Switching Linear Inverse-Regression Model for Tracking Head Pose

Drouard, Vincent; Ba, Silèye; Horaud, Radu

doi:10.1109/wacv.2017.142

Cited by 8 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These HPT methods make use of 2D or 3D facial landmarks, which stays in contrast with the proposed method that directly exploits high-dimensional feature representations of faces. For completeness, we also compared our algorithms with the HPE method of [18] and with GPB2, Section V and [64]. To quantitatively evaluate HPT we compute average and standard deviation of the absolute error between the estimated pose parameters and the ground-truth parameters provided with each annotated dataset.…”

Section: Resultsmentioning

confidence: 99%

Variational Inference and Learning of Piecewise-linear Dynamical Systems

Alameda-Pineda¹,

Drouard²,

Horaud³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Modeling the temporal behavior of data is of primordial importance in many scientific and engineering fields. The baseline method assumes that both the dynamic and observation models follow linear-Gaussian models. Non-linear extensions lead to intractable solvers. It is also possible to consider several linear models, or a piecewise linear model, and to combine them with a switching mechanism, which is also intractable because of the exponential explosion of the number of Gaussian components. In this paper, we propose a variational approximation of piecewise linear dynamic systems. We provide full details of the derivation of a variational expectation-maximization algorithm that can be used either as a filter or as a smoother. We show that the model parameters can be split into two sets, a set of static (or observation parameters) and a set of dynamic parameters. The immediate consequences are that the former set can be estimated off-line and that the number of linear models (or the number of states of the switching variable) can be learned based on model selection. We apply the proposed method to the problem of visual tracking and we thoroughly compare our algorithm with several visual trackers applied to the problem of head-pose estimation.

show abstract

Section: Resultsmentioning

confidence: 99%

Variational Inference and Learning of Piecewise-linear Dynamical Systems

Alameda-Pineda¹,

Drouard²,

Horaud³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, [15], [16], [17] leverage well visible facial features on RGB input images, and [18] on 3D data. [19] proposed to predict pose parameters from highdimensional feature vectors, embedding a Gaussian mixture of linear inverse-regression model into a dynamic Bayesian model. However, these methods need facial (e.g.…”

Section: Related Workmentioning

confidence: 99%

Face-from-Depth for Head Pose Estimation on Depth Images

Borghi

Fabbri

Vezzani

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete end-to-end system. The core element of the framework is a Convolutional Neural Network, called POSEidon + , that receives as input three types of images and provides the 3D angles of the pose as output. Moreover, a Face-from-Depth component based on a Deterministic Conditional GAN model is able to hallucinate a face from the corresponding depth image. We empirically demonstrate that this positively impacts the system performances. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Experimental results show that our method overcomes several recent state-of-art works based on both intensity and depth input data, running in real-time at more than 30 frames per second.

show abstract

A Novel Convolutional Neural Network for Head Detection and Pose Estimation in Complex Environments from Single-Depth Images

Wang,

Lei,

et al. 2023

Cogn Comput

View full text Add to dashboard Cite

Switching Linear Inverse-Regression Model for Tracking Head Pose

Cited by 8 publications

References 32 publications

Variational Inference and Learning of Piecewise-linear Dynamical Systems

Variational Inference and Learning of Piecewise-linear Dynamical Systems

Face-from-Depth for Head Pose Estimation on Depth Images

A Novel Convolutional Neural Network for Head Detection and Pose Estimation in Complex Environments from Single-Depth Images

Contact Info

Product

Resources

About