CM22010: Visual computing
[Page last updated: 03 June 2024]
| Academic Year: | 2024/25 |
| Owning Department/School: | Department of Computer Science |
| Credits: | 10 [equivalent to 20 CATS credits] |
| Notional Study Hours: | 200 |
| Level: | Intermediate (FHEQ level 5) |
| Period: |
|
| Assessment Summary: | CWSI 50%, EXCB 50% |
| Assessment Detail: |
|
| Supplementary Assessment: |
|
| Requisites: |
Before taking this module you must ( take CM12005 AND take CM12006 )
While taking this module you must take CM22009 |
| Learning Outcomes: |
1. Describe and explain how images and videos are formed and displayed.
2. Formulate and explain fundamental image processing operations.
3. Describe low-level computer vision analysis and implement low-level operators.
4. Identify and manipulate suitable mathematical models for representing graphical objects.
5. Describe and implement algorithms to produce appropriate images on display devices.
6. Identify challenges in mid-level computer vision operations and select appropriate algorithms with justification.
7. Identify the challenges of interactive graphics and describe methods to overcome them.
8. Describe machine learning pipelines for computer vision operations and implement basic end-to-end learning systems. |
| Synopsis: | You will explore fundamental mathematical and computational techniques for processing and generating digital images from models of 2D and 3D objects and scenes. You will learn how to manipulate and animate these models, implement low-level operations and basic machine learning systems for computer vision, and generate realistic images and interactive visualizations. |
| Content: | Basics: images; colour spaces; imaging and display devices; video
Image formation: camera models, projections; calibration (concepts, not detail)
Image processing: image filtering; convolutions; warping; Fourier transform
Modelling: 2D/3D transformations and projections; lines, curves and surfaces; meshes and textures
Low-level computer vision: edge detection; corners
Mid-level computer vision: tracking; optical flow; stereo; geometry
Rendering: ray tracing (physics of image formation); visibility; lighting and shading; rasterisation
Animation/Interaction: basics of animation; interactive graphics/visualisation
Panorama stitching: features; descriptors; matching; alignment; blending
Deep learning: convolutional neural networks (CNNs) |
| Course availability: |
CM22010 is Compulsory on the following courses:Department of Computer Science
|
Notes:
|