Computer Vision
Module aims
In this module you will learn how images are represented on computers and how they can be analysed by computer algorithms to extract semantic information. As part of the module you will have the opportunity to develop algorithms for detecting interesting features in images, design neural networks to perform natural image classification and explore algorithms for solving real-world problems such as hand-written digit recognition etc.
Learning outcomes
Upon successful completion of this module you will be able to:
- Design filters for image processing, edge detection and interest point detection
- Compare different feature descriptors used for interest point description and image classification
- Develop and implement neural networks for image classfication
- Appraise ideas underlying object detection and image segmentation
- Compare commonly used methods for motion estimation and object tracking
- Transform between the 2D coordinate system of an image and the 3D world
Module syllabus
This module covers the following topics:
- Image filtering
- Edge detection and interest point detection
- Feature descriptors
- Image classification
- Object detection and image segmentation
- Neural networks
- Motion estimation
- 3D vision
Teaching methods
The teaching approach is centred around the desire to solve real-world visual information processing problems, such as natural image classification, object detection and image segmentation etc. Such examples are used throughout to demonstrate how the principles taught can be applied in practice.
The concepts that you have learnt in lectures will be reinforced by unassessed, formative, tutorial exercises and assessed computer-based courseworks. The courseworks will cover both low-level and high-level vision topics. The lab sessions are supervised, so you will receive technical support from Graduate Teaching Assistants (GTAs).
An online service will be used as a discussion forum for the module.
Assessments
Computer-based courseworks count for 30% of the marks and the final exam counts for the remaining 70% of the marks. The courseworks are in the format of jupyter notebook, which enables you to fill in source code, discuss your solutions and display results as a pdf file for submission.
There will be detailed written feedback for each of the assessed courseworks and class-wide feedback explaining common pitfalls and suggestions for improvement.