Incremental and Adaptive Abnormal Behaviour Detection ∗ (2009)
We develop a novel visual behaviour modelling approach that performs incremental and adaptive model learning for online abnormality detection in a visual surveillance scene. The approach has the...
Minimum Cuts of A Time-Varying Background (2008)
Motivated by the demand for an effective background model, robust to non-stationary environmental changes in outdoor scenes, we present a technique using Combinatorial Optimization to extract...
Conditional Mutual Infomation Based Boosting for Facial Expression Recognition (2008)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
This paper proposes a novel approach for facial expression recognition by boosting Local Binary Patterns (LBP) based classifiers. Low-cost LBP features are introduced to effectively describle local...
Ra Psarrout, Shaogang Gong, Hilary Buxtons
We address the problem of trajectory prediction in machine vision applications using variants of Elman’s partially recurrent networks. We use dynamic context to constrain the represen-tation learnt...
Sparse Multiscale Local Binary Patterns (2008)
In a Local Binary Pattern (LBP) representation, circular point features are taken in their entirety as predicates and restricted to uniform patterns with limited scales of small numbers of features...
Stephen Mckenna, Shaogang Gong
Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or...
Recognising the dynamics of faces across multiple views (2008)
Yongmin Li, Shaogang Gong, Heather Liddell
We present an integrated framework for dynamic face detection and recognition, where head pose is estimated using Support Vector Regression, face detection is performed by Support Vector...
Model Selection for Unsupervised Learning of Visual Context (2008)
This study addresses the problem of choosing the most suitable probabilistic model selection criterion for unsupervised learning of visual context of a dynamic scene using mixture models. A rectified...
Optimal Dynamic Graphs for Video Content Analysis (2008)
This study addresses the problem of learning the optimal structure of a dynamic graphical model for video content analysis given sparse data. We propose a Completed Likelihood AIC (CL-AIC) scoring...
Dynamic Facial Expression Recognition Using A Bayesian Temporal Manifold Model (2008)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
In this paper, we propose a novel Bayesian approach to modelling temporal transitions of facial expressions represented in a manifold, with the aim of dynamical facial expression recognition in image...
Capturing Correlations Among Facial Parts for Facial Expression Analysis (2008)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
Capturing and analyzing the correlations among facial parts are important for interpreting facial behaviors precisely. In this paper, we exploit Canonical Correlation Analysis (CCA) to model the...
Beyond Facial Expressions: Learning Human Emotion from Body Gestures (2008)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
Vision-based human affect analysis is an interesting and challenging problem, impacting important applications in many areas. In this paper, beyond facial expressions, we investigate affective body...
Conditional Random Field for Natural Scene Categorization (2008)
Conditional random field (CRF) has been widely used for sequence labeling and segmentation. However, CRF does not offer a straightforward approach to classify whole sequences. On the other hand,...
Coupling Face Registration and Super-Resolution (2008)
Kui Jia, Shaogang Gong, Alex Po Leung
Existing approaches to learning-based face image super-resolution require low-resolution testing inputs manually registered to pre-aligned highresolution training models [9, 12, 13, 5]. This...
Online Video Behaviour Abnormality Detection Using Reliability Measure (2008)
An approach is proposed for robust online behaviour recognition and abnormality detection based on discovering natural grouping of bebaviour patterns through unsupervised learning and a time...
Quantifying Ambiguities in Inferring Vector-Based 3D Models (2008)
This paper presents a framework for directly addressing issues arising from self-occlusions and ambiguities due to the lack of depth information in vector-based representations. Visual data directly...
Wavelet-based holistic sequence descriptor for generating (2008)
video summaries
Spectral clustering with eigenvector selection (2008)
The task of discovering natural groupings of input patterns, or clustering, is an important aspect of machine learning and pattern analysis. In this paper, we study the widely used spectral...
Shaogang Gong, Jeffrey Ng, Jamie Sherrah
the semantics of visual behaviour, structured events and trajectories of
Michael Walter Alex, Ra Psarrou, Shaogang Gong
We present an approach to automatically segment and label a continuous observation sequence of hand gestures for a complete unsupervised model acquisition. The method is based on the assumption that...
Online Feature Selection Using Mutual Information for Real-Time Multi-View Object Tracking (2008)
Abstract. It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online feature...
