Skip to Content

Future Students - Courses

click here for a printable version of this page  

Computer Vision Systems

Unit Code: HET543




Duration

Contact Hours

Campus

Prerequisite

Corequisite


1 Semester

60 Hours

Hawthorn, Sarawak

200 Credit Points of any University Degree Course


Nil

Credit Points: 12.5 Credit Points

Related Course/s:

Back to Top

Aims & Objectives:

The aim of this subject is to introduce engineering students to computer vision systems. Students will then be able to develop skills for image analysis and processing. Students will also be able to explore and design a wide range of computer vision systems with application to industry. In addition, students will be exposed to some examples of computer vision system research in engineering disciplines.
After successfully completing this unit, you should be able to:
  • Understand the fundamental techniques of low-level image analysis methods, including image formation, edge detection, feature detection, and image segmentation.
  • Reconstruct three-dimensional scene information using techniques such as depth from stereo, structure from motion, and shape from shading.
  • Design machine learning algorithms for pattern recognition in computer vision systems.
  • Solve engineering problems by applying image processing and machine learning techniques.
  • Describe industry applications of computer vision systems.

Back to Top

Teaching Methods:

Lectures (36 hrs), Tutorials and Laboratory (24 hrs)

Back to Top

Assessment:

Examination (50%), Assignments and Laboratory reports (50%)

Back to Top

Generic Skills Outcomes:

Engineers Australia Generic Attributes

  • Ability to apply knowledge of basic science and engineering fundamentals.
  • In-depth technical competence in at least one engineering discipline.
  • Ability to undertake problem identification, formulation and solution.
  • Ability to utilise a system approach to design and operational performance.
  • Understanding of the principles of sustainable design and development.
  • Understanding of social, cultural global and environmental responsibilities of the professional engineer, and the need for sustainable development.

Swinburne Graduate Attributes intend to assist graduates to be:

  • Capable in their chosen professional, vocational or study areas.
  • Entrepreneurial in contributing to innovation and development within their business, workplace and community.
  • Effective and ethical in work and community situations.
  • Adaptable and able to manage changes.

Back to Top

Content:

Introduction to computer vision definition, application problems, operations on images and image devices
Imaging and image representation
Low-level image analysis
Pattern recognition concepts
Machine learning for pattern recognition
Perceiving 3D from 2D images
3D sensing and object pose computation
3D models and range image processing
Case studies

Back to Top

Textbooks:

Forsyth D. A. and Ponce J. , Computer Vision: A Modern Approach, Prentice Hall, Upper Saddle River, N.J., 2003

Back to Top

References:

Shapiro, L. G. and Stockman, G. C., Computer Vision, Prentice Hall, 2001
Kulkaini, A. D., Computer Vision and Fuzzy-Neural Systems, Prentice Hall, 2001

Back to Top