作者: Radu Bogdan Rusu , Nico Blodow , Michael Beetz , None
DOI: 10.1109/ROBOT.2009.5152473
关键词:
摘要: In our recent work [1],[2], we proposed Point Feature Histograms (PFH) as robust multi-dimensional features which describe the local geometry around a point p for 3D point cloud datasets. In this paper, we modify their mathematical expressions and perform a rigorous analysis on their robustness and complexity for the problem of 3D registration for overlapping point cloud views. More concretely, we present several optimizations that reduce their computation times drastically by either caching previously computed values or …