Head pose estimation by nonlinear manifold learning

Abstract. Head pose estimation is an important task for many face analysis applications, such as face recognition systems and human computer interactions. In this paper we aim to address the pose estimation problem under some challenging conditions, e.g., from a single image, large pose variation, and un-even illumination conditions. The approach we developed combines non-linear dimension reduction techniques with a learned distance metric transformation. The learned distance metric provides better intra-class clustering, therefore preserving a smooth lowdimensional manifold in the presence of large variation in the input images due to illumination changes. Experiments show that our method improves the performance, achieving accuracy within 2-3 degrees for face images with varying poses and within 3-4 degrees error for face images with varying pose and illumination changes.

show abstract

“…But none of them treats illumination variations in a principled way, most of them do not discuss the effect of illumination. [20] [−90…”

Section: Manifold Learningmentioning

confidence: 99%

“…Raytchev et al [20] apply ISOMAP-based manifold learning technique for user-independent pose estimation and evaluate their method in comparison with the Linear Subspace and Locality Preserving Projections(LPP) [21].…”

Section: Manifold Learningmentioning

confidence: 99%

Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning

Wang

Huang

Gao

et al. 2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Not surprisingly, some of the best performing headpose estimation methods rely either on dimensionality reduction followed by regression, [35,32,16,19,4,12,36], or on high-dimensional-to-low-dimensional regression, e.g. [28,22,8,10].…”

Section: Introductionmentioning

confidence: 99%

Switching Linear Inverse-Regression Model for Tracking Head Pose

Drouard¹,

Ba²,

Horaud³

2017

2017 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We propose to estimate the head-pose angles (pitch, yaw, and roll) by simultaneously predicting the pose parameters from observed high-dimensional feature vectors, and tracking these parameters over time. This is achieved by embedding a Gaussian mixture of linear inverse-regression model into a dynamic Bayesian model. The use of a switching Kalman filter (SKF) enables a principled way of carrying out this embedding. The SKF governs the temporal predictive distribution of the pose parameters (modeled as continuous latent variables) conditioned by the discrete variables associated with the mixture of linear inverse-regression formulation. We formally derive the equations of the proposed switching linear regression model, we propose an approximation that is both identifiable and computationally tractable, we design an EM procedure to estimate the SKF parameters in closed-form, and we carry out experiments and comparisons with other methods using recently released datasets.

show abstract

“…Appearance-based approach establishes a direct mapping relationship between the image and the head pose [3,4]. Related work often focuses on subspace methods [5,6] and learning methods based on image features [7]. Such method has high robustness and estimation accuracy, but because of it requires a lot of proper training data and accurate image registration, when in practical application it will make a larger workload.…”

Section: Introductionmentioning

confidence: 99%