ECE4076 Computer vision

When you finish this unit, you should be able to:

1. 1

   Interpret and apply mathematical optimisation, linear algebra, and supervised and unsupervised learning to computer vision problems.

2. 2

   Simulate cameras using projective and multi-view geometry to design model-based vision systems and algorithms that extract 3D and rotational information from images, alongside methods for image registration and stitching.

3. 3

   Differentiate between elements of the human visual system and computer vision pipelines, and reflect on the consequences for the design of algorithms for scene understanding.

4. 4

   Generate and document implementations of low, mid and high-level vision processes such as filtering and structure from motion, image segmentation and clustering, and model fitting and tracking.

5. 5

   Design ethical machine learning solutions to problems in computer vision, such as image classification, 3D reconstruction and pose estimation, object detection and semantic segmentation, by critically appraising information and publications.

6. 6

   Demonstrate the development, training and deployment of computer vision algorithms using a high-level programming language.