Note: This unit version is currently under review and is subject to change!
ELEC5304: Multidimensional Signal Processing (2019 - Semester 1)
| Unit: | ELEC5304: Intelligent Visual Signal Understanding (6 CP) |
| Mode: | Normal-Day |
| On Offer: | Yes |
| Level: | Postgraduate |
| Faculty/School: | School of Electrical & Computer Engineering |
| Unit Coordinator/s: |
Dr Ouyang, Wanli
|
| Session options: | Semester 1 |
| Versions for this Unit: |
| Campus: | Camperdown/Darlington |
| Pre-Requisites: | None. |
| Brief Handbook Description: | This unit of study introduces basic and advanced concepts and methodologies in image processing and computer vision. This course mainly focuses on image processing and analysis methods as well as intelligent systems for processing and understanding multidimensional signals such as images, which include basic topics like multidimensional signal processing fundamentals and advanced topics like visual feature extraction and image classification as well as their applications for face recognition and object/scene recognition. It mainly covers the following areas: multidimensional signal processing fundamentals, image enhancement in the spatial domain and frequency domain, edge processing and region processing, object recognition and detection. |
| Assumed Knowledge: | Mathematics (e.g. probability and linear algebra) and programing skills (e.g. Matlab/Java/Python/C++) |
| Additional Notes: | From 2020, this unit will be renamed to Intelligent Visual Signal Understanding. |
| Timetable: | ELEC5304 Timetable | ||||||||||||||||||||
| Time Commitment: |
|
||||||||||||||||||||
| T&L Activities: | Independent Study: Students are expected to undertake the prescribed reading and work on homework exercises and assignments. |
Learning outcomes are the key abilities and knowledge that will be assessed in this unit. They are listed according to the course goal supported by each. See Assessment Tab for details how each outcome is assessed.
(7) Project and Team Skills (Level 3)
1. To be able to report results in a professional manner
(4) Design (Level 4)
2. To be able to use appropriate software platforms and tools for a given image processing or computer vision task
(3) Problem Solving and Inventiveness (Level 4)
3. To be able to use the existing image processing and computer vision packages
4. To be able to apply the image processing and computer vision techniques to solve real world applications
(1) Maths/ Science Methods and Tools (Level 3)
5. To be able to understand the fundamental theory of image processing and computer vision algorithms
| Assessment Methods: |
|
||||||||||||||||||||||||
| Assessment Description: |
Final Exam. Total weight: 70% Project 1. Total weight: 15% Project 2. Total weight: 15% [1]Text-based similarity detecting software (Turnitin) will be used for all text-based written assignments. [2]Late submission for lab reports: 1) There is no penalty for submissions until 11:59pm of the due day; 2) For submissions that are late than 11:59pm of the due day, 15% penalty will be applied for each day. Submissions that are late for one week will be given ZERO marks. |
||||||||||||||||||||||||
| Grading: |
|
||||||||||||||||||||||||
| Policies & Procedures: | See the policies page of the faculty website at http://sydney.edu.au/engineering/student-policies/ for information regarding university policies and local provisions and procedures within the Faculty of Engineering and Information Technologies. |
| Prescribed Text/s: |
Note: Students are expected to have a personal copy of all books listed.
|
| Recommended Reference/s: |
Note: References are provided for guidance purposes only. Students are advised to consult these books in the university library. Purchase is not required.
|
Note that the "Weeks" referred to in this Schedule are those of the official university semester calendar https://web.timetable.usyd.edu.au/calendar.jsp
| Week | Description |
| Week 1 | Introduction / Multidimensional Signal Processing Fundamentals (Principles of camera systems for visual information acquisition and digitization) |
| Week 2 | Mathematical Preliminaries for multi-dimensional signal processing -- 2D Convolution and Z-transform |
| Week 3 | Mathematical Preliminaries for multi-dimensional signal processing -- Matrix Manipulation |
| Week 4 | Mathematical Preliminaries for multi-dimensional signal processing -- deep learning |
| Week 5 | Image Restoration |
| Week 6 | Image Restoration - part 2 |
| Week 7 | Image Enhancement |
| Week 8 | Image Analysis - Edge detection |
| Week 9 | Image Analysis - Segmentation |
| Week 10 | Image Analysis - Detection and recognition |
| Week 11 | Application of deep learning for Multidimensional Signal Processing - part 1 |
| Week 12 | Application of deep learning for Multidimensional Signal Processing - part 2 |
| Assessment Due: Project 1 | |
| Assessment Due: Project 2 | |
| Week 13 | Review and preparation for the exam |
| Exam Period | Assessment Due: Final Exam |
Course Relations
The following is a list of courses which have added this Unit to their structure.
Course Goals
This unit contributes to the achievement of the following course goals:
| Attribute | Practiced | Assessed |
| (6) Communication and Inquiry/ Research (Level 4) | No | 0% |
| (7) Project and Team Skills (Level 3) | No | 6% |
| (5) Interdisciplinary, Inclusiveness, Influence (Level 4) | No | 0% |
| (4) Design (Level 4) | No | 6% |
| (2) Engineering/ IT Specialisation (Level 4) | No | 0% |
| (3) Problem Solving and Inventiveness (Level 4) | No | 47% |
| (1) Maths/ Science Methods and Tools (Level 3) | No | 41% |
These goals are selected from Engineering & IT Graduate Outcomes Table 2018 which defines overall goals for courses where this unit is primarily offered. See Engineering & IT Graduate Outcomes Table 2018 for details of the attributes and levels to be developed in the course as a whole. Percentage figures alongside each course goal provide a rough indication of their relative weighting in assessment for this unit. Note that not all goals are necessarily part of assessment. Some may be more about practice activity. See Learning outcomes for details of what is assessed in relation to each goal and Assessment for details of how the outcome is assessed. See Attributes for details of practice provided for each goal.
