BooM-Vio: Bootstrapped Monocular Visual-Inertial Odometry with Absolute Trajectory Estimation through Unsupervised Deep Learning.
Kyle LindgrenSarah LeungWilliam D. NothwangE. Jared ShamwellPublished in: ICAR (2019)
Keyphrases
- deep learning
- unsupervised learning
- inertial sensors
- deep architectures
- weakly supervised
- angular velocity
- restricted boltzmann machine
- deep belief networks
- machine learning
- unsupervised feature learning
- sensor fusion
- supervised learning
- position and orientation
- semi supervised
- visual odometry
- image sequences
- pose estimation
- visual features
- d objects
- higher order
- object class
- viewpoint
- multiscale
- training data
- computer vision
- data mining