COIT29224 - Deep Learning for Applied Computer Vision

Showing: 2026 HE Term 2
General Information

Unit Synopsis

This unit introduces deep learning for applied computer vision, focusing on perception and decision-making problems in autonomous systems. You will build a solid foundation in supervised learning, neural networks, convolutional architectures, and state-of-the-art vision models. You will apply these techniques to real-world datasets, including RGB images, hyperspectral data, drone imagery, and sports video, gaining hands-on experience with data from robotic and sensor platforms. Through case-based learning and programming exercises, you will formulate practical problems as learning tasks, design and train models, and evaluate their performance using quantitative metrics and visual analysis. The unit takes an end-to-end perspective, covering data preprocessing, data annotation, model training, optimisation, testing, evaluation, and deployment. By the end of the unit, you will be able to build deployable deep learning pipelines suitable for use in robotic platforms and decision-support systems across various domains.

Details

Level Postgraduate
Unit Level 9
Credit Points 6
Student Contribution Band SCA Band 2
Fraction of Full-Time Student Load 0.125
Pre-requisites or Co-requisites

Pre-requisite: COIT20277 Introduction to Artificial Intelligence.

 

Important note: Students enrolled in a subsequent unit who failed their pre-requisite unit, should drop the subsequent unit before the census date or within 10 working days of Fail grade notification. Students who do not drop the unit in this timeframe cannot later drop the unit without academic and financial liability. See details in the Assessment Policy and Procedure (Higher Education Coursework).

Class Timetable View Unit Timetable
Residential School No Residential School

Unit Availabilities from Term 2 - 2026


Attendance Requirements

All on-campus students are expected to attend scheduled classes - in some units, these classes are identified as a mandatory (pass/fail) component and attendance is compulsory. International students, on a student visa, must maintain a full time study load and meet both attendance and academic progress requirements in each study period (satisfactory attendance for International students is defined as maintaining at least an 80% attendance record).

Assessment Overview

Recommended Student Time Commitment

Each 6-credit Postgraduate unit at CQUniversity requires an overall time commitment of an average of 12.5 hours of study per week, making a total of 150 hours for the unit.

Assessment Tasks

Assessment Task Weighting
1. Practical Assessment 25%
2. Practical Assessment 35%
3. Written Assessment 40%

This is a graded unit: your overall grade will be calculated from the marks or grades for each assessment task, based on the relative weightings shown in the table above. You must obtain an overall mark for the unit of at least 50%, or an overall grade of ‘pass’ in order to pass the unit. If any ‘pass/fail’ tasks are shown in the table above they must also be completed successfully (‘pass’ grade). You must also meet any minimum mark requirements specified for a particular assessment task, as detailed in the ‘assessment task’ section (note that in some instances, the minimum mark for a task may be greater than 50%).

Consult the University's Grades and Results Policy for more details of interim results and final grades

Past Exams

Previous Feedback

Feedback, Recommendations and Responses

Every unit is reviewed for enhancement each year. At the most recent review, the following staff and student feedback items were identified and recommendations were made.

Source: Student Evaluation
Feedback:
 The unit should include more real-world examples and applications of Evolution Strategies (ES).

Recommendation:
 We will review the unit content to include more real-world examples and applications in our next offering.

Action Taken:
 Demonstrated research papers showcasing real-world applications of Evolutionary Algorithms in IoT and multiprocessor system optimisation, and explained how GPU acceleration can enhance computational efficiency.
Source: Unit Coordinator Reflection
Feedback:
 Students would benefit from strengthening their understanding of mathematical foundations, particularly linear algebra and probability.

Recommendation:
 Introduce additional scaffolding materials or pre-assessment refreshers on linear algebra and probability to better prepare students for advanced topics such as CMA-ES and other metaheuristic algorithms.

Action Taken:
 In Progress
Source: Unit Coordinator Reflection
Feedback:
 Students would benefit from step-by-step examples and visual demonstrations to better connect algorithm theory with implementation.

Recommendation:
 Incorporate clear, step-by-step working examples and visual demonstrations to help students connect algorithm theory with implementation.

Action Taken:
 In Progress
Unit Learning Outcomes

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

  1. Formulate supervised deep learning tasks for real-world computer vision perception and decision-making problems by critically analysing and selecting suitable datasets
  2. Design, implement, and optimise deep learning models for image classification, detection, segmentation, and vision-based decision-making, justifying architectural choices for each application
  3. Develop and integrate software solutions that apply deep learning to practical vision problems, including prediction, detection, segmentation, and object tracking, demonstrating professional judgement in deployment
  4. Evaluate, interpret, and communicate model performance using quantitative metrics, visualisation techniques, and structured reporting, critically assessing model strengths, limitations, and potential improvements.

The Skills Framework for the Information Age (SFIA) standard covers the skills and competencies related to information and communication technologies. SFIA defines levels of responsibility and skills. SFIA is adopted by organisations, governments and individuals in many countries. SFIA is increasingly being used when developing job descriptions and role profiles. SFIA can be used by individuals to create a personal skills profile. The Australian Computer Society (ACS) recognises the SFIA and provides MySFIA to help ACS members build a skills profile.

This unit contributes to the following workplace skills as defined by SFIA 9 (the SFIA code is included):

  • Machine learning (MLNG) 
  • Artificial intelligence (AI) and data ethics (AIDE) 
  • Software design (SWDN)
  • Programming/software development (PROG)
  • Data visualisation (VISL)
  • Functional testing (TEST)
  • Application Support (ASUP).
Alignment of Assessment Tasks to Learning Outcomes
Assessment Tasks Learning Outcomes
1 2 3 4
1 - Practical Assessment • • • •
2 - Practical Assessment • • •
3 - Written Assessment • •
Alignment of Graduate Attributes to Learning Outcomes
• Professional Level
• Advanced Level
Graduate Attributes Learning Outcomes
1 2 3 4
1 - Knowledge • • • •
2 - Communication • •
3 - Cognitive, technical and creative skills • • •
4 - Research •
5 - Self-management •
6 - Ethical and Professional Responsibility •
7 - Leadership •
Alignment of Assessment Tasks to Graduate Attributes
• Professional Level
• Advanced Level
Assessment Tasks Graduate Attributes
1 2 3 4 5 6 7 8 8