Module Search

COMP4107: ADVANCED COMPUTER VISION

Please ensure you check the module availability box for each module outline, as not all modules will run in each academic year. Each module description relates to the year indicated in the module availability box, and this may change from year to year, due to, for example: changing staff expertise, disciplinary developments, the requirements of external bodies and partners, and student feedback. Current modules are subject to change in light of the ongoing disruption caused by Covid-19.

Type	Open
Level	4
Credits	10
Availability	Available in 2023/24
Module Cap	None.
Location	Durham
Department	Computer Science

Prerequisites

COMP3527 Computer Vision

Corequisites

None

Excluded Combinations of Modules

None

Aims

To enable students to critically evaluate the development of contemporary computer vision systems utilising both existing and emerging technologies.
To enable students to study and research a number of topic themes across relevant computer vision application areas, focusing on case studies, and undertake research within these topic themes.

Content

Themes will be chosen from contemporary areas of computer vision including the following:
Advanced fundamental topics: segmentation, superpixels, saliency, optic flow and image registration in 2D/3D.
Computer vision for advanced visual semantic models, attribute learning, zero-shot learning, visual question and answering.
Computer vision for advanced object and scene understanding.
Computer vision for behaviour understanding.
Computer vision for security and biometrics.
Computer vision for image manipulation and augmentation.

Learning Outcomes

Subject-specific Knowledge:

On completion of this module, students will be able to demonstrate a systematic understanding of the contemporary computer vision topics presented and acritical awareness of how they are applicable to both current and emerging needs within the associated industrial and research environment.

Subject-specific Skills:

On completion of the module, students will be able to demonstrate:
an ability to critically analyse the task suitability of current and future approaches within each of the contemporary computer vision topics presented.
an ability to independently evaluate research issues within each contemporary computer vision topic grouping including state-of-the-art and common industrial applications thereof.
an ability to identify challenges and barriers to emerging issues within the contemporary computer vision topic areas and propose potential solutions.
an ability to propose, plan and carry out research focused on such contemporary computer vision approaches to support current and future software applications.

Key Skills:

On completion of the module, students will be able to demonstrate:
an ability to exercise judgement on current research topics.
an ability to propose and apply the appropriate techniques to a range of industrial and research applications.
an ability to effectively evaluate and communicate technical information at the forefront of the associated field.
an ability to confidently use relevant research material in the development of existing and new application areas.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

Lectures enable the students to learn new material relevant to logic, discrete structures and mathematics, as well as their applications.
Practical classes enable the students to put into practice learning from lectures and strengthen their understanding through application.
Formative and summative assessments assess the application of methods and techniques.

Teaching Methods and Learning Hours

Activity	Number	Frequency	Duration	Total
lectures	20	2 per week	1 hour	20
practical classes	2	2 set within the teaching period of the module	1 hour	2
preparation and reading				78
total				100

Summative Assessment

Component: Coursework		Component Weighting: 100%
Element	Length / Duration	Element Weighting	Resit Opportunity
Summative Assignment		100	No

Formative Assessment

Example formative exercises are given during the course.

More information

If you have a question about Durham's modular degree programmes, please visit our FAQ webpages, Help page or our glossary of terms. If you have a question about modular programmes that is not covered by the FAQ, or a query about the on-line Undergraduate Module Handbook, please contact us.

Prospective Students: If you have a query about a specific module or degree programme, please Ask Us.

Current Students: Please contact your department.