Abstract

Most 3D recording methods generate multiple partial recon- structions that must be integrated to form a complete model. The coarse registration step roughly aligns the parts with each other. Several meth- ods for coarse registration have been developed that are based on match- ing points between difierent parts. These methods look for interest points and use a point signature that encodes the local surface geometry to find corresponding points. We developed a technique that is complementary to these methods. Local descriptions can fail or can be highly ineficient when the surfaces contain local symmetries. In stead of discarding these regions, we introduce a method that first uses the Gaussian image to detect planar, cylindrical and conical regions and uses this information to compute the rigid motion between the patches. For combining the information from multiple regions to a single solution, we use a a Hough space that accumulates votes for candidate transformations. Due to their symmetry, they update a subspace of parameter space in stead of a sin- gle bin. Experiments on real range data from difierent views of the same ob ject show that the method can find the rigid motion to put the patches in the same coordinates system. Keywords : Surface Registration, Surface geometry, Shape.