Safe Driving : Driver Action Recognition using SURF Keypoints - Université Polytechnique des Hauts-de-France Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Safe Driving : Driver Action Recognition using SURF Keypoints

Résumé

Driver distraction is one of the main factors of fatal road traffic injuries. According to the national Highway Traffic Safety Administration (NHTSA), in USA, 3450 are killed by distracted driving, in 2016. In order to save lives, Advanced Driver Assistance Systems (ADAS), more specifically those systems for distracted driver action recognition are introduced. Our method aim to extract, from each frame, a region of interest (KOI) that contains body parts performing in-vehicle actions. These regions hold the most important key points after eliminating those common ones that are similar to the key points of the safe driving actions. The proposed approach was evaluated on the distracted driver detection dataset. Experimental results illustrate the performance of the proposed approach.
Fichier non déposé

Dates et versions

hal-03579546 , version 1 (18-02-2022)

Identifiants

Citer

Imen Jegham, Anouar Ben Khalifa, Ihsen Alouani, Mohamed Ali Mahjoub. Safe Driving : Driver Action Recognition using SURF Keypoints. 2018 30th International Conference on Microelectronics (ICM), Dec 2018, Sousse, Tunisia. pp.60-63, ⟨10.1109/ICM.2018.8704009⟩. ⟨hal-03579546⟩
24 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More