BMVC 2004 Electronic Proceedings

Table of Contents

Kingston Bridge

Invited talks

Human Shape and Motion from Video (abstract) (paper)
P. Fua    (EPFL, Switzerland)   

From Subspace to Submanifold Methods (abstract) (paper)
M. Brand (MERL Research Lab, USA)                               


A Mid-Level Description of Video, with Application to Non-photorealistic Animation (abstract) (paper)
J. P. Collomosse and P. M. Hall (University of Bath)
EigenFairing: 3D Model Fairing using Image Coherence (abstract) (paper)
P. Mishra, O. Amidi, and T. Kanade (Carnegie Mellon University, USA)

Drums and Curve Descriptors (abstract) (paper)
M. Zuliani, C. Kenney, S. Bhagavathy and B. S. Manjunath (University of California, Santa Barbara)


Reversible Jump Markov Chain Monte Carlo for Unsupervised MRF Color Image Segmentation (abstract) (paper)
Z. Kato (University of Szeged, Hungary)
Texture-Based Vanishing Point Voting for Road Shape Estimation (abstract) (paper)
C. Rasmussen    (University of Delaware, USA)
Central Catadioptric Line Detection (abstract) (paper)
P. Vasseur and E. M. Mouaddib (UPJV, France)
Direct and Specific Fitting of Conics to Scattered Data (abstract) (paper)
M. Harker, P. O’Leary (University of Leoben, Austria) and P. Zsombor-Murray (McGill University, Canada)


Junction Matching and Fundamental Matrix Recovery in Widely Separated Views (abstract) (paper)
E. Vincent and R. Laganière (University of Ottawa, Canada)
A method for learning matching errors for stereo computation (abstract) (paper)
D. Kong and H.Tao (University of California, Santa Cruz)
Fast Stereo Matching by Iterated Dynamic Programming and Quadtree Subregioning (abstract) (paper)
S.C. Leung, B. Appleton (The University of Queensland, Australia) and  C. Sun (CSIRO, Australia)

On the Probabilistic Epipolar Geometry (abstract) (paper)
S. S. Brandt (Helsinki University of Technology, Finland)
Reconstructing Relief Surfaces (abstract) (paper)
G. Vogiatzis (University of Cambridge), P. Torr (Oxford Brookes University), S. M. Seitz (University of Washington, USA) and  R.Cipolla (University of Cambridge)   

Poster Session 1

The Visual Hull of Piecewise Smooth Objects (abstract) (paper)
A. Bottino and A. Laurentini (Politecnico di Torino, Italy)
Non-Mercer Kernels for SVM Object Recognition (abstract) (paper)
S. Boughorbel    (INRIA, France), J.P.Tarel (ESE, LCPC, France) and F. Fleuret (INRIA, France)
Markov-based Silhouette Extraction for Three--Dimensional Body Tracking in Presence of Cluttered Background (abstract) (paper)
A. Shahrokni, V. Lepetit (EPFL, Switzerland), T. Drummond (University of Cambridge) and  P. Fua (EPFL, Switzerland)
Affine Invariant Image Segmentation (abstract) (paper)
A. Bhalerao and R. Wilson (Warwick University)
Wavelet-based holistic sequence descriptor for generating video summaries (abstract) (paper)
A. Graves and  S. Gong (Queen Mary, University of London)
Activity Based Video Content Trajectory Representation and Segmentation (abstract) (paper)
T. Xiang and S. Gong (Queen Mary, University of London)
A Texture-based Method for Detecting Moving Objects (abstract) (paper)
M. Heikkilä, M. Pietikäinen, and J. Heikkilä (University of Oulu, Finland)
Towards an alternative GPS sensor in dense urban environment from visual memory (abstract) (paper)
E. Royer, M. Lhuillier    , M. Dhome and T. Chateau (Université Blaise-Pascal, France)       

Factorization-based Hierarchical Reconstruction for Circular Motion (abstract) (paper)
H. Zhong and Y.S. Hung (University of Hong Kong)
Using Multiple Views To Resolve Human Body Tracking Ambiguities (abstract) (paper)
A. Leykin, F. Cutzu and M. Tuceryan (Indiana University, USA)
Attending, Foveating and Recognizing Objects in Real World Scenes (abstract) (paper)
M. Björkman and J-O. Eklundh (Royal Institute of Technology, Sweden)
EM Clustering of Incomplete Data Applied to Motion Segmentation (abstract) (paper)
K.Y. Wong, L. Ye and M.E. Spetsakis(York University, Canada)

