Students

COMP8430 – Advanced Computer Vision and Action

2026 – Session 1, In person-scheduled-weekday, North Ryde

General Information

Download as PDF
Unit convenor and teaching staff Unit convenor and teaching staff Convenor, Lecturer
Xuhui Fan
xuhui.fan@mq.edu.au
4RPD 319
Lecturer
Diego Molla-Aliod
diego.molla-aliod@mq.edu.au
4RPD 358
Credit points Credit points
10
Prerequisites Prerequisites
COMP6420
Corequisites Corequisites
Co-badged status Co-badged status
Unit description Unit description

Computer vision is at the centre of AI technology, and the ability of an AI agent to take actions depends on it. Robots need it to navigate in a dynamic environment and self-driving cars need it to navigate on a road without causing harm to itself and others. This unit will expose students to fundamentals of computer and human vision, image formation, low-level image processing, and reinforcement learning techniques. Students will also gain an understanding of various computer vision tasks such as object detection and image style transfer, and in linking computer vision and image formation to other modalities like language (such as in text to image generation). Students will also apply computer vision to learning actions carried out by AI agents, including robots, in contexts such as game-playing or following instructions.  In doing so they will gain advanced skills involving cutting-edge deep learning models and related technologies. 

Learning in this unit enhances student understanding of global challenges identified by the United Nations Sustainable Development Goals (UNSDGs) Industry, Innovation and Infrastructure; Sustainable Cities and Communities

Important Academic Dates

Information about important academic dates including deadlines for withdrawing from units are available at https://www.mq.edu.au/study/calendar-of-dates

Learning Outcomes

On successful completion of this unit, you will be able to:

  • ULO1: Identify the key computer vision applications that match current and emerging industry needs.
  • ULO2: Explain the main techniques that are used to develop and implement computer vision applications, and how they link to the ability of AI to act in the world.
  • ULO3: Implement computer vision applications using common tools and libraries used in industry.
  • ULO4: Design AI and robotic agents that can act in environments using reinforcement learning techniques.
  • ULO5: Design computer vision applications using advanced deep learning techniques.
  • ULO6: Apply computer vision methods and techniques to industry applications using real data.
  • ULO7: Apply good practice in the development, monitoring, and deployment of computer vision systems

General Assessment Information

The assessment of this unit consists of three assignments and a final exam. You will submit the solutions to the three assignments via iLearn by the due date. The final examination is a closed book examination, and will be taken in person during the exam period.

Late Submission Policy

  • 5% penalty per day: If you submit your assessment late, 5% of the total possible marks will be deducted for each day (including weekends), up to 7 days.

    • Example 1 (out of 100): If you score 85/100 but submit 20 hours late, you will lose 5 marks and receive 80/100.

    • Example 2 (out of 30): If you score 27/30 but submit 1 day late, you will lose 1.5 marks and receive 25.5/30.

  • After 7 days: Submissions more than 7 days late will receive a mark of 0.

  • Extensions:

    • Automatic short extension: Some assessments are eligible for automatic short extension. You can only apply for an automatic short extension before the due date.

    • Special Consideration: If you need more time due to serious issues and for any assessments that are not eligible for Short Extension, you must apply for Special Consideration.

Need help? Review the Special Consideration page HERE

 

Assessments Release Dates

The assignments will be released no later than the dates listed below.

  • Major project - 09/03/2025
  • Programming Assignment - 20/04/2025

Assessments where Late Submissions will be accepted

  • Programming assignment - YES, Standard Late Penalty applies
  • Major Project - YES, Standard Late Penalty applies
  • Exam - NO, unless Special Consideration is Granted

Supplementary Exam

If you receive Special Consideration for the final exam, a supplementary exam will be scheduled after the normal exam period, following the release of marks. By making a special consideration application for the final exam you are declaring yourself available for a resit during the supplementary examination period and will not be eligible for a second special consideration approval based on pre-existing commitments. Please ensure you are familiar with the policy prior to submitting an application. Approved applicants will receive an individual notification one week prior to the exam with the exact date and time of their supplementary examination.

