Machine Vision - 2019 entry

***DATA SCIENCE AND DATA SCIENCE WITH BUSINESS STUDENTS ONLY***

How do we recognise objects and people?  How can we catch a ball?  How do we navigate our way from our desk to the coffee machine, withouth bumping into each other?  These seemingly simple tasks have represented a challenge for AI scientists for decades.  Recent developments in machine vision have seen significant improvement in important applications (face detection cameras, body tracking, and autonomous cars).

Pre-requisites: ECMM430 Fundamentals of Data Science, ECMM434 Machine Learning & Statistical Modelling.
Co-requisites: None.

This module will provide you with the fundamentals of machine vision and image processing, covering the essential challenges and key algorithms for solving a variety of problems related to automated processing of visual data. The course will provide both theoretical grounding and a practical introduction to classical and state-of-the-art approaches. Theory and methods will be taught through practical applications of machine vision and will cover a broad range of problems, from low-level image processing to object recognition, motion tracking and 3D vision.

Content will be delivered in an intensive one-week teaching block consisting of lectures and practical work. Self-study and coursework will complete the module teaching activities.

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge

Discipline Specific Skills and Knowledge

Personal and Key Transferable / Employment Skills and Knowledge

Topics will include:

• Image processing: convolution, linear filters, Fourier transforms, image gradients
• Feature extraction & matching: edge & corner detection, multi-scale analysis, feature descriptors, feature matching and tracking
• Geometric Image formation: geometric transformations, pinhole camera and perspective effects
• Multi-view geometry and structure from motion
• Dense image correspondences: dense motion estimation, optical flow, stereo
• Recognition in Computer Vision: Classical approaches, Neural Networks and Convolutional Neural Networks
• Shape reconstruction: 2D and 3D shape modelling and fitting, active appearance models, 3D morphable models, motion capture

Deferral – if you miss an assessment for certificated reasons judged acceptable by the Mitigation Committee, you will normally be either deferred in the assessment or an extension may be granted. The mark given for a reassessment taken as a result of deferral will not be capped and will be treated as it would be if it were your first attempt at the assessment.

Referral – if you have failed the module overall (i.e. a final overall module mark of less than 50%) you will be required to re-take some or all parts of the assessment, as decided by the Module Convenor. The final mark given for a module where re-assessment was taken as a result of referral will be capped at 50%.

Basic reading:

ELE: http://vle.exeter.ac.uk/

Web based and Electronic Resources:

CVOnline: an online compendium of computer vision techniques: http://homepages.inf.ed.ac.uk/rbf/CVonline/

Website of R. Szelinski’s Computer Vision book (including a free electronic version of the book): http://szeliski.org/Book

Getting Started with MATLAB: http://uk.mathworks.com/help/matlab/getting-started-with-matlab.html

Computer Vision System Toolbox of MATLAB: https://uk.mathworks.com/products/computer-vision.html

Keras: The Python Deep Learning library: https://keras.io/

Other Resources:

Reading list for this module: