Please use this identifier to cite or link to this item:
Title: Image-based driver drowsiness detection
Authors: Dornaika, F.
Khattar, F.
Reta, J.
Arganda-Carreras, I.
Hernandez, M. 
Ruichek, Y.
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Drowsiness detection
Hand-crafted features
Deep features
Supervised classification
Issue Date: 2019
Publisher: Springer 
Journal: Lecture Notes in Computer Science 
Conference: 3rd International Workshop on Face and Facial Expression Recognition from Real World Videos (FFER 2018). 2nd International Conference on Pattern Recognition (DLPR 2018) 
Abstract: How to extract effective features of fatigue in images and videos is important for many applications. This paper introduces a face image descriptor that can be used for discriminating driver fatigue in static frames. In this method, first, each facial image in the sequence is represented by a pyramid whose levels are divided into non-overlapping blocks of the same size, and hybrid image descriptor are employed to extract features in all blocks. Then the obtained descriptor is filtered out using feature selection. Finally, non-linear Support Vector Machines is applied to predict the drowsiness state of the subject in the image. The proposed method was tested on the public dataset NTH Drowsy Driver Detection (NTHUDDD). This dataset includes a wide range of human subjects of different genders, poses, and illuminations in real-life fatigue conditions. Experimental results show the effectiveness of the proposed method. These results show that the proposed hand-crafted feature compare favorably with several approaches based on the use of deep Convolutional Neural Nets.
ISBN: 978-3-030-12176-1
ISSN: 0302-9743
DOI: 10.1007/978-3-030-12177-8_6
Source: Video Analytics. Face and Facial Expression Recognition. FFER 2018, DLPR 2018. Lecture Notes in Computer Science, v. 11264 LNCS, p. 61-71
Appears in Collections:Capítulo de libro
Show full item record


checked on Sep 25, 2022

Page view(s)

checked on Jun 11, 2022

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.