigue and lack of concentration

Number of pages: 112 File Format: word File Code: 31081
Year: 2008 University Degree: Master's degree Category: Computer Engineering
Tags/Keywords: artificial intelligence - Driver face monitoring system - Face monitoring system - Face recognition system - Fatigue detection system - Image processing algorithm - Imaging - Robotics - sleepiness
  • Part of the Content
  • Contents & Resources

  • Summary of Designing the driver's face monitoring system to detect fatigue and lack of concentration

    Dissertation for Master's Degree

    Computer Engineering-Artificial Intelligence and Robotics

    Abstract

    Every year, many traffic accidents occur all over the world due to driver drowsiness and lack of concentration, which cause a lot of loss of life and money. One of the ways to detect fatigue and lack of concentration is to use driver face monitoring systems. By receiving images from the camera and processing them, the driver's face monitoring systems extract signs of drowsiness and lack of concentration from the eyes, head and face. In this thesis, a driver's face monitoring system has been designed, which estimates the driver's loss of alertness by extracting signs of fatigue and lack of focus from the eyes and face. In this system, four features including percentage of eyes closed (PERCLOS), blink rate, reduction of the distance between the eyelids and head rotation rate are extracted. The first three characteristics are related to the signs of fatigue and lack of focus in the eye area, and the last characteristic is related to the signs of decreased alertness in the face and head area. The features of the eye area are extracted based on changes in the horizontal projection of the eye area and the features of the face area are extracted based on the examination of the face template. Then these features are processed by a fuzzy expert system to estimate the driver's fatigue and lack of concentration. Imaging of the proposed system has been done in the visible spectrum with a gray level camera. The results of the tests on the videos prepared in the real and laboratory environment show that the proposed method has a very good accuracy in extracting features and detecting the driver's loss of consciousness. In terms of algorithm execution speed, the speed of the proposed system is about 5 frames per second, which can be considered a real-time system.

    Keywords:

    monitoring the driver's face, detecting fatigue, detecting sleepiness, detecting lack of concentration, accident prevention.

    Foreword

    The increase in the number of cars in the world and as a result the increase in the statistics of damages and casualties caused by accidents, made the researchers to Seek to discover the main causes of traffic accidents. One of the most important causes is the driver's fatigue and inattention, which is the main cause of about 20% of accidents. Considering the effective role of driver's fatigue and lack of concentration in the occurrence of accidents, solutions were introduced to deal with this factor. One of the main and new solutions for detecting driver fatigue and lack of concentration and warning when necessary is the driver's face monitoring systems. The proposal to produce driver's face monitoring systems was first proposed at the end of the 20th century, but most of the research in this field is after 2000.

    So far, the design and production of such systems in Iran has not been seriously investigated. The system presented in this thesis is the first driver's face monitoring system in Iran, which is able to estimate the driver's fatigue and lack of attention by processing the driver's face images. Although more research is needed to produce a driver's face monitoring system with the aim of being used in commercial vehicles, this thesis can be a very good start to start research in this field. Intelligent transportation systems [1] or ITS for short is the application of computer and information and communication technology in human and goods transportation networks. The advanced driver assistant system [2] is one of the parts of the intelligent transportation system. These systems are used to improve the performance of the car and increase the safety of the driver and its passengers, and in critical situations, they warn the driver or take the appropriate decision to control and drive the car instead of the driver.

    The driver's face monitoring system is a real-time system[3] that monitors the driver's physical condition and to some extent his mental condition based on the processing of the driver's facial image. Usually, the driver's condition can be recognized from the closed eyelids, the way they blink, the eyes are staring at a certain point, the direction of the eyes, yawning and head movement. This system issues a warning [4] when the driver is sleepy, tired and not paying attention to the road.

