Driver Gaze Zone Estimation via Head Pose Fusion Assisted Supervision and Eye Region Weighted Encoding

Driver gaze zone estimation is an important task in Advanced Driver Assistance Systems (ADAS), which suffers difficulties including head pose, capture direction, glass occlusion, and real-time requirement, etc. Most previous methods combine face modalities and head pose using concat process, which m...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on consumer electronics 2021-11, Vol.67 (4), p.275-284
Main Authors: Yang, Yirong, Liu, Chunsheng, Chang, Faliang, Lu, Yansha, Liu, Hui
Format: Article
Language:English
Subjects:
Advanced driver assistance systems
Cameras
driver monitoring
dual-channel feature fusion
Encoding
Eye movements
Faces
Feature extraction
Gaze tracking
Gaze zone estimation
Head movement
head pose estimation
Occlusion
Pose estimation
Real time
spatial attention mechanism
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Driver gaze zone estimation is an important task in Advanced Driver Assistance Systems (ADAS), which suffers difficulties including head pose, capture direction, glass occlusion, and real-time requirement, etc. Most previous methods combine face modalities and head pose using concat process, which may result in over-fitting due to the unbalanced dimension. Focusing on gaze zone estimation problems, we propose the Head Pose Fusion Assisted supervision & Eye Region Weighted Encoding ( HP-ERW ) structure, which fuses head pose attribute and face modalities together through spatial attention and Kronecker product mechanisms. Firstly, we introduce a pre-processing module dealing with head pose and face information, with the purpose of extracting input vectors and improving the fusion speed of the HP-ERW structure. Secondly, an Eye Region Weighted Encoding Network (ERW-Net) based on spatial attention is proposed to strengthen the networks perception ability for encoding features. Finally, we propose a dual-channel Head Pose Fusion Network ( HP-Net ) based on the Kronecker product mechanism, with the purpose of fusing head pose and improving the estimation accuracy. Experiments show that the HP-ERW outperforms compared existing methods on several public datasets. The designed ADAS using the proposed method achieves 23.5 fps real-time application with small memory requirement of 4,884 KB.
ISSN:0098-3063
1558-4127
DOI:10.1109/TCE.2021.3127006