Open Access System for Information Sharing

Login Library

 

Article
Cited 41 time in webofscience Cited 50 time in scopus
Metadata Downloads

Real-time head pose estimation using multi-task deep neural network SCIE SCOPUS

Title
Real-time head pose estimation using multi-task deep neural network
Authors
Ahn, ByungtaeChoi, Dong-GeolPark, JaesikKweon, In So
Date Issued
2018-05
Publisher
Elsevier BV
Abstract
Driver inattention is one of the main causes of traffic accidents. To avoid such accidents, advanced driver assistance system that passively monitors the driver’s activities is needed. In this paper, we present a novel method to estimate a head pose from a monocular camera. The proposed algorithm is based on multi-task learning deep neural network that uses a small grayscale image. The network jointly detects multi-view faces and estimates head pose even under poor environment conditions such as illumination change, vibration, large pose change, and occlusion. We also propose a multi-task learning method that does not bias on a specific task with different datasets. Moreover, in order to fertilize training dataset, we establish and release the RCVFace dataset that has accurate head poses. The proposed framework outperforms state-of-the-art approaches quantitatively and qualitatively with an average head pose mean error of less than 4° in real-time. The algorithm applies to driver monitoring system that is crucial for driver safety.
URI
https://oasis.postech.ac.kr/handle/2014.oak/100556
DOI
10.1016/j.robot.2018.01.005
ISSN
0921-8890
Article Type
Article
Citation
Robotics and Autonomous Systems, vol. 103, page. 1 - 12, 2018-05
Files in This Item:
There are no files associated with this item.

qr_code

  • mendeley

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

Views & Downloads

Browse