Course Title: Visual Data Processing Applications

Part A: Course Overview

Course Title: Visual Data Processing Applications

Credit Points: 12.00

Terms

Course Code	Campus	Career	School	Learning Mode	Teaching Period(s)
MANU2452	City Campus	Postgraduate	172H School of Engineering	Face-to-Face	Sem 1 2017

Course Coordinator: Professor Alireza Bab-Hadiashar

Course Coordinator Phone: +61 3 9925 1692

Course Coordinator Email: abh@rmit.edu.au

Course Coordinator Location: City Campus 57.3

Pre-requisite Courses and Assumed Knowledge and Capabilities

None.

Course Description

This course develops your skills in the application of visual data processing techniques. Visual data is referred to as data obtained by light sensors, including cameras, laser scanners and the newer generation of devices such as Microsoft Kinect. The primary focus is on the techniques for segmentation of visual data for designing automated engineering systems. Segmentation is the art of breaking data into meaningful parts. In this course the emphasis is upon parametric segmentation using statistical model fitting techniques.
The course will specifically:
• Provide an understanding of probability and statistical modelling techniques;
• Develop high level skills in robust statistical segmentation techniques;
• Develop skills in the selection and application of visual sensors and their associated data processing techniques for various engineering tasks;
• Develop an ability to anticipate the social and financial impacts of decisions related to implementation of visual based technologies;
• Develop knowledge of future trends in visual data technologies.

Objectives/Learning Outcomes/Capability Development

This course contributes to the development of the following program learning outcomes.

1.Needs, Context and Systems
- Describe, investigate and analyse complex engineering systems and associated issues (using systems thinking and modelling techniques)

2.Problem Solving and Design
- Develop creative and innovative solutions to engineering problems
- Anticipate the consequences of intended action or inaction and understand how the consequences are managed collectively by your organisation.

3.Analysis
- Comprehend and apply advanced theory-based understanding of engineering fundamentals and specialist bodies of knowledge in the selected discipline area to predict the effect of engineering activities.
- Apply underpinning natural, physical and engineering sciences, mathematics, statistics, computer and information sciences.

4.Professional Practice
- Understand the scope, principles, norms, accountabilities and bounds of contemporary engineering practice in the specific discipline

5.Research
- Be aware of knowledge development and research directions within the engineering discipline.
- Develop creative and innovative solutions to engineering challenges.

Course Learning Outcomes (CLOs)

Upon successful completion of this course you should be able to:
1. Demonstrate knowledge on the development and research directions in visual data processing. 
2. Develop creative and innovative solutions to a visual data processing problem and anticipate the financial and social consequences of any intended action.
3. Comprehend and apply advanced theory-based understanding of the use of visual data processing in designing automated industrial solutions, in the context of new and emerging manufacturing technologies.
4. Apply robust statistical modelling techniques within the context of designing intelligent solutions.
5. Use experience with practical industrial examples of visual data processing to assess the application of theoretical knowledge to industrial situations and demonstrations.
  

Overview of Learning Activities

Learning activities include: lectures, tutorials, group project and laboratory simulation activities.

Overview of Learning Resources

Course-related resources will be provided on Blackboard, which is accessed through myRMIT. This can include lecture material, practical examples, and there is a prescribed textbook and several recommended references for this course.

Overview of Assessment

 

 

 

 

X This course has no hurdle requirements.

☐ All hurdle requirements for this course are indicated clearly in the assessment regime that follows, against the relevant assessment task(s) and all have been approved by the College Deputy Pro Vice-Chancellor (Learning & Teaching).

 

 

 

Assessment item:  Group project and presentation
Weighting of final grade:  50%
Related course learning outcomes:  1, 2, 3, 4, 5
Description:  There will be a major assignment in which students in small groups will analyse an industrial application of visual data. You will be required to develop a computer program to simulate that application and present and justify your findings.

Assessment item:  Assignment
Weighting of final grade:  50%
Related course learning outcomes:  1, 2, 3, 4, 5
Description:  You will undertake an individual assignment to explore the application of a selected topic of the course in an industrial setting. This will involve problem definition, analysis, design, modelling, simulation, and interpretation of modelling and simulation results.