METHOD AND DEVICE FOR EXTRACTING LOCAL FEATURES OF THREE-DIMENSIONAL POINT CLOUD

摘要

A method and device for extracting local features of a three-dimensional point cloud. Angle information and concave-convex information about a feature point to be extracted and a point of an adjacent body element are calculated based on a local reference system corresponding to points of each body element, and a feature relationship between the two points can be calculated accurately. The property of invariance in translation and rotation is possessed. In addition, since concave-convex information about a local point cloud is contained during extraction, the problem of inaccurate extraction caused by ignoring concave-convex ambiguity in previous 3D local feature description is solved. During normalization processing, exponential normalization processing and second-normal-form normalization processing are adopted, and the problem of inaccurate similarity calculation caused by a circumstance that a few elements in a vector are too large or too small during feature extraction is solved, so that the accuracy of extracted three-dimensional local features can be improved.