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 every other week. INM 200 (A-M), INM 202 (N-Z)
Please check the course schedule and bring your own laptops for the exercise sessions.
Questions
If you have any questions please post them in the discussion forum and we will answer you.
Contact TAs
If you have any questions please email one of the TAs and we can arrange a meeting.
Andrey Davydov (andrey.davydov@epfl.ch)
Benoît Guillard (benoit.guillard@epfl.ch)
Michal Jan Tyszkiewicz (michal.tyszkiewicz@epfl.ch)
Ren Li (ren.li@epfl.ch)
Zhao Chen (chen.zhao@epfl.ch)
Hussein Osman (hussein.osman@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. It will count for 80% of your final grade.It will take place on Monday the 4th of July from 15:15 to 16:45.Graded Exercise Sessions
We will grade two of the exercise sessions. They will count for 10% of you final grade each.
Recorded Lectures
The recorded lectures from the 2020/2021 school year will be available on the webpages.
-
21-02-2022 Course 28-02-2022 Course 01-03-2022 Exercise Session 1 07-03-2022 Course 14-03-2022 Course 15-03-2022 Exercise Session 2 21-03-2022 Course 28-03-2022 Course 29-03-2022 Exercise Session 3 GRADED 04-04-2022 Course 11-04-2022 Course 12-04-2022 Exercise Session 4 18-04-2022 No Course (holiday - Lundi de Pâques) 25-04-2022 Course 02-05-2022 Course 03-05-2022 Exercise Session 5 09-05-2022 Course 16-05-2022 Course 17-05-2022 Exercise Session 6 GRADED 23-05-2022 Course 30-05-2022 Course 31-05-2022 Exercise Session 7 -
R. Szeliki, Computer Vision: Computer Vision: Algorithms and Applications, 2021.
R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.
-
Edge definition, edge operators, Canny edge detector, and machine-learning based detectors.
-
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.
-
Recovering 3D shape from one single image.
-
Recovering Depth from Multiple Images
-
Recovering 3D shape from edges and occluding contours
-
Recovering Shape from Video Sequences
-
Introduction to Python for Computer Vision
-
Convolutions, image filters, gradients
-
- Applying dijkstra to edge detection and delineation problem (Ex 3 last year)
- Circular Hough Transform
-
General Hough Transform
-
K-Means Clustering for Image Segmentation, Image Sharpening