3D Computer Vision I - Summer Term 2011

Administrative Info Lecture by Prof. Nassir Navab Exercises by Slobodan Ilic and Stefan Hinterstoisser and Alexandru Duliu and Stefan Holzer and Jakob Vogel 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 For the intermediate exam, only one handwritten Din A4 (front+back) page with notes is allowed; calculators are allowed (however, computers are not allowed!) For the final exam, only one handwritten Din A4 page (front+back) with notes is allowed; calculators are allowed (however, computers are not allowed!) 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 Overview Lecture Content Lecture Schedule Exercise Schedule Exams Readings

Announcements The end-term exam is finally corrected, and the grades have been entered on TUM Online. You can examine your corrected exams on Thursday, September 15, between 10:30 am and 12:00 pm. The repeat exam will take place on Thursday, September 29, in room MI 03.13.010 from 10:00 am to 12:00 pm. Registration Please register through TUMOnline. Homeworks Homework will be checked on June 9 and July 7 at 04:00 pm and July 26 at 10am. Please note that we postponed the last date due to multiple request. On these dates 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 all the previous yet unchecked assignments. Matlab In order to do the exercises students must know how to program in Matlab. A basic introduction is given on Mai 5th during the exercise. 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

Exercise Schedule

Exams

• Midterm Exam: Tue, June 21, 2011, 10:00 am – 12:00 am (Results)
• Final Exam: Fri, July 29, 2011, 03:30 pm – 05:30 pm, MW 1550
• Repeat Exam: Thr, Sept. 29, 2011, 10:00 am – 12:00 am,

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