A Probabilistic Hierarchical Framework for Expression Classification (2008)
Lukasz Zalewski, Shaogang Gong
We address the issue of understanding facial expressions through statistical modelling and analysis without the need for any temporal information whatsoever. We introduce a hierarchical decomposition...
Global Abnormal Behaviour Detection Using a Network of CCTV Cameras (2008)
Zelniker, Emanuel E., Gong, Shaogang, Xiang, Tao
This paper investigates the detection of global abnormal behaviours across a network of CCTV cameras. Although the problem of multiple camera tracking has attracted much attention recently, little...
Global Abnormal Behaviour Detection Using a Network of CCTV Cameras (2008)
Zelniker, Emanuel E., Gong, Shaogang, Xiang, Tao
This paper investigates the detection of global abnormal behaviours across a network of CCTV cameras. Although the problem of multiple camera tracking has attracted much attention recently, little...
From Local Temporal Correlation to Global Anomaly Detection (2008)
Loy, Chen Change, Xiang, Tao, Gong, Shaogang
In this paper, we propose a novel framework tailored towards global video behaviour anomaly detection in complex outdoor scenes involving multiple temporal processes caused by correlated behaviours...
Multi-camera Matching under Illumination Change Over Time (2008)
Prosser, Bryan, Gong, Shaogang, Xiang, Tao
Illumination differences between disjoint cameras can have a dramatic effect on the appearance of objects, thus increasing the difficulty of multi-camera object association. Although methods to model...
From Local Temporal Correlation to Global Anomaly Detection (2008)
Loy, Chen Change, Xiang, Tao, Gong, Shaogang
In this paper, we propose a novel framework tailored towards global video behaviour anomaly detection in complex outdoor scenes involving multiple temporal processes caused by correlated behaviours...
Multi-camera Matching under Illumination Change Over Time (2008)
Prosser, Bryan, Gong, Shaogang, Xiang, Tao
Illumination differences between disjoint cameras can have a dramatic effect on the appearance of objects, thus increasing the difficulty of multi-camera object association. Although methods to model...
Recognising the dynamics of faces across multiple views (2007)
Yongmin Li, Shaogang Gong, Heather Liddell
We present an integrated framework for dynamic face detection and recognition, where head pose is estimated using Support Vector Regression, face detection is performed by Support Vector...
Representation and Invariance in Face Recognition (2007)
J. J. Collins, Stephen J. McKenna, Shaogang Gong
Photometric based representation schemes for face recognition are compared and contrasted. The choice of representation is discussed within the context of recognition which requires the ability to...
Activity Based Surveillance Video Segmentation (2007)
There is an urgent need for applications that allow for intelligent and quick access to the vast amount of surveillance video footages generated everyday. In this paper, we address the issue of...
Recognising the dynamics of faces across multiple views (2007)
Yongmin Li, Shaogang Gong, Heather Liddell
We present an integrated framework for dynamic face detection and recognition, where head pose is estimated using Support Vector Regression, face detection is performed by Support Vector...
Mean shift tracking with random sampling (2006)
In this work, boosting the efficiency of Mean-Shift Tracking using random sampling is proposed. We obtained the surprising result that mean-shift tracking requires only very few samples. Our...
Object Localization by Generative Graph Configuration (2006)
Huaijun Qiu, Shaogang Gong, Huaijun Qiu, Shaogang Gong
State-of-art statistical models for object recognition are sensitive to large affine transformations in scale and rotation. This is due to the rather strict spacial correlation assumption made...
Beyond tracking: modelling activity and understanding behaviour (2006)
In this work, we present a unified bottom-up and top-down automatic model selection based approach for modelling complex activities of multiple objects in cluttered scenes. An activity of multiple...
In this work we present a framework for robust people detection in highly cluttered scenes with low resolution image sequences. Our model utilises both human appearance and their long-term motion...
Incremental visual behaviour modelling (2006)
We develop a novel visual behaviour modelling approach that performs incremental and adaptive behaviour model learning for online abnormality detection. Three key features make our approach...
DOI: 10.1007/s11263-005-5024-8 Model Selection for Unsupervised Learning of Visual Context (2005)
Abstract. This study addresses the problem of choosing the most suitable probabilistic model selection criterion for unsupervised learning of visual context of a dynamic scene using mixture models. A...
Video behaviour profiling and abnormality detection without manual labelling (2005)
A novel framework is developed for automatic behaviour profiling and abnormality sampling/detection without any manual labelling of the training dataset. Natural grouping of behaviour patterns is...
