Type of course

Admission requirements

A relevant undergraduate Bachelor Engineering program with minimum 25 credits mathematics, 5 credits statistics, 7,5 credits physics.

Application code: 9371

FYS-2010 Image Analysis, FYS-2006 Signal Processing or FYS-2021 Machine Learning is recommended.

Course content

This course builds on the knowledge gained from Image Analysis and Machine Learning courses.

Fundamentals of technical and scientific report writing with emphasis on performing experiments and data analysis pertaining to image analysis themes.

Introduction to machine vision: fundamentals of image formation and camera parameters. An overview of Image sensing pipeline, Demosaicing, and JPEG compression.

Our visual system, eye tracking, eye tracking technologies, analysis of eye tracking data, visual saliency, and deep visual saliency. Monocular and Binocular cues for depth perception.

Feature extraction methods: RANSAC, SIFT, and HOG.

Fundamentals of Geometric Image Formation, Pinhole camera model, Camera Calibration, Extrinsic and Intrinsic parameters.

A high-level summary of advanced deep learning methods for image analysis such as object detection, inpainting, super-resolution and/or image generation.

Recommended prerequisites

Objectives of the course

Knowledge:

This interdisciplinary course should give the candidate a good understanding of machine vision with special focus on a case study in one of the following areas: Machine Learning, Automation, Drone Technology, Medical Informatics & Imaging, Nautical Science, Remote Sensing, and Industrial Applications.

Skills:

• Candidate will build knowledge in image formation, cameras, and vision sensors.
• Candidate will learn about image analysis techniques for eye tracking data analysis and visual saliency.
• Candidate will learn state-of-the-art machine learning methods for image analysis (i.e., pattern detection and recognition).
• Candidate should be able to use state-of-the-art image analysis methods in practical problems.
• Candidate should be able to understand and use the knowledge from machine vision in their selected domain.
• Candidate should be able to demonstrate their knowledge using Python or MATLAB®.
• Candidate should be able to demonstrate scientific analysis of data or experiments in a case study report.

Language of instruction and examination

Teaching methods

Information to incoming exchange students

This course is open for inbound exchange student who meets the admission requirements. Please see the Admission requirements" section".

Master Level

Do you have questions about this module? Please check the following website to contact the course coordinator for exchange students at the faculty: https://en.uit.no/education/art?p_document_id=510412.

There are no restrictions on the number of inbound students on exchange.