Autumn Semester 2020 takes place in a mixed form of online and classroom teaching.
Please read the published information on the individual courses carefully.

Luc Van Gool: Catalogue data in Autumn Semester 2016

Name Prof. Dr. Luc Van Gool
FieldComputer Vision
Address
Institut für Bildverarbeitung
ETH Zürich, ETF C 117
Sternwartstrasse 7
8092 Zürich
SWITZERLAND
Telephone+41 44 632 65 78
E-mailvangool@vision.ee.ethz.ch
DepartmentInformation Technology and Electrical Engineering
RelationshipFull Professor

NumberTitleECTSHoursLecturers
227-0447-00LImage Analysis and Computer Vision Information 6 credits3V + 1UL. Van Gool, O. Göksel, E. Konukoglu
AbstractLight and perception. Digital image formation. Image enhancement and feature extraction. Unitary transformations. Color and texture. Image segmentation and deformable shape matching. Motion extraction and tracking. 3D data extraction. Invariant features. Specific object recognition and object class recognition.
ObjectiveOverview of the most important concepts of image formation, perception and analysis, and Computer Vision. Gaining own experience through practical computer and programming exercises.
ContentThe first part of the course starts off from an overview of existing and emerging applications that need computer vision. It shows that the realm of image processing is no longer restricted to the factory floor, but is entering several fields of our daily life. First it is investigated how the parameters of the electromagnetic waves are related to our perception. Also the interaction of light with matter is considered. The most important hardware components of technical vision systems, such as cameras, optical devices and illumination sources are discussed. The course then turns to the steps that are necessary to arrive at the discrete images that serve as input to algorithms. The next part describes necessary preprocessing steps of image analysis, that enhance image quality and/or detect specific features. Linear and non-linear filters are introduced for that purpose. The course will continue by analyzing procedures allowing to extract additional types of basic information from multiple images, with motion and depth as two important examples. The estimation of image velocities (optical flow) will get due attention and methods for object tracking will be presented. Several techniques are discussed to extract three-dimensional information about objects and scenes. Finally, approaches for the recognition of specific objects as well as object classes will be discussed and analyzed.
Lecture notesCourse material Script, computer demonstrations, exercises and problem solutions
Prerequisites / NoticePrerequisites:
Basic concepts of mathematical analysis and linear algebra. The computer exercises are based on Linux and C.
The course language is English.
227-0919-00LKnowledge-Based Image Interpretation Information 0 credits2SL. Van Gool
AbstractWith the lecture series on special topics of Knowledge based image interpretation we sporadically offer special talks.
ObjectiveTo become acquainted with selected, recent results in image analysis and interpretation.
263-5902-00LComputer Vision Information 6 credits3V + 1U + 1AL. Van Gool, V. Ferrari, A. Geiger
AbstractThe goal of this course is to provide students with a good understanding of computer vision and image analysis techniques. The main concepts and techniques will be studied in depth and practical algorithms and approaches will be discussed and explored through the exercises.
ObjectiveThe objectives of this course are:
1. To introduce the fundamental problems of computer vision.
2. To introduce the main concepts and techniques used to solve those.
3. To enable participants to implement solutions for reasonably complex problems.
4. To enable participants to make sense of the computer vision literature.
ContentCamera models and calibration, invariant features, Multiple-view geometry, Model fitting, Stereo Matching, Segmentation, 2D Shape matching, Shape from Silhouettes, Optical flow, Structure from motion, Tracking, Object recognition, Object category recognition
Prerequisites / NoticeIt is recommended that students have taken the Visual Computing lecture or a similar course introducing basic image processing concepts before taking this course.