3D Computer Vision II Winter Term 2010/2011
Administrative InfoLecture by Prof. Nassir NavabExercises by Cedric Cagniart, Loren Schwarz, Dr. Martin Groher and Hauke Heibel 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 & RequirementsTuesday 10:30-12:00 MI 03.13.010Exercises: Thursday 12:30-14:00 MI 03.13.010 Course information and certificate requirements:
|
Site Content |
AnnouncementsYou can take one A4 page (two-sided) with hand-written notes to the final exam. No book or other notes are allowed. The final exam will take place on Thursday, February 10, during our regular Thursday's hours (12:30-14:00), in the regular seminar room (MI 03.13.010). |
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
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
- Intro, motivation & overview
- Projective geometry and 2D, 3D transformations
- Parameter estimation
- Camera model
- Two-View: Epipolar Geometry, 3D reconstruction, Fundamental Matrix, Structure computation
- Two-View: Mixed Camera Models: Perspective and Orthographic, Combined Othrographic and Perspective (COP) Images
- Three-View: The Trifocal Tensor
- Multi-View: Factorization Method, Multi-view Reconstruction, Motion and Structure from Motion
Course Schedule
Please scroll down for the exercise schedule.Exercise Schedule
Additional Resources
MATLAB Workshop| TeachingForm | |
|---|---|
| Title: | 3D Computer Vision II |
| Professor: | Prof. Dr. Nassir Navab |
| Tutors: | Cedric Cagniart, Loren Schwarz, Dr. Martin Groher, Hauke Heibel |
| Type: | Lecture |
| Information: | 2 + 2 SWS, 5 ECTS Credits (Module IN 2123) |
| Term: | 2010WiSe |
| 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. |
