Unseen head pose prediction using dense multivariate label distribution

Gao-li SANG; Hu CHEN; Ge HUANG; Qi-jun ZHAO

doi:10.1631/FITEE.1500235

Your Location：

Home >

Browse articles >

Unseen head pose prediction using dense multivariate label distribution

Regular Papers | Updated：2022-05-19

- Unseen head pose prediction using dense multivariate label distribution
- 基于稠密多变量标签的“连续”头部姿态估计方法
- Frontiers of Information Technology & Electronic Engineering Vol. 17, Issue 6, Pages: 516-526(2016)
- Affiliations：
  
  1State Key Laboratory of Fundamental Science on Synthetic Vision,College of Computer Science, Sichuan University, Chengdu 610064, China
  2College of Mathematics and Information Engineering, Jiaxing University, Jiaxing 314001, China
- Author bio：
  
  E-mail:g.sang@foxmail.com
  E-mail:huchen@scu.edu.cn
  E-mail:26434368@qq.com
  E-mail:qjzhao@scu.edu.cn
- Funds：
- DOI：10.1631/FITEE.1500235
  CLC： TP391.4
- Received：23 July 2015，
  
  Accepted：16 February 2015，
  
  Published：2016-06
- Accepted：
Scan QR Code
Gao-li SANG, Hu CHEN, Ge HUANG, et al. Unseen head pose prediction using dense multivariate label distribution[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(6): 516-526.
DOI：

Gao-li SANG, Hu CHEN, Ge HUANG, et al. Unseen head pose prediction using dense multivariate label distribution[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(6): 516-526. DOI： 10.1631/FITEE.1500235.

摘要

目的

精确的头部姿态估计对于人脸相关的应用，如人脸识别、视线估计、情感分析等具有重要意义。大多数现有的人脸姿态估计方法仅能对训练数据库包含姿态的情况进行估计。为实现对训练数据库不包含姿态的情况进行预测，有学者提出了基于回归的头部姿态估计方法。然而，这些基于回归的方法虽然可以预测连续的姿态，但是却很少有相关的系统性性能评估。

方法

针对训练数据库不包含姿态的估计问题，本文提出使用稠密多变量标签分布表示人脸姿态。通过给样本分配稠密化的多变量标签，可以实现对数据库不包含姿态的情况进行较为准确的估计。

结论

本文方法在Pointing’04数据库上的yaw和pitch方向分别取得了平均绝对误差4.01°和2.13°。此外，在CAL-PEAL，Multi-PIE等公开库上的实验表明，本文方法在训练数据库包含姿态上的预测性能也优于其他比较先进的方法。

Abstract

Accurate head poses are useful for many face-related tasks such as face recognition

gaze estimation

and emotion analysis. Most existing methods estimate head poses that are included in the training data (i.e.

previously seen head poses). To predict head poses that are not seen in the training data

some regression-based methods have been proposed. However

they focus on estimating continuous head pose angles

and thus do not systematically evaluate the performance on predicting unseen head poses. In this paper

we use a dense multivariate label distribution (MLD) to represent the pose angle of a face image. By incorporating both seen and unseen pose angles into MLD

the head pose predictor can estimate unseen head poses with an accuracy comparable to that of estimating seen head poses. On the Pointing’04 database

the mean absolute errors of results for yaw and pitch are 4.01° and 2.13°

respectively. In addition

experiments on the CAS-PEAL and CMU Multi-PIE databases show that the proposed dense MLD-based head pose estimation method can obtain the state-of-the-art performance when compared to some existing methods.

关键词

Keywords

references

J Aghajanian , , , SJD Prince . . Face pose estimation in uncontrolled environments . . 2009 . . Proc. British Machine Vision Conf. . . 1 - - 11 . . . .

AL Berger , , , VJD Pietra , , , SAD Pietra . . A maximum entropy approach to natural language processing . . Comput. Ling. , , 1996 . . 22 ( ( 1 ): ): 39 - - 71 . . . .

KW Bowyer , , , K Chang , , , P Flynn . . A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition . . Comput. Vis. Image Understand. , , 2006 . . 101 ( ( 1 ): ): 1 - - 15 . . DOI: 10.1016/j.cviu.2005.05.005 http://doi.org/10.1016/j.cviu.2005.05.005 . .

R Brunelli . . Estimation of pose and illuminant direction for face processing . . Image Vis. Comput. , , 1997 . . 15 ( ( 10 ): ): 741 - - 748 . . DOI: 10.1016/S0262-8856(97)00024-3 http://doi.org/10.1016/S0262-8856(97)00024-3 . .

