Computer Vision Methods

Relations:

It is not possible to register for the course B4M33MPV if the student is concurrently registered for or has already completed the course AE4M33MPV (mutually exclusive courses).

It is not possible to register for the course B4M33MPV if the student is concurrently registered for or has already completed the course BE4M33MPV (mutually exclusive courses).

In order to register for the course B4M33MPV, the student must have registered for the required number of courses in the group BEZBM no later than in the same semester.

The requirement for course B4M33MPV can be fulfilled by substitution with the course BE4M33MPV.

It is not possible to register for the course B4M33MPV if the student is concurrently registered for or has previously completed the course BE4M33MPV (mutually exclusive courses).

It is not possible to register for the course B4M33MPV if the student is concurrently registered for or has previously completed the course AE4M33MPV (mutually exclusive courses).

Course guarantor:

Jiří Matas

Lecturer:

Jan Čech, Jiří Matas, Dmytro Mishkin, Torsten Sattler, Georgios Tolias

Tutor:

Georgios Kordopatis-Zilos, Jiří Matas, Dmytro Mishkin, Lukáš Neumann, Jonáš Šerých, Pavel Šuma

Supervisor:

Department of Cybernetics

Synopsis:

The course covers selected computer vision problems: search for correspondences between images via interest point detection, description and matching, image stitching, detection, recognition and segmentation of objects in images and videos, image retrieval from large databases and tracking of objects in video sequences.

This course is also part of the inter-university programme prg.ai Minor. It pools the best of AI education in Prague to provide students with a deeper and broader insight into the field of artificial intelligence. More information is available at https://prg.ai/minor.

Requirements:

Knowledge of calculus and linear algebra.

Syllabus of lectures:

1. Correspondences and wide baseline stereo I. Motivation and applications. Perspective pinhole camera model.

Interest point and distinguished regions detection: Harris detector (corner detection)

2.Correspondences and wide baseline stereo II. Laplace operator and its approximation by difference of Gaussians. Affine covariant version. Descriptors of SIFT (scale invariant feature transform), RootSIFT.

Multiview feature matching. Deep learned features: R2D2, Super Glue.

3.RANSAC (Random Sample and Consensus)

4.3D reconstruction I.

5.3D reconstruction II

6.Deep learning I. Convolutional Neural Networks, Transformers. Architectures for image recognition.

7.Deep learning II. Architectures for object detection and semantic segmentation.. Foundation models (CLIP, DINO, Segment Anything, Depth Anything)

8.Tracking I. Problem formulation. KLT - Lucas-Kanade tracker, DCF - discriminative correlation tracker.

9.Tracking II. Long-term tracking.

10.Image Retrieval I., Bag-of-Words, VLAD, spatial verification, special objectives: zoom in/out .

11.Image Retrieval II. deep metric learning, architectures, losses

12.Self-supervised representation learning. Auto-encoders, learning via augmentations, contrastive approaches

13.Generative modelling for Computer Vision

Syllabus of tutorials:

1.Introduction to Image Processing in python using PyTorch.

2.Debugging pytorch.

3.Correspondence problem I, detection of the interest points.

4.Correspondence problem II, computing local invariant description.

5.Correspondence problem III, finding tenative correspondences and RANSAC.

6.Correspondence problem, summary.

7.Convolutional Neural Networks: training a classifier.D LN recording 2022

8.Convolutional Neural Networks II: debugging training process.

9.Image Retrieval, BoW TF-IDF, fast spatial verification.

10.Assignment defence.

11.Deep metric learning.

12.Self-supervised Learning.

13.Tracking.

Study Objective:

The course covers core computer vision problems: search for correspondences between images, 3D reconstruction, object detection, recognition, segmentation of objects in images and videos, image retrieval from large databases and tracking of objects in video sequences. In the labs, the students implement selected methods and test performance on real-world problems.

Study materials:

D. A. Forsyth, J. Ponce. Computer Vision: A Modern Approach. Prentice Hall 2003

I. Goodfellow, Y. Bengio, A. Courville: Deep Learning, 2016

A. Torralba, P. Isola, W. T. Freeman: Foundations of Computer Vision,

Note:

URL: https://cw.fel.cvut.cz/wiki/courses/mpv/start

Further information:

https://cw.fel.cvut.cz/wiki/courses/mpv/start

Time-table for winter semester 2025/2026:

Time-table is not available yet

Time-table for summer semester 2025/2026:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon	roomKN:E-107 Matas J. Čech J. 09:15–10:45 (lecture parallel1) Karlovo nám.
Tue
Wed	roomKN:E-230 Mishkin D. Neumann L. 14:30–16:00 (lecture parallel1 parallel nr.101) Karlovo nám. roomKN:E-230 Mishkin D. Neumann L. 16:15–17:45 (lecture parallel1 parallel nr.102) Karlovo nám.
Thu
Fri

The course is a part of the following study plans:

• Medical electronics and bioinformatics (compulsory elective course)
• Open Informatics - Computer Vision and Image Processing (compulsory course of the specialization)
• Medical electronics and bioinformatics (compulsory elective course)
• Medical electronics and bioinformatics (PS)
• Medical electronics and bioinformatics (compulsory elective course)
• Cybernetics and Robotics (compulsory elective course)