Multi-Modal Tensor Face for Simultaneous Super-Resolution and Recognition (2005)
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recognition rate of all...
Hallucinating Multiple Occluded CCTV Face Images of Different Resolutions (2005)
In this paper, we present a novel learning-based algorithm to super-resolve multiple partially occluded CCTV lowresolution face images. By integrating hierarchical patchwise alignment and inter-frame...
Visual learning given sparse data of unknown complexity (2005)
This study addresses the problem of unsupervised visual learning. It examines existing popular model order selection criteria before proposes two novel criteria for improving visual learning given...
Appearance manifold of facial expression (2005)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
Abstract. This paper investigates the appearance manifold of facial expression: embedding image sequences of facial expression from the high dimensional appearance feature space to a low dimensional...
Conditional Mutual Information Based Boosting for Facial Expression Recognition (2005)
Caifeng Shan, Shaogang Gong, Peter W. Mcowan
This paper proposes a novel approach for facial expression recognition by boosting Local Binary Patterns (LBP) based classifiers. Low-cost LBP features are introduced to effectively describle local...
2d statistical models of facial expressions for realistic 3d avatar animation (2005)
Lukasz Zalewski, Shaogang Gong
We address the issue of modelling facial expressions for realistic 3D avatar animation. We introduce a hierarchical decomposition of a human face into different components and model them according to...
Abstract. In this work, we present a unified bottom-up and top-down automatic model selection based approach for modelling complex activities of multiple objects in cluttered scenes. An activity of...
Multi-Modal Tensor Face for Simultaneous Super-Resolution and Recognition (2005)
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recognition rate of all...
An optimization framework for real-time appearance-based tracking under weak perspective (2005)
In this work, we present a framework for tracking objects in changing views by finding the subwindow most likely to be the object using Haar-like features selected by AdaBoost as the representation....
Multi-modal face image superresolutions in tensor space (2005)
Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. To overcome these problems, super-resolution techniques can be exploited....
Quantifying temporal saliency (2004)
A significant problem in automatic scene interpretation is the ability to perform contextually meaningful segmentation of both static and moving images using a bottom-up approach. We examine and...
Synthesis and recognition of facial expressions in virtual 3d views (2004)
Lukasz Zalewski, Shaogang Gong
The human face exhibits complex and rich changes that are both unpredictable and varying in time. In this paper we present a novel method for synthesising and recognition of facial expression changes...
Activity based video content trajectory representation and segmentation (2004)
A novel approach is developed to segment continuous CCTV recordings according to the activities captured in the scene. This approach differs from previous approaches which are mostly based on shot...
Spotting scene change for indexing surveillance video (2003)
We address the issue of forming a pre-attentive mechanism that can be used to analyse surveillance sequences. We address the problem of spotting scene change by performing temporal segmentation on...
We present a novel approach to behaviour recognition in visual surveillance under which scene events corresponding to object behaviours are modelled as groups of affiliated autonomous pixel-level...
Constructing Facial Identity Surfaces for Recognition (2003)
Yongmin Li, Shaogang Gong, Heather Liddell
We present a novel approach to face recognition by constructing facial identity structures across views and over time, referred to as identity surfaces, in a Kernel Discriminant Analysis (KDA)...
Recognition of group activities using dynamic probabilistic networks (2003)
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of different object temporal events in the scene for a coherent and robust scene-level...
Constructing Facial Identity Surfaces for Recognition (2003)
Yongmin Li, Shaogang Gong, Heather Liddell
We present a novel approach to face recognition by constructing facial identity structures across views and over time, referred to as identity surfaces, in a Kernel Discriminant Analysis (KDA)...
Tao Xiang, Shaogang Gong, Dennis Parkinson
Modelling events is one of the key problems in dynamic scene analysis when salient and autonomous visual changes occuring in a scene need to be characterised effectively as meaningful events. We...
Tao Xiang, Shaogang Gong, Dennis Parkinson
Modelling events is one of the key problems in dynamic scene analysis when salient and autonomous visual changes occuring in a scene need to be characterised effectively as meaningful events. We...
Recognising Trajectories of Facial Identities Using Kernel Discriminant Analysis (2001)
Yongmin Li, Shaogang Gong, Heather Liddell
We present a comprehensive approach to address three challenging problems in face recognition: modelling faces across multi-views, extracting the non-linear discriminating features, and recognising...
