Drowsy Driver Detection Through Facial Movement Analysis

The advance of computing technology has provided the means for building intelligent vehicle systems. Drowsy driver detection system is one of the potential applications of intelligent vehicle systems. Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes. Automatic classifiers for 30 facial actions from the Facial Action Coding system were developed using machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a number of other facial movements. In addition, head motion was collected through automatic eye tracking and an accelerometer. These measures were passed to learningbased classifiers such as Adaboost and multinomial ridge regression. The system was able to predict sleep and crash episodes during a driving computer game with 96% accuracy within subjects and above 90% accuracy across subjects. This is the highest prediction rate reported to date for detecting real drowsiness. Moreover, the analysis revealed new information about human behavior during drowsy driving.

2008

Several approaches were proposed for the detection and prediction of drowsiness. The approaches can be categorized as estimating the fitness of duty, modeling the sleep-wake rhythms, measuring the vehicle based performance and online operator monitoring. Computer vision based online operator monitoring approach has become prominent due to its predictive ability of detecting drowsiness. Previous studies with this approach detect driver drowsiness primarily by making preassumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes. Automatic classifiers for 30 facial actions from the Facial Action Coding system were developed using machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a number of other facial movements. In addition, head motion was collected through automatic eye tracking and an accelerometer. These measures were passed to learning-based classifiers such as Adaboost and multinomial ridge regression. The system was able to predict sleep and crash episodes during a driving computer game with 96% accuracy within subjects and above 90% accuracy across subjects. This is the highest prediction rate reported to date for detecting real drowsiness. Moreover, the analysis revealed new information about human behavior during drowsy driving.

Asian Research Journal of Current Science., 2024

The advancement in the integration of computer vision and machine learning for solving practical problems of man has motivated various researchers to develop solutions in the domain of drowsy driving using different technological advancements. This paper aims at developing a Driver Drowsiness Detection System to enhance road safety by leveraging facial expression analysis for real-time detection of drowsiness in drivers. It monitors facial cues such as eyelid closure, head nodding, and yawning to detect drowsy driving. The key features of this system include nonintrusiveness, adaptability to varying road conditions, and seamless integration with existing vehicle systems. Through the synergistic application of machine learning algorithms and advanced facial recognition techniques, the system offers robust and timely alerting mechanisms to drivers, for effective prevention of road accidents thereby saving lives. The proposed system was implemented Original Research Article

2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), 2017

This paper presents a literature review of driver drowsiness detection based on behavioral measures using machine learning techniques. Faces contain information that can be used to interpret levels of drowsiness. There are many facial features that can be extracted from the face to infer the level of drowsiness. These include eye blinks, head movements and yawning. However, the development of a drowsiness detection system that yields reliable and accurate results is a challenging task as it requires accurate and robust algorithms. A wide range of techniques has been examined to detect driver drowsiness in the past. The recent rise of deep learning requires that these algorithms be revisited to evaluate their accuracy in detection of drowsiness. As a result, this paper reviews machine learning techniques which include support vector machines, convolutional neural networks and hidden Markov models in the context of drowsiness detection. Furthermore, a meta-analysis is conducted on 25 papers that use machine learning techniques for drowsiness detection. The analysis reveals that support vector machine technique is the most commonly used technique to detect drowsiness, but convolutional neural networks performed better than the other two techniques. Finally, this paper lists publicly available datasets that can be used as benchmarks for drowsiness detection.

2019

The drowsiness of the drivers can lead to road accidents. With the growth of computer vision and image processing technology it is now feasible to investigate this problem. This study aims to maintain driver’s consciousness and detect drowsiness using a 300W dataset with the application of API Based Histogram of Oriented Gradients and Linear Support Vector Machine method. This enable face detection and classification, Random Forest Regression with 2 Node Splits for each tree for facial landmark, and Euclidean Distance points extraction for the eyes and mouth to detect drowsiness based on closing of the eyes and yawning. Our results show the model attained: i) a 91.67% accuracy rate performance in 0° degree camera angle, and ii) 93.33% accuracy in detecting drowsiness activity in both +45° to -45° camera angle, both in with 85% accuracy result in detecting both eye and mouth simultaneously.