COMPM054 - Machine Vision
This database contains 2017-18 versions of the syllabuses. For current versions please see here.
|Code||COMPM054 (Also taught as COMPGI14)|
|Prerequisites||Successful completion of years 1 and 2 of the Computer Science, Mathematics and Computer Science or other Physical Science or Engineering programme with sufficient mathematical and programming content|
|Taught By||Gabriel Brostow (100%)|
|Aims||The course addresses algorithms for automated computer vision. It focuses on building mathematical models of images and objects and using these to perform inference. Students will learn how to use these models to automatically find, segment and track objects in scenes, perform face recognition and build three-dimensional models from images.|
|Learning Outcomes||To be able to understand and apply a series of probabilistic models of images and objects in machine vision systems. To understand the principles behind face recognition, segmentation, image parsing, super-resolution, object recognition, tracking and 3D model building.|
Two-dimensional visual geometry:
2-D transformation family. The homography. Estimating 2-D transformations. Image panoramas.
Three dimensional image geometry:
The projective camera. Camera calibration. Recovering pose to a plane.
More than one camera:
The fundamental and essential matrices. Sparse stereo methods. Rectification. Building 3D models. Shape from silhouette.
Vision at a single pixel:
Background subtraction and colour segmentations problems. Parametric, non-parametric and semi-parametric techniques. Fitting models with hidden variables.
Dynamic programming for stereo vision. Markov random fields. MCMC methods. Graph cuts.
Texture synthesis, super-resolution and denoising, image inpainting. The epitome of an image.
Dense Object Recognition:
Modelling covariances of pixel regions. Factor analysis and principle components analysis.
Sparse Object Recognition:
Bag of words, latent dirilecht allocation, probabilistic latent semantic analysis.
Probabilistic approaches to identity recognition. Face recognition in disparate viewing conditions.
Point distribution models, active shape models, active appearance models.
The Kalman filter, the Condensation algorithm.
Method of Instruction
Lectures, practical lab classes
The course has the following assessment components:
- Written Examination (2.5 hours, 80%)
- Coursework Section (2 pieces, 20%)
To pass this course, students must:
- Obtain an overall pass mark of 50% for all sections combined
- Obtain a minimum mark of 40% in each component worth ≥ 30% of the module as a whole.
The examination rubric is:
Answer 3 questions
Reading list available via the UCL Library catalogue.