A sleepy driver is arguably much more dangerous on the road than the one who is speeding as he is a victim of microsleeps. Automotive researchers and manufacturers are trying to curb this problem with several technological solutions that will avert such a crisis. This article focuses on the detection of such micro sleep and drowsiness using neural networkbased methodologies. Our previous work in this field involved using machine learning with multi-layer perceptron to detect the same. In this paper, accuracy was increased by utilizing facial landmarks which are detected by the camera and that is passed to a Convolutional Neural Network (CNN) to classify drowsiness. The achievement with this work is the capability to provide a lightweight alternative to heavier classification models with more than 88% for the category without glasses, more than 85% for the category night without glasses. On average, more than 83% of accuracy was achieved in all categories. Moreover, as for model size, complexity and storage, there is a marked reduction in the new proposed model in comparison to the benchmark model where the maximum size is 75 KB. The proposed CNN based model can be used to build a real-time driver drowsiness detection system for embedded systems and Android devices with high accuracy and ease of use.

No abstract

Qatar expects more than a million visitors during the 2022 World Cup, which will pose significant challenges. The high number of people will likely cause a rise in road traffic congestion, vehicle crashes, injuries and deaths. To tackle this problem, Naturalistic Driver Behavior can be utilised which will collect and analyze data to estimate the current Qatar traffic system, including traffic data infrastructure, safety planning, and engineering practices and standards. In this paper, an IoTbased solution to facilitate such a study in Qatar is proposed. Different data points from a driver are collected and recorded in an unobtrusive manner, such as trip data, GPS coordinates, compass heading, minimum, average, and maximum speed and his driving behavior, including driver's drowsiness level. Analysis of these data points will help in prediction of crashes and road infrastructure improvements to reduce such events. It will also be used for drivers' risk assessment and to detect extreme road user behaviors. A framework that will help to visualize and manage this data is also proposed, along with a Deep Learning-based application that detects drowsy driving behavior that netted an 82% accuracy.

No abstract

No abstract