Monash University Handbook 2011 Undergraduate - Unit

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

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.

Objectives

To understand camera models
To learn to apply geometry and photometry to image analysis.
To understand the basic principles of laser scanners.
To understand the elements of the human visual system and perception.
To learn to implement low level vision processes (linear filtering, edge detection, texture, multi view geometry, stereopsis, structure from motion, optic flow).
To learn to implement midlevel vision (segmentation and clustering, model fitting, tracking).
To learn to implement high-level vision (model-based vision, surfaces and outlines, graphs, range data, templates and classifiers, learning methods).
To complete programming exercises (C, MatLab for example).

Assessment

Continuous assessment: 30%
Examination: (3 hours) 70%Students must achieve a mark of 45% in each of these two components to achieve an overall pass grade.

Contact hours

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

Prerequisites

ENG2092, ECE2071 or TRC2400 and ECE2011 or TRC3500

Prohibitions

ECE4711, ECE4712, ECE5076, ECE5711, ECE5712