3D Computer Vision
Module IN2057
This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.
Basic Information
IN2057 is a semester module in English language at Bachelor’s level and Master’s level which is offered in summer semester.
This module description is valid to WS 2018/9.
| Total workload | Contact hours | Credits (ECTS) |
|---|---|---|
| 150 h | 60 h | 5 CP |
Content, Learning Outcome and Preconditions
Content
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 from Hartley & Zisserman's "Multiple View Geometry in Computer Vision"
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 from Hartley & Zisserman's "Multiple View Geometry in Computer Vision"
Learning Outcome
After attending the module, the participants know and understand the basics of projective 2D and 3D geometry. They can handle the fundamental methods of computer vision: parameter estimation of 2D and 3D transformations/projections, error propagation, camera calibration and 3D reconstruction using two or more views.
Preconditions
MA0901 Linear Algebra for Informatics, MA0902 Analysis for Informatics
Courses, Learning and Teaching Methods and Literature
Learning and Teaching Methods
Lecture, exercise course, problems for individual study
Media
Slides
Literature
Hartley & Zisserman - "Multiple View Geometry in Computer Vision"
Module Exam
Description of exams and course work
In the written exam of 75 minutes the participants have to prove that, without using any further help, they are able to understand and describe problems of computer vision. The questions cover all topics of the lecture and should show that the participant is able to apply the concepts of projections, transformations and geometry estimation to provided problems and that the participant knows the established algorithms to accomplish these tasks. The exam can contain assignments where participants have to derive mathematical properties or need to provide graphical explanations.
Exam Repetition
The exam may be repeated at the end of the semester.