<A ID="pgfId999337"></A>
PETS2000 Camera Calibration
Here is a calibration for of the camera for the test and training sequences.
FocalLength f=1360
ImageCentre (u,v) = (384, 288)
Homogeneous Transform
T
=
0.77900

0.18953

0.59769

0.00000

0.62703

0.23676

0.74215

0.00000

0.00084

0.95290

0.30327

0.00000

3479.05000

849.37500

33783.70000

1.00000

The transformation takes a coordinated frame with the xy plane as the ground plane and the Z axis vertical to the camera frame with nodal point at the origin, the z axis along the camera axis and the image plane aligned with the xy plane. To convert to raster coordinates you need to scale by the focal length and add the ImageCentre. Note real world measurements are in millimeters and image measurements are in pixels.
So let
x
be a point in the coordinate frame of the ground plane. Then that point in the coordinate frame of the camera is
x
T
. The image of the point in raster coordinates is then given by
(f(
x
T
)
x
/(
x
T
)
z
+ u, f(
x
T
)
y
/(
x
T
)
z
+ v)
For example consider the point at the origin of the ground plane coordinates
x
= (0,0,0,1). Then
x
T
= (3479.05, 849.375, 33783.7) and image of the point in raster coordinates is given by
(1360 x 3479.05 / 33783.7 + 384, 1360 x 849.375 / 33783.7 + 288)
= (140.0 + 384, 34.2 + 288)
= (244, 253.8)
Similarly a point 1 meter above the ground plane origin
x
= (0, 0, 1000, 1) would be (3479.05 + 0.84, 849.375  952.9, 33783.7  303.27) = (3478.21, 1802.275, 33480.43). The image of the point is then given by
(1360 x  3478.21/ 33480.43 + 384, 1360 x 1802.275 / 33480.43 + 288)
= (141.3 + 384, 73.2 + 288)
= (242.7, 214.8)