Dynamic Tracking of Facial Expressions Using Adaptive, Overlapping Subspaces

We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear subspaces. The learned subspaces adaptively adjust to the subject by tracking the shapes independently using Kanade Lucas Tomasi(KLT) point tracker. The novelty of our approach is that the tracking of feature points is used to generate independent training examples for updating the learned shape manifold and the appearance model. We use landmark based shape analysis to train a Gaussian mixture model over the aligned shapes and learn a Point Distribution Model(PDM) for each of the mixture components. The target 2D shape is searched by first maximizing the mixture probability density for the local feature intensity profiles along the normal followed by constraining the global shape using the most probable PDM cluster. The feature shapes are robustly tracked across multiple frames by dynamically switching betwe...

• Type: Conference
• Year: 2007
• Where: ICCS
• Authors: Dimitris N. Metaxas, Atul Kanaujia, Zhiguo Li
• Keywords: 2d Shape, ICCS 2007, Shape Manifold, Target 2D Shape