Recommended prerequisite for participation in the module

The student is recommended to have basic knowledge in probability theory, statistics, and linear algebra

Content, progress and pedagogy of the module

Cameras capture visual data from the surrounding world. Building systems which can automatically process such data requires image processing and computer vision methods. Students who complete the module will understand relevant theories and methods within image processing and computer vision as well their applicability.

Learning objectives

Knowledge

• Must be able to understand the general framework of image processing including point- and neighborhood operations
• Must be able to explain the principles behind robust feature point algorithms
• Must have knowledge of different motion analysis principles
• Must be able to understand how to obtain 3D data via sensors, stereo vision or structure-from-motion
• Must be able to understand how deep learning can be applied to images

Skills

• Must be able to apply one or more tracking frameworks
• Must be able to apply deep learning approaches to image classification
• Must be able to apply deep learning approaches to object detection
• Must be able to apply deep learning approaches to semantic segmentation
• Must be able to apply appropriate annotation tools and evaluation metrics

Competences

• Must be able to analyse a specific problem and based upon this select, implement and evaluate an appropriate image processing or computer vision method
• Must have competencies in understanding the strengths and weaknesses of a method in relation to a specific problem

Type of instruction

As described in § 17.

Exam

Prerequisite for enrollment for the exam

• Submission of mini-project report

Exams

Name of exam	Image Processing and Computer Vision
Type of exam	Written or oral exam
ECTS	5
Assessment	7-point grading scale
Type of grading	Internal examination
Criteria of assessment	The criteria of assessment are stated in the Examination Policies and Procedures