Semantic Structure from Motion: A Novel Framework for Joint Object Recognition and 3D Reconstruction.
Sid Ying-Ze BaoSilvio SavaresePublished in: Theoretical Foundations of Computer Vision (2011)
Keyphrases
- structure from motion
- object recognition
- computer vision
- bundle adjustment
- image sequences
- missing data
- camera parameters
- feature tracking
- point cloud
- scene structure
- camera motion
- image correspondences
- reconstruction from multiple images
- d scene
- maximum likelihood
- image features
- optical flow
- camera positions
- urban scenes
- motion stereo