Computer Vision and Image Analysis PG (8890.3)
| Available teaching periods | Delivery mode | Location |
|---|---|---|
| View teaching periods | On-campus |
Bruce, Canberra |
| EFTSL | Credit points | Faculty |
| 0.125 | 3 | Faculty Of Science And Technology |
| Discipline | Study level | HECS Bands |
| Academic Program Area - Technology | Post Graduate Level | Band 2 2021 (Commenced After 1 Jan 2021) Band 3 2021 (Commenced Before 1 Jan 2021) |
Through specific, applied examples, students will explore this highly topical field in the context of a widespread use of digital camera and image technology. These include examples from application areas such as digital photography, digital image enhancement, computer graphics, object recognition, object tracking, image segmentation, visual motion estimation, and multi-view camera systems.
As computer vision and image analysis draw from other related fields, such as perceptual psychology, digital signal processing, human-computer interaction, artificial intelligence and pattern recognition, students will be able to explore relevant theories and algorithms in these areas.
This unit may be cotaught with 11376 Computer Vision and Image Analysis.
Learning outcomes
On successfully completing the unit, students will have a sound understanding of and will have gained hands-on experience in:1. What computer vision and image analysis entails;
2. How images are formed and represented;
3. Understanding the basics of image processing and analysis techniques;
4. Understanding the concepts of fundamental theories in computer vision;
5. Writing Matlab programs for performing computer vision and image analysis tasks;
6. Being able to choose appropriate computer vision and image analysis techniques to solve real-world problems; and
7. Understanding the relationships between computer vision and image analysis on the one hand and fields such as perceptual psychology, digital signal processing, artificial intelligence and pattern recognition on the other hand.
Graduate attributes
1. UC graduates are professional - employ up-to-date and relevant knowledge and skills1. UC graduates are professional - communicate effectively
1. UC graduates are professional - use creativity, critical thinking, analysis and research skills to solve theoretical and real-world problems
1. UC graduates are professional - display initiative and drive, and use their organisation skills to plan and manage their workload
1. UC graduates are professional - take pride in their professional and personal integrity
2. UC graduates are global citizens - think globally about issues in their profession
2. UC graduates are global citizens - adopt an informed and balanced approach across professional and international boundaries
2. UC graduates are global citizens - communicate effectively in diverse cultural and social settings
2. UC graduates are global citizens - make creative use of technology in their learning and professional lives
2. UC graduates are global citizens - behave ethically and sustainably in their professional and personal lives
3. UC graduates are lifelong learners - reflect on their own practice, updating and adapting their knowledge and skills for continual professional and academic development
3. UC graduates are lifelong learners - adapt to complexity, ambiguity and change by being flexible and keen to engage with new ideas
3. UC graduates are lifelong learners - evaluate and adopt new technology
Prerequisites
11512 Pattern Recognition and Machine Learning PGCorequisites
None.Incompatible units
11376 Computer Vision and Image AnalysisEquivalent units
None.Assumed knowledge
Working knowledge of discrete mathematics, algebra and numerical analysis.| Year | Location | Teaching period | Teaching start date | Delivery mode | Unit convener |
|---|---|---|---|---|---|
| 2025 | Bruce, Canberra | Semester 1 | 03 February 2025 | On-campus | Dr Ibrahim Radwan |
| 2026 | Bruce, Canberra | Semester 1 | 16 February 2026 | On-campus | Dr Ibrahim Radwan |
Required texts
Required:
Richard Szeliski, "Computer Vision: Algorithms and Applications", 2nd ed., Springer, 2022, ISBN 978-3030343712
This book is available for purchase, for example, through The School Locker. This textbook is also available as an e-book. A limited number of copies of this book is also available from the UC Library.
Recommended for advanced students:
E R Davies & Matthew Turk, "Advanced Methods and Deep Learning in Computer Vision", Academic Press, ISBN: 978-0128221099
A limited number of copies of this book is also available from the UC Library.
Submission of assessment items
Extensions & Late submissions
Assessments are meant to be individual work, unless explicitly stated otherwise, although talking a problem over with another student or tutor is considered one reasonable way of learning. However, the actual submitted assessment must be the student's own work. Students are expected to familiarise themselves with the University's Student Charter https://www.canberra.edu.au/Policies/PolicyProcedure/Index/200. Experience has shown that students who do not do their own work are unlikely to successfully complete the unit.