Detection of Planar Regions with Uncalibrated Stereo using Distributions of Feature Points (abstract) (paper)
Y. Kanazawa and H. Kawakami (Toyohashi University of Technology, Japan)
HMM and IOHMM for the Recognition of Mono- and Bi-Manual 3D Hand Gestures (abstract) (paper)
A. Just    (IDIAP, France), O. Bernier (France Telecom Research and Development) and S. Marcel (IDIAP, France)
Motion based 3D Target Tracking with Interacting Multiple Linear Dynamic Models (abstract) (paper)
Z. Jia and A. Balasuriya (Nanyang Technological University, Singapore).                

A Multi-Stage Approach to Facial Feature Detection (abstract) (paper)
D. Cristinacce, T. Cootes and I. Scott (University of Manchester)
Articulated Shape Mixtures for Object Recognition (abstract) (paper)
A. Al-Shaher and E.R. Hancock (University of York)
Graph Matching using Spectral Embedding and Semidefinite Programming (abstract) (paper)
X. Bai, H. Yu and E. Hancock (University of York)

Dynamic Classifier for Non-rigid Human motion analysis (abstract) (paper)
H. Fei and I. Reid (University of Oxford)

Spectral Embedding and Min Cut for Image Segmentation (abstract) (paper)
F. Estrada, A. Jepson and C. Chennubhotla (University of Toronto, Canada)
Image normalization by mutual information (abstract) (paper)
E. Bart and S. Ullman (Weizmann Institute of Science, Israel)
Learning to detect low-level features (abstract) (paper)
P. Hall and M. Owen (University of Bath)
Face Inpainting with Local Linear Representations (abstract) (paper)
Z. Mo, J.P. Lewis and U. Neumann (University of Southern California)
A General Framework for 2D Multiframe and 3D Surface-to-surface Motion Estimation (abstract) (paper)
M. Li, C. Kambhamettu (University of Delaware, USA) and M. Stone (University of Maryland, USA)

Contour-based 3D Face Modeling from a Monocular Video (abstract) (paper)
H. Gupta (Object Video, USA), A.K. RoyChowdhury (University of California, USA) and R. Chellapa (University of Maryland Dental School, USA)

A Geometrically Calibrated Pinhole Camera Model for Single Omnidirectional Imaging System (abstract) (paper)
D. Moldovan, T. Wada (Wakayama University)

Oriented Discriminant Analysis (abstract) (paper)
F. De la Torre and T. Kanade (Carnegie Mellon University, USA)
Multi-Camera Target Tracking in Blind Regions of Cameras with Non-overlapping Fields of View (abstract) (paper)
A. Chilgunde (National University of Singapore), P. Kumar (Institute for InforComm Research, Singapore), S. Ranganath (University of Singapore) and H Weimin (Institute for InfoComm Research, Singapore)

Registration and Alignment

Image Mosaicing from Uncalibrated Views of a Surface of Revolution (abstract) (paper)
C. Colombo, A. Del Bimbo and F. Pernici (Università di Firenze, Italy)
Groupwise Non-Rigid Registration: The Minimum Description Length Approach (abstract) (paper)
C. J. Twining (University of Manchester), S. Marsland (Massey University, N.Z.) and C. Taylor (University of Manchester)   

Constraints on perspective images and circular panoramas (abstract) (paper)
M. Menem and T. Pajdla (Czech Technical University, Prague)

Statistical Modelling

Fitting a Single Active Appearance Model Simultaneously to Multiple Images (abstract) (paper)
C. Hu, J. Xiao, I. Matthews, S. Baker, J. F. Cohn, and T. Kanade    (Carnegie Mellon University)

Diffeomorphic Statistical Shape Models (abstract) (paper)
T.F. Cootes, C.J. Twining and C.J. Taylor (University of Manchester)
Generic vs. Person Specific Active Appearance Models (abstract) (paper)
R. Gross, I. Matthews, and S. Baker (Carnegie Mellon University)       