Requirements to Pass this Unit

To pass this unit, you must achieve a total mark equal or greater than 50%. This unit does not have hurdle assessments.

Special Consideration

The Special Consideration Policy aims to support students who have been impacted by short-term circumstances or events that are serious, unavoidable and significantly disruptive, and which may affect their performance in assessment. If you experience circumstances or events that affect your ability to complete the assessments in this unit on time, please inform the convenor and submit a Special Consideration request through ask.mq.edu.au.  

Assessment Tasks

Name Weighting Hurdle Due Groupwork/Individual Short Extension AI Approach
Programming assignment 30% No 29/05/2026 Individual Yes Open
Major Project 30% No 05/06/2026 Group No Open
Examination 40% No Exam Period Individual No Observed

Programming assignment

Assessment Type 1: Experiential task
Indicative Time on Task 2: 30 hours
Due: 29/05/2026
Weighting: 30%
Groupwork/Individual: Individual
Short extension 3: Yes
AI Approach: Open

You will implement an AI agent using reinforcement learning.
On successful completion you will be able to:
  • Explain the main techniques that are used to develop and implement computer vision applications, and how they link to the ability of AI to act in the world.
  • Design AI and robotic agents that can act in environments using reinforcement learning techniques.

Major Project

Assessment Type 1: Portfolio
Indicative Time on Task 2: 30 hours
Due: 05/06/2026
Weighting: 30%
Groupwork/Individual: Group
Short extension 3: No
AI Approach: Open

You will design, implement, deploy, evaluate, and monitor an industrial grade computer vision application that uses realistic data, requires advanced deep learning techniques, and integrates a robotic agent.
On successful completion you will be able to:
  • Identify the key computer vision applications that match current and emerging industry needs.
  • Explain the main techniques that are used to develop and implement computer vision applications, and how they link to the ability of AI to act in the world.
  • Implement computer vision applications using common tools and libraries used in industry.
  • Design computer vision applications using advanced deep learning techniques.
  • Apply computer vision methods and techniques to industry applications using real data.
  • Apply good practice in the development, monitoring, and deployment of computer vision systems

Examination

Assessment Type 1: Examination
Indicative Time on Task 2: 22 hours
Due: Exam Period
Weighting: 40%
Groupwork/Individual: Individual
Short extension 3: No
AI Approach: Observed

You will demonstrate an understanding of a selection of topics covered in the unit.
On successful completion you will be able to:
  • Identify the key computer vision applications that match current and emerging industry needs.
  • Explain the main techniques that are used to develop and implement computer vision applications, and how they link to the ability of AI to act in the world.
  • Implement computer vision applications using common tools and libraries used in industry.
  • Design AI and robotic agents that can act in environments using reinforcement learning techniques.
  • Design computer vision applications using advanced deep learning techniques.
  • Apply computer vision methods and techniques to industry applications using real data.

1 If you need help with your assignment, please contact:

  • the academic teaching staff in your unit for guidance in understanding or completing this type of assessment
  • Academic Success for academic skills support.

2 Indicative time-on-task is an estimate of the time required for completion of the assessment task and is subject to individual variation.

3 An automatic short extension is available for some assessments. Apply through the Service Connect Portal.

Delivery and Resources

During most of the weeks, there will be 2 hours of lectures and 2 hours of Practicals. All the required software will be installed in the computers of the PC labs allocated for the Practicals but you are free to bring your own device and install the software.

Lectures and practicals start on Week 1.

Delivery Modes

All lectures and Practicals are delivered in campus. The lectures will also be recorded and recordings of the lecture will be available via iLearn. There will not be recordings of the Practical sessions.

Methods of Communication

We will communicate with you via your university email or through announcements in iLearn. Queries to convenors can be made via the Contact tool in iLearn or sent to xiaohan.yu@mq.edu.au from your university email address.

Reading

Every week there will be a list of required and recommended readings. The list will be maintained in iLearn.

