6D ROTATION REPRESENTATION FOR UNCONSTRAINED HEAD POSE ESTIMATION

被引:63
作者
Hempel, Thorsten [1 ]
Abdelrahman, Ahmed A. [1 ]
Al-Hamadi, Ayoub [1 ]
机构
[1] Otto Von Guericke Univ, Fac Elect Engn & Informat Technol, NeuroInformat Technol, Magdeburg, Germany
来源
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2022年
关键词
head pose estimation; orientation regression; rotation matrix; geodesic loss;
D O I
10.1109/ICIP46576.2022.9897219
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which exceeds the capabilities of previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the SO(3) manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20%. We open-source our training and testing code along with our trained models: https://github.com/thohemp/6DRepNet.
引用
收藏
页码:2496 / 2500
页数:5
相关论文
共 20 条
[1]   A Vector-based Representation to Enhance Head Pose Estimation [J].
Cao, Zhiwen ;
Chu, Zongcheng ;
Liu, Dongfang ;
Chen, Yingjie .
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, :1187-1196
[2]   RepVGG: Making VGG-style ConvNets Great Again [J].
Ding, Xiaohan ;
Zhang, Xiangyu ;
Ma, Ningning ;
Han, Jungong ;
Ding, Guiguang ;
Sun, Jian .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :13728-13737
[3]   Random Forests for Real Time 3D Face Analysis [J].
Fanelli, Gabriele ;
Dantone, Matthias ;
Gall, Juergen ;
Fossati, Andrea ;
Van Gool, Luc .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2013, 101 (03) :437-458
[4]  
He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/ICCV.2017.322, 10.1109/TPAMI.2018.2844175]
[5]   QuatNet: Quaternion-Based Head Pose Estimation With Multiregression Loss [J].
Hsu, Heng-Wei ;
Wu, Tung-Yu ;
Wan, Sheng ;
Wong, Wing Hung ;
Lee, Chen-Yi .
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (04) :1035-1046
[6]   Improving head pose estimation using two-stage ensembles with top-k regression [J].
Huang, Bin ;
Chen, Renwen ;
Xu, Wang ;
Zhou, Qinbang .
IMAGE AND VISION COMPUTING, 2020, 93
[7]  
Joo Hanbyul, 2015, PANOPTIC STUDIO MASS
[8]  
Murphy-Chutorian E, 2007, 2007 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE, VOLS 1 AND 2, P1049
[9]   Head Pose Estimation and Augmented Reality Tracking: An Integrated System and Evaluation for Monitoring Driver Awareness [J].
Murphy-Chutorian, Erik ;
Trivedi, Mohan Manubhai .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2010, 11 (02) :300-311
[10]   Fine-Grained Head Pose Estimation Without Keypoints [J].
Ruiz, Nataniel ;
Chong, Eunji ;
Rehg, James M. .
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, :2155-2164