Smart City Gnosys
Smart city article details
| Title | Drowsydet: A Mobile Application For Real-Time Driver Drowsiness Detection |
|---|---|
| ID_Doc | 21105 |
| Authors | Yu C.; Qin X.; Chen Y.; Wang J.; Fan C. |
| Year | 2019 |
| Published | Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019 |
| DOI | http://dx.doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00116 |
| Abstract | The number of accidents during driving is increasing day by day and drowsy driving has been implicated as a causal factor of road accidents. Research on driver drowsiness detection is important to improve road traffic safety. However, most of the conventional methods are intrusive since they often require expensive sensors. Moreover, their performances are rather limited since only single features and shallow classifiers are adopted. In this paper, we propose DrowsyDet, a real-time mobile application to detect driver drowsiness. DrowsyDet consists of the following steps. Firstly, the facial region and landmarks are extracted with a face detection model and landmark model. Secondly, three CNN (Convolutional Neural Networks) models are built to classify facial drowsiness state, eyes state, and mouth state respectively. Finally, the drivers' state (i.e. normal, yawn, and sleep) is obtained based on all the models' results. All the models are lightweight CNN models that can be deployed on a mobile phone. Compared with existing methods, DrowsyDet is non-intrusive since it only requires a mobile phone without the Internet. We also build a large driver drowsiness dataset to test our approach, which includes different genders, ages, head poses, and illuminations. Experimental results demonstrate that DrownsyDet can reach a significantly high average accuracy of 97.8%. © 2019 IEEE. |
| Author Keywords | Driver drowsiness; Driver drowsiness dataset; Lightweight cnn models; Mobile devices |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
21015  | 0.895 | Mridha K.; Shaw R.N.; Kumar D.; Ghosh A. | Driver Drowsiness Alert System Using Real-Time Detection | Studies in Computational Intelligence, 1002 (2022) |
| 914 | 0.892 | Malik R.; Vijarania M.; Malik M. | A Comprehensive Review Of Deep Learning And Iot In Driver Drowsiness Detection For Safer Roads | Proceedings of the 2024 3rd Edition of IEEE Delhi Section Flagship Conference, DELCON 2024 (2024) |
| 56493 | 0.887 | Almurabit M.A.; Abougreen A.N. | The Role Of Artificial Intelligence In Real-Time Driver Drowsiness Detection | EAI/Springer Innovations in Communication and Computing, Part F3967 (2025) |
| 36047 | 0.875 | Roy A.; Ghosh D. | Machine Learning-Based Driver Assistance System Ensuring Road Safety For Smart Cities | Internet of Things and Big Data Analytics for a Green Environment (2024) |
| 44351 | 0.874 | Misbhauddin M.; AlMutlaq A.; Almithn A.; Alshukr N.; Aleesa M. | Real-Time Driver Drowsiness Detection Using Wearable Technology | ACM International Conference Proceeding Series (2019) |
| 21016 | 0.859 | Abbas Q.; Alsheddy A. | Driver Fatigue Detection Systems Using Multi-Sensors, Smartphone, And Cloud-Based Computing Platforms: A Comparative Analysis | Sensors (Switzerland), 21, 1 (2021) |
| 57898 | 0.856 | Lago T.K.; Gonzalez E.R.; Campista M.E.M. | Towards A Real-Time System Based On Regression Model To Evaluate Driver'S Attention | 2021 IEEE International Smart Cities Conference, ISC2 2021 (2021) |