Volltext-Downloads (blau) und Frontdoor-Views (grau)

A kalman filter with state constraints for model-based dynamic facial action unit estimation

  • This paper describes a dynamic, model-based approach for estimating intensities of 22 out of 44 different basic facial muscle movements. These movements are defined as Action Units (AU) in the Facial Action Coding System (FACS) [1]. The maximum facial shape deformations that can be caused by the 22 AUs are represented as vectors in an anatomically based, deformable, point-based face model. The amount of deformation along these vectors represent the AU intensities, and its valid range is [0, 1]. An Extended Kalman Filter (EKF) with state constraints is used to estimate the AU intensities. The focus of this paper is on the modeling of constraints in order to impose the anatomically valid AU intensity range of [0, 1]. Two process models are considered, namely constant velocity and driven mass-spring-damper. The results show the temporal smoothing and disambiguation effect of the constrained EKF approach, when compared to the frame-by-frame model fitting approach ‘Regularized Landmark Mean-Shift (RLMS)’ [2]. This effect led to more than 35% increase in performance on a database of posed facial expressions.

Export metadata

Additional Services

Search Google Scholar Check availability

Statistics

Show usage statistics
Metadaten
Document Type:Conference Object
Language:English
Author:Teena Hassan, Dominik Seuß, Andreas Ernst, Jens Garbas
Parent Title (English):Längle, Puente León et al. (Hg.): Forum Bildverarbeitung 2018, 29.-30. Novemver 2018 in Karlsruhe
ISBN:978-3-7315-0833-5
URL:https://doi.org/10.5445/KSP/1000085290
Publisher:KIT Scientific Publishing
Place of publication:Karlsruhe
Date of first publication:2018/11/21
Keyword:Kalman filter; action unit recognition; facial expression analysis; state constraints
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 006 Spezielle Computerverfahren
Entry in this database:2023/04/13