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

Revision as of 00:54, 8 April 2014

Recent news you should be aware of ...
 * The schedule of 2014 lectures is out!
 * A new version of the course is scheduled for the year 2013/2014

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.

Teachers

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

• Matteo Matteucci
• Vincenzo Caglioti
• Marco Marcon
• Domenico G. Sorrenti

Course Schedule

The course schedule for this yeas edition foresees 3 hour lectures from 14:30 to 17:30 (time might change according to participants needs) of the following days: 12/05/2014, 14/05/2014, 16/05/2014, 19/05/2014, 21/05/2014, 23/05/2014, 26/05/2014, 28/05/2014.

The room for all the lectures is: "Aula Seminari Alessandra Alario" 4th Floor - Building 21 Campus Leonardo.

In the following you find a tentative syllabus for the course.

• 3d Vision Basics
  • Course introduction
  • Feature extraction, matching and tracking
  • Projection model and projection matrix
  • Fundamental and Essential matrices
• Structure from Motion and Visual Odometry
  • Optical flow
  • Combined estiamation of 3D structure and camera egomotion
  • Motion extraction and 3D reconstruction
• Unconventional Visual Odometry
  • Uncalibrated visual odometry
  • Omnidirectional odometry
• Simulataneous Localization and Mapping
  • From Bayesian Filtering to SLAM
  • EKF-Based SLAM
• Visual SLAM
  • EKF-based Monocular SLAM
  • Stereo and Omnidirectional visual SLAM
  • Why filters? PTAM and FrameSLAM

Course Material & Referencies

The following is some suggested material to follow the course lectures.

Slides and lecture notes

• Correspondence analysis and RANSAC (2011-2012 ed.)
• Camera geometry, single view, and two view geometry material
• Two view geometry and visual odometry material
• 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
• Panoramic Visual Odomentry
• Parallel Tracking and Mapping

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

TBC

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.