Challenging 3D Head Tracking and Evaluation Using Unconstrained Test Data Set

3D face tracking using one monocular camera is an important topic, since it is useful in many domains such as: video surveillance system, human machine interaction, biometrics, etc. In this paper, we propose a new 3D face tracking which is robust to large head rotations. Underlying cascaded regressi...

Full description

Saved in:
Bibliographic Details
Published in2017 21st International Conference Information Visualisation (IV) pp. 205 - 210
Main Authors Ababsa, Fakhreddine, Ngoc-Trung Tran, Charbit, Maurice
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2017
Subjects
3D pose estimation
Cameras
cascaded regression
evaluation
Face
Face tracking
Feature extraction
Shape
test data sets
Three-dimensional displays
Tracking
Online AccessGet full text

Cover

More Information
Summary:3D face tracking using one monocular camera is an important topic, since it is useful in many domains such as: video surveillance system, human machine interaction, biometrics, etc. In this paper, we propose a new 3D face tracking which is robust to large head rotations. Underlying cascaded regression approach for 2D landmark detection, we build an extension in context of 3D pose tracking. To better work with out-of-plane issues, we extend the training dataset by including a new set of synthetic images. For evaluation, we propose to use a new recording system to capture automatically face pose ground-truth, and create a new test dataset, named U3PT (Unconstrained 3D Pose Tracking). The performance of our method along with the state-of-the-art methods are carried out to analyze advantage as well as limitations need to be improved in the future.
ISSN:2375-0138
DOI:10.1109/iV.2017.40