Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification.
Alessandro BergamoSudipta N. SinhaLorenzo TorresaniPublished in: CVPR (2013)
Keyphrases
- structure from motion
- bundle adjustment
- image sequences
- missing data
- computer vision
- camera parameters
- feature extraction
- point cloud
- feature tracking
- reconstruction from multiple images
- image classification
- machine learning
- focal length
- relative pose
- image based localization
- model selection
- camera motion
- feature vectors
- scene structure
- feature correspondences
- camera positions
- reprojection error