- Homepage
- Key Information
- Students
- Taught programmes (UG / PGT)
- Student Services and Procedures
- Student Support
- Events and Colloquia
- International Students
- Students as Change Agents (SACA)
- Student Staff Liaison Committees (SSLC)
- The Exeter Award
- Peer Support
- Skills Development
- Equality and Diversity
- Athena SWAN
- Outreach
- Living Systems Institute Webpage
- Alumni
- Info points and hubs
- Inbound Exchange Students
- Staff
- PGR
- Health and Safety
- Computer Support
- National Student Survey (NSS)
- Intranet Help
- College Website
Engineering, Mathematics and Physical Sciences Intranet
COMM413DA - Machine Vision (2023)
MODULE TITLE | Machine Vision | CREDIT VALUE | 15 |
---|---|---|---|
MODULE CODE | COMM413DA | MODULE CONVENER | Dr Anjan Dutta (Coordinator) |
DURATION: TERM | 1 | 2 | 3 |
---|---|---|---|
DURATION: WEEKS |
Number of Students Taking Module (anticipated) | 90 |
---|
DESCRIPTION - summary of the module content
How do we recognise objects and people? How can we catch a ball? How do we navigate our way from our desk to the coffee machine, without bumping into each other? These seemingly simple tasks have represented a challenge for AI scientists for decades. Recent developments in machine vision have seen significant improvement in important applications (face detection cameras, body tracking, and autonomous cars).
Pre-requisites: COMM416DA Learning from Data.
Co-requisites: None.
This module is a part of the dual-qualification MSc Data Science (Professional) / Level 7 Research Scientist Apprenticeship programme. It cannot be taken as an elective by students on other programmes.
The apprenticeship standard and other documentation relating to the Level 7 Research Scientist Apprenticeship can be found here: https://www.instituteforapprenticeships.org/apprenticeship-standards/research-scientist-v1-0.
AIMS - intentions of the module
This module will provide you with the fundamentals of machine vision and image processing, covering the essential challenges and key algorithms for solving a variety of problems related to automated processing of visual data. The course will provide both theoretical grounding and a practical introduction to classical and state-of-the-art approaches. Theory and methods will be taught through practical applications of machine vision and will cover a broad range of problems, from low-level image processing to object recognition, motion tracking and 3D vision.
In addition to its academic aims as part of the programme, this module has specific aims as part of the Level 7 Research Scientist Apprenticeship. The full list of Knowledge, Skills and Behaviours that must be demonstrated to complete the Apprenticeship can be found here: https://www.instituteforapprenticeships.org/apprenticeship-standards/research-scientist-v1-0.
This module will deliver content that may be used to evidence the Knowledge, Skills and Behaviours set out below. Primarily: K1, K4 and K5. Secondarily: S1, S2 and S6.
Knowledge (K), Skill (S) or Behaviour (B)
K1: Subject specific knowledge: A deep and systemic understanding of a named / recognised scientific subject as found in an industrial setting, such as biology, chemistry or physics, found in the nuclear, food manufacture, pharmacology or energy production sectors, at a level that allows strategic and scientific decision making, while taking account of inter relationships with other relevant business areas / disciplines.
K4: Research methodologies: Methodologies appropriate to the sector and how to formulate and apply a hypothesis. Appropriate application of scientific process. The unpredictability of research projects and the need to adapt and adjust daily planning needs to accommodate new developments.
K5: Data analysis and evaluation: Statistical analysis techniques, numerical modelling techniques and how they are applied in context. How to interpret and categorise data to make informed and objective decisions against the goals and targets of the project. How to evaluate and interpret the data and associated analysis against company objectives.
S1: Scientific Knowledge: Apply a range of advanced, new and emerging practical and experimental skills appropriate to the role (e.g. chemical synthesis, bio analysis, computational modeling).
S2: Data Collection and Reporting: Capture and evaluate data critically drawing a logical conclusion, e.g. Case Report Forms, Data Management Plans, Data Review Plans, edit checks and User Acceptance Testing Plans.
S6: Critical Thinking: Conceptualise, evaluate and analyse information to solve problems.
INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)
On successful completion of this module you should be able to:
Module Specific Skills and Knowledge
1. Explain key computer vision and image processing problems and their mathematical formulation.
2. Design and implement vision and image processing algorithms in a high-level language.
Discipline Specific Skills and Knowledge
3. Analyse and propose solutions for computer vision and image processing problems.
4. Select appropriate statistical representations, features and algorithms to suit problem specificities.
Personal and Key Transferable / Employment Skills and Knowledge
5. Understand and appreciate the limitations of different methods.
6. Effectively communicate to a technical audience using reports and documentation.
7. Critically read and report on research papers.
SYLLABUS PLAN - summary of the structure and academic content of the module
Topics will include:
- Image processing: convolution, linear filters, image gradients
- Feature extraction & matching: edge & corner detection, multi-scale analysis, feature descriptors, feature matching and tracking
- Geometric Image formation: geometric transformations, pinhole camera and perspective effects
- Multi-view geometry and structure from motion: 3D reconstruction
- Recognition in Computer Vision: classical approaches for image classification, and object detection, k-nearest neighbours and support vector machine classifiers. Deep learning for computer vision: neural networks, convolutional neural networks, object detection, semantic and instance segmentation.
LEARNING AND TEACHING
LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)
Scheduled Learning & Teaching Activities | 40.00 | Guided Independent Study | 110.00 | Placement / Study Abroad | 0.00 |
---|
DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS
Category | Hours of study time | Description |
Scheduled Learning and Teaching | 40 | Lectures, Practicals |
Guided independent study | 110 | Reading, preparation, coursework |
ASSESSMENT
FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade
Form of Assessment | Size of Assessment (e.g. duration/length) | ILOs Assessed | Feedback Method |
---|---|---|---|
Practical work | 16 hours | All | Oral |
SUMMATIVE ASSESSMENT (% of credit)
Coursework | 100 | Written Exams | 0 | Practical Exams | 0 |
---|
DETAILS OF SUMMATIVE ASSESSMENT
Form of Assessment | % of Credit | Size of Assessment (e.g. duration/length) | ILOs Assessed | Feedback Method |
---|---|---|---|---|
Programming practice and written essay | 40 | 8 hours, code+report | All | Written feedback and model answers |
Programming practice and written essay | 60 | 12 hours, code + report | All | Written feedback and model answers |
DETAILS OF RE-ASSESSMENT (where required by referral or deferral)
Original Form of Assessment | Form of Re-assessment | ILOs Re-assessed | Time Scale for Re-assessment |
---|---|---|---|
Summative assessment |
Programming practice and written essay (100%)
|
All | August re-assessment period |
RE-ASSESSMENT NOTES
Deferral – if you miss an assessment for certificated reasons judged acceptable by the Mitigation Committee, you will normally be either deferred in the assessment or an extension may be granted. The mark given for a reassessment taken as a result of deferral will not be capped and will be treated as it would be if it were your first attempt at the assessment.
Referral – if you have failed the module overall (i.e., a final overall module mark of less than 50%) you will be required to re-take some or all parts of the assessment, as decided by the Module Convenor. The final mark given for a module where re-assessment was taken as a result of referral will be capped at 50%.
RESOURCES
INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener
information that you are expected to consult. Further guidance will be provided by the Module Convener
Basic reading:
ELE: http://vle.exeter.ac.uk/
Web based and Electronic Resources:
CVOnline: an online compendium of computer vision techniques: http://homepages.inf.ed.ac.uk/rbf/CVonline/
Website of R. Szelinski’s Computer Vision book (including a free electronic version of the book): http://szeliski.org/Book
Getting Started with MATLAB: http://uk.mathworks.com/help/matlab/getting-started-with-matlab.html
Computer Vision System Toolbox of MATLAB: https://uk.mathworks.com/products/computer-vision.html
Keras: The Python Deep Learning library: https://keras.io/
Other Resources:
Reading list for this module:
Type | Author | Title | Edition | Publisher | Year | ISBN | Search |
---|---|---|---|---|---|---|---|
Set | Bishop, John C. | Pattern recognition and machine learning | Springer | 2006 | [Library] | ||
Set | Forsyth, David & Jean Ponce | Computer vision: a modern approach | 2nd | Pearson | 2011 | [Library] | |
Set | Jan Erik Solem | Programming Computer Vision with Python: Tools and algorithms for analyzing images | O'Reiley | 2012 | [Library] | ||
Set | Szeliski, Richard | Computer vision: algorithms and applications | 2nd | Springer | 2021 | [Library] |
CREDIT VALUE | 15 | ECTS VALUE | 7.5 |
---|---|---|---|
PRE-REQUISITE MODULES | COMM416DA |
---|---|
CO-REQUISITE MODULES |
NQF LEVEL (FHEQ) | 7 | AVAILABLE AS DISTANCE LEARNING | No |
---|---|---|---|
ORIGIN DATE | Thursday 06 July 2017 | LAST REVISION DATE | Tuesday 24 January 2023 |
KEY WORDS SEARCH | Computer vision, image processing, object recognition, object detection and segmentation, tracking, pattern recognition. |
---|