SAM-Net: Semantic probabilistic and attention mechanisms of dynamic objects for self-supervised depth and camera pose estimation in visual odometry applications.
Binchao YangXinying XuJinchang RenLan ChengLei GuoZhe ZhangPublished in: Pattern Recognit. Lett. (2022)
Keyphrases
- visual odometry
- camera pose estimation
- camera pose
- depth images
- pose estimation
- ego motion
- structure from motion
- autonomous navigation
- feature points
- camera motion
- point correspondences
- focal length
- bundle adjustment
- position and orientation
- depth information
- camera parameters
- closed form solutions
- depth map
- single view
- camera calibration
- image sequences
- multi view
- d objects
- field of view
- urban environments
- mobile robot
- viewpoint