3D Computer Vision - Summer Term 2014
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)
ECTS: 5 Credits
Course Language: English
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).
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!
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:
(Adapted form Hartley & Zisserman's "Multiple View Geometry in Computer Vision")
- matches between the images
- the 3D position of the points that generate these matches
- the cameras that generate the images
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