    1-2- Necessity of driver face monitoring systems

    One of the most important factors in accidents, especially on intercity roads [5], is the driver's fatigue, sleepiness and lack of concentration.Fatigue and sleepiness reduce the understanding and decision-making power of the driver to control the car. Research shows that usually, naturally, after an hour of driving, the driver gets tired. But in the early hours of the afternoon, after lunch, and also in the middle of the night, the driver feels drowsy in less than an hour. Of course, in addition to natural causes, the consumption of alcohol, drugs and drugs that lead to a decrease in alertness are also effective in the driver's sleepiness. Most of the accidents, the main cause of which is fatigue or lack of concentration, occur on intercity roads and for heavy vehicles. Most of these accidents happen around 2-6 or 15-16 [2].

    In different countries, different statistics have been presented about accidents that occur due to driver fatigue and lack of concentration, but in general, it can be said that the cause of about 20% of accidents and 30% of accidents leading to death is driver drowsiness and lack of concentration. This number has been reported up to 50% in single car accidents[6] or heavy vehicle accidents.

    Iran has a critical situation in terms of traffic safety, not only among the countries of the world, but also among the developing countries. According to forensic statistics in 2016, more than 23,000 people were killed and 245,000 were injured due to traffic accidents [11]. According to the announced statistics, the damage caused by accidents in Iran is estimated to be more than 65,000 billion rials (equivalent to 67 billion dollars), which is about 6.4% of the national gross product [7] [12]. Meanwhile, Australia, as a developed country, has declared the damage caused by accidents to be about 17 billion dollars and is equivalent to 2.3% of the gross national product [13]. Considering the many life and financial losses resulting from driver drowsiness and inattention, the design and development of drowsiness and inattention detection systems seems very necessary. One of the best practical methods for this purpose is monitoring the driver's face. Based on studies, it is predicted that the use of sleepiness and inattention detection systems can reduce between 10% and 20% of accidents [14]. 1-3- Basic challenges in driver face monitoring systems In a driver face monitoring system, there are two main problems: "how to measure fatigue" and "how to measure concentration". These problems are known as the main challenges of face monitoring systems. Despite the progress of science in the field of physiology and psychology, no precise definition of fatigue has been provided yet. Certainly, due to the lack of a precise definition of fatigue, no measurable criteria [8] can be provided for it [9]. However, there are correlations between sleepiness and body surface temperature, skin electrical resistance, eye activity and movement, breathing rate, heart rate, and brain activity. One of the first and most important signs of fatigue appears in the eyes. Based on the research, there is a direct relationship between the amount of fatigue and the percentage of closed eyelids in a certain period of time. The percentage of closed eyelids in a period of time is called PERCLOS [9]. For this reason, in almost all the driver's face monitoring systems, processing the eye area and checking the degree of closed eyelids are used as the first and most important criteria in measuring fatigue.

    Another fundamental problem is measuring the driver's attention to the road. The amount of attention of the driver can be estimated to some extent by the direction of the head and where the eyes are looking. But the problem is that if the direction of the head is towards the front and looking towards the road, the driver does not necessarily pay attention to the road. In other words, looking at the road does not mean paying attention to it [9].

    Apart from the main challenges of driver face monitoring systems, real-time implementation of the system on common hardware, reducing system error in face detection, reducing face tracking error, increasing the efficiency of feature extraction methods and increasing the accuracy of algorithms for detecting drowsiness and lack of concentration are other problems of these systems.

    1-4- Concepts of fatigue, Drowsiness and lack of attention

    In this section, the concepts of fatigue[10], drowsiness[11] and lack of attention[12] are examined from the perspective of physiology and psychology. Although the concepts of fatigue and sleepiness are different in terms of physiology and psychology, but in this report, similar to many articles presented in this field, fatigue and sleepiness are considered synonymous concepts.

