Drowsy driver detection using image processing

Download

index.pdf

Date

2014

Author

Girit, Arda

Metadata

Show full item record

Item Usage Stats

232
views

280
downloads

This thesis is focused on drowsy driver detection and the objective of this thesis is to recognize driver’s state with high performance. Drowsy driving is one of the main reasons of traffic accidents in which many people die or get injured. Drowsy driver detection methods are divided into two main groups: methods focusing on driver’s performance and methods focusing on driver’s state. Furthermore, methods focusing on driver’s state are divided into two groups: methods using physiological signals and methods using computer vision. In this thesis, driver data are video segments captured by a camera and the method proposed belongs to the group that uses computer vision to detect driver’s state. There are two main states of a driver, those are alert and drowsy states. Video segments captured are analyzed by making use of image processing techniques. Eye regions are detected and those eye regions are input to right and left eye region classifiers, which are implemented using artificial neural networks. The neural networks classify the right and left eye as open, semi-closed or closed eye. The eye states along the video segment are fused and the driver’s state is predicted as alert or drowsy. The proposed method is tested on 30-second- long video segments. The accuracy of the driver’s state recognition method is 99.1% and the accuracy of our eye state recognition method is 94%. Those results are comparable with the results in literature.

Subject Keywords

Image processing., Artificial intelligence., Neural networks (Computer science)., Motor vehicle driving., Drowsy driving., Traffic accidents.

URI

http://etd.lib.metu.edu.tr/upload/12617015/index.pdf
https://hdl.handle.net/11511/23446

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Development of the professional driver behavior questionnaire Yılmaz, Şerife; Öz, Bahar; Özkan, Türker; Department of Psychology (2018) The aim of the present study was to develop a comprehensive scale measuring professional drivers' driver behaviors. For this reason, a semi-structured interview form was prepared and applied to different professional driver groups in order to collect behavioral examples displayed in traffic context (Study 1). These examples were grouped based on Reason's taxonomy of human error and Professional Driver, Driver Behavior Scale (PDBQ) was developed. PDBQ along with some other behavior scales such as ODBQ and DB...
The Relationship between the health belief model constructs and driver behaviors: mediating role of driving skills Özbay, İrem; Öz, Bahar; Özkan, Türker; Department of Psychology (2017) The aim of the present study is to examine the relationship between driver behaviors (emphasized violations), the Health Belief Model (HBM) constructs, and driver skills. Although the HBM is a widely used model in health settings, there are very few studies investigating the model at traffic settings. In the present study a total of 505 drivers (217 female, 288 male) whose mean age was 27 participated. The Driver Behavior Questionnaire was used to measure driver behaviors; that is, violations within the sco...
Steering dynamics of tracked vehicles Özdemir, Mehmet Nuri; Ünlüsoy, Yavuz Samim; Department of Mechanical Engineering (2016) The main objective of this thesis study is the development of a general transient steering model for tracked vehicles which is simple, accurate, and simulation results are in agreement with test results to a satisfactory level. For modeling Matlab/Simulink platform is utilized. The model represents a general tracked vehicle having rear or front sprockets, with variable centre of gravity and wheel positions, and number of wheels. The vehicle hull is modelled as a rigid body having 3 degree of freedom; transl...
Motor imagery EEG signal classification using deep learning for brain computer interfaces Rezaaei Tabar, Yousef; Halıcı, Uğur; Kalaycıoğlu, Canan; Department of Biomedical Engineering (2017) In this thesis we proposed a novel method for classification of Motor Imagery (MI) EEG signals based on deep learning. Convolutional Neural Networks (CNN) and Stacked Autoencoders (SAE) networks were investigated for MI EEG classification. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and also a new deep network combining CNN and SAE is proposed in this thesis. In the proposed network, the features that are extracted by CNN are classified thr...
Identification of inertia tensor of vehicles Kutluay, Emir; Ünlüsoy, Yavuz Samim; Department of Mechanical Engineering (2007) The aim of this thesis is to develop a methodology for obtaining mass properties of a vehicle using specific test rig. Investigated mass properties are the mass, location of center of gravity and the inertia tensor. Accurate measurement of mass properties of vehicles is crucial for vehicle dynamics research. The test rig consists of a frame on which the vehicle is fixed and which is suspended from the ceiling of the laboratory using steel cables. Mass and location of center of gravity are measured using the...

Citation Formats

A. Girit, “Drowsy driver detection using image processing,” M.S. - Master of Science, Middle East Technical University, 2014.