Surveillance and Monitoring                 

Occlusion Analysis: Learning and Utilising Depth Maps in Object Tracking (abstract) (paper)
D. Greenhill, J. Renno. J. Orwell and G.A. Jones (Kingston University)
Detecting inexplicable behaviour (abstract) (paper)
H. Dee and D. Hogg (University of Leeds)
Unsupervised Learning of Multi-Object Events (abstract) (paper)
S. Hongeng (University of Hamburg, Germany)
Real-time occupant detection system in an active illumination (abstract) (paper)
J.J. Yoon (City University) and T. J.Ellis (Kingston University)


Appearance factorization for facial expression analysis (abstract) (paper)
B. Abboud and F. Davoine (University of Technology of  Compiègne)
A New Kernel Direct Discriminant Analysis (KDDA) Algorithm for Face Recognition (abstract) (paper)
X. J. Wu (Jiangsu University of Science and Technology, China), J. Kittler (University of Surrey), J.Y. Yang (Nanjing University of Science & Technology, China), K. Messer (University of Surrey) and S. T. Wang (Nanjing University of Science & Technology, China)

Three-Dimensional Face Recognition Using Surface Space Combinations (abstract) (paper)
T. Heseltine, N. Pears and J. Austin (The University of York)
An Illumination Invariant Face Recognition System for Access Control using Video (abstract) (paper)
O. Arandjelović and R. Cipolla (University of Cambridge)
A Bayesian Occlusion Model for Sequential Object Matching (abstract) (paper)
T. Tamminen and J. Lampinen (Helsinki University of Technology, Finland)

Poster Session 2

Underexposed Image Correction Via Approximation of the Scene Radiance Function (abstract) (paper)
A. Robles-Kelly and E. Hancock (University of York)
2 Dimensional Electrophoresis Gel Registration Using Point Matching and Local Image-Based Refinement (abstract) (paper)
M. Rogers, J. Graham (University of Manchester) and R.P. Tong (AstraZeneca)
Single image facial view synthesis using SFS (abstract) (paper)
W.A.P. Smith, A. Robles-Kelly and E. Hancock (University of York)

Analysis of Features for Rigid Structure Vehicle Type Recognition (abstract) (paper)
V.S. Petrovic and T. Cootes (University of Manchester)

Real-Time Markerless Human Body Tracking with 3-D Voxel Reconstruction (abstract) (paper)
F. Caillette and T. Howard (University of Manchester)

Non-Linear Feature Selection for Classification (abstract) (paper)
M. Brown (UMIST) and N.P. Costen (Manchester Metropolitan University)

Map-Based Microscope Positioning (abstract) (paper)
G. Begelman, M. Lifshits and E. Rivlin (Technion, Israel)

From Maximum Entropy to Belief Propagation : An application to Skin Detection (abstract) (paper)
H. Zheng, M. Daoudi (ENIC-Telecom, France) and B. Jedynak (The Johns Hopkins University, US)

Restructured Eigenfilter Matching for Novelty Detection in Random Textures (abstract) (paper)
A. Monadjemi, M. Mirmehdi and B. Thomas (University of Bristol)

Fresnel Correction of the Beckmann Model (abstract) (paper)
H. Ragheb (Bu-Ali Sina University, Iran) and E. Hancock (University of York).

Indoor autonomous navigation using visual memory and pattern tracking (abstract) (paper)
O. Ait Aider, T. Chateau and  J.T. Lapresté (Université Blaise-Pascal, France)

Efficient Video Retrieval by Motion Trajectory (abstract) (paper)
Y. Jin and F. Mokhtarian (University of Surrey)

Robust Fusion of Colour Appearance Models for Object Tracking (abstract) (paper)
C.  Town and S. Moran (University of Cambridge)

Robust incremental rectification of sports video sequences (abstract) (paper)
J.B. Hayet, J. Piater and J. Verly (University of Liége)

On the choice of the goodness-to-fit term for multibaseline stereovision (abstract) (paper)
M. Sanfourche, G. Le Besnerais and F. Champagnat (ONERA, France)

Segmentation of colour images using variational expectation-maximization algorithm (abstract) (paper)
N. Nasios and A.G. Bors (University of York)

Metrology from Vertical Objects (abstract) (paper)
X. Cao    and H. Foroosh (University of Central Florida, USA)

Quantifying Temporal Saliency (abstract) (paper)
H. Hung and S. Gong (Queen Mary, University of London)

SAP: A robust approach to track objects in video streams with Snakes And Points (abstract) (paper)
V. Gouet and B. Lameyre (CNAM, France)

Recovering Camera Pose from Omni-directional Images (abstract) (paper)
A. Wan, A. Siu and R. Lau (City University of Hong Kong)

Interaction between hand and wearable camera in 2d and 3d environments (abstract) (paper)
W.W. Mayol, A.J. Davison, B.J. Tordoff, N.D.Molton and D.W. Murray (University of Oxford)

A Course to Fine Multiscale Approach for Linear Least Squares Optical Flow Estimation (abstract) (paper)
F. Lauze (IT University of Copenhapen, Denmark), P. Kornprobst (INRIA, France) and E. Mémin (University of Rennes, France)
A Variational Algorithm For Motion Compensated Inpainting (abstract) (paper)
F. Lauze and M. Nielsen (IT University of Copenhapen, Denmark)
Extending Pictorial Structures for Object Recognition (abstract) (paper)
M. Pawan Kumar, P.H.S. Torr (Oxford Brookes University) and A. Zisserman     (University of Oxford)
Principal Components Analysis of Optical Snow (abstract) (paper)
V. Chapdelaine-.Couture, S. Roy (University of Montreal, Canada), M.S. Langer (McGill University, Canada) and R. Mann (University of Waterloo, Canada)
Two--level MRF Models for Image Restoration and Segmentation (abstract) (paper)
M.Rivera (Centro de Investigacion en Matematicas, Mexico) and J.C.Gee (University of Pennsylvania, USA)

An Image-Based System for Urban Navigation (abstract) (paper)
D. Robertsone and R. Cipolla (Cambridge University)

Real-time 3D Football Ball Tracking from Multiple Cameras (abstract) (paper)
J. Ren, J. Orwell, G.A. Jones and M. Xu    (Kingston University)
Shadow Classification and Evaluation for Soccer Player Detection (abstract) (paper)
J. Renno, J. Orwell, D. Thirde and G.A. Jones (Kingston University)

Motion and Tracking

View-based Location and Tracking of Body Parts for Visual Interaction (abstract) (paper)
A. Micilotta and R. Bowden (University of Surrey)            

Multi-Modal Tracking using Texture Changes (abstract) (paper)
C. Kemp and T. Drummond (University of Cambridge)
Order Matters: A Distributed Sampling Method for Multi-Object Tracking (abstract) (paper)
K. Smith and D. Gatica-Perez (IDIAP Research Institute, Switzerland)                                

Optical Flow                                                

Locally Planar Patch Features for Real-Time Structure from Motion (abstract) (paper)
N. Molton, A. Davison and I. Reid (University of Oxford)      

A Local Approach for Robust Optical Flow Estimation under Varying Illumination (abstract) (paper)
Y.H. Kim (Purdue University, USA), A. M. Martínez (The Ohio State University, USA) and A.C. Kak (Purdue University, USA)                    
Direct Estimation of Non-Rigid Registration (abstract) (paper)
A. Bartoli and A. Zisserman (University of Oxford)               

Techniques 1

Noise Filtering and Testing Illustrated Using a Multi-Dimensional Partial Volume Model of MR Data (abstract) (paper)
N.A. Thacker, M. Pokrić and D.C. Williamson (University of Manchester)
Shape from Diffuse Polarisation (abstract) (paper)
G. Atkinson and E. Hancock (University of York)
A Unified Framework for Scene Illuminant Estimation (abstract) (paper)
W. Zhou and C. Kambhamettu (University of Delaware, USA)    

Techniques 2

Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition (abstract) (paper)
T. Kadir (University of Oxford), R. Bowden, E. J. Ong (University of Surrey) and A. Zisserman (University of Oxford)    

Likelihood Models For Template Matching using the PDF Projection Theorem (abstract) (paper)
A. Thayananthan,  R. Navaratnam (University of Cambridge) P. H. S. Torr  (Oxford Brookes University) and R. Cipolla (University of Cambridge)
Semi-Local Affine Parts for Object Recognition (abstract) (paper)
S. Lazebnik (University of Illinois, USA), C. Schmid (INRIA, France) and Jean Ponce (University of Illinois, USA)                   

A Hybrid Object-Level/Pixel-Level Framework For Shape-based Recognition (abstract) (paper)
O. Carmichael and M. Hebert    (Carnegie Mellon University, USA)