Search For:

Displaying 1-38 out of 38 total
C-Slate: A Multi-Touch and Object Recognition System for Remote Collaboration using Horizontal Surfaces
Found in: Horizontal Interactive Human-Computer Systems, International Workshop on
By Shahram Izadi, Ankur Agarwal, Antonio Criminisi, John Winn, Andrew Blake, Andrew Fitzgibbon
Issue Date:October 2007
pp. 3-10
We introduce C-Slate, a new vision-based system, which utilizes stereo cameras above a commercially available tablet technology to support remote collaboration. The horizontally mounted tablet provides the user with high resolution stylus input, which is a...
 
Efficient Human Pose Estimation from Single Depth Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jamie Shotton,Ross Girshick,Andrew Fitzgibbon,Toby Sharp,Mat Cook,Mark Finocchio,Richard Moore,Pushmeet Kohli,Antonio Criminisi,Alex Kipman,Andrew Blake
Issue Date:December 2013
pp. 2821-2840
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image without using any temporal information. The key to both approaches is the use of a large, realistic, ...
 
Geodesic star convexity for interactive image segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Varun Gulshan, Carsten Rother, Antonio Criminisi, Andrew Blake, Andrew Zisserman
Issue Date:June 2010
pp. 3129-3136
In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler's [25] star-convexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths. Global minima of t...
 
Reconstructing High Quality Face-Surfaces using Model Based Stereo
Found in: Computer Vision, IEEE International Conference on
By Brian Amberg, Andrew Blake, Andrew Fitzgibbon, Sami Romdhani, Thomas Vetter
Issue Date:October 2007
pp. 1-8
We present a novel model based stereo system, which accurately extracts the 3D shape and pose of faces from multiple images taken simultaneously. Extracting the 3D shape from images is important in areas such as pose-invariant face recognition and image ma...
 
Learning priors for calibrating families of stereo cameras
Found in: Computer Vision, IEEE International Conference on
By Andrew W. Fitzgibbon, Duncan P. Robertson, Antonio Criminisi, Srikumar Ramalingam, Andrew Blake
Issue Date:October 2007
pp. 1-8
Online camera recalibration is necessary for long-term deployment of computer vision systems. Existing algorithms assume that the source of recalibration information is a set of features in a general 3D scene; and that enough features are observed that the...
 
Fusion Moves for Markov Random Field Optimization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Victor Lempitsky, Carsten Rother, Stefan Roth, Andrew Blake
Issue Date:August 2010
pp. 1392-1405
The efficient application of graph cuts to Markov Random Fields (MRFs) with multiple discrete or continuous labels remains an open question. In this paper, we demonstrate one possible way of achieving this by using graph cuts to combine pairs of suboptimal...
 
Dense Stereo Matching over the Panum Band
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ankur Agarwal, Andrew Blake
Issue Date:March 2010
pp. 416-430
Stereo matching algorithms conventionally match over a range of disparities sufficient to encompass all visible 3D scene points. Human vision, however, works over a narrow band of disparities—Panum's fusional band—whose typical range may be as little as 1/...
 
Bayesian color constancy revisited
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Peter Vincent Gehler, Carsten Rother, Andrew Blake, Tom Minka, Toby Sharp
Issue Date:June 2008
pp. 1-8
Computational color constancy is the task of estimating the true reflectances of visible surfaces in an image. In this paper we follow a line of research that assumes uniform illumination of a scene, and that the principal step in estimating reflectances i...
 
High Precision Multi-touch Sensing on Surfaces using Overhead Cameras
Found in: Horizontal Interactive Human-Computer Systems, International Workshop on
By Ankur Agarwal, Shahram Izadi, Manmohan Chandraker, Andrew Blake
Issue Date:October 2007
pp. 197-200
We present a method to enable multi-touch interactions on an arbitrary flat surface using a pair of cameras mounted above the surface. Current systems in this domain mostly make use of special touch-sensitive hardware, require cameras to be mounted behind ...
 
LogCut - Efficient Graph Cut Optimization for Markov Random Fields
Found in: Computer Vision, IEEE International Conference on
By Victor Lempitsky, Carsten Rother, Andrew Blake
Issue Date:October 2007
pp. 1-8
Markov Random Fields (MRFs) are ubiquitous in low-level computer vision. In this paper, we propose a new approach to the optimization of multi-labeled MRFs. Similarly to ¿-expansion it is based on iterative application of binary graph cut. However, the num...
 
