Aims

The aims of the course are to:

• introduce the principles, models and applications of computer vision.
• cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
• give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.

Objectives

As specific objectives, by the end of the course students should be able to:

• design feature detectors to detect, localise and track image features.
• model perspective image formation and calibrate single and multiple camera systems.
• recover 3D position and shape information from arbitrary viewpoints;
• appreciate the problems in finding corresponding features in different viewpoints.
• analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
• understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint.
• appreciate the commerical and industrial potential of computer vision but understand its limitations.

Content

• Introduction (1L)
  Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. Geometrical and statistical frameworks for vision. 3D interpretation of 2D images. Applications.
   
• Image structure (4L)
  Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem and corner detection. Image pyramids, blob detection with band-pass filtering. The SIFT feature descriptor for matching. Characterising textures.
   
• Projection (4L)
  Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants. 
   
• Stereo vision and Structure from Motion (2L)
  Epipolar geometry and the essential matrix. Recovery of depth by triangulation. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape examples from multiple view stereo.
   
• Deep Learning for Computer Vision  (5L)
  Basic architectures for deep learning in computer vision. Object detection, classification and semantic segmentation. Object recognition, feature embedding and metric learning. Transformer architectures and self-supervised learning.
   
• Example classes
  Discussion of examples papers and past examination papers will be integrated with lectures.

This syllabus contributes to the following areas of the UK-SPEC standard:

Toggle display of UK-SPEC areas.

 
Last modified: 28/09/2023 15:45

Aims

The aims of the course are to:

• introduce the principles, models and applications of computer vision.
• cover image structure, projection, stereo vision, structure from motion and object detection and recognition.
• give case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.

Objectives

As specific objectives, by the end of the course students should be able to:

• design feature detectors to detect, localise and track image features.
• model perspective image formation and calibrate single and multiple camera systems.
• recover 3D position and shape information from arbitrary viewpoints;
• appreciate the problems in finding corresponding features in different viewpoints.
• analyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;
• understand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoin.
• appreciate the industrial potential of computer vision but understand the limitations of current methods.

Content

• Introduction (1L)
  Computer vision: what is it, why study it and how ? The eye and the camera, vision as an information processing task. A geometrical framework for vision. 3D interpretation of 2D images. Applications.
   
• Image structure (3L)
  Image intensities and structure: edges, corners and blobs. Edge detection, the aperture problem. Corner and blob  detection. Contour extraction using B-spline snakes. Texture. Feature descriptors and matching.
   
• Projection (3L)
  Orthographic projection. Planar perspective projection. Vanishing points and lines. Projection matrix, homogeneous coordinates. Camera calibration, recovery of world position. Weak perspective and the affine camera. Projective invariants. 
   
• Stereo vision and Structure from Motion (3L)
  Epipolar geometry and the essential matrix. Recovery of depth. Uncalibrated cameras and the fundamental matrix. The correspondence problem. Structure from motion. 3D shape from multiple view stereo.
   
• Object detection and recognition (3L)
  Basic target detection and tracking. Machine learning for object detection and recognition. Random decision forests, support vector machines and boosting. Deep learning with convolutional neural networks.
   
• Example classes (3L)
  Discussion of examples papers and past examination papers.

This syllabus contributes to the following areas of the UK-SPEC standard:

Toggle display of UK-SPEC areas.

 
Last modified: 31/05/2017 10:06

Objectives

As specific objectives, by the end of the course students should be able to:

• understand the kinematical properties of curved surfaces;
• understand the load-carrying mechanisms for plates and shell structures;
• formulate the governing equations of deformation for small displacement behaviour;
• identify the benefits and limitations associated with closed-form solutions;
• appreciate the difference between stretching and bending effects in shells;
• appreciate the effects of geometrical non-linearity;
• be aware of the current state-of-the art in advanced shells;
• understand the nature of stability, instability and multistability in shells, and their practical exploitation.

Content

This module introduces the mechanics of plates and shells: thin-walled elastic surfaces that are important components of many structures and engineering devices. Key kinematical concepts are introduced for describing the initial and deformed shape of surface, either to make the description more succinct, or to reveal essential/invariant properties: these include the familiar Mohr’s circle, surfaces of revolution, and the Gaussian curvature. The relationship between internal strains and external shape is revealed for conventional smooth elastic shells. The manufacture of traditional engineering shells is reviewed, and their constitutive response is formulated: more “advanced” shell materials are introduced, including smart materials. The imperatives of equilibrium, compatibility and Hooke’s law are presented for deriving the final governing equations of deformation for circular and rectangular plates undergoing small displacements—a fraction of the thickness of shell. The distinction between bending and stretching responses of the shell is tackled through the membrane hypothesis and extended, first, to axisymmetrical pipe problems, and then to panel buckling under end-wise compression, which introduces geometrically non-linear behaviour. This is extended in cases of more compliant shells where displacements are expected to be much larger—of the order of the thickness, requiring more elaborate analysis techniques for tractable solutions: two approaches are presented, including an introduction of inextensibility theory. Finally, the behaviour and analysis of multistable shells are introduced: these show dramatic shape-changing properties, which may be exploited in novel “morphing” structures.

