TeachingSs12CV

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 Summer Term 2012

Administrative Info

Lecture by Prof. Nassir Navab
Exercises by S. Hinterstoisser and S.Ilic and V. Belagiannis and R. Stauder and V. Haltakov and D.Tan

Type: Lecture Module IN2057
Programs: Informatics (Bachelor, Master)
Informatics (Diploma, Wahlpflichtfach, Theoretische Informatik)
Information Systems (Bachelor), Computational Science and Engineering (Master)
Master Sports Engineering
SWS: 2+2
ECTS: 5 Credits
Course Language: English

Time, Location & Requirements

Lecture: Tuesday 10:00-11:30 MI 03.13.010

Exercises: Thursday 13:00-14:30 MI 03.13.010

Requirements:

  • The classes and exam are in English
  • Exams are to be written in English only
  • The final exam contains 100 points, you need to have 50 points to pass it
  • Up to 40 bonus points can be earned from the homework and the intermediate exam

Site Content

Announcements

A repeat exam will be available in TUM-Online (link) for the students who didn't manage to attend to the first one. Please register on time.

For the final exam you are allowed to bring 1 sheet of hand written notes and a non-programmable calculator.

Registration

You need to register for the class and the exam on Tum-Online. Only registered students can take part in the exam!

Homeworks

We will announce special dates on which students have to show their homework either on their own computer or on the computers of the CAMP-Lab. In these sessions, we will check the latest 3-5 homeworks.

The first date for checking the homework is the 14.6.2012 right after the exercise!

Final exam and final grades

For the final exam you are allowed to bring 1 sheet of hand written notes and a non-programmable calculator.

Midterm exam

  • Exam is to be written in English only
  • The midterm exam takes place on 19.6.2012, 17:15-18:45, MW 2050.
  • For the midterm exam, only one handwritten Din A4 (front+back) page with notes is allowed; calculators are allowed (however, computers and mobile phones are not allowed!)
  • Make sure you are registered for the exam. Only registered students can take part in the exam. If you have problems registering, please contact the student help desk!

Homeworks

We will announce special dates on which students have to show their homework either on their own computer or on the computers of the CAMP-Lab. In these sessions, we will check the latest 3-5 homeworks.

Matlab

In order to do the exercises students must know how to program in Matlab. A basic introduction is given on April 22nd from 14:30-16:00 in MI 03.13.010. The time of the exercise is a SINGLE EXCEPTION since it is hold jointly with the CAMP lecture. The regular time of the exercises is each Thursday between 12:30-14:00. Please read the Matlab tutorial/sheet given under Exercises if you want to attend!

-->

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")

The fundamental mathematics and a profound comprehension of the basics of projective geometry as well as one-view geometry are the core of the lecture 3D Computer Vision.

Lecture Content

  1. Intro, motivation & Overview
  2. 2D Transformations
  3. Projective 2D Geometry
  4. 3D Transformations
  5. Projective 3D Geometry
  6. Parameter Estimation
  7. Camera Models
  8. Camera Calibration
  9. Conclusion & Discussion

Lecture Schedule

Date Conducted by Topic Material/Literature
Tue. 17.04.12 Prof. Nassir Navab Introduction and Motivation Introduction (without Videos)
Thu. 19.04.12 Prof. Nassir Navab Basic Transformations & 2D Projective Geometry Lecture 1
Thu. 26.04.12 Prof. Nassir Navab Transformations & 2D Projective Geometry Lecture 2
Tue. 01.05.12 Prof. Nassir Navab no lecture due to holiday day  
Thu. 10.05.12 Prof. Nassir Navab Parameter Estimation: Linear Estimation, DLT, Cost Functions
Tue. 22.05.12 Prof. Nassir Navab Parameter Estimation: Sampson Error, Statistical Cost Functions Lecture 3 & 4
Tue. 29.05.12 Prof. Nassir Navab no lecture due to holiday day  
Tue. 05.06.12 Dr. Slobodan Ilic Non-linear Parameter Estimation Lecture 5
Thu. 07.06.12 Prof. Nassir Navab No lecture due to holiday day  
Tue. 12.06.12 Prof. Nassir Navab Algorithm Evaluation & Error Analysis Lecture 7
Thu. 21.06.12 Prof. Nassir Navab Projection and Camera Models Lecture 8
  Prof. Nassir Navab Computation of the Projection Matrix
Tue. 26.06.12 / 03.07.2012 Prof. Nassir Navab Camera Models II / Modeling and Correction of Distortion Lecture 9a, Lecture 9b
Thu. 12.07.12 Prof. Nassir Navab Two View Geometry Lecture 10
Tue. 17.07.12 Prof. Nassir Navab Two View Geometry II  

