Undergraduate Programme and Module Handbook 2020-2021 (archived)

Module COMP3527: COMPUTER VISION

Department: Computer Science

COMP3527: COMPUTER VISION

Type	Open	Level	3	Credits	10	Availability	Available in 2020/21	Module Cap	None.	Location	Durham

Prerequisites

(COMP2271 Data Science AND COMP2261 Artificial Intelligence) OR COMP2231 Software Methodologies

Corequisites

COMP3547 Deep Learning and Reinforcement Learning

Excluded Combination of Modules

None

Aims

To enable students to critically evaluate the development of computer vision solutions across existing and emerging technology areas.
To enable students to understand and evaluate general image and video understanding themes across relevant application areas, focusing on relevant case studies.
To understand and apply the fundamental principles of applied computer vision solutions to a range of real world problems.

Content

Themes will be chosen from contemporary areas of computer vision including the following:
edge features, contours and shape fitting.
feature points for object detection and classification.
stereo vision (3D point clouds and depth images).
object classification using distributions of gradient information.
background modelling and object tracking.
end-to-end image classification and real-time object detection via deep machine learning.
image and video mosaicking and 3D scene reconstruction.
visual odometry for autonomous navigation.

Learning Outcomes

Subject-specific Knowledge:

On completion of this module, students will be able to demonstrate an in-depth knowledge of the contemporary computer vision topics presented, how these are applicable to relevant industrial problems and have future potential for emerging needs in both a research and industrial setting.

Subject-specific Skills:

On completion of the module, students will be able to demonstrate:
an ability to critically analyse contemporary computer vision deployment ("in-the-wild") and how they aid the delivery of broader software applications.
an ability to independently evaluate research issues in computer vision including current practices, recent developments and emerging trends.
an ability to appreciate the overlap between contemporary computer vision topics and how they are mutually beneficial in broader systems and applications design and development.

Key Skills:

On completion of the module, students will be able to demonstrate:
an ability to understand and effectively communicate technical information.
an ability to use research and industry standard material within both existing and new system scenarios.

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 computer vision as well as their applications.
Practical classes enable the students to put into practice learning from lectures and strengthen their understanding through application.
Formative assessments assess the application of methods and techniques, and examinations in addition assess an understanding of core concepts.

Teaching Methods and Learning Hours

Activity	Number	Frequency	Duration	Total/Hours
lectures	22	2 per week, unless there is a practical class that week	1 hour	22
practical classes	2	2 set within the teaching period of the module	1 hour	2
preparation and reading				76
total				100

Summative Assessment

Component: Examination		Component Weighting: 100%
Element	Length / duration	Element Weighting	Resit Opportunity
Examination	2 hours	100%	No

Formative Assessment:

Example formative exercises are given during the course. Additional revision lectures may be arranged in the module's lecture slots in the 3rd term.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University