Imaging Technologies

Higher education teachers: Kovačič Stanislav
Collaborators: Perš Janez

Subject description

Prerequisits:

• Enrolment in the year.

Content (Syllabus outline):

• Multi-camera systems, multi-camera calibration, structure from motion, active vision.
• Feature detectors and descriptors, corner detectors, SIFT, HOG, MSER, COV, and others.
• Multi-resolution, multi-scale approaches.
• Deformable models, active contour models, active shape models, active appearance models.
• Image matching and registration, similarity measures, registration models.
• Object detection and tracking, tracking by detection, Kalman filters, particle filters.
• Computer vision and machine vision applications.

Objectives and competences:

The aims of this course are to cover selected topics of computer vision and to prepare students for team and independent research and development work.

Intended learning outcomes:

Be able to implement advanced computer vision algorithms. Be able to provide solutions to moderately complex problems.

Learning and teaching methods:

Lectures, laboratory work, home work, project.

Study materials

1. D. Forsyth, J. Ponce, Computer vision, a modern approach, Prentice Hall, 2003.
2. R. Gonzales, R. Woods, Digital image processing, 2nd Ed., Prentice Hall, 2002.
3. E. Trucco, A. Verri, Introductory techniques for 3-D computer vision, Prentice Hall, 1998.
4. M. Sonka, V. Hlavac, R. Boyle, Image processing, analysis and machine vision, Chapman and Hall Computing series, 1993.
5. A. Bovik (Ed.), Handbook of image and video processing, 2nd ed., Elsevier AP, 2005.