Exercise Schedule

Date Conducted by Topic Exercises Solutions Homework due
Tue 24.04.12 V. Belagiannis Matlab tutorial - see anouncements  Announcements
 MATLAB Workshop
 MATLAB Primer
Load images demo
  no homework
Thu 03.05.12 S. Hinterstoisser Homogeneous Coordinates; Hierarchy of Transformations (2D);
Duality of Points and Lines (also under Transformations)
    14.6.2012
Tue 08.05.12 S. Hinterstoisser 3D Rigid Transformations; Rotation representations; Rodrigues Angles; Representing Projective Geometry in R3     14.6.2012
Tue 15.05.12 no exercise due to student council      
Thu 17.05.12   no exercise due to holidays      
Thu 24.05.12 R. Stauder Cross-Ratio of Points and Lines, DLT, Mosaicing     14.6.2012
Thu 31.05.12 D. Tan Error Models, Homography     14.6.2012
Thu 07.06.12   no lectures due to holidays      
Thu 14.06.12 V. Belagiannis Maximum Likelihood Estimation, Non-linear estimation methods     12.07.12 (at 11:00h)
Tue 19.06.12 V. Belagiannis Error Propagation     12.07.12 (at 11:00h)
Thu 28.06.12 V. Haltakov Projection Matrices, Camera Calibration     12.07.12 (at 11:00h)
Thu 05.07.12 V. Haltakov Planar Camera Calibration, Radial Distortion     12.07.12 (at 11:00h)
Tue 10.07.12 V. Haltakov Two View Geometry     optional
Thu 19.07.12 Questions and Feedback      

Exams

  • Midterm Exam: 19.6.2012, 17:15-18:45, MW 2050.
  • Final Exam: 24.7.2012, 10:00-11:30, 102 - Interims Hoersaal 2 .

Readings

  • Primary Reading
    • Multiple View Geometry in Computer Vision by Richard Hartley & Andrew Zisserman

  • General Introduction to 3D Computer Vision
    • Three-Dimensional Computer Vision by Olivier Faugeras
    • Computer Vision: A Modern Approach by David A. Forsyth & Jean Ponce
    • Introductory Techniques for 3-D Computer Vision by Emanuele Trucco & Alessandro Verri

  • More Specific Readings
    • The Geometry of Multiple Images: The Laws That Govern the Formation of Multiple Images of a Scene and Some of Their Applications by Olivier Faugeras, Quang-Tuan Luong, Theodore H. Papadopoullos; MIT Press; 2001

TeachingForm
Title: 3D Computer Vision I
Professor: Prof. Dr. Nassir Navab
Tutors: Stefan Hinterstoisser, Vasilis Belagiannis, Ralf Stauder, Vladimir Haltakov,
Type: Lecture
Information: 2+2 SWS, 5 ECTS, Theoretische Informatik, Wahlpflichtfach
Term: 2012SoSe
Abstract: The class covers projective and one-view geometry for Computer Vision Applications.


Edit | Attach | Refresh | Diffs | More | Revision r1.68 - 28 Jan 2014 - 11:21 - WadimKehl

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