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

From Chrome
Jump to: navigation, search
(Course Schedule)
 
(31 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
Recent news you should be aware of ...
 +
  * New schedule published with teachers specified
 +
  * The schedule of 2014 lectures is out!
 +
  * A new version of the course is scheduled for the year 2013/2014
 +
 +
<!--
 +
  * 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.
 
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.
  
Line 12: Line 25:
 
* [http://www.dei.polimi.it/people/matteucci Matteo Matteucci]
 
* [http://www.dei.polimi.it/people/matteucci Matteo Matteucci]
 
* [http://www.dei.polimi.it/people/caglioti Vincenzo Caglioti]
 
* [http://www.dei.polimi.it/people/caglioti Vincenzo Caglioti]
* [http://www.dei.polimi.it/people/marcon Marco Marcon]
+
<!--* [http://www.dei.polimi.it/people/marcon Marco Marcon]-->
 
+
<!--* [http://personal.disco.unimib.it/sorrenti/ Domenico G. Sorrenti]-->
With possibly special guests
+
* [http://www.dei.polimi.it/people/ceriani Simone Ceriani]
+
* [http://personal.disco.unimib.it/sorrenti/ Domenico G. Sorrenti]
+
  
 
===Course Schedule===
 
===Course Schedule===
  
  Please consider this schedule as tentative ...
+
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:
  The course will start in March 2012, details about lecture time will be available soon
+
 
 +
*12/05/2014: Feature extraction, matching and tracking (Matteo Matteucci)
 +
*14/05/2014: Projection model and projection matrix (Vincenzo Caglioti)
 +
*16/05/2014: Fundamental and Essential matrices (Vincenzo Caglioti)
 +
*19/05/2014: Structure from Motion and Visual Odometry (Vincenzo Caglioti)
 +
*21/05/2014: Simulataneous Localization and Mapping (Matteo Matteucci)
 +
*23/05/2014: Unconventional Visual Odometry: Uncalibrated visual odometry, Omnidirectional odometry (Vincenzo Caglioti)
 +
*26/05/2014: Visual SLAM with filters (Matteo Matteucci)
 +
*28/05/2014: Visual SLAM without filters (Matteo Matteucci)
 +
 
 +
The room for all the lectures is: "Aula Seminari Alessandra Alario" 4th Floor - Building 21 Campus Leonardo.
  
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.  
+
<!--In the following you find a tentative syllabus for the course.  
  
*'''3d Vision Basics''' (9 hours)
+
*'''3d Vision Basics'''  
** Course introduction (1h M. Matteucci)
+
** Course introduction  
** Feature extraction, matching and tracking (2h M. Matteucci)
+
** Feature extraction, matching and tracking
** Projection model and projection matrix (3h V. Caglioti)
+
** Projection model and projection matrix  
** Fundamental and Essential matrices (3h V. Caglioti)
+
** Fundamental and Essential matrices
*'''Structure from Motion and Visual Odometry''' (6 hours)
+
*'''Structure from Motion and Visual Odometry'''  
** Optical flow (1.5h M. Marcon)
+
** Optical flow  
** Combined estiamation of 3D structure and camera egomotion (1.5h M.Marcon)
+
** Combined estiamation of 3D structure and camera egomotion
** Motion extraction and 3D reconstruction (3h V. Caglioti)
+
** Motion extraction and 3D reconstruction  
*'''Unconventional Visual Odometry''' (3 hours)
+
*'''Unconventional Visual Odometry'''  
**Stereo e Omnidirectional odometry (TBD)
+
** Uncalibrated visual odometry
**Uncalibrated visual odometry (1.5h V. Caglioti)
+
** Omnidirectional odometry  
**Omnidirectional odometry (1.5h V. Caglioti)
+
*'''Simulataneous Localization and Mapping'''  
*'''Simulataneous Localization and Mapping''' (3 hours)
+
** From Bayesian Filtering to SLAM  
** From Bayesian Filtering to SLAM (1.5h M. Matteucci)
+
** EKF-Based SLAM  
** EKF-Based SLAM (1.5h M. Matteucci)
+
*'''Visual SLAM'''  
*'''Visual SLAM''' (6 hours)
+
** EKF-based Monocular SLAM
** EKF-based Monocular SLAM (3h D.G. Sorrenti)
+
** Stereo and Omnidirectional visual SLAM
** Why filters? PTAM and FrameSLAM (3h M. Matteucci)
+
** Why filters? PTAM and FrameSLAM -->
*'''3D without 3D''' (3 hours)
+
<!--
 +
*'''3D without 3D'''  
 
** Plenoptic methods, lumigraph, albedo, non Lambertian surfaces (3h M. Marcon)
 
** Plenoptic methods, lumigraph, albedo, non Lambertian surfaces (3h M. Marcon)
 +
-->
  
 
==Course Material & Referencies==
 
==Course Material & Referencies==
Line 52: Line 74:
  
 
===Slides and lecture notes===
 
===Slides and lecture notes===
 +
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/FeatureTracking.pdf Correspondence analysis and RANSAC] (2011-2012 ed.)
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/MultipleViewGeometry.pdf Camera geometry, single view, and two view geometry material]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/MultipleViewGeometry.pdf Camera geometry, single view, and two view geometry material]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/VisualOdometry.pdf Two view geometry and visual odometry material]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/VisualOdometry.pdf Two view geometry and visual odometry material]
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/FeatureTracking.pdf Correspondence analysis and RANSAC]
 
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/FeatureTrackingEgomotion.pdf Optical flow tracking and egomotion estimation]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/FeatureTrackingEgomotion.pdf Optical flow tracking and egomotion estimation]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/StructureFromMotion.pdf Structure from Motion]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/StructureFromMotion.pdf Structure from Motion]
Line 63: Line 85:
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/PanoramicVisualOdometry.pdf Panoramic Visual Odomentry]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/PanoramicVisualOdometry.pdf Panoramic Visual Odomentry]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/PTAM.pdf Parallel Tracking and Mapping]
 
* [http://home.dei.polimi.it/matteucc/lectures/3DSFVM/PTAM.pdf Parallel Tracking and Mapping]
* 3D without 3D
+
<!-- * 3D without 3D -->
  
 
===Suggested Bibliography===
 
===Suggested Bibliography===

Latest revision as of 22:02, 11 May 2014

Recent news you should be aware of ...
 * New schedule published with teachers specified
 * 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)

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: Feature extraction, matching and tracking (Matteo Matteucci)
  • 14/05/2014: Projection model and projection matrix (Vincenzo Caglioti)
  • 16/05/2014: Fundamental and Essential matrices (Vincenzo Caglioti)
  • 19/05/2014: Structure from Motion and Visual Odometry (Vincenzo Caglioti)
  • 21/05/2014: Simulataneous Localization and Mapping (Matteo Matteucci)
  • 23/05/2014: Unconventional Visual Odometry: Uncalibrated visual odometry, Omnidirectional odometry (Vincenzo Caglioti)
  • 26/05/2014: Visual SLAM with filters (Matteo Matteucci)
  • 28/05/2014: Visual SLAM without filters (Matteo Matteucci)

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


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

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.