Advances in Vision-Based Human Body Modeling - 3D Modeling and Animation: Synthesis and Analysis Techniques for the Human Body - page 16

history of motion (e.g., more recently moving pixels are brighter). MEI and MHI
temporal templates are then matched to stored instances of views of known
actions.
A technique for human motion recognition in an unconstrained environment,
incorporating hypotheses which are probabilistically propagated across space
and time, is presented in Bregler (1997). EM clustering, recursive Kalman and
Hidden Markov Models are used as well. The feasibility of this method is tested
on classifying human gait categories (running, walking and skipping). HMMs are
quite often used for classifying and recognizing human dynamics. In Pavlovic &
Rehg (2000), HMMs are compared with switching linear dynamic systems
(SLDS) towards human motion analysis. It is argued that the SLDS framework
demonstrates greater descriptive power and consistently outperforms standard
HMMs on classification and continuous state estimation tasks, although the
learning-inference mechanism is complicated.
Finally, a novel approach for the identification of human actions in an office
(entering the room, using a computer, picking up the phone, etc.) is presented in
Ayers & Shah (2001). The novelty of this approach consists in using prior
knowledge about the layout of the room. Action identification is modeled by a
state machine consisting of various states and the transitions between them. The
performance of this system is affected if the skin area of the face is occluded,
if two people get too close and if prior knowledge is not sufficient. This approach
may be applicable in surveillance systems like those ones described in the next
section.
Applications
3D HBMs have been used in a wide spectrum of applications. This section is only
focused on the following four major application areas: a) Virtual reality; b)
Surveillance systems; c) User interface; and d) Medical or anthropometric
applications. A brief summary is given below.
Virtual Reality
The efficient generation of 3D HBMs is one of the most important issues in all
virtual reality applications. Models with a high level of detail are capable of
conveying emotions through facial animation (Aubel, Boulic & Thalmann, 2000).
However, it is still nowadays very hard to strike the right compromise between
realism and animation speed. Balcisoy et al. (2000) present a combination of