Page 230 -

4.1 Points and patches 209

Figure 4.29 Real-time head tracking using the fast trained classifiers of Lepetit, Pilet, and Fua (2004) c 2004
IEEE.

moving objects or points. Yilmaz, Javed, and Shah (2006) and Lepetit and Fua (2005) survey
the larger field of object tracking, which includes not only feature-based techniques but also
alternative techniques based on contour and region (Section 5.1).
One of the newest developments in feature tracking is the use of learning algorithms to
build special-purpose recognizers to rapidly search for matching features anywhere in an
image (Lepetit, Pilet, and Fua 2006; Hinterstoisser, Benhimane, Navab et al. 2008; Rogez,
¨
2
Rihan, Ramalingam et al. 2008; Ozuysal, Calonder, Lepetit et al. 2010). By taking the time
to train classifiers on sample patches and their affine deformations, extremely fast and reliable
feature detectors can be constructed, which enables much faster motions to be supported
(Figure 4.29). Coupling such features to deformable models (Pilet, Lepetit, and Fua 2008)or
structure-from-motion algorithms (Klein and Murray 2008) can result in even higher stability.

4.1.5 Application: Performance-driven animation

One of the most compelling applications of fast feature tracking is performance-driven an-
imation, i.e., the interactive deformation of a 3D graphics model based on tracking a user’s
motions (Williams 1990; Litwinowicz and Williams 1994; Lepetit, Pilet, and Fua 2004).
Buck, Finkelstein, Jacobs et al. (2000) present a system that tracks a user’s facial expres-
sions and head motions and then uses them to morph among a series of hand-drawn sketches.
An animator first extracts the eye and mouth regions of each sketch and draws control lines
over each image (Figure 4.30a). At run time, a face-tracking system (Toyama 1998) deter-
mines the current location of these features (Figure 4.30b). The animation system decides

2 See also my previous comment on earlier work in learning-based tracking (Avidan 2001; Jurie and Dhome
2002; Williams, Blake, and Cipolla 2003).