  • Contents & References of Designing the driver's face monitoring system to detect fatigue and lack of concentration

    List:

    1- Introduction. 1-1-Definition of driver's face monitoring systems 1-1-2-Necessity of driver's face monitoring systems 2-1-3-Basic challenges in driver's face monitoring systems 3-1-4-Concepts of fatigue, sleepiness and lack of attention. 4

    1-4-1- Fatigue and sleepiness. 4

    1-4-2- lack of focus. 6

    1-5- Methods of detecting driver fatigue and lack of attention 6

    1-6- Outline of the thesis. 7

    2- Review of past works. 8

    2-1-General configuration of driver face monitoring systems 9

    2-1-1- Imaging. 9

    2-1-2- hardware and processor 10

    2-1-3- intelligent software. 11

    2-2- Face detection 13

    2-2-1- Methods based on color model. 13

    2-2-2- Methods based on pseudo-rabies characteristics. 14

    2-2-3- methods based on neural network. 14

    2-3- Revealing the eye. 15

    2-3-1- Methods based on lighting and imaging in the infrared spectrum. 15

    2-3-2- Methods based on two-level image. 18

    2-3-3- Projection-based methods. 19

    2-3-4- Learning-based methods. 20

    2-4- Revealing other parts of the face 21

    2-4-1- Revealing the mouth (lips) 21

    2-4-2- Revealing the nose. 21

    2-5- Tracking the face and its components. 22

    2-5-1- Motion estimation. 23

    2-5-2- Matching. 23

    2-6- extracting the features related to the loss of consciousness. 24

    2-6-1- Characteristics of the eye area. 24

    2-6-2- Characteristics of the mouth. 30

    2-6-3- Characteristics of the head. 30

    2-7- Detection of fatigue and lack of concentration. 31

    2-7-1- Threshold-based methods. 31

    2-7-2- Knowledge-based methods. 32

    2-7-3- methods based on statistics and probability. 33

    2-8- Driver face monitoring systems in commercial vehicles. 34

    3- Proposed system. 35

    3-1- General configuration of the proposed system. 35

    3-1-1- Lighting and imaging. 36

    3-1-2- hardware and processor 37

    3-1-3- intelligent software. 37

    3-2- Revealing the face 38

    3-2-1- Pseudo-rabies features. 39

    3-2-2- Selecting and determining the importance of features to form a strong classifier. 41

    3-2-3- Reinforced cascade decision tree 42

    3-3- Face tracking 44

    3-3-1- Search window. 45

    3-3-2- Matching criterion. 46

    3-4- extracting the features related to the loss of consciousness. 47

    3-4-1- Characteristics of the eye area. 47

    3-4-2- Characteristics of the face and head area. 55

    3-5- Diagnosing loss of consciousness. 58

    3-5-1- Fuzzy expert system. 58

    3-5-2- Production of final output. 64

    4- Results of tests and system evaluation. 69

    4-1- How to test the system. 69

    4-2- Evaluation criteria. 72

    4-3- Face detection 73

    4-4- Face tracking 75

    4-5- Extracting features of the eye area. 77

    4-6- Extracting the features of the head and face area 82

    4-7- Detecting loss of consciousness. 86

    4-8- Overall evaluation of the system and algorithms 93

    4-8-1- Checking the processing speed of the proposed system. 93

    4-8-2- Investigating the computational complexity of algorithms 94

    5- Conclusions and suggestions. 95

    6- References 99

     

    Source:

     

     ADDIN EN.REFLIST field-separator'>[1] Narelle L. Haworth, Thomas J. Triggs, Elizabeth M. Gray, "Driver Fatigue: Concepts, Measurement and Crash Countermeasures", Human Factors Group, Department of Psychology, Monash University, June, 1988.

    [2] Mohammadreza Ahadi, Ali Zairzadeh, "Parameters affecting driver fatigue and its role in accidents", First International Conference on Accidents Driving and Road, Tehran, Iran, page 358-364, December 1384.

    [3] Chin Teng Lin, Li Wei Ko, I Fang Chung, Teng Yi Huang, Yu Chieh Chen, Tzyy Ping Jung, Sheng Fu Liang, "Adaptive EEG-Based Alertness Estimation System by Using ICA-Based Fuzzy Neural Networks", IEEE Transactions on Circuits and Systems, vol. 53, no. 11, pp. 2469-2476, November,

    [4] G. Yang, Y. Lin, P. Bhattacharya, "A Driver Fatigue Recognition Model Using Fusion of Multiple Features", in IEEE International Conference on Systems, Man and Cybernetics (SMC), Hawaii, USA, pp. 1777-1784, 2005.