Geometry and kinematics of surfaces (4L)

• Properties of curves and surfaces: curvature and twist.
• Mohr’s circle of curvature and twist.
• Kinematics of surfaces of revolution and circular plates.
• Gaussian curvature: extrinsic and intrinsic viewpoints, principal radii of curvature.
• Inextensibility of creased sheets: simple surface strain, Gauss’ Theorema Egregium.
• Mixed/hierarchical kinematics: corrugated and compliant shells.

Materials (2L)

• Traditional engineering materials: metals, composites and natural materials, methods of manufacture, applications.
• Constitutive laws: bending and stretching generalised Hooke’s laws, thermal effects.
• Bending and stretching strain energy densities.
• Advanced engineering materials: review of smart/actuating materials, applications.
• Natural shells: growth and bio-mimicry, constitutive laws.

Loading of shells: small displacement theories (3L)

• Bending of circular and rectangular plates: imperatives of equilibrium, Hooke’s Law, and compatibility.
• Surfaces of revolution: membrane hypothesis and bending-stretching interaction in pipes.
• Two-surface idealisation and panel buckling.

Loading of shells: large displacement theories (3L)

• Non-linear methods: solutions by inspection and substitution; the lenticular plate.
• Inextensibility Theory.

Unloaded shells: multistability (2L)

• Applications.
• Analytical modelling: effects of material constitution, pre-stress, actuation and shape.

This syllabus contributes to the following areas of the UK-SPEC standard:

Toggle display of UK-SPEC areas.

 
Last modified: 11/06/2025 17:44

Objectives

As specific objectives, by the end of the course students should be able to:

• have some appreciation of the principles of architectural engineering, with a strong focus on environmental and structural aspects.
• be aware of the various functional requirements of building services and building envelopes, and of how they can be met by combinations of materials and proper construction techniques.
• be aware of current digital and computational techniques used in design analysis.
• design using timber

Content

This module is run in conjunction with the Department of Architecture. CUED students who elect to do this module will work together one full afternoon per week with final year students from the Department of Architecture. The module involves an architectural engineering design exercise, with students working in mixed groups of architects and engineers.

The course focuses on energy-efficient building designs. It also considers structural design -- specifically timber.

Mich 2017 exercise was on designing tall timber buildings. Projects vary from year to year.

The teaching format will be unconventional. Each afternoon will probably begin with a talk by one of the lecturers or by an external speaker. For the remaining class time, students will work (in groups) on developing environmental, structural and other strategies for their design project.

On week 6 of the course, each group will make a presentation of its design (including a physical model) to an assembled group of architectural, structural, environmental experts.  Weeks 7-8 will be devoted to developing detailed design of parts of the project, with students working on their individual reports.

Course Schedule

All classes will be in LR3, Inglis Building, Engineering Dept., 2.00-5.00pm Thursdays.

1. Thursday 4^th October

             Course Introduction

• Lecture 1: Supertall Timber  (Michael Ramage)
• Teams will be formed and the following Project Tasks distributed:

A:   Precedent timber construction materials

B:   Precedent Tall Buildings

C:   Exemplary Tall Timber buildings

D:   Exemplary timber building (not necessarily tall)

E:   Fire Safety in tall buildings

F:    Ventilation of tall buildings

G:   Energy efficiency and sustainability of tall buildings

H:   Façade Design of Tall Buildings

J:     Daylighting and solar control of tall buildings

K:   Site: analysis of climate data of London

L:    Site: Digital 3D Model of the Site & Urban Context

M:  PassiveHaus and other Energy Efficiency Standards

N:   Site: Solar & daylighting Analysis

N:   Site: Local Air Movement Analysis

O:   Urban Design Analysis of the Site

Teams will upload their documentation by 2 pm, 11^th October onto Moodle.

2. Thursday 11^th October

• Lecture 2: Timber Engineering (Ed Moseley, Director of Adams Kara Taylor AKT II )
• Group work

Project Tasks Due (5% mark)

3. Thursday 18^th October

• Lecture 3: Passive house principles in tall buildings (Ivan Jovanovich, Associate Director of Atelier Ten)
• Group work

4. Thursday 25^th October

• Lecture 4: Urban design lecture (Kevin Flanagan, PLP Architecture)
• Group work

5. Thursday 1st^th  November

• Lecture 5: Daylighting & Energy Efficiency (Ruchi Choudhary)
• Group Work

6. Thursday 8^nd November

• Design Review (20% mark) Critics: Ron Baker, Kevin Flanagan, Ed Moseley, Simon Smith, Shaun Fitzgerald, Michael Ramage, Ruchi Choudhary, Allan McRobie, Meredith Davey

7. Thursday 15^th November

• Workshop 1: Ventilation Design of tall buildings (Prof. Shaun FitzGerald, Royal Academy of Engineering Visiting Professor)

8. Thursday 22^rd  November

• Workshop 2: Structural Detailing of Timber Buildings (Simon Smith, Smith & Wallworks)

This syllabus contributes to the following areas of the UK-SPEC standard:

Toggle display of UK-SPEC areas.

 
Last modified: 03/10/2018 12:21