• A. O. Rakova Kharkiv National University of Radio Electronics, Kharkiv, Ukraine
  • N. V. Bilous Kharkiv National University of Radio Electronics, Kharkiv, Ukraine



Face orientation vector, head moves, recognition, deep learning.


Context. The direction of the human face vector is an indicator of human attention. It has many applications in our daily lives, such as human-computer interaction, teleconferencing, virtual reality and 3D sound rendering. Moreover, determining the position of the head can be used to compare the exercises performed by a person with a certain standard, which brings us to investigation of ways to efficiently track moves. Depth-camera based systems, frequently used for these purposes, have significant drawbacks such as accuracy decreasing on the direct sunlight and necessity of additional equipment. The recognition from the two-dimensional image becomes more widespread and eliminates difficulties related to depth cameras which allows them to be used indoors and outdoors. 

Objective. The purpose of this work is creation of the method that will allow us to track human head moves and record only significant vectors of head direction.

Methods. This paper suggests reference points method that decreases set of recorded vectors to minimal amount significant to describe head moves. It also investigates and compares existing methods for determining the vector of the face in terms of use in suggested approach. 

Results. Suggested reference points method shows ability to highly decrease set of head direction vectors that describe the move. According to the results of the study, regression-based methods showed significantly better accuracy and independence from light and partial face closure so they were chosen to be used as methods to get head direction vector in reference points approach.

Conclusions. Research confirmed applicability of reference points method for human movements tracking and shown that methods of determining human head vector by two-dimensional image can compete in accuracy with RGBD-based methods. Thus combined with suggested approach these methods expose less restrictions in use than RGBD-based ones. 

Author Biographies

A. O. Rakova, Kharkiv National University of Radio Electronics, Kharkiv

Student of the Software Engineering Department

N. V. Bilous, Kharkiv National University of Radio Electronics, Kharkiv

PhD, Associate Professor, Professor of the Software Engineering Department


Borghi G., Fabbri M., Vezzani R. et al. ace-from-Depth for Head Pose Estimation on Depth Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, Vol. 42, pp. 596–609. DOI: 10.1109/TPAMI.2018.2885472

Viola P., Jones M. Rapid object detection using a boosted cascade of simple features, Computer Society Conference on Computer Vision and Pattern Recognition, 8–14 December 2001: proceedings. Kauai, IEEE, 2001. DOI: 10.1109/CVPR.2001.990517

Shcherbakova G., Krylov V. N., Bilous N. V. Methods of automated classification based on wavelet-transform for automated medical diagnostics, Information Technologies in Innovation Business Conference (ITIB), 7–9 October 2015: proceedings. Kharkiv, IEEE, 2015, pp. 7–10. DOI: 10.1109/ITIB.2015.7355048

Wallhoff F., AblaBmeier M., Rigoll G. Multimodal Face Detection, Head Orientation and Eye Gaze Tracking, International Conference on Multisensor Fusion and Integration for Intelligent Systems, 3–6 September 2006: proceedings. Heidelberg, IEEE, 2006, pp. 13–18. DOI: 10.1109/MFI.2006.265612

Ahn B., Park J., Kweon I. S. Real-time head orientation from a monocular camera using deep neural network, Asian Conference on Computer Vision: 12th Asian Conference on Computer Vision, 1–5 November 2014: proceedings. Singapore, ACCV, 2014, pp. 82–96. DOI: 10.1007/978-3319-16811-1_6

Patacchiola M., Cangelosi A. Head pose estimation in the wild using convolutional neural networks and adaptive gradient methods, Pattern Recognition, 2017, Vol. 71, pp. 132–143. DOI: 10.1016/j.patcog.2017.06.009

Huang B., Chen R., Xu W. et al Improving head pose estimation using two-stage ensembles with top-k regression, Image and Vision Computing, 2020, Vol. 93. DOI: 10.1016/j.imavis.2019.11.005

Kumar A., Alavi A., Chellappa R. KEPLER: Keypoint and pose estimation of unconstrained faces by learning efficient H-CNN regressors, Image and Vision Computing, 2018, pp. 258–265. DOI: 10.1016/j.imavis.2018.09.009

Hien L. T., Toan D. N., Lang T. V. Detection of Human Head Direction Based on Facial Normal Algorithm, International Journal of Electronics Communication and Computer Engineering, 2015, Vol. 6, pp. 110–114

Tsun-Yi Y., Yi-Ting C., Yen-Yu L. et al. FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image, Conference on Computer Vision and Pattern Recognition (CVPR), 15–20 June 2019: proceedings. Long Beach, IEEE, 2019, pp. 1087–1096. DOI: 10.1109/CVPR.2019.00118

Ruiz N., Chong E., Rehg J. M. Fine-grained head pose estimation without keypoints, Conference on Computer Vision and Pattern Recognition Workshop, 18–22 June 2018: proceedings. Salt Lake City, IEEE, 2018, pp. 1821– 1829. DOI: 10.1109/CVPRW.2018.00281

Fanelli G., Dantone M., Gall J. et al. Random forests for real time 3D face analysis, International Journal of Computer Vision, 2013, Vol. 101, pp. 437–458. DOI: 10.1007/s11263012-0549-0

Zhu X., Lei Z., Liu X. et al. Face alignment across large poses: A 3D solution, Conference on Computer Vision and Pattern Recognition, 27–30 June 2016: proceedings. Las Vegas, 2016. – P. 146–155. DOI: 10.1109/CVPR.2016.23

Koestinger M., Wohlhart P., Roth P. M. et al. Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization, International Conference on Computer Vision Workshops, 6–13 November 2011: proceedings. Barcelona, IEEE, 2011, pp. 2144–2151. DOI: 10.1109/ICCVW.2011.6130513


How to Cite

Rakova, A. O., & Bilous, N. V. (2020). REFERENCE POINTS METHOD FOR HUMAN HEAD MOVEMENTS TRACKING. Radio Electronics, Computer Science, Control, (3), 121–128.



Neuroinformatics and intelligent systems