Computer Engineering MA, Computer Vision and Multiview Geometry, 6 credits

Aim

The course aims to give a good understanding of theoretical concepts and practical methods in traditional computer vision and multivew geometry.

Course objectives

After completing the course the student shall be able to:
- describe fundamental concepts, terminology, models and methods in traditional computer vision and multiview geometry.
- apply acquired knowledge within the fields of traditional computer vision and multi-view geometry to solve relevant problems with camera based technology
- implement a number of fundamental methods/techiques within computer vision and multiview geometry
- systematically evaluate algorithms within the fields of traditional computer vision and multiview geometry with respect to pros and cons for different tasks and problems

Content

- Acquisition: images and image representations, cameras and camera models, capture and estimation of scene depth
- Detection: image processing, local descriptors and features, segmentation, objects, clustering, classification, and recognition
- Model fitting: Hough transform, RANSAC, structure from motion, 
- Tracking: by detection / optical flow and matching
- Registration: coordinate system alignment, merging
- Multiview geometry: projective geometry and transformations, two-view geometry, stereopsis, epipolar geometry

Entry requirements

Computer or Electrical Engineering, 60 credits, including programming, 10 credits, and Signal and Image Processing, 6 credits; Mathematical subjects, 30 credits, including probability theory and statistics, and linear algebra.

Selection rules and procedures

The selection process is in accordance with the Higher Education Ordinance and the local order of admission.

Teaching form

The course is taught using lectures, seminars, and laboratory sessions. The large part of the course is with limited supervision, where the student is assumed to work on lecture material and laboratory work.

Examination form

L101: Laboratory exercises, 2 Credits
Grade scale: Two-grade scale

T102: Written exam, 4 Credits
Grade scale: Seven-grade scale, A-F o Fx

Link to grading criteria: https://www.miun.se/gradingcriteria.

The examiner has the right to offer alternative examination arrangements to students who have been granted the right to special support by Mid Sweden University’s disabilities adviser.

Examination restrictions

Students are entitled to three examination opportunities within one year according to the examination format given in this version of the course syllabus. After the one-year period, the examination format given in the most recent version of the course syllabus applies.

Grading system

Seven-grade scale, A-F o Fx