Vision, Graphics and Visualisation Group

 

Vision, Graphics and Visualisation

There is a significant computer vision component within the IRG group, including: feature-based localisation of aerial platforms for planetary exploration; extraction of the 3D structure of complex objects; EPSRC-funded work on appearance-based methods to provide mobile robots with various capabilities including topological mapping and pose stabilisation. These areas have recently led to additional funding covering vision aspects in planetary science and topological data analysis.

Our vision research has gone beyond a supporting role for robotics, reflected in the Department’s recent strategy to further develop the vision research sub-group. Texture analysis and synthesis is used in image manipulation and medical image understanding: developments in the topological aspects of the domain are supported by EPSRC funding and are leading to improved understanding of human image evaluation. Registration has concentrated on computational geometry and other mathematical properties of images and volumes, recognition of articulated motion for evaluating human walking patterns, and medical shape analysis.

Research Topics

  • Visual Navigation and Mapping
  • Topological Data Analysis
  • 3D Registration and Reconstruction
  • Medical Image Understanding
  • Inverse Brain/Robotics Eng.

Recent Submissions

  • McIntyre, James; Church, Andrew; Labrosse, Frédéric (2009-09)
    In this paper, we present an efficient way of representing and tracking a moving object in images. In our approach, the object is visually represented as a set of pixels corresponding to an ideal view of the object as seen ...
  • Woodland, Alan; Ugail, Hassan; Labrosse, Frédéric (British Machine Vision Association, 2007-09)
    This paper presents a method to extend PDE surfaces to high dimensional spaces. We review a common existing analytic solution, and show how it can be used straightforwardly to increase the dimension of the space the surface ...
  • Woodland, Alan; Labrosse, Frédéric (2008-06)
    Building computer representations of real objects, which could be archaeological artifacts or planned buildings, is a very active research area. Typically objects are represented in computer memory as a collection of ...
  • Woodland, Alan; Labrosse, Frédéric (Eurographics, 2005)
    Many computer vision and graphics related techniques rely upon illumination invariance of images to derive meaning from images of an object under varying lighting conditions. This is all the appearance-based methods. In ...
  • Lipsa, Dan R.; Laramee, Robert S.; Cox, Simon John; Davies, Ioan Tudur (2011-12-01)
    Research in the field of complex fluids such as polymer solutions, particulate suspensions and foams studies how the flow of fluids with different material parameters changes as a result of various constraints. Surface ...
  • Ugail, H.; Doherty, V.; Zwiggelaar, R.; Appleyard, S.; Huddy, G.; Rajoub, B.; Yap, M. H. (IEEE Press, 2012-06-13)
    The purpose of this paper is to present short reviews the face detection techniques and to study the effect of Multifractal analysis in detecting facial features. In reviewing the existing techniques, we have compared the ...
  • Strange, Harry George; Zwiggelaar, Reyer (2009-07)
    In the problem of mammographic image classification one seeks to classify an image, based on certain aspects or features, into a risk assessment class. The use of breast tissue density features provide a good way of ...
  • Davies, Ioan Tudur; Cox, Simon John (2009-07-20)
    The sedimentation of circular discs in a dry two-dimensional, monodisperse foam is studied. This, a variation of the classical Stokes experiment, provides a prototype experiment to study a foam’s response. The interaction ...
  • Little, Anthony C.; Jones, Benedict C.; Waitt, Corri; Tiddeman, Bernie; Feinberg, David R.; Perrett, David I.; Apicella, Coren L.; Marlowe, Frank W. (2008-05-07)
    Background Many animals both display and assess multiple signals. Two prominently studied traits are symmetry and sexual dimorphism, which, for many animals, are proposed cues to heritable fitness benefits. These traits ...
  • Fenelon, Valquiria; Santos, Paulo E.; Dee, Hannah Mary; Cozman, Fabio G. (2013-06-01)
    This paper describes a logic-based formalism for qualitative spatial reasoning with cast shadows (Perceptual Qualitative Relations on Shadows, or PQRS) and presents results of a mobile robot qualitative self-localisation ...
  • Zwiggelaar, R.; Ugail, H.; Yap, M. H. (2012-10-16)
    this paper proposes a method to detect the facial Action Units (AUs) and introduce an automatic measurement in predicting the intensity scores of each AU in near-to-frontal face image sequences. To our knowledge, this is ...
  • Zwiggelaar, Reyer; Roscoe, Jonathan Francis; Dee, Hannah (2012)
    Ultrasound is notorious for having significant noise with a low signal-to-noise ratio. This inhibits the performance of segmentation and causes difficulty for clinical evaluation, thus noise reduction is paramount to ...
  • Ugail, H.; Yap, M. H.; Rajoub, B.; Zwiggelaar, R.; Doherty, V.; Appleyard, S.; Huddy, G. (2012-05-21)
    The aim of our project is to provide a real-time dynamic passive profiling technique which will assist as a decision aid to Border Control Agencies, which has the potential to improve the hit rates. This paper discusses a ...
  • Vu, Ngoc-Son; Dee, Hannah Mary; Caplier, Alice (2012-07)
    Real-world face recognition systems require careful balancing of three concerns: computational cost, robustness, and discriminative power. In this paper we describe a new descriptor, POEM (patterns of oriented edge ...
  • Dee, Hannah Mary; Cohn, Anthony G.; Hogg, David C. (2012-03-13)
    This paper describes a method for building semantic scene models from video data using observed motion. We do this through unsupervised clustering of simple yet novel motion descriptors, which provide a quantized representation ...
  • Ashford, Isabella; Woodland, Alan (Nuffield Foundation, 2011-11-23)
  • Dee, Hannah; Santos, Paulo E. (2011-08-07)
    Recently, psychologists have turned their attention to the study of castshadows and demonstrated that the human perceptual system values information fromshadows very highly in the perception of spatial qualities, sometimes ...
  • MacParthalain, Neil; Jensen, Richard (2011-07-06)
    Much work has been carried out in the area of fuzzy-rough sets for supervised learning. However, very little has been accomplished for the unsupervised or semi-supervised tasks. For many real-word applications, it is often ...
  • Santos, Paulo E.; Fenelon, Valquiria; Dee, Hannah (2010)
  • Hogg, David C.; Dee, Hannah (2006)
    This paper will describe new work that attempts to perform the modelling of human behaviour not at the level of visible patterns of motion, but at the level of intentions. By inferring intentions in terms of known goals, ...

View more