Analysis of mixed reality cross-device localization algorithms based on point cloud registration

Analysis of mixed reality cross-device localization
algorithms based on point cloud registration

State of art approaches for localization and mapping is based on local features in images. Along with this, modern augmented and mixed reality devices allow building a mesh of the surrounding space. Using this mesh map, we can solve the problem of cross-device localization. This approach is independent of the type of feature descriptors and SLAM used onboard the AR / MR device. The mesh could be reduced to the points cloud, which takes only vertices. We propose the approach for co-localization of AR / MR devices using point clouds which do not depend on algorithms onboard the device. We analyzed various algorithms for registering point clouds and discuss of it limitation for the co-localization problem.

Read the article


Authors:

Alexander Osipov (Innopolis University, a.osipov@innopolis.university)


Mikhail Ostanin (Innopolis University, m.ostanin@innopolis.ru)


Alexandr Klimchik (Innopolis University, a.klimchik@innopolis.ru)

in Proceedings of the Third International Conference Nonlinearity,Information and Robotics 2022, August 24, 2022