Abstract | ||
---|---|---|
This paper describes a method of automatically performing the registration of two range images that have significant overlap. We first find points of interest in the intensity data that comes with each range image. Then we perform a triangulation of the 3D range points associated with these 2D interest points. All possible pain of triangles between the two 3D triangulations are then matched. The fact that we have 3D data available makes it possible to efficiently prune matches. We do this pruning by using a simple and effective set of compatibility tests between potentially matching triangles and vertices. The best match is the one that aligns the larqest number of interest points between the two mnge images. The algorithms are demonstrated experimentally on a number of different range image pairs. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/IM.1999.805349 | 3DIM |
Keywords | Field | DocType |
interest point,compatibility test,overlapping range image,best match,possible pain,range point,larqest number,intensity data,different range image pair,mnge image,range image,computational geometry,point of interest,testing,information technology,error correction,pruning,robustness,triangulation,solid modeling,image registration | Template matching,Computer vision,Feature detection (computer vision),Computer science,Range segmentation,Computational geometry,Image processing,Triangulation (social science),Artificial intelligence,Point of interest,Image registration | Conference |
ISBN | Citations | PageRank |
0-7695-0062-5 | 31 | 2.11 |
References | Authors | |
14 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gerhard Roth | 1 | 264 | 16.52 |