COSC428-21S1 (C) Semester One 2021

Computer Vision

15 points

Start Date: Monday, 22 February 2021
End Date: Sunday, 27 June 2021
Withdrawal Dates
Last Day to withdraw from this course:
  • Without financial penalty (full fee refund): Sunday, 7 March 2021
  • Without academic penalty (including no fee refund): Friday, 14 May 2021


This course covers advanced techniques and algorithms used in real-time 3D computer vision and image processing, from medical imaging to intelligent autonomous UAV/robot vision.

The goal of computer vision/machine vision/robot vision/drone vision and deep learning is to recognise objects and their motion by creating a model of the real world from images. Object recognition and tracking needs to allow for large variations in appearance caused by changes in viewing position, illumination, occlusion and object shape.

This course encompasses the theory and practical applications of computer vision including image processing (useful in early stages of computer vision, usually to enhance particular information and suppress noise) and visual cognition (computational models of human vision) – from medical imaging to intelligent autonomous UAV/robot vision.

The objective of this course is to present an insight into the world of computer vision that goes beyond image processing algorithms. Students will acquire knowledge and an understanding of artificial vision from a system’s viewpoint. Various aspects will be examined and the main approaches currently available in the literature will be discussed, opening the door to the most important research themes.

COSC428 is available to all computer science, computer engineering, mechatronics, electrical engineering and software engineering students enrolled in their fourth year. The mathematical nature of computer vision enables the course material to be pitched as algorithms to computer science students and mathematics to engineering students (images are 2D matrices after all) and students have the option of completing their projects using any programming language/script (such as Python, C, C++, MATLAB, C#, Java) on any operating system (such as Windows, Linux, macOS, iOS or Android).

Learning Outcomes

  • The topics studied in this course will include:
  • Image processing
  • Deep learning
  • Filtering, Image Representations, and Texture Models
  • Image registration and mosaics
  • Colour Vision
  • Neurophysiology of vision
  • Multi-view Geometry
  • Projective Reconstruction
  • Stereo vision
  • Bayesian Vision; Statistical Classifiers
  • Clustering & Segmentation; Voting Methods
  • Invariant local features
  • Object recognition
  • Medical Imaging
  • Image Databases
  • Motion interpretation
  • Tracking and Density Propagation
  • Biometric authentication
  • Human activity recognition
  • Visual Surveillance and Activity Monitoring
  • Real-time robot vision (for robots and drones)
  • Innovative computer vision based human-computer interfaces


Subject to approval of the Head of Department.

Course Coordinator

Richard Green


Assessment Due Date Percentage 
Research Project 50%
Participation 10%
Final Exam (during the examinations period) 40%

Research Project
You will decide on a research topic, in consultation with Richard Green, early in the course. This computer vision project is evaluated by the quality of a 6 page conference style paper (not more than 4000 words), that describes your work . Depending on project choice, COSC428 students can access the computer vision lab in Erskine room 234.

Your research project consists of:
1. Final conference ready paper.
2. Commented documented source code (which you authored) and associated documentation
3. Demonstration of your project (where demos are expected to match your conference paper results).

Our (40%) COSC428 two-hour test is CLOSED BOOK.

Updated Semester One 2020 assessment deadlines and details will be available once finalised.

Textbooks / Resources

1. “Computer Vision, A Modern Approach”, by D.A. Forsyth & J. Ponce, Prentice Hall.
2. “Machine Vision”, by R. Jain, R. Kasturi, B. G. Schunck, McGraw Hill.
3. “Learning OpenCV: Computer Vision with the OpenCV Library”, by Gary Rost Bradski, Adrian Kaehler.

Indicative Fees

Domestic fee $1,033.00

* All fees are inclusive of NZ GST or any equivalent overseas tax, and do not include any programme level discount or additional course-related expenses.

For further information see Computer Science and Software Engineering .

All COSC428 Occurrences

  • COSC428-21S1 (C) Semester One 2021