Premium
A research of surgical navigation system of mixed reality based on image registration
Author(s) -
Zhou Na,
Yin Xiangyun,
Wang Lijun
Publication year - 2020
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1002/sdtp.13743
Subject(s) - computer vision , point cloud , computer science , artificial intelligence , iterative closest point , process (computing) , image registration , feature (linguistics) , point (geometry) , augmented reality , computer graphics (images) , image (mathematics) , mathematics , linguistics , philosophy , geometry , operating system
This paper studies a registration method that is more suitable for using Microsoft HoloLens as a surgical navigation instrument. The most important step in the surgical navigation process is to register the virtual model with the corresponding lesion. Our registration method is mainly as follows: first use the 3D model recognition in vuforia for coarse registration; then extract the point cloud data of model and real scene scanned by HoloLens; finally use the normal vector geometric features to extract the feature points of the point cloud data, and then use the ICP algorithm Perform fine registration. Our registration method can solve the problem that the traditional ICP algorithm is easy to fall into a local optimum, and it can also improve the registration accuracy to a certain extent.