Skip to main content
 

COMP52615: Computer Vision

It is possible that changes to modules or programmes might need to be made during the academic year, in response to the impact of Covid-19 and/or any further changes in public health advice.

Type Tied
Level 5
Credits 15
Availability Available in 2023/24
Module Cap None.
Location Durham
Department Computer Science

Prerequisites

  • None

Corequisites

  • COMP52815 Robotics - Planning and Motion; COMP52715 Deep Learning for Computer Vision and Robotics; PHYS51915 Introduction to Machine Learning and Statistics; PHYS52015 Introduction to Scientific and High Performance Computing

Excluded Combinations of Modules

  • None

Aims

  • Develop knowledge of key concepts, approaches and algorithms in Computer Vision related to automatic understanding of image and video data sources;
  • Develop critical understanding and appreciation of current theoretical and empirical research in computer vision and its application within industry.

Content

  • Themes will be chosen from contemporary areas of computer vision including the following:
  • basic, intermediate and advanced features representations
  • object detection and object/scene classification
  • stereo vision
  • object tracking
  • real-time processing approaches
  • scene reconstruction from multiple images
  • applications of computer vision for autonomous navigation

Learning Outcomes

Subject-specific Knowledge:

  • By the end of the module students should have:
  • developed a critical understanding 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;
  • developed an advanced knowledge of the principles and practice of analysing relevant computer vision algorithms for problem suitability;
  • developed a good understanding of managing the trade-off between task performance and real-time processing performance within the context of computer vision;
  • explored the most recent advancements in the relevant academic literature and developed a critical understanding of their implications for current industry practice.

Subject-specific Skills:

  • By the end of the module, students should have developed highly specialised and advanced technical, professional and academic skills that enable them to:
  • formulate and solve problems that involve the automatic understanding of image and video data sources using a range of algorithmic approaches;
  • develop computer vision software solutions and use appropriate algorithms and approaches to address both industrial and research application tasks

Key Skills:

  • Written communication;
  • Planning, organising and time management;
  • Problem solving and analysis;
  • Using initiative
  • Adaptability
  • Numeracy
  • Computer literacy

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

  • A combination of lectures, seminars, and guided reading will contribute to achieving the aims and learning outcomes of this module.
  • The summative written assignment will test students' knowledge and critical understanding of the material covered in the module, their analytical and problem-solving skills.

Teaching Methods and Learning Hours

ActivityNumberFrequencyDurationTotalMonitored
Lectures102 per week2 hours20 
Seminars62 per week2 hours12 
Preparation and Reading118 
Total150 

Summative Assessment

Component: CourseworkComponent Weighting: 100%
ElementLength / DurationElement WeightingResit Opportunity
Coursework or Take-Home Exam48 hours100 

Formative Assessment

Feedback on coursework/take-home exam.

More information

If you have a question about Durham's modular degree programmes, please visit our Help page. If you have a question about modular programmes that is not covered by the Help page, or a query about the on-line Postgraduate 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.