Robust, real-time tracking of objects from visual data requires probabilistic fusion of multiple visual cues. Previous approaches have either been ad hoc or relied on a Bayesian network with discrete...
Modelling faces dynamically across views and over time (2001)
Yongmin Li, Shaogang Gong, Heather Liddell
A comprehensive novel multi-view dynamic face model is presented in this paper to address two challenging problems in face recognition and facial analysis: modelling faces with large pose variation...
Modelling faces dynamically across views and over time (2001)
Yongmin Li, Shaogang Gong, Heather Liddell
A comprehensive novel multi-view dynamic face model is presented in this paper to address two challenging problems in face recognition and facial analysis: modelling faces with large pose variation...
Modelling faces dynamically across views and over time (2001)
Yongmin Li, Shaogang Gong, Heather Liddell
A comprehensive novel multi-view dynamic face model is presented in this paper to address two challenging problems in face recognition and facial analysis: modelling faces with large pose variation...
Recognising Trajectories of Facial Identities (2001)
Using Kernel Discriminant, Yongmin Li, Shaogang Gong, Heather Liddell
We present a comprehensive approach to address three challenging problems in face recognition: modelling faces across multi-views, extracting the non-linear discriminating features, and recognising...
Data Driven Gesture Model Acquisition Using Minimum Description Length (2001)
Michael Walter, Alexandra Psarrou, Shaogang Gong, Michael Walter Alex, Ra Psarrou
An approach is presented to automatically segment and label a continuous observation sequence of hand gestures for a complete unsupervised model acquisition. The method is based on the assumption...
Robust, real-time tracking of objects from visual data re-quires probabilistic fusion of multiple visual cues. Previous approaches have either been ad hoc or relied on a Bayesian network with...
Tracking Multiple People with a Multi-Camera System (2001)
Ting-hsun Chang, Shaogang Gong
We present a multi-camera system based on Bayesian modality fusion to track multiple people in an indoor environment. Bayesian networks are used to combine multiple modalities for matching subjects...
Modelling faces dynamically across views and over time (2001)
Yongmin Li, Shaogang Gong, Heather Liddell
A coniprehensive novel multi-view dynamic face model is presented in this paper to address two challenging prob-lems in face recognition and facial analysis: modelling faces with large pose variation...
Learning pixel-wise signal energy for understanding semantics (2001)
Visual interpretation of events requires both an appropriate representation of change occurring in the scene and the application of semantics for differentiating between different types of change....
Support vector regression and classification based multi-view face detection and recognition (2000)
Yongmin Li, Shaogang Gong, Heather Liddell
A Support Vector Machine based multi-view face detection and recognition framework is described in this paper. Face detection is carried out by constructing several detectors, each of them in charge...
Interpretation of group behaviour in visually mediated interaction (2000)
Jamie Sherrah, Shaogang Gong, A. Jonathan Howell, Hilary Buxton
While full computer understanding of dynamic visual scenes containing several people may be currently unattainable, we propose a computationally efficient approach to determine areas of interest in...
Tracking discontinuous motion using bayesian inference (2000)
Abstract. Robustly tracking people in visual scenes is an important task for surveillance, human-computer interfaces and visually mediated interaction. Existing attempts at tracking a person's...
Multi-view face detection using support vector machines and eigenspace modelling (2000)
Yongmin Li, Shaogang Gong, Jamie Sherrah, Heather Liddell
An approach to multi-view face detection based on head pose estimation is presented in this paper. Support Vector Regression is employed to solve the problem of pose estimation. Three methods, the...
Exploiting the Dynamics of Faces in Spatial-temporal Context (2000)
Yongmin Li, Shaogang Gong, Heather Liddell
We present an approach to dynamically recognise faces in a spatial-temporal context from video sequences. Linear Discriminant Analysis (LDA), head pose estimation, and multi-view face detection are...
Multi-view face detection using support vector machines and eigenspace modelling (2000)
Yongmin Li, Shaogang Gong, Jamie Sherrah, Heather Liddell
An approach to multi-view face detection based on head pose estimation is presented in this paper. Support Vector Regression is employed to solve the problem of pose estimation. Three methods, the...
VIGOUR: A system for tracking and recognition of multiple people and their activities (2000)
Tracking multiple people and their behaviours is a fundamental task for visually mediated interaction. We present VIGOUR, a platform for simultaneously tracking of multiple people and recognition of...
