COSC428-19S1 (C) Semester One 2019

Computer Vision

15 points
18 Feb 2019 - 23 Jun 2019

Description

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 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.

Pre-requisites

Subject to approval of the Head of Department.

Timetable 2019

Students must attend one activity from each section.

Lecture A
Activity Day Time Location Weeks
01 Thursday 09:00 - 11:00 Ernest Rutherford 140 18 Feb - 7 Apr
29 Apr - 2 Jun
Computer Lab A
Activity Day Time Location Weeks
01 Monday 17:00 - 19:00 Jack Erskine 134 Lab 3 18 Feb - 7 Apr
29 Apr - 2 Jun
02 Thursday 13:00 - 15:00 Jack Erskine 134 Lab 3 18 Feb - 7 Apr
29 Apr - 2 Jun
Tutorial A
Activity Day Time Location Weeks
01 Monday 11:00 - 12:00 Ernest Rutherford 140 18 Feb - 7 Apr
29 Apr - 2 Jun

Course Coordinator

Richard Green

Assessment

Assessment Due Date Percentage 
Research Project 50%
Lab test (in the last week of term 1) 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 the work . All COSC428 students will have access to 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).

Textbooks

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.

Additional Course Outline Information

Syllabus

The topics studied in this course will include:
• Image processing
• 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

Indicative Fees

Domestic fee $1,002.00

* Fees include New Zealand GST 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

  • COSC428-19S1 (C) Semester One 2019