Lecture: Computer Vision

15th September 2017
Lecture: Computer Vision

Lecturer: Prof. Aljosa Smolic. This course is an advanced master class in computer vision.

Module Code CS7GV1
Module Name Computer Vision
Module Short Title
Semester Taught HT
Contact Hours 2 lecture hours per week
Module Personnel Professor Aljosa Smolic
Learning Outcomes On successful completion of this module, students will be able to:

  • Review and asses advanced computer vision technologies
  • Present and discuss state-of-the-art computer vision algorithms
  • Implement, test, evaluate and report exemplary computer vision solutions
Learning Aims This course is an advanced master class in computer vision. It does not intend to teach fundamentals, but focuses on latest research. Guest lecturers will present leading edge research from various hot areas of computer vision. Students will get direct exposure to high class scientists and their research. In their own work, students will select each a recent paper and present it to the class. Further, they will be asked to execute small projects to explore selected state-of-the-art computer vison technology.
Module Content Specific topics addressed in this module may include:

  • Deep learning
  • Segmentation, keying, matting
  • Visual saliency and attention modelling
  • High dynamic range imaging
  • Light field technologies
  • Augmented, virtual, mixed reality
  • Free viewpoint video
  • 3D reconstruction
  • Visual effects
  • Colour transfer
  • Optical flow
  • Object detection and recognition
Recommended Reading List Fundamentals of computer vision in any form, e.g.

Computer Vision: Algorithms and Applications, Richard Szeliski, September 3, 2010 draft, 2010 Springer


Multiple View Geometry in Computer Vision

Second Edition

Richard Hartley and Andrew Zisserman,

Cambridge University Press, March 2004.


Module Prerequisites
Assessment Details 100% coursework:

50% Seminar presentation

50% Project


Assessment in the Supplemental session will be based on 100% coursework.

Module Website
Academic Year of Data: 2017/18