Support vector regression and classification based multi-view face detection and recognition (2000)
Yongmin Li, Shaogang Gong, Heather Liddell
A Support Vector Machine based multi-view face detection and recognition framework is described in this paper. Face detection is carried out by constructing several detectors, each of them in charge...
Fusion of Perceptual Cues for Robust Tracking of. . . (2000)
Jamie Sherrah, Shaogang Gong, Of Queen Mary, West Eld College
The paradigm of perceptual fusion provides robust solutions to computer vision problems. By combining the outputs of multiple vision modules, the assumptions and constraints of each module are...
Exploiting the Dynamics of Faces in Spatial-temporal Context (2000)
Yongmin Li Shaogang, Yongmin Li, Shaogang Gong, Heather Liddell
We present an approach to dynamically recognise faces in a spatial-temporal context from video sequences. Linear Discriminant Analysis (LDA), head pose estimation, and multi-view face detection are...
Interpretation of Group Behaviour in Visually Mediated Interaction (2000)
Jamie Sherrah And, Jamie Sherrah, Shaogang Gong, A. Jonathan Howell, Hilary Buxton
While full computer understanding of dynamic visual scenes containing several people may be currently unattainable, we propose a computationally efficient approach to determine areas of interest in...
On utilising template and feature-based correspondence in multi-view appearance models (2000)
Sami Romdhani, Ra Psarrou, Shaogang Gong
Abstract. In principle, the recovery and reconstruction of a 3D object from its 2D view projections require the parameterisation of its shape structure and surface re ectance properties. Explicit...
VIGOUR: A system for tracking and recognition of multiple people and their activities (2000)
Tracking multiple people and their behaviours is a fundamental task for visually mediated interaction. We present VIGOUR, a platform for simultaneously tracking of multiple people and recognition of...
Support vector regression and classification based multi-view face detection and recognition (2000)
Yongmin Li, Shaogang Gong, Heather Liddell
A Support Vector Machine based multi-view face detection and recognition framework is described in this paper. Face detection is carried out by constructing several detectors, each of them in charge...
Abstract The dynamics of linear combinations: tracking 3D skeletons of human subjects (2000)
We propose a general framework for addressing three fundamental issues using linear combinations: �1) the properties of the examples to linearly combine, �2) the constraints, and �3) the method...
Composite support vector machines for detection of faces across views
Resolving visual uncertainty and occlusion through probabilistic reasoning (2000)
Tracking interacting human body parts from a single two-dimensional view is difficult due to occlusion, ambiguity and spatio-temporal discontinuities. We present a Bayesian network method for this...
An algorithm is described for modelling and recognising temporal structures of visual activities. The method is based on (1) learning prior probabilistic knowledge using Hidden Markov Models, (2)...
Fusion of perceptual cues using covariance estimation (1999)
The paradigm of perceptual fusion provides robust solutions to computer vision problems. By combining the outputs of multiple vision modules, the assumptions and constraints of each module are...
A dynamic human model using hybrid 2d-3d representations in hierarchical pca space (1999)
We propose a novel framework for a hybrid 2D-3D dynamic human model with which robust matching and tracking of a 3D skeleton model of a human body among multiple views can be performed. We describe a...
Learning support vector machines for a multi-view face model (1999)
Jeffrey Ng, Sing Kwong, Shaogang Gong
Support Vector Machines have shown great potential for learning classification functions that can be applied to object recognition. In this work, we extend SVMs to model the appearance of human faces...
Understanding pose discrimination in similarity space (1999)
Jamie Sherrah, Shaogang Gong, Eng-jon Ong
Identity-independent estimation of head pose from prototype images is a perplexing task, requiring pose-invariant face detection. The problem is exacerbated by changes in illumination, identity and...
Understanding pose discrimination in similarity space (1999)
Jamie Sherrah, Shaogang Gong, Eng-jon Ong
Identity-independent estimation of head pose from prototype images is a perplexing task, requiring pose-invariant face detection. The problem is exacerbated by changes in illumination, identity and...
Support Vector Machines have shown great potential for learning classification functions that can be applied to object recognition. In this work, we extend SVMs to model the 2D appearance of human...
Fusion of 2D Face Alignment and 3D Head Pose Estimation for Robust and Real-Time Performance (1999)
In order to perform coherent and robust interpretation of moving faces, one must resolve the inconsistency and ambiguities observed among multiple sources of highly noisy visual measurements. In this...