Multiscale Categorical Object Recognition Using Contour Fragments
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jamie Shotton, Andrew Blake, Roberto Cipolla
Issue Date:July 2008
pp. 1270-1281
Psychophysical studies [9], [17] show that we can recognize objects using fragments of outline contour alone. This paper proposes a new automatic visual recognition system based only on local contour features, capable of localizing objects in space and sca...
 
Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Carsten Rother, Tom Minka, Andrew Blake, Vladimir Kolmogorov
Issue Date:June 2006
pp. 993-1000
We introduce the term cosegmentation which denotes the task of segmenting simultaneously the common parts of an image pair. A generative model for cosegmentation is presented. Inference in the model leads to minimizing an energy with an MRF term encoding s...
 
Sparse and Semi-supervised Visual Mapping with the S^3GP
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oliver Williams, Andrew Blake, Roberto Cipolla
Issue Date:June 2006
pp. 230-237
This paper is about mapping images to continuous output spaces using powerful Bayesian learning techniques. A sparse, semi-supervised Gaussian process regression model (S3GP) is introduced which learns a mapping using only partially labelled training data....
 
Contour-Based Learning for Object Detection
Found in: Computer Vision, IEEE International Conference on
By Jamie Shotton, Andrew Blake, Roberto Cipolla
Issue Date:October 2005
pp. 503-510
We present a novel categorical object detection scheme that uses only local contour-based features. A two-stage, partially supervised learning architecture is proposed: a rudimentary detector is learned from a very small set of segmented images and applied...
 
Sparse Bayesian Learning for Efficient Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Oliver Williams, Andrew Blake, Roberto Cipolla
Issue Date:August 2005
pp. 1292-1304
This paper extends the use of statistical learning algorithms for object localization. It has been shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of spatial perturbation of the SVM. While this SVM applies ...
 
Digital Tapestry
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Carsten Rother, Sanjiv Kumar, Vladimir Kolmogorov, Andrew Blake
Issue Date:June 2005
pp. 589-596
This paper addresses the novel problem of automatically synthesizing an output image from a large collection of different input images. The synthesized image, called a digital tapestry, can be viewed as a visual summary or a virtual ?thumbnail? of all the ...
 
A Sparse Probabilistic Learning Algorithm for Real-Time Tracking
Found in: Computer Vision, IEEE International Conference on
By Oliver Williams, Andrew Blake, Roberto Cipolla
Issue Date:October 2003
pp. 353
This paper addresses the problem of applying powerful pattern recognition algorithms based on kernels to efficient visual tracking. Recently Avidan [1] has shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of...
 
Integrated Tracking with Vision and Sound
Found in: Image Analysis and Processing, International Conference on
By Andrew Blake, Michel Gangnet, Patrick Perez, Jaco Vermaak
Issue Date:September 2001
pp. 0354
Abstract: The research summarised here is working towards automatic control systems for cameras, in support of remote meetings. Progress is reported on several fronts: use of active contours to track heads, stereo sound analysis; applying particle filterin...
 
Probabilistic Tracking in a Metric Space
Found in: Computer Vision, IEEE International Conference on
By Kentaro Toyama, Andrew Blake
Issue Date:July 2001
pp. 50
A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especially temporal fusion, in a principled manner. Exemplars are selected representatives of...
 
JetStream: Probabilistic Contour Extraction with Particles
Found in: Computer Vision, IEEE International Conference on
By Patrick Pérez, Andrew Blake, Michel Gangnet
Issue Date:July 2001
pp. 524
The problem of extracting continuous structures from noisy or cluttered images is a difficult one. Successful extraction depends critically on the ability to balance prior constraints on continuity and smoothness against evidence garnered from image analys...
 
Computationally Efficient Face Detection
Found in: Computer Vision, IEEE International Conference on
By Sami Romdhani, Philip Torr, Bernhard Schölkopf, Andrew Blake
Issue Date:July 2001
pp. 695
This paper describes an algorithm for finding faces within an image. The basis of the algorithm is to run an observation window at all possible positions, scales and orientation within the image. A non-linear support vector machine is used to determine whe...
 
Learning and Classification of Complex Dynamics
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ben North, Andrew Blake, Michael Isard, Jens Rittscher
Issue Date:September 2000
pp. 1016-1034
<p><b>Abstract</b>—Standard, exact techniques based on likelihood maximization are available for learning Auto-Regressive Process models of dynamical processes. The uncertainty of observations obtained from real sensors means that dynamic...
 
