Metrically-Scaled Monocular SLAM using Learned Scale Factors

© 2020 IEEE. We propose an efficient method for monocular simultaneous localization and mapping (SLAM) that is capable of estimating metrically-scaled motion without additional sensors or hardware acceleration by integrating metric depth predictions from a neural network into a geometric SLAM factor...

Full description

Bibliographic Details
Main Authors: Greene, W. Nicholas (William Nicholas) (Author), Roy, Nicholas (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor)
Format: Article
Language:English
Published: IEEE, 2021-11-03T20:03:07Z.
Subjects:
Online Access:Get fulltext