Vision-based method for detecting driver drowsiness and distraction in driver monitoring system

Abstract

Most driver-monitoring systems have attempted to detect either driver drowsiness or distraction, although both factors should be considered for accident prevention. Therefore, we propose a new drivermonitoring method considering both factors. We make the following contributions. First, if the driver is looking ahead, drowsiness detection is performed; otherwise, distraction detection is performed. Thus, the computational cost and eye-detection error can be reduced. Second, we propose a new eye-detection algorithm that combines adaptive boosting, adaptive template matching, and blob detection with eye validation, thereby reducing the eye-detection error and processing time significantly, which is hardly achievable using a single method. Third, to enhance eyedetection accuracy, eye validation is applied after initial eye detection, using a support vector machine based on appearance features obtained by principal component analysis (PCA) and linear discriminant analysis (LDA). Fourth, we propose a novel eye state-detection algorithm that combines appearance features obtained using PCA and LDA, with statistical features such as the sparseness and kurtosis of the histogram from the horizontal edge image of the eye. Experimental results showed that the detection accuracies of the eye region and eye states were 99 and 97%, respectively. Both driver drowsiness and distraction were detected with a success rate of 98%. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

Eye Status Based on Eyelid Detection: A Driver Assistance System

“…We implemented and examined the method proposed in [6] and we noticed that the values of sparseness and kurtosis mainly depend on lighting conditions, and it also varies depending on the subjects. The method is a reasonable solution for determining open or closed eyes, but it is still difficult to measure the degree of eye closure.…”

“…The authors report an average median error magnitude of 0.15 and an average 90 th percentile error magnitude 0.42 of eye closure, which is unreliable for differentiating eyes into states. The authors of [6] propose eye state-detection that uses statistical features such as sparseness and kurtosis of the histogram from the horizontal edge image of the eye.…”

Detecting Driver Drowsiness Using Eye State

“…This means, even when the driver's eyes are not closed for fatigue, car accidents may still happen because of distraction [8]. Generally, drowsiness detection is applied when the driver's head rotation angle lies between -15 degree and 15 degrees; otherwise, distraction detection is applied.…”

Measuring the engagement level of TV viewers

“…For instance, people in the automotive industry have been working on detecting driver inattention to prevent car accidents and improve overall car safety [10]. In online educational settings, educators want to monitor the interest levels of students to appropriately change their lessons and speed-up the learning process [11].…”