Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision

Jaeseong Park, Suwoong Heo, Kyungjune Lee, Hyewon Song, Sanghoon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we present a robust framework for facial pose estimation from binocular stereoscopic vision. Unlike prior work on the facial pose estimation that employs the whole landmarks even located in the wrong position, we propose a landmark selection method to remove the erroneous landmarks for better performance, especially in the large facial pose case. For this purpose, we train a convolutional neural network (CNN) in order to measure the confidence of each facial landmark detected by using a well-known landmark detection algorithm. Also, by fitting selected landmarks to 3D space, our framework becomes more robust even when a small number of landmarks are selected. Due to the absence of public dataset for the binocular stereo facial pose, we construct facial pose data sets using a motion sensor for performance validation. In our experiments, our method achieves the higher accuracy of the pose estimation than the previous method, especially for large facial pose cases.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages186-190
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 2018 Aug 29
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period18/10/718/10/10

Fingerprint

Binoculars
Stereo vision
Neural networks
Sensors
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Park, J., Heo, S., Lee, K., Song, H., & Lee, S. (2018). Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 186-190). [8451443] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451443
Park, Jaeseong ; Heo, Suwoong ; Lee, Kyungjune ; Song, Hyewon ; Lee, Sanghoon. / Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 186-190 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{9cff575a46fd4794b15678d473cc9893,
title = "Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision",
abstract = "In this paper, we present a robust framework for facial pose estimation from binocular stereoscopic vision. Unlike prior work on the facial pose estimation that employs the whole landmarks even located in the wrong position, we propose a landmark selection method to remove the erroneous landmarks for better performance, especially in the large facial pose case. For this purpose, we train a convolutional neural network (CNN) in order to measure the confidence of each facial landmark detected by using a well-known landmark detection algorithm. Also, by fitting selected landmarks to 3D space, our framework becomes more robust even when a small number of landmarks are selected. Due to the absence of public dataset for the binocular stereo facial pose, we construct facial pose data sets using a motion sensor for performance validation. In our experiments, our method achieves the higher accuracy of the pose estimation than the previous method, especially for large facial pose cases.",
author = "Jaeseong Park and Suwoong Heo and Kyungjune Lee and Hyewon Song and Sanghoon Lee",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451443",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "186--190",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",
address = "United States",

}

Park, J, Heo, S, Lee, K, Song, H & Lee, S 2018, Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451443, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 186-190, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 18/10/7. https://doi.org/10.1109/ICIP.2018.8451443

Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision. / Park, Jaeseong; Heo, Suwoong; Lee, Kyungjune; Song, Hyewon; Lee, Sanghoon.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 186-190 8451443 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision

AU - Park, Jaeseong

AU - Heo, Suwoong

AU - Lee, Kyungjune

AU - Song, Hyewon

AU - Lee, Sanghoon

PY - 2018/8/29

Y1 - 2018/8/29

N2 - In this paper, we present a robust framework for facial pose estimation from binocular stereoscopic vision. Unlike prior work on the facial pose estimation that employs the whole landmarks even located in the wrong position, we propose a landmark selection method to remove the erroneous landmarks for better performance, especially in the large facial pose case. For this purpose, we train a convolutional neural network (CNN) in order to measure the confidence of each facial landmark detected by using a well-known landmark detection algorithm. Also, by fitting selected landmarks to 3D space, our framework becomes more robust even when a small number of landmarks are selected. Due to the absence of public dataset for the binocular stereo facial pose, we construct facial pose data sets using a motion sensor for performance validation. In our experiments, our method achieves the higher accuracy of the pose estimation than the previous method, especially for large facial pose cases.

AB - In this paper, we present a robust framework for facial pose estimation from binocular stereoscopic vision. Unlike prior work on the facial pose estimation that employs the whole landmarks even located in the wrong position, we propose a landmark selection method to remove the erroneous landmarks for better performance, especially in the large facial pose case. For this purpose, we train a convolutional neural network (CNN) in order to measure the confidence of each facial landmark detected by using a well-known landmark detection algorithm. Also, by fitting selected landmarks to 3D space, our framework becomes more robust even when a small number of landmarks are selected. Due to the absence of public dataset for the binocular stereo facial pose, we construct facial pose data sets using a motion sensor for performance validation. In our experiments, our method achieves the higher accuracy of the pose estimation than the previous method, especially for large facial pose cases.

UR - http://www.scopus.com/inward/record.url?scp=85062899990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062899990&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451443

DO - 10.1109/ICIP.2018.8451443

M3 - Conference contribution

AN - SCOPUS:85062899990

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 186

EP - 190

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -

Park J, Heo S, Lee K, Song H, Lee S. Robust Facial Pose Estimation Using Landmark Selection Method for Binocular Stereo Vision. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 186-190. 8451443. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451443