Titre :

Deep learning-based hard spatial attention for driver in-vehicle action monitoring

Auteur(s) :

Jegham, Imen [Auteur]
Laboratory of Advanced Technology and Intelligent Systems [LATIS]
Alouani, Lihsen [Auteur]
Queen's University [Belfast] [QUB]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Ben Khalifa, Anouar [Auteur]
Laboratory of Advanced Technology and Intelligent Systems [LATIS]
Mahjoub, Mohamed Ali [Auteur]
Laboratory of Advanced Technology and Intelligent Systems [LATIS]

Titre de la revue :

Expert systems with applications

Pagination :

119629

Éditeur :

Elsevier

Date de publication :

2023-06

ISSN :

0957-4174

Mot(s)-clé(s) en anglais :

Driver
Action
Recognition
In-vehicle action monitoring
Hard attention
Deep learning
Hybrid network

Discipline(s) HAL :

Physique [physics]
Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

Distracted driving is one of the main causes of deaths and injuries in the world. Monitoring driver behaviors through Driver Action Recognition (DAR) contributes significantly to building safer transportation systems. ...
Lire la suite >Distracted driving is one of the main causes of deaths and injuries in the world. Monitoring driver behaviors through Driver Action Recognition (DAR) contributes significantly to building safer transportation systems. However, in naturalistic driving settings, this task is complex and challenging because of numerous difficulties, such as high illumination variation and cluttered and dynamic background. In this paper, we introduce a novel hard attention network that highlights the most pertinent driving-scene information while filtering out irrelevant data. Specifically, only local discriminative salient regions are exploited through a hard attention mechanism. The experimental results indicate that our approach significantly enhances DAR performance. We evaluated our network on three diverse state-of-the-art datasets recorded in real-world conditions: it achieves up to 95.83% in terms of safe driving recognition and up to 99.07% in terms of distraction detection. The proposed approach outperforms the soft attention-based DAR not only in detection and recognition performance but also in computation complexity by 38.71% less runtime. For reproducible research, the code is available at https://github.com/JEGHAMI/HSALire moins >

Langue :

Anglais

Vulgarisation :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL