Description
Aims:
The module 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 object recognition and build three-dimensional models from images.
Intended learning outcomes:
On successful completion of the module, a student will be able to:
- Understand and apply a series of probabilistic models of images and objects in machine vision systems.
- Understand the principles behind object recognition, segmentation, super-resolution, scene analysis, tracking, and 3D model building.
Indicative content:
The following are indicative of the topics the module will typically cover:
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 silhouettes.
Vision at a single pixel:
- Background subtraction and colour segmentations problems. Parametric, non-parametric and semi-parametric techniques. Fitting models with hidden variables.
Connecting pixels:
- Dynamic programming for stereo vision. Markov random fields. MCMC methods. Graph cuts.
Texture:
- 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/Regression:
- Convolutional Neural Networks, Auto-encoders, Adversarial training, Equivariance.
Shape Analysis:
- Point distribution models, active shape models, active appearance models.
Tracking:
- The Kalman filter, the Condensation algorithm.
Requisites:
To be eligible to select this module as an optional or elective, a student must: (1) be registered on a programme and year of study for which it is a formally available; (2) have a UK-equivalent honours degree (or higher) in the field of Computer Science, Mathematics, or physical sciences and engineering; and (3) have some familiarity with digital imaging and digital image processing.
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
Ìý