TeachingSs143DCV

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

3D Computer Vision - Summer Term 2014

Administrative Info

Lecture by Prof. Nassir Navab
Exercises by Wadim Kehl, Vasileios Belagiannis

Type: Lecture Module IN2057
Programs: Informatics (Bachelor, Master)
Biomedical Computing (Master)
Computational Science and Engineering (Master)
Wirtschaftsinformatik (Bachelor, Master)
SWS: 2+2
ECTS: 5 Credits
Course Language: English
Contact:

NOTE: Only exercise solutions of the theoretic parts will be posted on the web-site.

Time, Location & Requirements

Location: Interimshörsaal 1, 5620.01.101
Lectures: Mondays, 14:00 - 16:00
Exercises: Tuesdays, 15:00 - 16:30

Course information and certificate requirements:

  • The classes as well as the exercises will be held in English.
  • Exercises will consist of practical and theoretical tasks. Practical exercises will be done in MATLAB. A license is available to every TUM student and can be found at: MATLAB RBG
  • A MATLAB workshop and a primer can be found here: Workshop, Primer
  • The lecture consists of one intermediate exam and a final exam.
  • All exams are hand written and closed-book exam (no notes allowed).

Site Content

Announcements

The final results are out (PDF)! Write a mail in case of questions/problems!


The repetition exam is going to take place on September 24th from 9 to 11. You can already register for it!

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 and multiple view geometry are the core of the lecture 3D Computer Vision.

Course Schedule

Date Topic Conducted by Additional material
Mon, 07.04.2014 Introduction Prof. Nassir Navab  
Tue, 08.04.2014 1 - 2D Transformations Prof. Nassir Navab  
Mon, 14.04.2014 2 - 3D Transformations Prof. Nassir Navab  
Mon, 21.04.2014 Ostermontag - no lecture    
Mon, 28.04.2014 3 - Conics, 4 - Parameter Estimation Prof. Nassir Navab  
Tue, 12.05.2014 5 - Algorithm Evaluation and Error Analysis Prof. Nassir Navab  
Mon, 19.05.2014 6 - Camera Models I (Calibration) Bertram Drost  
Tue, 20.05.2014 7 - Nonlinear Optimization Christian Unger  
Mon, 26.05.2014 8 - Camera Models II Prof. Nassir Navab  
Mon, 02.06.2014 Q&A    
Mon, 09.06.2014 Pfingstmontag - no lecture    
Mon, 16.06.2014 9 - Camera Calibration Prof. Nassir Navab  
Mon, 23.06.2014 10 - Epipolar geometry Prof. Nassir Navab  
Mon, 30.06.2014 11 - Fundamental matrix Wadim Kehl  
Mon, 07.07.2014 12 - 3D reconstruction    

Exercise Schedule

Date Topic Conducted by Solutions Notes
Tue, 08.04.2014 Announcements Wadim Kehl , Vasileios Belagiannis    
Tue, 15.04.2014 Exercise sheet 1 Vasileios Belagiannis Solution sheet 1  
Tue, 22.04.2014 Osterferien - no exercise      
Tue, 29.04.2014 Exercise sheet 2 Paul Huang Solution sheet 2 Besides the derivations given in the exercise session, there is an alternative way to derive Rodrigues' formula. Please check the solution sheet.
Mon, 05.05.2014 Exercise sheet 3 Wadim Kehl Solution sheet 3 TU Finger 1 , TU Finger 2 , Skyscraper
Tue, 13.05.2014 Exercise sheet 4 Vasileios Belagiannis Solution sheet 4 TUM MI1 , TUM MI2 , MATLAB matches file
Tue, 20.05.2014 Lecture instead of exercise Christian Unger    
Tue, 27.05.2014 Exercise sheet 5 Wadim Kehl Solution sheet 5  
Tue, 03.06.2014 MID-TERM EXAM      
Tue, 10.06.2014 Pfingstferien - no exercise      
Tue, 17.06.2014 Exercise sheet 6 Vasileios Belagiannis Solution sheet 6 Image 1 , Image 2 , error_ellipse.m
Tue, 24.06.2014 Exercise sheet 7 Wadim Kehl Solution sheet 7 Distorted image , UPDATE: The sheet now has the updated intrinsics for the last exercise
Tue, 01.07.2014 Exercise sheet 8 Wadim Kehl    
Tue, 08.07.2014        

TeachingForm
Title: 3D Computer Vision
Professor: Prof. Dr. Nassir Navab
Tutors: Wadim Kehl , Vasileios Belagiannis
Type: Lecture
Information: 2+2 SWS, 5 ECTS Credits ( IN2057 )
Term: 2014SoSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.63 - 05 Sep 2014 - 08:02 - WadimKehl

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