User manual
Table Of Contents
- Introduction
- Getting started with smallv
- Stereo Geometry
- Calibration
- API Reference – C++ Language

Small Vision System User Manual 27
horopter range of 16; see Section 4 for technical details.
Changing the disparity search size affects the time it takes to process stereo. A search space of 32
pixels will take about twice as long as a search space of 16 pixels. It will actually take a little less, because
there is some fixed overhead in processing the images. Obviously, the smallest search range necessary for
the application is the best choice.
Disparities are interpolated to 1/16 pixel, so a search range of 16 means that there are 256 integral
disparity values, ranging from 0 (no disparity) to 255 (maximum disparity of 15 15/16 pixels).
The search range is selected using the Disparities value in the Parameters area. When the
range is switched, the disparity image will lighten or darken to reflect the changed values of disparities.
2.4.5 Adjusting the Horopter
The stereo rectification procedure sets up the horopter, or depth of field of stereo, so that objects are
matched from infinity to some distance in front of the camera. Objects closer than this near point will not
be matched, and will produce random disparity readings. The near point distance is a function of the
search size, the stereo baseline, and the focal length of the camera lenses. One can adjust the horopter by
adjusting a horizontal X offset, moving the depth range closer to the camera. The depth range desired in
the end application would drive the setting of this parameter. For example, if the image does not contain
any objects farther than a certain distance, the X offset can be adjusted so that the far point of the horopter
is at that distance. Changing the X offset causes the disparity display to get uniformly lighter or darker, as
the horopter is shifted and the disparity of an object changes. Adjusting the horopter to cover a specific
range of depths is discussed in Section 4.
2.4.6 Pixel Information
SVS will show pixel information when the left button is clicked in either SVS display window. The
information is displayed in the text window in the format:
x232 y120 [131] [11] Xaaa Ybbb Zccc
The image coordinates of the mouse are given by the x,y values. The values in square brackets are the
pixel values of the left and right images. If the right image is displaying stereo disparities, then the right
value is the disparity value. Finally, the X,Y,Z values are the real-world coordinates of the image point,
in mm. Note that X,Y,Z values are calculated only if stereo is being computed, and to be accurate, a good
calibration file must be input (Section 4).
2.4.7 Correlation Window Size
The size of the correlation window used for matching affects the results of the stereo processing. A
larger window will produce smoother disparity images, but will tend to “smear” objects, and will miss
smaller objects. A smaller window will give more spatial detail, but will tend to be noisy. Typical sizes
Figure 2-9 Uncalibrated (left) and calibrated (right) disparity images.