New 3D Vision Technologies at HANNOVER MESSE 2009
Methods for Perspective Matching:
The descriptor-based matching is a revolutionary new matching technology. This method is able to find perspectively distorted objects. It is based on the detection of interest points where gray values are clearly differentiated from neighboring areas (brightness, curvature, corners, spots).
The perspective, deformable matching is also able to match perspectively distorted objects. In contrast to descriptor-based matching, the perspective, deformable matching is edge-based (like HALCON's shape-based matching) and thus can best be used with objects with clearly distinguishable edges.
During stereo processing often the problem occurs that complete areas do not have any texture. To close this information gap, MVTec implemented the multigrid stereo that eliminates the disadvantages of the conventional stereo method. After processing by multigrid stereo, the areas without information appear as proper edges and structures. Thus, multigrid stereo can bridge texture gaps in stereo images and delivers highly accurate results.
Furthermore, HALCON 9.0 provides new operators for sheet-of-light measurement, which extract projected laser lines and thus generate a 2 1/2 D model.
3D Camera Calibration:
HALCON disposes of a unique 3D camera calibration. By this method, the internal and external camera parameters and pose are determined and pixel coordinates can be converted into world coordinates. Thus, robot control becomes easier. In HALCON 9.0, the underlying camera model for 3D calibration was enhanced to also eliminate complex distortions as well as alignment errors of the lenses. Thus, the accuracy of results of 3D algorithms, e.g., 3D matching or stereo, gets enhanced significantly.
Conclusion: HALCON 9.0 provides comprehensive solutions for all demanding 3D vision challenges.
More information: http://www.halcon.com
More press releases: http://www.mvtec.com/press/