ECE4076 - Computer vision - 2018

6 points, SCA Band 2, 0.125 EFTSL

Undergraduate - Unit

Refer to the specific census and withdrawal dates for the semester(s) in which this unit is offered.

Faculty

Engineering

Organisational Unit

Department of Electrical and Computer Systems Engineering

Chief examiner(s)

Professor Tom Drummond

Coordinator(s)

Professor Tom Drummond (Clayton)
Dr Maxine Tan (Malaysia)

Not offered in 2018

Prerequisites

ENG2092 or ENG2005, ECE2071 or TRC2400 and ECE2111 or TRC3500 or FIT1002 for students studying double degrees with science

Prohibitions

ECE4711, ECE4712, ECE5076, ECE5711, ECE5712

Synopsis

This unit aims to develop an understanding of methods for extracting useful information (eg 3-D structure; object size, motion, shape, location and identity, etc) from images. It will allow students to understand how to construct computer vision systems for robotics, surveillance, medical imaging, and related application areas.

Outcomes

At the successful completion of this unit you will be able to:

  1. Describe camera models.
  2. Describe the elements of the human visual system and perception.
  3. Apply geometry and photometry to image analysis.
  4. Generate implementations for low level vision processes such as linear filtering, edge detection, texture, multi view geometry, stereopsis, structure from motion and optical flow and mid-level vision processes, such as segmentation and clustering, model fitting and tracking.
  5. Design high-level vision processes such as model-based vision, surfaces and outlines, graphs, range data, templates and classifiers and learning methods.
  6. Generate code to complete computer vision programming exercises in programming languages such as C and MatLab.

Assessment

Continuous assessment: 40%

Examination (2 hours): 60%

Students are required to achieve at least 45% in the total continuous assessment component (assignments, tests, mid-semester exams, laboratory reports) and at least 45% in the final examination component and an overall mark of 50% to achieve a pass grade in the unit. Students failing to achieve this requirement will be given a maximum of 45% in the unit.

Workload requirements

2 hours lectures, 4 hours laboratory and practice classes and 6 hours of private study per week

See also Unit timetable information

This unit applies to the following area(s) of study