Bayesian cue integration of structure from motion and CNN-based monocular depth estimation for autonomous robot navigation.
Fuseini MumuniAlhassan MumuniPublished in: Int. J. Intell. Robotics Appl. (2022)
Keyphrases
- structure from motion
- depth estimates
- depth estimation
- image sequences
- depth map
- stereo vision
- bundle adjustment
- depth information
- stereo matching
- computer vision
- missing data
- camera motion
- point cloud
- d scene
- real scenes
- stereo pair
- dynamic scenes
- three dimensional
- optical flow
- pose estimation
- super resolution
- multi view
- scene understanding
- vision system
- motion estimation
- high quality
- range images
- maximum likelihood
- feature matching
- feature points
- object boundaries
- disparity map