Closed-form solution to cooperative visual-inertial structure from motion.
Agostino MartinelliPublished in: CoRR (2018)
Keyphrases
- structure from motion
- closed form solutions
- relative pose
- line correspondences
- bundle adjustment
- camera pose
- closed form
- image sequences
- point correspondences
- camera parameters
- point cloud
- computer vision
- feature tracking
- missing data
- inertial sensors
- reconstruction from multiple images
- camera motion
- special case
- scene structure
- motion estimates
- image alignment
- constrained optimization
- three dimensional
- rigid motion
- line segments
- camera positions
- point features
- factorization method
- optical flow
- reprojection error
- viewpoint
- computational complexity
- multiple views