Abstract | ||
---|---|---|
The ICP (Iterative Closest Point) algorithm is the de facto standard for geometric alignment of three-dimensional models when an initial relative pose estimate is available. The basis of ICP is the search for closest points. Since the development of ICP, k-d trees have been used to accelerate the search. This paper presents a novel search procedure, namely cached k-d trees, exploiting iterative behavior of the ICP algorithm. It results in a significant speedup of about 50% as we show in an evaluation using different data sets. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/3DIM.2007.15 | Montreal, QC |
Keywords | Field | DocType |
icp algorithm,different data set,iterative behavior,geometric alignment,novel search procedure,closest point,cached k-d tree,cached k-d tree search,iterative closest point,k-d tree,significant speedup,industrial automation,three dimensional,iterative algorithm,de facto standard,pose estimation,facility management,computational geometry,search algorithm,side effect,iterative methods,point cloud,nearest neighbor,data sets,k d tree,coordinate system,data processing | De facto standard,Data set,Iterative method,Cache,Computer science,Computational geometry,k-d tree,Algorithm,Speedup,Iterative closest point | Conference |
ISSN | ISBN | Citations |
1550-6185 | 0-7695-2939-4 | 59 |
PageRank | References | Authors |
3.36 | 16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andreas Nuchter | 1 | 114 | 8.69 |
Kai Lingemann | 2 | 555 | 35.98 |
Joachim Hertzberg | 3 | 1571 | 142.29 |