CM52035: Advanced computer vision
[Page last updated: 22 April 2025]
Academic Year: | 2025/26 |
Owning Department/School: | Department of Computer Science |
Credits: | 10 [equivalent to 20 CATS credits] |
Notional Study Hours: | 200 |
Level: | Masters UG & PG (FHEQ level 7) |
Period: |
|
Assessment Summary: | CWRI 50%, CWSG 50% |
Assessment Detail: |
|
Supplementary Assessment: |
|
Requisites: |
In taking this module you cannot take CM32022 OR take CM30080
Before taking this module you must ( take CM22009 AND take CM22010 ) OR ( take CM20315 AND take CM20219 ) |
Learning Outcomes: |
1. Describe and implement advanced image processing algorithms;
2. Describe the mathematics of multi-view geometry and their applications to 3D reconstruction;
3. Understand classical and learning-based low- and high-level computer vision techniques;
4. Appreciate a broad range of contemporary computer vision and its applications;
5. Critically evaluate the strengths and weaknesses of various computer vision algorithms. |
Synopsis: | "Advanced Computer Vision dives deeper into advanced ways of processing images to extract information and models. This unit develops a deeper understanding of the underlying mathematics of images, to become familiar with several advanced computational techniques and algorithms in vision as well as their applications.
" |
Content: | Practical camera models: projections; calibration; rectification
Advanced image processing: feature detection; scale spaces and pyramids; compressed sensing
Multi-camera vision: planar geometry; epipolar geometry; the fundamental matrix
3D reconstruction; depth estimation; triangulation; structure from motion
Advanced classical and deep learning techniques for vision problems such as segmentation, detection, recognition; classification and regression models
Contemporary topics and applications of computer vision |
Course availability: |
CM52035 is Optional on the following courses:Department of Computer Science
|
Notes:
|