Difference between revisions of "3D Structure From Visual Motion"

From Chrome
Jump to: navigation, search
Line 11: Line 11:
 
* [http://www.dei.polimi.it/people/marcon Marco Marcon]
 
* [http://www.dei.polimi.it/people/marcon Marco Marcon]
  
With possibly special guest
+
With possibly special guests
 
* [http://www.dei.polimi.it/people/ceriani Simone Ceriani]
 
* [http://www.dei.polimi.it/people/ceriani Simone Ceriani]
 
* [http://personal.disco.unimib.it/sorrenti/ Domenico G. Sorrenti]
 
* [http://personal.disco.unimib.it/sorrenti/ Domenico G. Sorrenti]
Line 19: Line 19:
 
This is the schedule foreseen for the course. The timing refers to the duration of the room reservation not necessarily the duration of the lecture ;-)
 
This is the schedule foreseen for the course. The timing refers to the duration of the room reservation not necessarily the duration of the lecture ;-)
  
*'''15/02/2010 14:30-18:30 in Sala Seminari DEI'''
+
*'''15/02/2010 14:30-18:30 in Sala XXX DEI'''
 
** Course introduction (M. Matteucci)
 
** Course introduction (M. Matteucci)
 
** Correspondence analysis: tracking and ransac (D. Migliore)
 
** Correspondence analysis: tracking and ransac (D. Migliore)
*'''17/02/2010 14:30-18:30 in Aula PT1 DEI'''
+
*'''17/02/2010 14:30-18:30 in Sala XXX DEI'''
 
** Projection model and projection matrix (V. Caglioti)
 
** Projection model and projection matrix (V. Caglioti)
 
** Fundamental and Essential matrices (V. Caglioti)
 
** Fundamental and Essential matrices (V. Caglioti)
*'''22/02/2010 14:30-18:30 in Sala Seminari DEI'''
+
*'''22/02/2010 14:30-18:30 in Sala XXX DEI'''
 
** Motion extraction and 3D reconstruction (V. Caglioti)  
 
** Motion extraction and 3D reconstruction (V. Caglioti)  
*'''24/02/2010 14:30-18:30 in Sala Seminari DEI'''
+
*'''24/02/2010 14:30-18:30 in Sala XXX DEI'''
 
**Stereo e Omnidirectional odometry (D. Migliore)
 
**Stereo e Omnidirectional odometry (D. Migliore)
 
**Uncalibrated visual odometry (V. Caglioti)
 
**Uncalibrated visual odometry (V. Caglioti)
 
**Omnidirectional odometry (V. Caglioti)  
 
**Omnidirectional odometry (V. Caglioti)  
*'''26/02/2010 14:30-18:30 in Sala Seminari DEI'''     
+
*'''26/02/2010 14:30-18:30 in Sala XXX DEI'''     
 
** Optical flow (M. Marcon)
 
** Optical flow (M. Marcon)
 
** Combined estiamation of 3D structure and camera egomotion (M.Marcon)  
 
** Combined estiamation of 3D structure and camera egomotion (M.Marcon)  
*'''01/03/2010 14:30-18:30 in Aula PT1'''
+
*'''01/03/2010 14:30-18:30 in Sala XXX DEI'''
 
** Bayesian Filtering and SLAM (M. Matteucci)
 
** Bayesian Filtering and SLAM (M. Matteucci)
*'''03/03/2010 14:30-18:30 in Aula PT1 DEI'''
+
*'''03/03/2010 14:30-18:30 in Sala XXX DEI'''
 
** MonoSLAM, PTAM and FrameSLAM (M. Matteucci, D.G. Sorrenti)
 
** MonoSLAM, PTAM and FrameSLAM (M. Matteucci, D.G. Sorrenti)
*'''05/03/2010 14:30-18:30 in Sala Seminari DEI'''
+
*'''05/03/2010 14:30-18:30 in Sala XXX DEI'''
 
** 3D without 3D: plenoptic methods, lumigraph, albedo, non Lambertian surfaces (M. Marcon)
 
** 3D without 3D: plenoptic methods, lumigraph, albedo, non Lambertian surfaces (M. Marcon)
  
Line 67: Line 67:
 
** ''Parallel Tracking and Mapping for Small AR Workspaces'' by Georg Klein and David Murray [http://www.robots.ox.ac.uk/~gk/publications/KleinMurray2007ISMAR.pdf]
 
** ''Parallel Tracking and Mapping for Small AR Workspaces'' by Georg Klein and David Murray [http://www.robots.ox.ac.uk/~gk/publications/KleinMurray2007ISMAR.pdf]
 
** ''FrameSLAM: from Bundle Adjustment to Realtime Visual Mappping'' by Kurt Konolige and Motilal Agrawal [http://www.ai.sri.com/~agrawal/frameslam.pdf]
 
** ''FrameSLAM: from Bundle Adjustment to Realtime Visual Mappping'' by Kurt Konolige and Motilal Agrawal [http://www.ai.sri.com/~agrawal/frameslam.pdf]
 +
 +
== Course Evaluation ==

Revision as of 18:15, 13 October 2011


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 (myself) the course is held by (in order of appearance)

With possibly special guests

Course Schedule

This is the schedule foreseen for the course. The timing refers to the duration of the room reservation not necessarily the duration of the lecture ;-)

  • 15/02/2010 14:30-18:30 in Sala XXX DEI
    • Course introduction (M. Matteucci)
    • Correspondence analysis: tracking and ransac (D. Migliore)
  • 17/02/2010 14:30-18:30 in Sala XXX DEI
    • Projection model and projection matrix (V. Caglioti)
    • Fundamental and Essential matrices (V. Caglioti)
  • 22/02/2010 14:30-18:30 in Sala XXX DEI
    • Motion extraction and 3D reconstruction (V. Caglioti)
  • 24/02/2010 14:30-18:30 in Sala XXX DEI
    • Stereo e Omnidirectional odometry (D. Migliore)
    • Uncalibrated visual odometry (V. Caglioti)
    • Omnidirectional odometry (V. Caglioti)
  • 26/02/2010 14:30-18:30 in Sala XXX DEI
    • Optical flow (M. Marcon)
    • Combined estiamation of 3D structure and camera egomotion (M.Marcon)
  • 01/03/2010 14:30-18:30 in Sala XXX DEI
    • Bayesian Filtering and SLAM (M. Matteucci)
  • 03/03/2010 14:30-18:30 in Sala XXX DEI
    • MonoSLAM, PTAM and FrameSLAM (M. Matteucci, D.G. Sorrenti)
  • 05/03/2010 14:30-18:30 in Sala XXX 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

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:
    • Unified Inverse Depth Parametrization for Monocular SLAM by J.M.M. Montiel, Javier Civera, and Andrew J. Davison [1]
    • Parallel Tracking and Mapping for Small AR Workspaces by Georg Klein and David Murray [2]
    • FrameSLAM: from Bundle Adjustment to Realtime Visual Mappping by Kurt Konolige and Motilal Agrawal [3]

Course Evaluation