Game Development Reference
In-Depth Information
If we want to express motion in real space, we must relate the motion measured
in terms of pixel coordinates to the real/virtual world coordinates. That is, we
need to relate the world reference frame to the image reference frame. Simply
knowing the pixel separation in an image does not allow us to determine the
distance of those points in the real world. We must derive some equations to link
the world reference frame to the image reference frame in order to find the
relationship between the coordinates of points in 3D-space and the coordinates
of the points in the image. We introduce the camera reference frame because
there is no direct relation between the previously mentioned reference frames.
Then, we can find an equation linking the camera reference frame with the image
reference frame (LinkI), and another equation linking the world reference frame
with the camera reference frame (LinkE). Identifying LinkI and LinkE is
equivalent to finding the camera's characteristics, also known as the camera's
extrinsic and intrinsic parameters.
Many calibration techniques exist that have been reported in the past two
decades. The developed methods can be roughly classified into two groups:
photogrammetic calibration and self-calibration. We refer the reader to Zhang
(2000) and Luong and Faugeras (1997) to obtain examples and more details
about these approaches.
Illumination analysis and compensation
Other unknown parameters during face analysis are the lighting characteristics
of the environment in which the user is being filmed. The number, origin, nature
and intensity of the light sources of the scene can significantly transform the
appearance of a face. Face reflectance is not uniform all over the face and, thus,
is very difficult to model.
There are two major categories of reflected light:
1.
Diffuse Reradiation (scattering): this occurs when the incident light pen-
etrates the surface and is reflected equally in all directions.
2.
Specular Reflection: light does not penetrate the object, but it is instead
directly reflected from its outer surface.
The intensity of the pixels that we get from the image of the face is the result of
the light from the recorded scene (i.e., the face) scattered towards the camera
lens. The nature of the reflection phenomenon requires the knowledge of some
vector magnitudes (Figure 2):
Search WWH ::
Custom Search