3D Structure From Visual Motion

From Chrome
Revision as of 23:48, 16 May 2012 by Matteo (Talk | contribs)

Jump to: navigation, search
Recent news you should be aware of ...
 * 17/05/2012: Change in the lecture topics in the schedule
 * 18/04/2012: Change of Fri 20/04 room: lecture will be in D2.2
 * 11/04/2012: Rooms for classes updated and first class material published.
 * 18/03/2012: Detailed course schedule published!
 * 06/03/2012: Detailed course schedule coming out soon if you did not received the notification email please contact me!

This is a description page for the PhD course on 3D Structure from Visual Motion: Novel Techniques in Computer Vision and Autonomous Robots/Vehicles. This course can be taken also by students from Computer Engineering in the Laurea Magistrale track.

Course Aim & Organization

Simultaneous estimate of the unknown motion of a camera (or the vehicle this camera is upon) while reconstructing the 3D structure of the observed world is a challenging task that has been deeply studied in the recent literature. The PhD course on 3D Structure from Visual Motion: Novel Techniques in Computer Vision and Autonomous Robots/Vehicles will present modern techniques to simultaneously estimate the unknown motion of a camera while reconstructing the 3D structure of the observed world to be applied in scientific fields such as: 3D reconstruction, autonomous robot navigation, aerial/field surveying, unmanned vehicle maneuvering, etc.


Although formally entitled to just one of the teachers (myself) the course is also held by (in order of appearance)

Course Schedule

All lectures are on:

  • Friday from 15:15 to 18:15

In the following you find the detailed schedule for the course and the rooms booked for it. In brackets you find also the lecturer for each specific topic.

  • 3d Vision Basics (9 hours)
    • 30/03/2012 (Sala conferenze - DEI): Course introduction (1h M. Matteucci)
    • 30/03/2012 (Sala conferenze - DEI): Feature extraction, matching and tracking (2h M. Matteucci)
    • 13/04/2012 (Aula PT1 - Piano terra DEI): Projection model and projection matrix (3h V. Caglioti)
    • 20/04/2012 (D2.2 - coord 45.47737, 9.23517): Fundamental and Essential matrices (3h V. Caglioti)
  • Structure from Motion and Visual Odometry (6 hours)
    • 27/04/2012 (Sala Seminari - Piano terra DEI): Optical flow (1.5h M. Marcon)
    • 27/04/2012 (Sala Seminari - Piano terra DEI): Combined estiamation of 3D structure and camera egomotion (1.5h M.Marcon)
    • 04/05/2012 (Sala Seminari - Piano terra DEI): Motion extraction and 3D reconstruction (3h V. Caglioti)
  • Unconventional Visual Odometry (6 hours)
    • 11/05/2012 (Sala Seminari - Piano terra DEI): Uncalibrated visual odometry (1.5h V. Caglioti)
    • 11/05/2012 (Sala Seminari - Piano terra DEI): Omnidirectional odometry (1.5h V. Caglioti)
  • Simulataneous Localization and Mapping (3 hours)
    • 18/05/2012 (Sala Seminari - Piano terra DEI): From Bayesian Filtering to SLAM (1.5h M. Matteucci)
    • 18/05/2012 (Sala Seminari - Piano terra DEI): EKF-Based SLAM (1.5h M. Matteucci)
  • Visual SLAM (6 hours)
    • 25/05/2012 (Aula PT1 - Piano terra DEI): EKF-based Monocular SLAM (3h D.G. Sorrenti)
    • 01/06/2012 (Aula PT1 - Piano terra DEI): Stereo and Omnidirectional visual SLAM (3h M. Matteucci)
    • 08/06/2012 (Sala Seminari - Piano terra DEI): Why filters? PTAM and FrameSLAM (3h M. Matteucci)
  • 3D without 3D (3 hours)
    • 15/06/2012 (Sala Seminari - Piano terra DEI): Plenoptic methods, lumigraph, albedo, non Lambertian surfaces (3h 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:
    • Simultaneous Localization and Mapping (SLAM): Part I The Essential Algorithms. H. Durrant-Whyte, T. Bailey [1]
    • Unified Inverse Depth Parametrization for Monocular SLAM by J.M.M. Montiel, Javier Civera, and Andrew J. Davison [2]
    • Parallel Tracking and Mapping for Small AR Workspaces by Georg Klein and David Murray [3]
    • FrameSLAM: from Bundle Adjustment to Realtime Visual Mappping by Kurt Konolige and Motilal Agrawal [4]

Libraries and Demos


Course Evaluation

The course evaluation will be done on the basis of a project which could be completed also in groups of two people. In the case of PhD students this project could/should be somehow related to their research interests.