TeachingWs11Cv2

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 2011/2012

Administrative Info

Lecture by Prof. Nassir Navab
Exercises by Loren Schwarz, Stefan Hinterstoisser

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 13:00-14:30 MI 03.13.010

NOTE: Lectures and Exercises can be both on Tuesday or Thursday. Please have a look to the lecture/exercise table.

Course information and certificate requirements:

  • The classes as well as the exercises will be held in English.

Office hours (Stefan Hinterstoisser, Loren Schwarz): Thursday 14:30-15:30

Site Content

Announcements

* You can look at your exams on Wednesday 18th April at 10:30-12:00. Please come to the office of Stefan Hinterstoisser.

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 (the content might still change)

  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
18.10.2011 Introduction Prof. Dr. N. Navab Introduction
20.10.2011 Reminder: Projective Geometry, Transformations Prof. Dr. N. Navab Transformations
27.10.2011 Reminder: Camera Models Prof. Dr. N. Navab Camera Models
8.11.2011 Two-view Geometry I (Epipolar Geometry) Prof. Dr. N. Navab Epipolar Geometry
15.11.2011 No lecture due to Studentische Vollversammlung --  
22.11.2011 Two-view Geometry II (Fundamental Matrix) Prof. Dr. N. Navab Fundamental Matrix
24.11.2011 Two-view Geometry III (continued) Prof. Dr. N. Navab  
6.12.2011 Stereo I (Rectification, Disparity) C. Unger Rectification
13.12.2011 Stereo II (Matching, Reconstruction) C. Unger Stereo
20.12.2012 Mid-Term Exam --
10.01.2012 Multi-view 3D Reconstruction Dr. S. Ilic Multi-View 3D-Reconstruction
17.01.2011 Trifocal Tensor Prof. Dr. N. Navab Trifocal Tensor
24.01.2012 Time-of-Flight / Kinect Imaging L. Schwarz Depth Imaging
31.01.2012 Multimodal Detection in Cluttered Background S. Hinterstoisser
14.02.2012 Final Exam --

Exercise Schedule

Date Topic Conducted by Exercises Solutions Homework due Notes
25.10.2011 Introduction, MATLAB Tutorial Stefan Hinterstoisser    
03.11.2011 Reminder Projective Geometry Stefan Hinterstoisser Announcements,
Exercise Sheet 1,
Homework Material
  01.12.11  
10.11.2011 Reminder Camera Models, Projection Matrix Stefan Hinterstoisser Exercise Sheet 2   01.12.11  
17.11.2011 Epipolar Geometry Loren Schwarz Exercise Sheet 3
mag_table_0.jpg
mag_table_1.jpg
Fmat.mat
  01.12.11  
29.11.2011 Estimation of Fundamental Matrix Loren Schwarz Exercise Sheet 4   07.02.12  
01.12.2011 Attestation Exercise Team        
08.12.2011 No Exercise due to Dies Academicus          
15.12.2011 Exercise to Stereo I and II Christian Unger Exercise Sheet 5   07.02.12  
22.12.2011 Midterm correction Loren Schwarz        
12.01.2012 Multi-view 3D Reconstruction Vasilis Belagiannis Exercise Sheet 6
Publication, Data
  07.02.12  
19.01.2012 Factorization Loren Schwarz Factorization
Exercise Sheet 7
hotel_points.dlm
hotel_pictures.zip
  07.02.12  
26.01.2012 Time of Flight / Kinect Victor Castañeda Exercise Sheet 8
Homework Material
  07.02.12
02.02.2012 Reminder Exercise Team      
07.02.2012 Attestation Exercise Team        

Additional Resources


TeachingForm
Title: 3D Computer Vision II
Professor: Prof. Dr. Nassir Navab
Tutors: Loren Schwarz, Stefan Hinterstoisser
Type: Lecture
Information: 2 + 2 SWS, 5 ECTS Credits (Module IN 2123)
Term: 2011WiSe
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 r1.39 - 16 Apr 2012 - 09:15 - StefanHinterstoisser

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