Y Cai , , , ML Yang , , , ZQ Li . . Robust head pose estimation using a 3D morphable model . . Math. Prob.Eng. , , 2015 . . 678973.1 - - 678973.10 . . DOI: 10.1155/2015/678973 http://doi.org/10.1155/2015/678973 . .

MN Do . . Fast approximation of Kullback-Leibler distance for dependence trees and hidden Markov models . . IEEE Signal Process. Lett. , , 2003 . . 10 ( ( 4 ): ): 115 - - 118 . . DOI: 10.1109/LSP.2003.809034 http://doi.org/10.1109/LSP.2003.809034 . .

M Fenzi , , , L Leal-Taix , , , B Rosenhahn , , , 等 . . Class generative models based on feature regression for pose estimation of object categories . . 2013 . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition . . 755 - - 762 . . . .

P Fitzpatrick . . Head Pose Estimation Without Manual Initialization , , 2000 . . : Cambridge : Report, Massachusetts Institute of Technology , , . .

W Gao , , , B Cao , , , SG Shan , , , 等 . . The CASPEAL large-scale Chinese face database and baseline evaluations . . IEEE Trans. Syst. Man Cybern. A , , 2008 . . 38 ( ( 1 ): ): 149 - - 161 . . DOI: 10.1109/TSMCA.2007.909557 http://doi.org/10.1109/TSMCA.2007.909557 . .

X Geng , , , Y Xia . . Head pose estimation based on multivariate label distribution . . 2014 . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition . . 1837 - - 1842 . . . .

N Gourier , , , D Hall , , , JL Crowley . . Estimating face orientation from robust detection of salient facial features . . Proc. Int. Workshop on Visual Observation of Deictic Gestures , , 2004 . . Available from: http://www-prima.inrialpes.fr/perso/Gourier/Faces/HPDatabase.html http://www-prima.inrialpes.fr/perso/Gourier/Faces/HPDatabase.html . .

R Gross , , , I Matthews , , , J Cohn , , , 等 . . Multi-PIE . . Image Vis. Comput. , , 2010 . . 28 ( ( 5 ): ): 807 - - 813 . . DOI: 10.1016/j.imavis.2009.08.002 http://doi.org/10.1016/j.imavis.2009.08.002 . .

MA Haj , , , J Gonzlez , , , LS Davis . . On partial least squares in head pose estimation: how to simultaneously deal with misalignment . . 2012 . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition . . 2602 - - 2609 . . DOI: 10.1109/CVPR.2012.6247979 http://doi.org/10.1109/CVPR.2012.6247979 . .

CL Hu , , , LY Gong , , , TJ Wang , , , 等 . . An effective head pose estimation approach using Lie algebrized Gaussians based face representation . . Multim. Tools Appl. , , 2014 . . 73 ( ( 3 ): ): 1863 - - 1884 . . DOI: 10.1007/s11042-013-1676-5 http://doi.org/10.1007/s11042-013-1676-5 . .

D Huang , , , M Storer , , , F de la Torre , , , 等 . . Supervised local subspace learning for continuous head pose estimation . . 2011 . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition . . 2921 - - 2928 . . DOI: 10.1109/CVPR.2011.5995683 http://doi.org/10.1109/CVPR.2011.5995683 . .

V Jain , , , JL Crowley . . Head pose estimation using multi-scale Gaussian derivatives . . 2013 . . Proc. 18th Scandinavian Conf. on Image Analysis . . 319 - - 328 . . DOI: 10.1007/978-3-642-38886-6_31 http://doi.org/10.1007/978-3-642-38886-6_31 . .

V Krger , , , G Sommer . . Gabor wavelet networks for efficient head pose estimation . . Image Vis. Comput. , , 2002 . . 20 ( ( 9-10 ): ): 665 - - 672 . . DOI: 10.1016/S0262-8856(02)00056-2 http://doi.org/10.1016/S0262-8856(02)00056-2 . .

DC Liu , , , J Nocedal . . On the limited memory BFGS method for large scale optimization . . Math. Program. , , 1989 . . 45 ( ( 1 ): ): 503 - - 528 . . DOI: 10.1007/BF01589116 http://doi.org/10.1007/BF01589116 . .

F Lu , , , Y Sugano , , , T Okabe , , , 等 . . Head pose-free appearance-based gaze sensing via eye image synthesis . . 2012 . . Proc. 21st Int. Conf. on Pattern Recognition . . 1008 - - 1011 . . . .

F Lu , , , T Okabe , , , Y Sugano , , , 等 . . Learning gaze biases with head motion for head pose-free gaze estimation . . Image Vis. Comput. , , 2014 . . 32 ( ( 3 ): ): 169 - - 179 . . DOI: 10.1016/j.imavis.2014.01.005 http://doi.org/10.1016/j.imavis.2014.01.005 . .

BP Ma , , , XJ Chai , , , TJ Wang . . A novel feature descriptor based on biologically inspired feature for head pose estimation . . Neurocomputing , , 2013 . . 115 1 - - 10 . . DOI: 10.1016/j.neucom.2012.11.005 http://doi.org/10.1016/j.neucom.2012.11.005 . .

BP Ma , , , AN Li , , , XJ Chai , , , 等 . . CovGa: a novel descriptor based on symmetry of regions for head pose estimation . . Neurocomputing , , 2014 . . 143 97 - - 108 . . DOI: 10.1016/j.neucom.2014.06.014 http://doi.org/10.1016/j.neucom.2014.06.014 . .

BP Ma , , , R Huang , , , L Qin . . VoD: a novel image representation for head yaw estimation . . Neurocomputing , , 2015 . . 148 455 - - 466 . . DOI: 10.1016/j.neucom.2014.07.019 http://doi.org/10.1016/j.neucom.2014.07.019 . .

XH Ma , , , YQ Tan , , , GM Zheng . . A fast classification scheme and its application to face recognition . . J. Zhejiang Univ.-Sci. C (Comput. & Electron.) , , 2013 . . 14 ( ( 7 ): ): 561 - - 572 . . DOI: 10.1631/jzus.CIDE1309 http://doi.org/10.1631/jzus.CIDE1309 . .

E Murphy-Chutorian , , , MM Trivedi . . Head pose estimation in computer vision: a survey . . IEEE Trans.Patt. Anal. Mach. Intell. , , 2009 . . 31 ( ( 4 ): ): 607 - - 626 . . DOI: 10.1109/TPAMI.2008.106 http://doi.org/10.1109/TPAMI.2008.106 . .

H Pang , , , A Lin , , , M Holford , , , 等 . . Pathway analysis using random forests classification and regression . . Bioinformatics , , 2006 . . 22 ( ( 16 ): ): 2028 - - 2036 . . DOI: 10.1093/bioinformatics/btl344 http://doi.org/10.1093/bioinformatics/btl344 . .

T Sim , , , S Baker , , , M Bsat . . The CMU pose, illumination, and expression (PIE) database . . 2002 . . Proc. 5th IEEE Int. Conf. on Automatic Face and Gesture Recognition . . 46 - - 51 . . DOI: 10.1109/AFGR.2002.1004130 http://doi.org/10.1109/AFGR.2002.1004130 . .

YQ Tang , , , ZN Sun , , , TN Tan . . A survey on head pose estimation . . Patt. Recogn. Artif. Intell. , , 2014 . . 27 ( ( 3 ): ): 213 - - 225 . . . .

JW Wu , , , MM Trivedi . . A two-stage head pose estimation framework and evaluation . . Patt. Recog. , , 2008 . . 41 ( ( 3 ): ): 1138 - - 1158 . . DOI: 10.1016/j.patcog.2007.07.017 http://doi.org/10.1016/j.patcog.2007.07.017 . .

ZP Zhang , , , P Luo , , , CC Loy , , , 等 . . Facial landmark detection by deep multi-task learning . . 2014 . . Proc. 13th European Conf. on Computer Vision . . 94 - - 108 . . DOI: 10.1007/978-3-319-10599-4_7 http://doi.org/10.1007/978-3-319-10599-4_7 . .

RH Zhu , , , GL Sang , , , Y Cai , , , 等 . . Head pose estimation with improved random regression forests . . 2013 . . Proc.8th Chinese Conf. on Biometric Recognition . . 457 - - 465 . . DOI: 10.1007/978-3-319-02961-0_57 http://doi.org/10.1007/978-3-319-02961-0_57 . .

XX Zhu , , , D Ramanan . . Face detection, pose estimation, and landmark localization in the wild . . 2012 . . Proc.IEEE Conf. on Computer Vision and Pattern Recognition . . 2879 - - 2886 . . DOI: 10.1109/CVPR.2012.6248014 http://doi.org/10.1109/CVPR.2012.6248014 . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Multiclass classification based on a deep convolutional network for head pose estimation

Related Author

CAI Ying

YANG Meng-long

LI Jun

Related Institution

School of Computer Science, Sichuan University

College of Information Engineering, Sichuan Agricultural University, Yaan

School of Aeronautics and Astronautics, Sichuan University

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