Stereo Camera Technology#

This topic describes the principle behind stereo vision technology.

In stereo vision, 3D information about a scene can be extracted by comparing two images taken from different viewpoints. The idea behind using a camera pair for measuring depth is the fact that object points appear at different positions in the two camera images depending on their distance from the camera pair.

Very distant object points appear at approximately the same position in both images, whereas very close object points occupy different positions in the left and right camera image. The object points' displacement in the two images is called disparity. The larger the disparity, the closer the object is to the camera. The Stereo Camera Viewer uses the disparity values to calculate the depth maps and point clouds for an image.

In contrast to time of flight, stereo vision is a form of passive sensing. This means that no light or other signals are emitted to measure the runtime and to calculate distances based on that. Instead, only light that is emitted or reflected by the environment is used. Therefore, the Basler products utilizing this sensing method work indoors and outdoors. Also, multiple devices can be used together without interferences between them.

To compute the 3D information, the stereo matching algorithm must be able to find corresponding object points in the images of the left and right cameras. For this, the algorithm requires texture in the images, meaning changes in intensity due to patterns or the objects' surface structure. This texture is provided by the camera's integrated projector.

Stereo matching isn't possible if the target is completely untextured, such as a flat white wall without any visible surface structure. The stereo matching method used by Stereo ace cameras is called Semi-Global Matching (SGM). This provides the best trade-off between speed and accuracy, even for very fine structures.

For stereo matching, the position and orientation of the left and right cameras relative to each other has to be known with very high accuracy. This is achieved by calibration. The Stereo ace cameras are calibrated during production.

There may be situations when a Stereo ace camera loses its calibration, e.g., through shock or vibration during transport or use. A sure sign that the calibration has become corrupted is that the camera suddenly doesn't deliver any 3D data anymore. If that happens, the camera has to be recalibrated. See the Camera Calibration topic for details.