Computer vision
Topic outline
-
Welcome to the Computer Vision class!
Computer Vision is the branch of Computer Science whose goal is to model the real world or to recognize objects from digital images. These images can be acquired using still and video cameras, infrared cameras, radars, or specialized sensors such as those used in the medical field.
The students will be introduced to the basic techniques of the field of Computer Vision. They will learn to apply Image Processing techniques where appropriate.
We will concentrate on the black and white and color images acquired using standard video cameras. We will introduce basic processing techniques, such as edge detection, segmentation, texture characterization, and shape recognition.Instructor
Prof. Pascal Fua
Computer Vision Laboratory (CVLAB)
BC 310
E-mail: pascal.fua@epfl.chCourse Times and Locations
Lectures: Monday 13:15 - 15:00 (CM3)
Exercises: Tuesday 10:15 - 12:00 (INM 200/202) - please check the course schedule and bring your own laptops for the exercise sessions.
Office Hours
If you have any questions please email one of the TAs and we can arrange a meeting.
Semih Günel (semih.gunel@epfl.ch)
Isinsu Katircioglu (isinsu.katircioglu@epfl.ch)
Udaranga Wickramasinghe (udaranga.wickramasinghe@epfl.ch)
Krishna Kanth Nakka (krishna.nakka@epfl.ch)
Michal Jan Tyszkiewicz (michal.tyszkiewicz@epfl.ch)
Kaicheng Yu (kaicheng.yu@epfl.ch)
Final Exam
It will be a 90min closed book exam with multiple-choice and open-ended questions. You will be allowed ONE hand-written A4 page of notes and 80% of your grade will come from this exam.
Graded Exercises
Not all practical sessions will be graded. However, two of them will be, one in the middle of the term and another towards the end. This will count for the remaining 20% of your grade.
-
17.02.2020
Course
24.02.2020
Course
25.02.2020
Exercise Session
02.03.2020
03.03.2020
Course
No Exercise session
09.03.2020
Course
10.03.2020
Exercise Session
16.03.2020
17.03.2020
Course
No Exercise session
23.03.2020
Course
24.03.2020
Exercise Session
30.03.2020
31.03.2020
Course
No Exercise session
06.04.2020
Course
07.04.2020
Exercise Session
13.04.2020
14.04.2020
No Course (holiday)
No Exercise session (holiday)
20.04.2020
21.04.2020
Course
No Exercise session
27.04.2020
Course
28.04.2020
Exercise Session
04.05.2020
05.05.2020
Course
No Exercise session
11.05.2020
Course
12.05.2020
Exercise Session
18.05.2020
19.05.2020
Course
No Exercise session
25.05.2020
Course
26.05.2020
Graded Exercise Session
-
R. Szeliki, Computer Vision: Computer Vision: Algorithms and Applications, 2010.
R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.
M. Nielsen, Neural Networks and Deep Learning, 2015.
-
Edge definition, edge operators, Canny edge detector, and parametric matching.
-
Going from edge elements to complete outlines.
-
Partitioning images into separate regions of interest.
-
Texture: What is it and how can it be characterized and analyzed.
-
Even though there will be no official I&C evaluation this semester, I would like some feedback on this class. I would therefore ask you to fill this questionnaire that mirrors the standard one. You answers will be totally anonymous as usual.
-
Recovering Depth from Multiple Images
-
Recovering 3D shape from edges and occluding contours
-
Recovering Shape from Video Sequences
-
Introduction to Python for Computer Vision
-
Image filtering and edge detection
