Skip to main content

Research Repository

Advanced Search

Cascaded continuous regression for real-time incremental face tracking

S�nchez Lozano, Enrique; Martinez, Brais; Tzimiropoulos, Georgios; Valstar, Michel F.

Cascaded continuous regression for real-time incremental face tracking Thumbnail


Authors

Enrique S�nchez Lozano

Brais Martinez

Georgios Tzimiropoulos

Michel F. Valstar



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.

Conference Name 14th European Conference on Computer Vision (EECV 2016)
End Date Oct 16, 2016
Acceptance Date Jul 13, 2016
Publication Date Oct 13, 2016
Deposit Date Aug 4, 2016
Publicly Available Date Oct 13, 2016
Peer Reviewed Peer Reviewed
Public URL https://nottingham-repository.worktribe.com/output/823697
Publisher URL http://link.springer.com/chapter/10.1007/978-3-319-46484-8_39
Additional Information The final publication is
available at http://link.springer.com/chapter/10.1007/978-3-319-46484-8_39

Files





Downloadable Citations