Delivered at:: School of Electronic Engineering

Course type:: Compulsory course

When:: 4 year, 1 module

Instructor

Vartanov, Sergey

Full Syllabus Ask Question

Abstract

Computer vision (CV) is a field of computer science that focuses on enabling computers to understand and interpret visual data from images or video. It basically tries to replicate human vision capabilities in various visual tasks such as object detection and recognition, image classification, object tracking and so on. Computer Vision can be applied to a variety of applications like Autonomous Vehicles, Facial Recognition, Medical Imaging, and Robotics, to name a few. This course aims to introduce students to computer vision, starting from basics and then turning to more modern deep learning models. It covers both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and finally image stylization, editing and new image generation.

Learning Objectives

Understand the key computations underlying deep learning, use them to build and train deep neural networks, and apply it to computer vision.
Distinguish the main tasks of computer vision and 2d image processing.
Understand various topics in computer vision, including image processing, feature extraction, object recognition, tracking, and autonomous driving.
Be prepared for future internships, research projects, and job opportunities in the field of computer vision.

Expected Learning Outcomes

Understand the key computations underlying deep learning, use them to build and train deep neural networks, and apply it to computer vision.
Distinguish the main tasks of computer vision and 2d image processing.
Understand various topics in computer vision, including image processing, feature extraction, object recognition, tracking, and autonomous driving.
Be prepared for future internships, research projects, and job opportunities in the field of computer vision.
Understand transformers and multimodal computer vision concepts.
Apply the knowledge and skills gained in the course to real-world computer vision applications.

Course Contents

Introduction to Computer Vision
Image matching and classification. Content-based image retrieval
Convolutional features for visual recognition
Object detection
Video analysis
Image segmentation and synthesis

Assessment Elements

Итоговая контрольная работа
Самостоятельная работа

Interim Assessment

2024/2025 1st module
1 * Итоговая контрольная работа

Bibliography

Recommended Core Bibliography

Mathematical methods in computer vision, , 2003
Искусственный интеллект и компьютерное зрение. Реальные проекты на Python, Keras и TensorFlow. - 978-5-4461-1840-3 - Коул Анирад, Ганджу Сиддха, Казам Мехер - 2023 - Санкт-Петербург: Питер - https://ibooks.ru/bookshelf/386799 - 386799 - iBOOKS
Компьютерное зрение : современный подход, Форсайт, Д., 2004
Компьютерное зрение : учеб. пособие для студентов вузов, Шапиро, Л., 2006

Recommended Additional Bibliography

Computer vision : models, learning, and inference, Prince, S. J. D., 2012
Computer vision for visual effects, Radke, R. J., 2013

Authors

Вартанов Сергей Александрович

Bachelor’s Programme 'Information and Communication Technologies and Systems'

Basics in computer vision