Computer Vision and Image Processing
This course is a first advanced introduction to computer vision and image processing. Topics that yesterday are i.a. camera modeling, multi-view geometry, reconstruction, some low-level image processing (eg image segmentation) and high-level data (eg object detection). The last part of the course describes different frameworks and programming libraries focused on applications. The course introduces the mathematical aspects and the background to the methods which are then applied in practice in different projects.
About the course:
The course is conducted as a series of lectures, homework, laboratory work and a final project. Laboratory work and projects are carried out in groups of up to 4 students. The labs will require a report and the final project will include a report summarizing the results and methodology.
At the end of the course you will be able to:
- describe both theoretical and practical aspects of computer vision and image processing including methodology and terminology
- describe basic principles for image creation and analysis
- select and implement methods related to image filtering, element extraction and image segmentation
- apply the geometric relationships between 2D images and the 3D world
- interpret higher image processing tasks as object detection and understand the principles of related deep neural networks
- implement, analyze and evaluate simple methods in the application of computer vision within the framework of service-oriented architecture
[/_special-polopoly/FormArticle.htm?a=215545&l=en]
