Unit information: Machine Vision (UWE, UFMFRR-15-M) in 2020/21

Unit name	Machine Vision (UWE, UFMFRR-15-M)
Unit code	EMATM0056
Credit points	15
Level of study	M/7
Teaching block(s)	Teaching Block 1 (weeks 1 - 12)
Unit director	Dr. Zhang
Open unit status	Not open
Pre-requisites	None
Co-requisites	None
School/department	School of Engineering Mathematics and Technology
Faculty	Faculty of Engineering

Description including Unit Aims

The definition and scope of what is meant by the term ‘machine vision’ is changing rapidly as, via increasing capabilities often enabled through innovation in machine learning, new and exciting contributions are being made in applications across a wide variety of disciplines - such as robot navigation, human-robot interaction, healthcare technologies and in precision agriculture. Given the ubiquity of camera equipped smartphones and the wide availability and variety of alternative imaging devices (e.g. thermal and RGB-D cameras), one should not be surprised to notice that machine vision technology is increasingly becoming a part of everyday life. Just as how a visual sense is important to human beings, it is arguably just as important to new forms of AI enabled systems. Therefore, the ability to “observe” the world with visual sensors, to “describe” the world from pictures or sequences of pictures, and to use this information to make useful decisions, is core to machine vision applications today.

This module provides an introduction to machine vision including the fundamentals of image formation and image processing as well as state-of-the-art feature extraction and image-based machine learning techniques. The course content is research-informed and practice-led, and as such, aims to provide students with the key skills that meet the needs of industry. The core syllabus is outlined below (note this is by no means an exhaustive list), where all elements are, where possible, supported using example case study materials drawn from current research and practical application.

AIMS

Basic concepts:

• What is machine vision/computer vision/robotic vision?
• Machine vision vs. human vision
• Machine vision applications across disciplines (e.g. healthcare, agriculture, security, robot navigation, etc.)
• Core stages of the machine vision process

Image formation and representation

• Camera model
• Hardware elements: lighting, camera, optical configuration, etc.
• Different types of projection
• Binary, greyscale and colour image representations

Basic image processing techniques

• Convolution
• Filtering
• Segmentation

Feature extraction

• Edges, corners and gradients
• Invariant features
• Feature detectors and descriptors

3D imaging

• Applications
• Laser triangulation
• Stereo triangulation
• Structured light
• Photometric stereo

Machine learning (deep learning) in machine vision

• Machine learning models for image/video analysis (e.g. recognition/classification tasks)
• Data preparation and model validation

Generating machine vision code

Intended Learning Outcomes

Refer to UWE unit level guidance.

Teaching Information

Refer to UWE unit level guidance.

Assessment Information

Refer to UWE unit level guidance.

Reading and References

https://rl.talis.com/3/uwe/lists/A1B547D8-85D2-BFCD-9029-443E63D59E22.html