Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2017

Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions

Abstract

Head-pose estimation has many applications, such as social-event analysis, human-robot and human-computer interaction, driving assistance, and so forth. Head-pose estimation is challenging because it must cope with changing illumination conditions, face orientation and appearance variabilities, partial occlusions of facial landmarks, as well as bounding-box-to-face alignment problems. We propose a mixture of linear regression method that learns how to map high-dimensional feature vectors (extracted from bounding-boxes of faces) onto both head-pose parameters and bounding-box shifts, such that at runtime they are simultaneously predicted. We describe in detail the mapping method that combines the merits of manifold learning and of mixture of linear regression. We validate our method with three publicly available datasets and we thoroughly benchmark four variants of the proposed algorithm with several state-of-the-art head-pose estimation methods.
Fichier principal
Vignette du fichier
main_jrnl_review2.pdf (4.73 Mo) Télécharger le fichier
Vignette du fichier
002.png (729.75 Ko) Télécharger le fichier
Vignette du fichier
002.jpg (145 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01413406 , version 1 (01-02-2017)

Identifiers

Cite

Vincent Drouard, Radu Horaud, Antoine Deleforge, Sileye Ba, Georgios Evangelidis. Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions. IEEE Transactions on Image Processing, 2017, 26 (3), pp.1428 - 1440. ⟨10.1109/TIP.2017.2654165⟩. ⟨hal-01413406⟩
1080 View
366 Download

Altmetric

Share

Gmail Facebook X LinkedIn More