Most of the contents of the unit will be based on the following books:

  • François Chollet, Matthew Watson (2025). Deep Learning with Python, 3rd Edition. Manning Publications. Available in the library.

  • Valliappa Lakshmanan, Martin Görner, Ryan Gillard (2021), Practical Machine Learning for Computer Vision. O'Reilly. Available in the library.

  • Ayyadevara, Reddy (2024), Modern Computer Vision with PyTorch - Second Edition

  • Rajalingappaa Shanmugamani (2018), Deep Learning for Computer Vision: expert techniques to train advanced neural networks using TensorFlow and Keras. Pakt Publishing. Available in the library.

  • Hu (2023), The Art of Reinforcement Learning

Software

The main software for this unit is Anaconda for Python 3.13 with the following packages:

  1. numpy
  2. scipy
  3. pandas
  4. scikit-learn
  5. scikit-image
  6. gensim
  7. pytorch
  8. tensorflow
  9. opencv
  10. pillow
  11. gymnasium, Stable-Baselines3

Unit Web Page

Note that the majority of the unit materials is publicly available while some material requires you to log in to iLearn to access it.

The unit will make extensive use of discussion boards hosted within iLearn. Please post questions there, they will be monitored by the staff on the unit.

 

Unit Schedule

The following schedule is tentative and is only an indication of the actual contents. The final schedule will be available in iLearn.

Week Topic
1 Review of Basic Computer Vision
2 Managing your Computer Vision Project
3 Transfer Learning
4 Generative Adversarial Networks
5 DeepDream and Neural Style Transfer
6 Visual Embeddings
  RECESS
7 Introduction to Reinforcement Learning
8 Deep Reinforcement Learning
9 Practical Reinforcement Learning for Computer Vision and Action
10 Advanced Object Detection
11 Image Generation from Text
12 Multimodal Large Language Models
13 Review for Exam

Policies and Procedures

Macquarie University policies and procedures are accessible from Policy Central (https://policies.mq.edu.au). Students should be aware of the following policies in particular with regard to Learning and Teaching:

Students seeking more policy resources can visit Student Policies (https://students.mq.edu.au/support/study/policies). It is your one-stop-shop for the key policies you need to know about throughout your undergraduate student journey.

To find other policies relating to Teaching and Learning, visit Policy Central (https://policies.mq.edu.au) and use the search tool.

Student Code of Conduct

Macquarie University students have a responsibility to be familiar with the Student Code of Conduct: https://students.mq.edu.au/admin/other-resources/student-conduct

Results

Results published on platform other than eStudent, (eg. iLearn, Coursera etc.) or released directly by your Unit Convenor, are not confirmed as they are subject to final approval by the University. Once approved, final results will be sent to your student email address and will be made available in eStudent. For more information visit connect.mq.edu.au or if you are a Global MBA student contact globalmba.support@mq.edu.au

Academic Integrity

At Macquarie, we believe academic integrity – honesty, respect, trust, responsibility, fairness and courage – is at the core of learning, teaching and research. We recognise that meeting the expectations required to complete your assessments can be challenging. So, we offer you a range of resources and services to help you reach your potential, including free online writing and maths support, academic skills development and wellbeing consultations.

Student Support

Macquarie University provides a range of support services for students. For details, visit http://students.mq.edu.au/support/

Academic Success

Academic Success provides resources to develop your English language proficiency, academic writing, and communication skills.

The Library provides online and face to face support to help you find and use relevant information resources. 

Student Services and Support

Macquarie University offers a range of Student Support Services including:

Student Enquiries

Got a question? Ask us via the Service Connect Portal, or contact Service Connect.

IT Help

For help with University computer systems and technology, visit http://www.mq.edu.au/about_us/offices_and_units/information_technology/help/. 

When using the University's IT, you must adhere to the Acceptable Use of IT Resources Policy. The policy applies to all who connect to the MQ network including students.

Changes from Previous Offering

The number of assessments are reduced to three assessments, including programming assignment, major project and final exam. 

Unit information based on version 2026.03 of the Handbook