    [5] Christos Papadelis, Chrysoula Kourtidou-Papadeli, Panagiotis D. Bamidis, Ioanna Chouvarda, D. Koufogiannis, E. Bekiaris, Nikos Maglaveras, "Indicators of Sleepiness in an Ambulatory EEG Study of Night Driving", in 28th IEEE Annual International Conference of the Engineering in Medicine and Biology Society (EMBS), New York, USA, pp. 6201-6204, 2006.

    [6]       Qiang Ji, Xiaojie Yang, "Real-Time Eye, Gaze, and Face Pose Tracking for Driver Vigilance Monitoring", Elsevier Real-Time Imaging, vol. 8, pp. 357–377, 2002.

    [7] T. Brandt, R. Stemmer, B. Mertsching, A. Rakotonirainy, "Affordable Visual Driver Monitoring System for Fatigue and Monotony", in IEEE International Conference on Systems, Man and Cybernetics (SMC), Hague, Netherlands, pp. 6451- 6456, 2004.

    [8] Paul Stephen Rau, "Drowsy Driver Detection and Warning System for Commercial Vehicle Drivers: Field Operational Test Design, Data Analyzes and Progress", National Highway Traffic Safety Administration of USA (NHTSA), 2005.

    [9] T. Von Jan, T. Karnahl, K. Seifert, J. Hilgenstock, R. Zobel, "Don't Sleep and Drive – VW's Fatigue Detection Technology", Center for Automotive Safety Research, Adelaide University, Australia, 2005.

    [10] S. Boverie, D. Daurenjou, D. Esteve, H. Poulard, J Thomas, "Driver Vigilance Monitoring - New Developments", in 15th IFAC World Congress on Automatic Control, Barcelona, ??Spain, 2002.

    [11] caused by traffic accidents referred to the forensic medical centers of the country in 2016", Road Safety Commission, Ministry of Roads and Transport, 2017.

    [12] Mirfazel Nikzad, "Traffic accidents on Iranian roads - we predict but cannot prevent", the third regional traffic management conference, Tehran, Iran, 2015.

    [13] Luke B. Connelly, Richard Supangan, "The Economic Costs of Road Traffic Crashes: Australia, States and Territories", Elsevier Accident Analysis and Prevention, vol. 38, no. 36, pp. 1087-1093, November, 2006.

    [14] Megan Bayly, Brian Fildes, Michael Regan, Kristie Young, "Review of Crash Effectiveness of Intelligent Transport Systems", TRaffic Accident Causation in Europe (TRACE), 2007.

    [15] H. Cai, Y. Lin, "An Experiment to Non-Intrusively Collect Physiological Parameters Towards Driver State Detection", in SAE 2007 World Congress, Detroit, Michigan, USA, 2007.

    [16] Tsuyoshi Nakagawa, Taiji Kawachi, Satori Arimitsu, Masayuki Kanno, Ken Sasaki, Hiroshi Hosaka, "Drowsiness Detection Using Spectrum Analysis of Eye Movement and Effective Stimuli to Keep Driver Awake", DENSO Technical Review, vol. 12, no. 1, pp. 113-118, 2006.

    [17] Mohammad Hossein Segari, "A brief review on the methods of detecting driver fatigue and inattention to prevent accidents", 2nd Joint Congress of Fuzzy and Intelligent Systems, 9th Iran Intelligent Systems Conference, Tehran, Iran, November 1387.

    [18] Mohammad Hossein Segari, "Review of driver face monitoring methods to prevent accidents", seminar Master of Artificial Intelligence, Faculty of Computer Engineering, Iran University of Science and Technology, Tehran, 2016.

