3D head tracking using non-linear optimization

Abstract

Accurate and reliable tracking of the 3D position of human heads is a continuing research problem in computer vision. This paper addresses the specific problem of model-based tracking with a generic deformable 3D head model. Following the work of Vetter and Blanz, a collection of head models is obtained from a 3D scanner, registered and parameterized to give a generic head model which is linearly parameterized by a small number of parameters. This is the 3D analogue of Cootes and Taylor's active appearance models. We cast tracking as a parameter estimation problem, and note that many existing solutions to the problem-such as CONDENSATION and Kalman filtering-are analogous to nonlinear optimization strategies in numerical analysis. We show how careful analysis of the error function, parameterization of the model pose parameters, and choice of optimizer allows us to robustly track 3D head pose in digital video camera footage of quickly moving heads.

Correlated Active Appearance Models

“…To do this we use the quotient rule for differentiation i.e. : (6) We use: (7) and (8) The term is a constant that can be taken out and put back in at the end. The derivatives of these are: (9) and (10) Putting these back into the quotient rule gives the derivative of the NCC with respect to parameter δ j as:…”

“…Paterson and Fitzgibbon [6] investigated the use of the mutual information index and correlation ratio as metrics for 3DMM tracking and showed improved performance over SSE.…”

Dense point-to-point correspondences between 3D faces using parametric remeshing for constructing 3D Morphable Models

“…The 3D Morphable Model (3DMM), presented by Blanz and Vetter in [4], is a powerful tool that is applicable for many tasks, such as face recognition [8], expression transfer between individuals [3], and face tracking [1,11,14]. The crucial step in constructing a 3DMM is to find dense pointto-point correspondences between 3D faces of a database, so that Principal Component Analysis can be applied.…”

Robust tracking of facial feature points with 3D Active Shape Models

“…[4,5,6,7,8]). However, limiting 3D tracking on a sparse set of facial feature points has several advantages.…”