An Effective Deep Network for Head Pose Estimation without Keypoints

Chien Thai, Viet Tran, Minh Bui, Huong Ninh, Hai Tran

2022

Abstract

Human head pose estimation is an essential problem in facial analysis in recent years that has a lot of computer vision applications such as gaze estimation, virtual reality, driver assistance. Because of the importance of the head pose estimation problem, it is necessary to design a compact model to resolve this task in order to reduce the computational cost when deploying on facial analysis-based applications such as large camera surveillance systems, AI cameras while maintaining accuracy. In this work, we propose a lightweight model that effectively addresses the head pose estimation problem. Our approach has two main steps. 1) We first train many teacher models on the synthesis dataset - 300W-LPA to get the head pose pseudo labels. 2) We design an architecture with the ResNet18 backbone and train our proposed model with the ensemble of these pseudo labels via the knowledge distillation process. To evaluate the effectiveness of our model, we use AFLW-2000 and BIWI - two real-world head pose datasets. Experimental results show that our proposed model significantly improves the accuracy in comparison with the state-of-the-art head pose estimation methods. Furthermore, our model has the real-time speed of ∼300 FPS when inferring on Tesla V100.

Paper Citation

in Harvard Style

Thai C., Tran V., Bui M., Ninh H. and Tran H. (2022). An Effective Deep Network for Head Pose Estimation without Keypoints. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 90-98. DOI: 10.5220/0010870900003122

in Bibtex Style

@conference{icpram22,
author={Chien Thai and Viet Tran and Minh Bui and Huong Ninh and Hai Tran},
title={An Effective Deep Network for Head Pose Estimation without Keypoints},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={90-98},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010870900003122},
isbn={978-989-758-549-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - An Effective Deep Network for Head Pose Estimation without Keypoints
SN - 978-989-758-549-4
AU - Thai C.
AU - Tran V.
AU - Bui M.
AU - Ninh H.
AU - Tran H.
PY - 2022
SP - 90
EP - 98
DO - 10.5220/0010870900003122