Sequentially adaptive active appearance model with regression-based online reference appearance template

• An online reference template is generated for tracking drifts correction.
• A correspondences map from Local feature to Landmark is learned via regression.
• An online reference appearance model update strategy is designed.
• The tracking accuracy is better than other state-of-the-art methods.

Statistically motivated approaches, such as the active appearance model (AAM), have been widely used for non-rigid objects registration and tracking. As an extension of AAM, sequential AAM (SAAM) was proposed, in which both an incremental updated component and a reference component were employed simultaneously in the fitting scheme. To make SAAM more adaptive to facial context variations during tracking, a regression-based online reference appearance model (ORAM) is presented to update the subject-specific appearance of the SAAM. The spatial map between scattered local feature correspondences and structured landmark correspondences is learned via Kernel Ridge Regression (KRR). Additionally, a shape deformation and appearance model evaluation strategies help to improve the accuracy and efficiency of the algorithm. The approach is experimentally validated by tracking face videos with improved fitting accuracy.