Robust statistics for feature-based active appearance models
Kopaczka M, Gräbel P, Merhof D (2018)
Publication Type: Conference contribution
Publication year: 2018
Publisher: SciTePress
Book Volume: 1
Pages Range: 421-426
Conference Proceedings Title: ICETE 2018 - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications
Event location: Porto, PRT
ISBN: 9789897583193
Abstract
Active Appearance Models (AAM) are a well-established method for facial landmark detection and face tracking. Due to their widespread use, several additions to the original AAM algorithms have been proposed in recent years. Two previously proposed improvements that address different shortcomings are using robust statistics for occlusion handling and adding feature descriptors for improved landmark fitting performance. In this paper, we show that a combination of both methods is possible and provide a feasible and effective way to improve robustness and precision of the AAM fitting process. We describe how robust cost functions can be incorporated into the feature-based fitting procedure and evaluate our approach. We apply our method to the challenging 300-videos-in-the-wild dataset and show that our approach allows robust face tracking even under severe occlusions.
Involved external institutions
Germany (DE)How to cite
APA:
Kopaczka, M., Gräbel, P., & Merhof, D. (2018). Robust statistics for feature-based active appearance models. In Christian Callegari, Marten van Sinderen, Paulo Novais, Panagiotis Sarigiannidis, Sebastiano Battiato, Angel Serrano Sanchez de Leon, Pascal Lorenz, Mohammad S. Obaidat, Mohammad S. Obaidat (Eds.), ICETE 2018 - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications (pp. 421-426). Porto, PRT: SciTePress.
MLA:
Kopaczka, Marcin, Philipp Gräbel, and Dorit Merhof. "Robust statistics for feature-based active appearance models." Proceedings of the 15th International Joint Conference on e-Business and Telecommunications, ICETE 2018, Porto, PRT Ed. Christian Callegari, Marten van Sinderen, Paulo Novais, Panagiotis Sarigiannidis, Sebastiano Battiato, Angel Serrano Sanchez de Leon, Pascal Lorenz, Mohammad S. Obaidat, Mohammad S. Obaidat, SciTePress, 2018. 421-426.
BibTeX: Download