In this subject students learn computer vision technology in general and also focus on several specific algorithms. Students study the multiple view geometry in computer vision which includes topics on planar geometry, camera models, camera parameter estimations and epipolar and fundamental matrix. The students study the theory and practice of Recursive Bayesian estimation which includes topics on Kalman Filter and Particle Filter. The students also study other emerging topics in computer vision as computer vision is still an evolving technology.
No offerings have been identified for this subject in 2019.
HD/FL
One session
School of Computing and Mathematics
* be able to demonstrate understanding of multiple view geometry used in computer vision including topics on planar geometry, camera models, camera parameter estimations and epipolar geometry with fundamental matrix;
* be able to apply the theory of Recursive Bayesian estimation, including Kalman Filtering and Particle Filtering in image based tracking problems;
* be able to implement and analyse several algorithms using low-level computer vision library;
* be able to discuss and analyse several seminal algorithms in computer vision
Part 1: Multiple view geometry in computer vision:
* Planar geometry
* Camera models
* Camera parameter estimations
* Epipolar geometry and fundamental matrix
Part 2: Recursive Bayesian estimation:
* Probabilistic theories
* Kalman Filter
* Particle Filter
For further information about courses and subjects outlined in the CSU handbook please contact:
The information contained in the CSU Handbook was accurate at the date of publication: May 2019. The University reserves the right to vary the information at any time without notice.