Overview
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
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).
Offerings For Term 1 - 2027
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).
All University policies are available on the CQUniversity Policy site.
You may wish to view these policies:
- Grades and Results Policy
- Assessment Policy and Procedure (Higher Education Coursework)
- Review of Grade Procedure
- Student Academic Integrity Policy and Procedure
- Academic Progression Policy and Procedure
- Student Refund and Credit Balance Policy and Procedure
- Complaints Policy and Procedure
- Information and Communications Technology Acceptable Use Policy and Procedure
This list is not an exhaustive list of all University policies. The full list of University policies are available on the CQUniversity Policy site.
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.
Feedback from UC reflection
Students can use AI to achieve very good assessment results, making it difficult for the assessment to accurately and fairly reflect their individual performance.
Improve assessment design to reduce inappropriate AI use, for example, by incorporating open-ended, competition-based tasks with no standard answers that require students to demonstrate originality and critical thinking.
Feedback from UC reflection
The current marking criteria are too broad to accurately assess the quality of student work.
Develop more detailed marking criteria that clearly align assessment tasks with the intended learning outcomes.