    [19] A.C. Boucouvalas, "IEC 825-1 Eye Safety Classification of Some Consumer Electronic Products", in IEE Colloquium on Optical Free Space Communication Links, London, UK, pp. 13/11-13/16, 1996.

    [20] Richard Grace, Vicky E. Byme, Damian M. Bierman, Jean-Michel Legrand, David Gricourt, Robert K. Davis, James J. Staszewski, Brian Carnahan, "A Drowsy Driver Detection System for Heavy Vehicles", in 17th AIAA/IEEE/SAE Digital Avionics Systems Conference (DASC), Washington, USA, pp. I36/31-I36/38, 1998.

    [21] Luis M. Bergasa, Jesus Nuevo, Miguel A.

Designing the driver's face monitoring system to detect fatigue and lack of concentration
How To Access The File
Related Contents:
Number of pages: 75 Category: Electronic Engineering

The master's thesis for obtaining a master's degree is an abstract of facial recognition in the fields of biometrics, machine vision, and pattern recognition, and has a wide range of applications, including issues related to security systems. Since various factors such as ambient lighting, noise, and image opacity are more or less effective in the performance of face recognition ...

Number of pages: 73 Category: Electronic Engineering

Abstract Face recognition is in the fields of biometrics, machine vision and pattern recognition and has a wide range of applications including issues related to security systems. Since various factors such as ambient lighting, noise, and image opacity are more or less effective in the performance of face recognition methods, therefore, investigating the methods of removing blur ...

Number of pages: 89 Category: Computer Engineering

Dissertation for Master's Degree in Computer Engineering - Artificial Intelligence Abstract Image segmentation is a basic process in many applications of image processing and machine vision, which can be considered as the first low-level processing step in digital image processing. Image segmentation has various applications such as medical image processing, face recognition, ...

Number of pages: 75 Category: Computer Engineering

Dissertation for Master's Degree in Computer Science Abstract Nowadays, in many fields, we need devices that can identify people's computers and recognize them based on their body characteristics. Face recognition system as a biometric system is basically a pattern recognition system that recognizes a person based on the vector of specific physiological characteristics or ...

Number of pages: 85 Category: Facilities - Mechanics

Master's Thesis in Applied Design, Abstract Face recognition has received much attention in recent years in the research fields related to biometrics, pattern recognition, and machine vision. Face recognition methods are also used in some commercial and security applications. These applications include people's security control, access control, identification of criminals, face ...

Number of pages: 85 Category: Electrical Engineering

Master's thesis in the field of medical engineering, improving the common spatial pattern filtering method to improve the efficiency of brain-computer interface systems. Therefore, this capability can help many sensory-motor patients and solve their problems in relation to their surroundings to a very high extent.

Number of pages: 86 Category: Electronic Engineering

Master's thesis in the field of medical engineering. Abstract: Improvement of common spatial pattern filtering method to improve the efficiency of computer-brain interface systems. Therefore, this capability can help many sensory-motor patients and solve their problems in relation to their surroundings to a very high extent.

Number of pages: 67 Category: Computer Engineering

Master's Thesis in Computer Engineering (M.Sc) Abstract: Today, automatic control is widely used in transportation systems. There are several reasons for using this method, the most important of which are cost reduction, the ability to make devices lighter, more safety for the passengers or to keep them away from danger. The last two cases are more visible in systems that have ...

Number of pages: 118 Category: Computer Engineering

Master's Thesis of Faculty of Technology and Engineering, Department of Computer Abstract: In this thesis, a new method is presented to detect the subtle emotional states of the face. Euler's video zoom method has been used to reveal subtle facial movements. Euler's video zoom method enhances the subtle movements of signals (color change or transition motion) by temporal and ...

Number of pages: 92 Category: Computer Engineering

Master's Thesis in Computer Engineering (Artificial Intelligence) Abstract In recent years, many methods have tried to investigate the level of mental fatigue with different criteria. These methods have used different scales for this task, including performance and electrophysiological based measurements. Among these tools, electroencephalogram (EEG) seems to work better and ...