Continuous Head Pose Estimation Using Manifold Subspace Embedding and Multivariate Regression
Open Access
- 19 March 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 18325-18334
- https://doi.org/10.1109/access.2018.2817252
Abstract
In this paper, a continuous head pose estimation system is proposed to estimate yaw and pitch head angles from raw facial images. Our approach is based on manifold learningbased methods, due to their promising generalization properties shown for face modelling from images. The method combines histograms of oriented gradients, generalized discriminative common vectors and continuous local regression to achieve successful performance. Our proposal was tested on multiple standard face datasets, as well as in a realistic scenario. Results show a considerable performance improvement and a higher consistence of our model in comparison with other state-of-art methods, with angular errors varying between 9 and 17 degrees.Funding Information
- Spanish projects (DPI2015-65286-R, 2017 SGR 1624)
- CERCA Programme
- Serra Húnter Fellowship
This publication has 33 references indexed in Scilit:
- From circle to 3-sphere: Head pose estimation by instance parameterizationComputer Vision and Image Understanding, 2015
- Real-Time Head Orientation from a Monocular Camera Using Deep Neural NetworkLecture Notes in Computer Science, 2015
- Incremental Generalized Discriminative Common Vectors for Image ClassificationIEEE Transactions on Neural Networks and Learning Systems, 2014
- Robust head pose estimation via supervised manifold learningNeural Networks, 2014
- A Two-Layer Framework for Piecewise Linear Manifold-Based Head Pose EstimationInternational Journal of Computer Vision, 2012
- An integrated approach for head gesture based interfaceApplied Soft Computing, 2012
- Measurement of Driver’s Visual Attention Capabilities Using Real-Time UFOV MethodInternational Journal of Intelligent Transportation Systems Research, 2011
- Human-Robot Interaction: A SurveyFoundations and Trends® in Human–Computer Interaction, 2007
- A new LDA-based face recognition system which can solve the small sample size problemPattern Recognition, 2000
- Eigenfaces vs. Fisherfaces: recognition using class specific linear projectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997