Cascaded continuous regression for real-time incremental face tracking

Sánchez Lozano, Enrique, Martinez, Brais, Tzimiropoulos, Georgios and Valstar, Michel F. (2016) Cascaded continuous regression for real-time incremental face tracking. In: 14th European Conference on Computer Vision (EECV 2016), 8-16 October 2016, Amsterdam, Netherlands.

Full text not available from this repository.

Abstract

This paper introduces a novel real-time algorithm for facial landmark tracking. Compared to detection, tracking has both additional challenges and opportunities. Arguably the most important aspect in this domain is updating a tracker's models as tracking progresses, also known as incremental (face) tracking. While this should result in more accurate localisation, how to do this online and in real time without causing a tracker to drift is still an important open research question. We address this question in the cascaded regression framework, the state-of-the-art approach for facial landmark localisation. Because incremental learning for cascaded regression is costly, we propose a much more efficient yet equally accurate alternative using continuous regression. More specifically, we first propose cascaded continuous regression (CCR) and show its accuracy is equivalent to the Supervised Descent Method. We then derive the incremental learning updates for CCR (iCCR) and show that it is an order of magnitude faster than standard incremental learning for cascaded regression, bringing the time required for the update from seconds down to a fraction of a second, thus enabling real-time tracking. Finally, we evaluate iCCR and show the importance of incremental learning in achieving state-of-the-art performance. Code for our iCCR is available from http://www.cs.nott.ac.uk/~psxes1.

Item Type: Conference or Workshop Item (Paper)
RIS ID: https://nottingham-repository.worktribe.com/output/823697
Additional Information: The final publication is available at http://link.springer.com/chapter/10.1007/978-3-319-46484-8_39
Schools/Departments: University of Nottingham, UK > Faculty of Science > School of Computer Science
Depositing User: Valstar, Michel
Date Deposited: 04 Aug 2016 14:37
Last Modified: 04 May 2020 18:17
URI: https://eprints.nottingham.ac.uk/id/eprint/35721

Actions (Archive Staff Only)

Edit View Edit View