3D Structure From Visual Motion
Contents
Course Aim & Organization
This is a description page for the PhD course on 3D Structure from Visual Motion: Novel Techniques in Computer Vision and Autonomous Robots/Vehicles. It is meant to present modern techniques to simultaneously estimate the unknown motion of a camera while reconstructing the 3D structure of the observed world to be applied un scientific fields such as: 3D reconstruction, autonomous robot navigation, aerial/field surveying, unmanned vehicle maneuvering, etc.
Teachers
Although formally entitled to just one of the teachers the course is held by (in order of appearance)
Course Schedule
21/05/2009 [14:30-18:30] Sala Seminari (DEI)
- Course introduction (M. Matteucci)
- Projection model and projection matrix (V. Caglioti)
25/05/2009 [14:30-17:30] Sala Conferenze (DEI)
- Correspondence analysis: tracking and ransac (D. Migliore)
29/05/2009 [14:30-18:30] Sala Conferenze (DEI)
- Fundamental and Essential matrices (V. Caglioti)
- Motion extraction and 3D reconstruction (V. Caglioti)
- Visual odometry (V. Caglioti)
03/06/2009 [09:30-13:30] Sala Seminari (DEI)
- Correspondences tracking and analysis(M. Marcon)
- Combined estiamation of 3D structure and camera egomotion (M.Marcon)
05/06/2009 [14:30-18:30] Sala Seminari (DEI)
- Perspective ambiguity (M. Marcon)
- Non rigid structure from motion and Hierarchical Shape Priors (M. Marcon)
- Implicit formulation (M. Marcon)
08/06/2009 [09:30-13:30] Sala Seminari (DEI)
- Bayesian filtering (M. Matteucci)
- SLAM Filter implementations (M. Matteucci)
12/06/2009 [09:30-13:30] Sala Seminari (DEI)
- Monocular SLAM (M. Matteucci)
15/06/2009 [09:30-13:30] Sala Seminari (DEI)
- Stereo SLAM (D. Migliore)
- Omnidirectional SLAM (D. Migliore)
19/06/2009 [09:30-13:30] Sala Seminari (DEI)
- TBD (TBD)
22/06/2009 [09:30-13:30] Sala Seminari (DEI)
- 3D without 3D: plenoptic methods, lumigraph, albedo, non Lambertian surfaces (M. Marcon)
Course Material & Referencies
The following is some suggested material to follow the course lectures.
Slides and lecture notes
- Camera geometry, single view, and two view geometry material
- Two view geometry and visual odometry material
- Correspondence analysis and RANSAC
- Optical flow tracking and egomotion estimation
- Structure from Motion
- Bayesian Filtering, Kalman Filtering, and SLAM
- Simultaneous Localization and Mapping a.k.a. SLAM!
- Monocular SLAM
- Stereo and Omnidirectional SLAM
- 3D without 3D
Suggested Bibliography
- R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision, Cambridge University Press, March 2004.
- S. Thrun, W. Burgard, D. Fox. Probabilistic Robotics, MIT Press, September 2005.
- Papers you might find useful to deepen your study:
- ...
