TeachingWs10Cv2

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

3D Computer Vision II Winter Term 2010/2011

Administrative Info

Lecture by Prof. Nassir Navab
Exercises by Cedric Cagniart, Loren Schwarz, Dr. Martin Groher and Hauke Heibel

Type: Lecture Module IN2123
Programs: Informatics (Bachelor, Master)
Biomedical Computing (Master)
Computational Science and Engineering (Master)
Wirtschaftsinformatik (Bachelor, Master)
SWS: 2+2
ECTS: 5 Credits
Course Language: English

NOTE: Only exercise solutions of the theoretic parts will be posted on the web-site.
Matlab exercises will be only discussed in the 'Attestation'.

Time, Location & Requirements

Tuesday 10:30-12:00 MI 03.13.010
Exercises: Thursday 12:30-14:00 MI 03.13.010

Course information and certificate requirements:

  • The classes as well as the exercises will be held in English.
  • The lecture consists of one intermediate exam and a final exam.
  • All exams are hand written, the midterm is a closed-book exam (no notes allowed).

Office hours: Thursday 14:00-16:00 (MI 03.13.043)

Site Content

Announcements

You can take one A4 page (two-sided) with hand-written notes to the final exam. No book or other notes are allowed. The final exam will take place on Thursday, February 10, during our regular Thursday's hours (12:30-14:00), in the regular seminar room (MI 03.13.010).

Overview

Making a computer see was something that leading experts in the field of Artificial Intelligence thought to be at the level of difficulty of a summer student's project back in the sixties. Forty years later the task is still unsolved and seems formidable. A whole field, called Computer Vision, has emerged as a discipline in itself with strong connections to mathematics and computer science and looser connections to physics, the psychology of perception and the neuro sciences.

Over the past decade there has been a rapid development in the understanding and modeling of the geometry of multiple views in computer vision. The theory and practice have now reached a level of maturity where excellent results can be achieved for problems that were unsolved a decade ago, and often thought unsolvable. These tasks and algorithms include problems like:
Given two/three/multiple images, and no further information, compute/estimate:

  • matches between the images
  • the 3D position of the points that generate these matches
  • the cameras that generate the images

adapted form Hartley & Zisserman's "Multiple View Geometry in Computer Vision"

This tasks and algorithms as well as the methods which allow us to reason about the quality of our results are the core of the lecture 3D Computer Vision II. This lecture deals with multiple view geometry problems and having attended 3D Computer Vision I is of great benefit, however, it is not, in any case, compulsory.

Content

  1. Intro, motivation & overview
  2. Projective geometry and 2D, 3D transformations
  3. Parameter estimation
  4. Camera model
  5. Two-View: Epipolar Geometry, 3D reconstruction, Fundamental Matrix, Structure computation
  6. Two-View: Mixed Camera Models: Perspective and Orthographic, Combined Othrographic and Perspective (COP) Images
  7. Three-View: The Trifocal Tensor
  8. Multi-View: Factorization Method, Multi-view Reconstruction, Motion and Structure from Motion

Course Schedule

Please scroll down for the exercise schedule.

Date Topic Conducted by Material/Literature
Tue, Oct 19 Introduction Prof. Dr. N. Navab Introduction
Thu, Oct 21 Reminder: Projective Geometry, Transformations Prof. Dr. N. Navab Transformations
Tue, Oct 26 Reminder: Camera Models Prof. Dr. N. Navab Camera Models
Thu, Oct 28 Two-view Geometry I (Epipolar Geometry) Prof. Dr. N. Navab Epipolar Geometry
Tue, Nov 9 Two-view Geometry II (Fundamental Matrix) Prof. Dr. N. Navab Fundamental Matrix
Tue, Nov 16 no lecture due to Studentische Vollversammlung    
Thu, Nov 18 Two-view Geometry III (continued) Prof. Dr. N. Navab  
Tue, Nov 23 Stereo I (Rectification, Disparity) Christian Unger Rectification
Tue, Nov 30 Stereo II (Matching, Reconstruction) Prof. Dr. N. Navab Stereo Matching
Tue, Dec 7 Multi-view 3D Reconstruction Cedric Cagniart 3D Reconstruction
Tue, Dec 21 Time-of-Flight Imaging Loren Schwarz Time-of-Flight Imaging
Tue, Jan 11 Combined Orthographic and Perspective Camera Models Prof. Dr. N. Navab COP Imaging
Tue, Jan 18 N-View Computational Methods Dr. Diana Mateus N-View Methods
Tue, Jan 25 Simultaneous Localization and Mapping Stefan Holzer SLAM
Tue, Feb 1 Three-view Geometry and Tri-focal Tensor Prof. Dr. N. Navab Trifocal Tensor

Exercise Schedule

Date Topic Conducted by Exercises Solutions Homework due Notes
Tue, Nov 2 Introduction, MATLAB Tutorial Hauke Heibel     Midterm Attestation  
Thu, Nov 4 Projective Geometry, Camera Models Cedric Cagniart     Midterm Attestation  
Thu, Nov. 11 Epipolar Geometry Martin Groher     Midterm Attestation  
Thu, Nov. 25 Estimation of Fundamental Matrix Loren Schwarz     Midterm Attestation  
Thu, Dec 2 no exercise due to Dies Academicus          
Thu, Dec 9 Attestation Exercise Team        
Tue, Dec 14 Multi-view 3D Reconstruction Cedric Cagniart     Final Attestation  
Thu, Dec 16 Midterm Exam Exercise Team        
Thu, Dec 23 no exercises          
Thu, Jan 13 Midterm Exam Correction Exercise Team        
Thu, Jan 20 Factorization Loren Schwarz     Final Attestation  
Thu, Jan 27 SLAM Stefan Holzer     Final Attestation  
Thu, Feb 3 Trifocal Tensor Martin Groher, Loren Schwarz     Optional  
Tue, Feb 8 Attestation Exercise Team        
Thu, Feb 10 Final Exam Exercise Team        

Additional Resources


TeachingForm
Title: 3D Computer Vision II
Professor: Prof. Dr. Nassir Navab
Tutors: Cedric Cagniart, Loren Schwarz, Dr. Martin Groher, Hauke Heibel
Type: Lecture
Information: 2 + 2 SWS, 5 ECTS Credits (Module IN 2123)
Term: 2010WiSe
Abstract: Making a computer see was something that leading experts in the field of Artificial Intelligence thought to be at the level of difficulty of a summer student's project back in the sixties. Forty years later the task is still unsolved and seems formidable. A whole field, called Computer Vision, has emerged as a discipline in itself with strong connections to mathematics and computer science and looser connections to physics, the psychology of perception and the neuro sciences. Over the past decade there has been a rapid development in the understanding and modelling of the geometry of multiple views in computer vision. The theory and practice have now reached a level of maturity where excellent results can be achieved for problems that were unsolved a decade ago, and often thought unsolvable. These tasks and algorithms include problems like: Given two/three/multiple images, and no further information, compute/estimate: * matches between the images * the 3D position of the points that generate these matches * the cameras that generate the images adapted form Hartley & Zisserman's "Multiple View Geometry in Computer Vision" This tasks and algorithms as well as the methods which allow us to reason about the quality of our results are the core of the lecture 3D Computer Vision II. This lecture deals with multiple view geometry problems and having attended 3D Computer Vision I is of great benefit, however, it is not, in any case, compulsory.


Edit | Attach | Refresh | Diffs | More | Revision r1.61 - 16 Nov 2011 - 13:37 - LorenSchwarz

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif