Technical Specs

where 𝑓 is the focal length after rectification in pixels and 𝑡 is the stereo baseline in meters, which was determined
during calibration. These values are also transferred over the GenICam interface (see Custom GenICam features
of the rc_visard, Section 8.1.1).
Note: The rc_visard reports a focal length factor via its various interfaces. It relates to the image width for
supporting different image resolutions. The focal length 𝑓 in pixels can be easily obtained by multiplying the
focal length factor by the image width in pixels.
Please note that equations (6.2.1) assume that the coordinate frame is centered in the middle of the image. The
following figure shows the definition of the image coordinate frame.
Fig. 6.2.1: The image coordinate frame’s origin is defined to be at the image’s center – 𝑤 is the image width and
ℎ is the image height.
The same equations, but with the corresponding GenICam parameters are given in Image stream conversions
:(Section 8.1.3).
The set of all object points computed from the disparity image gives the point cloud, which can be used for 3D
modeling applications. The disparity image is converted into a depth image by replacing the disparity value in
each pixel with the value of 𝑃
𝑧
.
Note: Roboception provides software and examples for receiving disparity images from the rc_visard via GigE
Vision and computing depth images and point clouds. See http://www.roboception.com/download.
6.2.3 Confidence and error images
For each disparity image, the rc_visard provides an error image and a confidence image, which give uncertainty
measures for each disparity value. These images have the same resolution and the same frame rate as the disparity
image. The error image contains the disparity error 𝑑
𝑒𝑝𝑠
in pixels corresponding to the disparity value at the same
image coordinates in the disparity image. The confidence image contains the corresponding confidence value 𝑐
between 0 and 1. The confidence is defined as the probability of the true disparity value being within the interval
of three times the error around the measured disparity 𝑑, i.e., [𝑑 − 3𝑑
𝑒𝑝𝑠
, 𝑑 + 3𝑑
𝑒𝑝𝑠
]. Thus, the disparity image
with error and confidence values can be used in applications requiring probabilistic inference. The confidence and
error values corresponding to an invalid disparity measurement will be 0.
The disparity error 𝑑
𝑒𝑝𝑠
(in pixels) can be converted to a depth error 𝑧
𝑒𝑝𝑠
(in meters) using the focal length 𝑓 (in
pixels), the baseline 𝑡 (in meters), and the disparity value 𝑑 (in pixels) of the same pixel in the disparity image:
𝑧
𝑒𝑝𝑠
=
𝑑
𝑒𝑝𝑠
· 𝑓 · 𝑡
𝑑
2
.
(6.2.2)
Combining equations (6.2.1) and (6.2.2) allows the depth error to be related to the depth:
𝑧
𝑒𝑝𝑠
=
𝑑
𝑒𝑝𝑠
· 𝑃
𝑧
2
𝑓 · 𝑡
.
With the focal length and baselines of both rc_visard models and the typical disparity error 𝑑
𝑒𝑝𝑠
of 0.5 pixels, the
depth error can be visualized as shown below.
6.2. Stereo matching 34