Drowsiness and lack of attention are some of the most fatal and underrated accident causes while driving. In this thesis a non intrusive classifier based on features from drivers' facial movements has been developed, focusing on detection strategies that could be deployed on low-complexity devices, like smartphones. Different classification architectures will be proposed and studied in order to understand which implementation performed the best in terms of detection accuracy.

Driver attention analysis and drowsiness detection using mobile devices

Ceccato, Simone
2020/2021

Abstract

Drowsiness and lack of attention are some of the most fatal and underrated accident causes while driving. In this thesis a non intrusive classifier based on features from drivers' facial movements has been developed, focusing on detection strategies that could be deployed on low-complexity devices, like smartphones. Different classification architectures will be proposed and studied in order to understand which implementation performed the best in terms of detection accuracy.
2020-01-07
drowsiness detection, driver, computer vision, machine learning, neural networks
File in questo prodotto:
File Dimensione Formato  
SimoneCeccatoMasterThesisDEI.pdf

Open Access dal 21/12/2022

Dimensione 8.62 MB
Formato Adobe PDF
8.62 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/28823