Tracking Hybrid 2D-3D Human Models from Multiple Views (1999)
A novel framework is proposed under which robust matching and tracking of a 3D skeleton model of a human body from multiple views can be performed. We propose a method for measuring the ambiguity of...
Learning Support Vector Machines for A Multi-View Face Model (1999)
Support Vector Machines have shown great potential for learning classification functions that can be applied to object recognition. In this work, we extend SVMs to model the appearance of human faces...
Exploiting Context in Gesture Recognition (1999)
Jamie Sherrah And, Jamie Sherrah, Shaogang Gong
. Recognition of human behaviour is receiving increasing attention in computer vision, and has many useful applications. In this work we investigate how head pose can be exploited to impose...
Fusion of Perceptual Cues using Covariance Estimation (1999)
Jamie Sherrah, Shaogang Gong, Jamie R. Sherrah
The paradigm of perceptual integration provides robust solutions to computer vision problems. By combining the outputs of multiple vision modules, the assumptions and constraints of each module are...
An algorithm is described for modelling and recognising temporal structures of visual activities. The method is based on (1) learning prior probabilistic knowledge using Hidden Markov Models, (2)...
A Multi-View Nonlinear Active Shape Model Using Kernel PCA (1999)
Sami Romdhani, Shaogang Gong, Alexandra Psarrou, Ra Psarrou
Recovering the shape of any 3D object using multiple 2D views requires establishing correspondence between feature points at different views. However changes in viewpoint introduce self-occlusions,...
Tracking Head Pose for Inferring Intention (1998)
Eng-Jon Ong, Stephen Mckenna, Shaogang Gong
. A real-time system for person-independent head pose recognition and tracking is presented. The system makes use of a face image database labelled with yaw and tilt pose angles ranging across 90 yaw...
Modelling Facial Colour and Identity with Gaussian Mixtures (1998)
Stephen J. McKenna, Shaogang Gong, Yogesh Raja
An integrated system for the acquisition, normalisation and recognition of moving faces in dynamic scenes is introduced. Four face recognition tasks are defined and it is argued that modelling...
Real-Time Face Pose Estimation (1998)
Stephen J. McKenna, Shaogang Gong
Methods were investigated for estimating the poses of human faces undergoing large rotations in depth. Dimensionality reduction using principal components analysis enabled pose changes to be...
Learning to Associate Faces across Views in Vector Space of Similarities to Prototypes (1998)
Shaogang Gong, Eng-Jon Ong, Stephen McKenna
We present a method for learning appearance models that can be used to recognise and track both 3D head pose and identities of novel subjects with continuous head movement across the view-sphere. We...
Tracking and Segmenting People in Varying Lighting Conditions using Colour (1998)
Yogesh Raja, Stephen J. McKenna, Shaogang Gong
Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for...
View Alignment with Dynamically Updated Affine Tracking (1998)
Shaogang Gong, Stephen McKenna
We propose a framework for fast view alignment using adaptive affine tracking. We address the issue of modelling both shape and texture information in eigenspace for view alignment. We present an...
Colour Model Selection and Adaptation in Dynamic Scenes (1998)
Yogesh Raja, Stephen J. McKenna, Shaogang Gong
. We use colour mixture models for real-time colour-based object localisation, tracking and segmentation in dynamic scenes. Within such a framework, we address the issues of model order selection,...
Segmentation and Tracking Using Colour Mixture Models (1998)
Yogesh Raja, Stephen J. Mckenna, Shaogang Gong
. A system is described that provides robust and real-time focus-of-attention for tracking and segmentation of multi-coloured objects. Gaussian mixture models were used to estimate the probability...
Object Tracking using Adaptive Colour Mixture Models (1998)
Stephen Mckenna, Yogesh Raja, Shaogang Gong
. The use of adaptive Gaussian mixtures to model the colour distributions of objects is described. These models are used to perform robust, real-time tracking under varying illumination, viewing...
Tracking and segmenting people in varying lighting conditions using colour (1998)
Yogesh Raja, Stephen J. Mckenna, Shaogang Gong
Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for...
Learning to Associate Faces across Views in (1998)
Vector Space Of, Shaogang Gong, Eng-jon Ong
We present a method for learning appearance models that can be used to recognise and track both 3D head pose and identities of novel subjects with continuous head movement across the view-sphere. We...
