ECE4076 · Computer vision

Overview

This unit aims to develop an understanding of methods for extracting useful information (eg 3-D structure; object size, motion, shape, location and identity, etc) from images. It will allow you to understand how to construct computer vision systems for robotics, surveillance, medical imaging, and related application areas.

Areas of study: E3001 Bachelor of Engineering (Honours) - Specialisation: Robotics and mechatronics engineering Minor: Artificial intelligence in engineering S2010 Bachelor of Applied Data Science - Applied studies: Computer systems engineering S3003 Bachelor of Applied Data Science Advanced (Honours) - Applied studies: Computer systems engineering

Offerings

Assessment

The Handbook lists an examination for this unit.

Continuous assessment: 40% Final assessment: 60% This unit contains threshold hurdle requirement that you must achieve to be able to pass the unit. You are required to achieve at least 45% in the total continuous assessment component and at least 45% in the final assessment component. The consequence of not achieving a hurdle requirement is a fail grade (NH) and a maximum mark of 45 for the unit.

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Requisites

Learning outcomes

1. Interpret and apply mathematical optimisation, linear algebra, and supervised and unsupervised learning to computer vision problems.
2. Simulate cameras using projective and multi-view geometry to design model-based vision systems and algorithms that extract 3D and rotational information from images, alongside methods for image registration and stitching.
3. Differentiate between elements of the human visual system and computer vision pipelines, and reflect on the consequences for the design of algorithms for scene understanding.
4. Generate and document implementations of low, mid and high-level vision processes such as filtering and structure from motion, image segmentation and clustering, and model fitting and tracking.
5. Design ethical machine learning solutions to problems in computer vision, such as image classification, 3D reconstruction and pose estimation, object detection and semantic segmentation, by critically appraising information and publications.
6. Demonstrate the development, training and deployment of computer vision algorithms using a high-level programming language.

Workload

The minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of 3-6 hours of scheduled learning activities and 6-9 hours of independent study per week. Scheduled activities may include a combination of teacher-directed learning, peer-directed learning and online engagement. Independent study may include associated readings, assessment and preparation for scheduled activities.

Student experience, not official rules. Nothing here changes what the Handbook says.