Game Development Reference
In-Depth Information
virtual reality with computer vision. This system— augmented reality system —
allows the interaction of real and virtual humans in an augmented reality context.
It can be understood as the link between computer graphics and computer vision
communities.
Kanade, Rander & Narayanan (1997) present a technique to automatically
generate 3D models of real human bodies, together with a virtual model of their
surrounding environment, from images of the real world. These virtual models
allow a spatio-temporal view interpolation and the users can select their own
viewpoints, independent of the actual camera positions used to capture the event.
The authors have coined the expression virtualized reality to call their novel
approach. In the same direction, Hoshnio (2002) presents a model-based
synthesis and analysis of human body images. It is used in virtual reality systems
to imitate appearance and behavior of a real-world human from video sequences.
Such a human model can be used to generate multiple-views, merge virtual
objects and change motion characteristics of human figures in video. Hilton et
al. (1999) introduce a new technique for automatically building realistic models
of people for use in virtual reality applications. The final goal is the development
of an automatic low-cost modeling of people suitable for populating virtual worlds
with personalised avatars. For instance, the participants in a multi-user virtual
environment could be represented by means of a realistic facsimile of their
shape, size and appearance. The proposed technique is based on a set of low-
cost color images of a person taken from four orthogonal views. Realistic
representation is achieved by mapping color texture onto the 3D model.
Surveillance Systems
Another important application domain is surveillance systems. Smart surveil-
lance systems, capable of more than single-motion detection, can take advantage
of the study of 3D human motion analysis by incorporating specific knowledge
about human shape and appearance, in order to decrease false alarms. In
addition, high-level analysis might even be able to distinguish between simple
authorized and non-authorized activities. Wren et al. (1997) present a real-time
system for tracking people and interpreting their behavior to be used, for
example, in surveillance systems. The proposed system uses a probabilistic
approach that segments the subject into a number of blobs and tracks those over
time. The disadvantages of the work proposed by Wren et al. (1997) are that the
system can only handle a single person with fixed-camera situations.
He & Derunner (2000) propose a different approach based on the study of the
periodicity of human actions. Periodic motions, specifically walking and running,
can be recognized. This approach is robust over variations in scene background,
Search WWH ::




Custom Search