Assessment submissions will be electronic through the Unit Website interface on UC Learn. For the Computer Vision Concepts Implementation assessment, students need to submit their programming code and any additional files, such as images etc. if required, to UC Learn. For the Student Colloquium Research Paper Presentation assessment, students need to submit all documents (presentation file(s) and research paper) that form part of their presentation to UC Learn.
Assessent submissions will be assessed for addressing the specific requirements of each assessment task, as stated in the assessment task descriptions, as well as for employing good software engineering principles. Assessment submissions will receive a numerical mark, which together in their entirety with the other assessment items define a student's final grade as outlined in this section.
Responsibility for understanding
If there is any doubt with regard to the requirements of any particular assignments or assessment procedure, the onus for clarifying the issue rests with the student who should contact the unit convenor or tutor. Further, it is the responsibility of students to ensure that they are correctly enrolled in the unit and that the tutor and Student Administration have their correct contact details.
Supplementary assessment
There will be no deferred assessments except for documented extenuating circumstances as per the university's Assessment Procedures.
Students must apply academic integrity in their learning and research activities at UC. This includes submitting authentic and original work for assessments and properly acknowledging any sources used.
Academic integrity involves the ethical, honest and responsible use, creation and sharing of information. It is critical to the quality of higher education. Our academic integrity values are honesty, trust, fairness, respect, responsibility and courage.
UC students have to complete the Academic Integrity Module annually to learn about academic integrity and to understand the consequences of academic integrity breaches (or academic misconduct).
UC uses various strategies and systems, including detection software, to identify potential breaches of academic integrity. Suspected breaches may be investigated, and action can be taken when misconduct is found to have occurred.
Information is provided in the Academic Integrity Policy, Academic Integrity Procedure, and University of Canberra (Student Conduct) Rules 2023. For further advice, visit Study Skills.
Learner engagement
Expected Average Student Workload: * denotes an assessable item
| Lectures | 12x 2h | = 24h |
| Computer laboratory classes | 12x 2h | = 24h |
| Content engagement (lectures, computer labs, reading) | 12x 2h | = 24h |
| * Computer Vision Concept implementation | = 45h | |
| * Student Colloquium Research Paper Presentation (incl. preparation) | = 18h | |
| * Online Tests #1-3 (incl. preparation) | = 15h |
Total 150 hours
Participation requirements
Participation in computer laboratory classes is a compulsory condition of this unit, and attendance will be recorded. You must participate in at least 75% of computer laboratory classes to pass this unit (e.g. at least 9 out of 12 classes). In the event that you cannot attend your assigned computer laboratory class due to illness or unavoidable work commitments, contact the Unit Convener as soon as possible to negotiate an alternate lab class later in the week (if available).
Experience has shown that students who do not attend the classes and do not engage with the content will have difficulty in satisfactorily passing the unit.
Required IT skills
- Fundamental programming concepts (i.e. this unit is not suitable for students who have no or only very limited prior programming experience)
- Usage of Windows or Mac computers
In-unit costs
Text book, 2x USB thumb drives
Work placement, internships or practicums
Not applicable to this unit
Additional information
In all cases of absence, sickness or personal problems, it is the student's responsibility to ensure that the unit convenor is informed. The minimum participation requirement must be met in order to pass the unit (regardless of supporting documentation).
It is important that students refer to the unit website (through UCLearn – UC's online learning environment) on a regular basis for any variations in the schedule and deadlines for the assessment tasks, which will be announced on the Unit Website. It is also the student's responsibility to ensure that they regularly check their UC email account, as electronic messages (whether via the unit's UCLearn site or directly) will be sent to this account.
The online discussion forum on the unit's UCLearn site is a very useful place for posting questions and students are strongly encouraged to make use of it.
- Semester 1, 2025, On-campus, UC - Canberra, Bruce (224463)
- Semester 1, 2024, On-campus, UC - Canberra, Bruce (218327)
- Semester 1, 2023, On-campus, UC - Canberra, Bruce (212721)
- Semester 1, 2022, On-campus, UC - Canberra, Bruce (205666)
- Semester 1, 2021, On-campus, UC - Canberra, Bruce (200272)
- Semester 1, 2020, On-campus, UC - Canberra, Bruce (193403)
- Semester 1, 2019, On-campus, UC - Canberra, Bruce (185102)
- Semester 1, 2018, On-campus, UC - Canberra, Bruce (182286)
