Research Article
A Point Cloud Registration Algorithm Based on Feature Extraction and Matching
Algorithm 1
Point cloud initial registration algorithm.
Input: source cloud , target cloud | Output: Registered point cloud | 1: Extract feature points from the source cloud and the target cloud separately | 2: for all points do | 3: if is a key point then | 4: | 5: end if | 6: end for | 7: for all do | 8: | 9: end for | 10: gets and in the same way | 11: for point do | 12: gets | 13: end for | 14: for point do | 15: most similar point to in | 16: | 17: end for | 18: getRemainingCorrespondences(); | 19: estimateRigidTransformation(,); | 20: transformPointCloud(,,transform_matrix); | 21: Return ; |
|