Computer Vision

Course guarantor:

Vanda Benešová

Lecturer:

Vanda Benešová, Radek Richtr

Tutor:

Vanda Benešová, Radek Richtr

Supervisor:

Department of Software Engineering

Synopsis:

The Computer Vision course focuses on the theoretical and practical mastery of modern methods and algorithms in the field of image data processing.Students will get acquainted with the basic principles of computer vision, gradually move to advanced computer vision techniques using deep learning. Emphasis is placed on theoretical knowledge as well as on practical applications and implementation of learned methods during exercises.

Topics covered include morphological operations, image filtering, color representations, object detection and recognition and segmentation through classical and recent approaches based on deep learning, deep neural networks for computer vision (including CNN, RCNN, YOLO, ViT), motion detection, visual expressiveness (saliency).

Requirements:

Input knowledge of the subject will be supplemented by the subject guarantor.

Syllabus of lectures:

1. Introduction, history of computer vision.

2. Morphological processing, image filtration, convolution.

3. Color: CIE L*a*b*, chromatic diagram .

4. Object detection and recognition, description of properties color, shape, texture, local descriptors.

5. (2) Deep neural networks in computer vision (DNN).

6. Conventional neural networks (CNN) and object recognition using CNN.

7. Object detection using DNN (RCNN, YOLO).

8. Object segmentation using DNN.

9. Vision transformers (ViT).

10. Generative DNN in computer vision.

11. Motion detection.

12. Visual Saliency modelling and applications.

Syllabus of tutorials:

In the exercises, students will have to work out 5 tasks using the OpenCv library:

1. the task trains the topics: morphological processing and filtering of the image, representation of the image in different color spaces

2. the task trains the topics: detection and recognition of objects with both traditional methods and deep neural networks.

3. the task trains the topic: segmentation of objects with both traditional methods and deep neural networks.

4. the task trains the topic of motion detection.

5. The student will work out a mini-project with an individual task.

Study Objective:

The aim of the course is to equip students with the knowledge and skills needed to understand, analyse and design computer vision systems in the context of current research trends and practical applications.

Study materials:

Recommended literature:

1. Mohamed Elgendy: Deep Learning for Vision Systems, 1st Edition. Manning, 2020. ISBN 1617296198.

2. Ian Godfellow and Yoshuma Benigo and Aaron Courville: Deep Learning, www.deeplearningbook.org. MIT Press Ltd., 2016. ISBN 9780262035613 / 9780262035613.

3. Elena ŠIKUDOVÁ, Zuzana ČERNEKOVÁ, Vanda BENEŠOVÁ, Zuzana HALADOVÁ, Júlia KUČEROVÁ: Počítačové videnie, detekcia a rozpoznávanie objektov. Wikina Praha, 2013. ISBN 978-80-87925-07-2.

Note:

The new course arose on the basis of the need to deepen the teaching of digital image processing and the expansion of computer vision and graphics. Presentation lectures and seminars supported by an e-learning portal with background material, streamed and recorded lectures and additional videos. Emphasis is placed on the understanding of theoretical substance and active work of students at seminars.

Further information:

https://courses.fit.cvut.cz/ANI-PIV

Time-table for winter semester 2025/2026:

Time-table is not available yet

Time-table for summer semester 2025/2026:

Time-table is not available yet

The course is a part of the following study plans:

• Master specialization Computer Security, in Czech, 2020 (elective course)
• Master specialization Design and Programming of Embedded Systems, in Czech, 2020 (elective course)
• Master specialization Computer Systems and Networks, in Czech, 202 (elective course)
• Master specialization Management Informatics, in Czech, 2020 (elective course)
• Master specialization Software Engineering, in Czech, 2020 (elective course)
• Master specialization System Programming, in Czech, version from 2020 (elective course)
• Master specialization Web Engineering, in Czech, 2020 (elective course)
• Master specialization Knowledge Engineering, in Czech, 2020 (elective course)
• Master specialization Computer Science, in Czech, 2020 (elective course)
• Mgr. programme, for the phase of study without specialisation, ver. for 2020 and higher (elective course)
• Study plan for Ukrainian refugees (elective course)
• Master specialization System Programming, in Czech, version from 2023 (elective course)
• Master specialization Computer Science, in Czech, 2023 (elective course)