Face Recognition in Dynamic Scenes (1997)
Stephen Mckenna Shaogang, Stephen Mckenna, Shaogang Gong, Yogesh Raja
An integrated system for the acquisition, normalisation and recognition of moving faces in dynamic scenes is introduced. Four face recognition tasks are defined and it is argued that modelling...
Tracking Facial Feature Points with Gabor Wavelets and Shape Models (1997)
Stephen J. McKenna, Shaogang Gong, Rolf P. Würtz, Jonathan Tanner, Daniel Banin
. A feature-based approach to tracking rigid and non-rigid facial motion is described. Feature points are characterised using Gabor wavelets and can be individually tracked by phase-based...
Stephen J. McKenna, Shaogang Gong
. Face recognition systems typically operate robustly only within highly constrained environments. This paper describes work aimed at performing face recognition in more unconstrained environments...
Tracking Facial Feature Points with Gabor Wavelets and Shape Models (1997)
Stephen J. McKenna, Shaogang Gong, Rolf P. Würtz, Jonathan Tanner, Daniel Banin
. A feature-based approach to tracking rigid and non-rigid facial motion is described. Feature points are characterised using Gabor wavelets and can be individually tracked by phase-based...
Face Recognition in Dynamic Scenes (1997)
Stephen Mckenna, Shaogang Gong, Yogesh Raja
An integrated system for the acquisition, normalisation and recognition of moving faces in dynamic scenes is introduced. Four face recognition tasks are defined and it is argued that modelling...
An Investigation into Face Pose Distributions (1996)
Shaogang Gong, Shaogang Gong, Stephen Mckenna, Stephen Mckenna, John J. Collins, John J. Collins
Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or...
Face Tracking and Pose Representation (1996)
Stephen Mckenna Shaogang, Stephen Mckenna, Shaogang Gong, J. J. Collins
We describe a dynamic face tracking system based on an integrated motion-based object tracking and model-based face detection framework. The motion-based tracker focuses attention for the face...
An Investigation into Face Pose Distributions (1996)
Shaogang Gong, Shaogang Gong, Stephen Mckenna, Stephen Mckenna, John J. Collins, John J. Collins
Visual perception of faces is invariant under many transformations, perhaps the most problematic of which is pose change (face rotating in depth). We use a variation of Gabor wavelet transform (GWT)...
Stephen Mckenna, Stephen Mckenna, Shaogang Gong, Shaogang Gong
Robust tracking and segmentation of faces is a prerequisite for face analysis and recognition. In this paper, we describe an approach to this problem which is well suited to surveillance applications...
Face Tracking and Pose Representation (1996)
Stephen Mckenna, Shaogang Gong, J. J. Collins
We describe a dynamic face tracking system based on an integrated motion-based object tracking and model-based face detection framework. The motion-based tracker focuses attention for the face...
An Investigation into Face Pose Distributions (1996)
Shaogang Gong, Stephen Mckenna, John J. Collins
Visual perception of faces is invariant under many transformations, perhaps the most problematic of which is pose change (face rotating in depth). We use a variation of Gabor wavelet transform (GWT)...
An Investigation into Face Pose Distributions (1996)
Shaogang Gong, Stephen Mckenna, John J. Collins
Visual perception of faces is invariant under many transformations, perhaps the most problematic of which is pose change (face rotating in depth). We use a variation of Gabor wavelet transform (GWT)...
Advanced Visual Surveillance using Bayesian Networks (1995)
Advanced visual surveillance systems not only need to track moving objects but also interpret their patterns of behaviour. This means that solving the information integration problem becomes very...
Alexandra Psarrou, Ra Psarrou, Shaogang Gong, Hilary Buxton
We address the problem of trajectory prediction in machine vision applications using variants of Elman's partially recurrent networks. We use dynamic context to constrain the representation...
Real-Time Tracking for an Integrated Face Recognition System (1995)
Stephen J. McKenna, Shaogang Gong, Heather Liddell
A real-time tracking system suitable for surveillance applications was implemented on pipeline image processing hardware. Motion estimation was performed using a symmetric spatio-temporal filter in...
In this work we address the issue of focused computation in computer vision for effectiveness and efficiency. In particular, we propose a scheme for motion segmentation and tracking that links...
Visual Observation as Reactive Learning (1992)
Meaningful objects in a scene move with purpose. The ability to induce visual expectations from such purpose is important in visual observation. By regarding the spatio-temporal regularities in the...
Parallel computation of visual motion. (1989)
Thesis (Ph. D.)--University of Oxford, 1989.