Everyday millions of images and videos are being uploaded on the social media platforms. This has given computer scientist an interesting opportunity to empower computers with the capability of understanding the visual world around them. This area of computer vision is a sub field of artificial intelligence and can help in adding ?eyes? to computers. Can we develop techniques for making cars of the future smarter by making them ?see? the cars, road lanes, pedestrians and signs? How can the computers be empathetic? How to make them understands the emotion of the users? Can the machines in manufacturing environment detect quality of their output with visual computing? These along with many other questions can be answered by studying the area of computer vision.

11/09/2019 - Admin: Unit name has been updated and added exam information.

18/09/2020 - Admin: Update to include new assessment and teaching approach fields as per Handbook requirements.

This unit is a core elective within C6007 Master of Artificial Intelligence.

On successful completion of this unit students should be able to:

1. describe image analysis and low-level vision
2. describe semantic image and video understanding techniques
3. describe CNN and their applications.
4. implement and extend existing computer vision algorithms.
5. evaluate and compare techniques suitable for adding vision capability to unimodal and multimodal intelligent systems

020119

This unit will discuss the fundamental and modern concepts in image and video analysis. The students will be introduced to the basics of image processing and low-level vision. The topics related to image formation, operations, features and segmentation will enable students with the understanding for developing vision enabled systems. Concepts related to convolutional neural networks (CNN) will be introduced and recent examples will be thoroughly analysed. Recent computer vision concepts will be discussed from a deep learning perspective. The unit will be balance between the theoretical and the practical implementation aspects of computer vision

Technological requirements

Assignments will use the Python programming language.

On-campus

Online learning

Active learning

Simulation or virtual practice

Research activities

Examination (2 hours and 10 minutes): 40%; In-semester assessment: 60%

1. Assignment 1 - 20% - ULO: 1
2. Assignment 2 - 20% - ULO: 2, 3
3. Assignment 3 - 20% - ULO: 3, 4
4. Examination - 40% - ULO: 1, 2, 3, 5

Minimum total expected workload equals 12 hours per week comprising:

A minimum of 8 hours per week of personal study for completing lab/tutorial activities, assignments, private study and revision.

FIT5197