3D vision technology - stereo vision

The 3D coordinates of the visible points on the object surface can be determined based on two or more images that are acquired from different points of view. This is done by calculating the disparity map of the calibrated camera setup.

This technology is particularly suitable for 3D reconstruction, i.e., determining the 3D shape of arbitrary objects. In this context, the technology is especially useful for mid- and large-sized textured objects. The technology can be used for quality inspection of 3D objects, or for the position recognition of 3D objects. Furthermore, stereo vision can be a pre-processing step for 3D matching.

Our software supports stereo vision by calculating the 3D coordinates on the object surface. For a stationary object, this can be done with the aid of a two camera setup (binocular) or multiple cameras (multi-view). Using only one camera, the 3D object shape can be computed from the relative motion between camera and object. Stereo vision is realized either by calculating dense 3D coordinates or distance images, or by determining the coordinates for specific points or edges – especially suitable for highly accurate height measuring. Furthermore, our software offers multigrid stereo – an advanced method to interpolate the 3D data in homogeneous image parts. This method yields higher accuracy for small objects.