Non-intrusive Driver Drowsiness Detection based on Face and Eye Tracking
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 7
Abstract
The rate of annual road accidents attributed to drowsy driving are significantly high. Due to this, researchers have proposed several methods aimed at detecting drivers’ drowsiness. These methods include subjective, physiological, behavioral, vehicle-based, and hybrid methods. However, recent reports on road safety are still indicating drowsy driving as a major cause of road accidents. This is plausible because the current driver drowsiness detection (DDD) solutions are either intrusive or expensive, thus hindering their ubiquitous nature. This research serves to bridge this gap by providing a test-bed for achieving a non-intrusive and low-cost DDD solution. A behavioral DDD solution is proposed based on tracking the face and eye state of the driver. The aim is to make this research an inception to DDD pervasiveness. To achieve this, National Tsing Hua University (NTHU) Computer Vision Lab’s driver drowsiness detection video dataset was utilized. Several video and image processing operations were performed on the videos so as to detect the drivers’ eye state. From the eye states, three important drowsiness features were extracted: percentage of eyelid closure (PERCLOS), blink frequency (BF), and Maximum Closure Duration (MCD) of the eyes. These features were then fed as inputs into several machine learning models for drowsiness classification. Models from the K-nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, and Artificial Neural Networks (ANN) machine learning algorithms were experimented. These models were evaluated by calculating their accuracy, sensitivity, specificity, miss rate, and false alarm rate values. Although these five metrics were evaluated, the focus was more on getting optimal accuracies and miss rates. The result shows that the best models were a KNN model when k = 31 and an ANN model that used an Adadelta optimizer with 3 hidden layer network of 3, 27, and 9 neurons respective. The KNN model obtained an accuracy of 72.25% with a miss rate of 16.67%, while the ANN model obtained 71.61% and 14.44% accuracy and miss rate respectively.
Authors and Affiliations
Ameen Aliu Bamidele, Kamilia Kamardin, Nur Syazarin Natasha Abd Aziz, Suriani Mohd Sam, Irfanuddin Shafi Ahmed, Azizul Azizan, Nurul Aini Bani, Hazilah Mad Kaidi
Keywords
Related Articles
- EP ID EP611492
- DOI 10.14569/IJACSA.2019.0100775
- Views 135
- Downloads 0
Survey of Contrast Enhancement Techniques based on Histogram Equalization
This Contrast enhancement is frequently referred to as one of the most important issues in image processing. Histogram equalization (HE) is one of the common methods used for improving contrast in digital images. Histogr...
Quality Ranking Algorithms for Knowledge Objects in Knowledge Management Systems
The emergence of web-based Knowledge Management Systems (KMS) has raised several concerns about the quality of Knowledge Objects (KO), which are the building blocks of knowledge expertise. Web-based KMSs offer large know...
Soft Error Tolerance in Memory Applications
This paper proposes a new method to detect and correct multi bit errors in memory applications using a combination of a clustering approach, Bit-Per-Byte error detection technique, and Majority Logic Decodable (MLD) code...
Automatic Facial Expression Recognition Based on Hybrid Approach
The topic of automatic recognition of facial expressions deduce a lot of researchers in the late last century and has increased a great interest in the past few years. Several techniques have emerged in order to improve...
WordNet based Implicit Aspect Sentiment Analysis for Crime Identification from Twitter
Crime analysis has become an interesting field that deals with serious public safety issues recognized around the world. Today, investigating Twitter Sentiment Analysis (SA) is a continuing concern within this field. Asp...