A Probabilistic Exclusion Principle for Tracking Multiple Objects
Found in: Computer Vision, IEEE International Conference on
By John MacCormick, Andrew Blake
Issue Date:September 1999
pp. 572
Tracking multiple targets whose models are indistinguishable is a challenging problem. Simply instantiating several independent 1-body trackers is not an adequate solution, because the independent trackers can coalesce onto the best-fitting target.This pap...
 
Robust Contour Tracking in Echocardiographic Sequences
Found in: Computer Vision, IEEE International Conference on
By Gary Jacob, J. Alison Noble, Andrew Blake
Issue Date:January 1998
pp. 408
In this paper we present an evaluation of a robust visual image tracker on echocardiographic image sequences. We show how the tracking framework can be customised to define an appropriate shape-space that describes heart shape deformations that can be lear...
 
Real-time human pose recognition in parts from single depth images
Found in: Communications of the ACM
By Alex Kipman, Andrew Blake, Andrew Fitzgibbon, Jamie Shotton, Mark Finocchio, Mat Cook, Richard Moore, Toby Sharp
Issue Date:January 2013
pp. 116-124
We propose a new method to quickly and accurately predict human pose---the 3D positions of body joints---from a single depth image, without depending on information from preceding frames. Our approach is strongly rooted in current object recognition strate...
     
An HMM-Based Segmentation Method for Traffic Monitoring Movies
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jien Kato, Toyohide Watanabe, Sébastien Joga, Jens Rittscher, Andrew Blake
Issue Date:September 2002
pp. 1291-1296
<p><b>Abstract</b>—Shadows of moving objects often obstruct robust visual tracking. We propose an HMM-based segmentation method which classifies in real time each pixel or region into three categories: shadows, foreground, and background ...
 
A Probabilistic Contour Discriminant for Object Localisation
Found in: Computer Vision, IEEE International Conference on
By John MacCormick, Andrew Blake
Issue Date:January 1998
pp. 390
A method of localising objects in images is proposed. Possible configurations are evaluated using the contour discriminant, a likelihood ratio which is derived from a probabilistic model of the feature detection process. We treat each step in this process ...
 
Error-Tolerant Visual Planning of Planar Grasp
Found in: Computer Vision, IEEE International Conference on
By Colin Davidson, Andrew Blake
Issue Date:January 1998
pp. 911
This paper describes an effcient method to calculate, from an image of an object, configurations of a two-fingered robot gripp er that form a
 
Accurate, Real-Time, Unadorned Lip Tracking
Found in: Computer Vision, IEEE International Conference on
By Robert Kaucic, Andrew Blake
Issue Date:January 1998
pp. 370
Human speech is inherently multi-modal, consisting of both audio and visual components. Recently researchers have shown that the incorporation of information about the position of the lips into acoustic speech recognisers enables robust recognition of nois...
 
A Mixed-State Condensation Tracker with Automatic Model-Switching
Found in: Computer Vision, IEEE International Conference on
By Michael Isard, Andrew Blake
Issue Date:January 1998
pp. 107
There is considerable interest in the computer vision community in representing and modelling motion. Motion models are use d as predictors to increase the robustness and accuracy of visual trackers, and as classifiers for gesture recognition. This paper p...
 
Learning Dynamical Models Using Expectation-Maximisation
Found in: Computer Vision, IEEE International Conference on
By Ben North, Andrew Blake
Issue Date:January 1998
pp. 384
Tracking with deformable contours in a filtering frame-work requir esa dynamical model for prediction. For any given application, tracking is improved by having an accurate model, learned from training data. We develop a method for learning dynamical model...
 
AutoCollage: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Andrew Blake, Carsten Rother, Lucas Bordeaux, Youssef Hamadi
Issue Date:July 2006
pp. 43-es
The paper defines an automatic procedure for constructing a visually appealing collage from a collection of input images. The aim is that the resulting collage should be representative of the collection, summarising its main themes. It is also assembled la...
     
AutoCollage: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Andrew Blake, Carsten Rother, Lucas Bordeaux, Youssef Hamadi
Issue Date:July 2006
pp. 43-es
The paper defines an automatic procedure for constructing a visually appealing collage from a collection of input images. The aim is that the resulting collage should be representative of the collection, summarising its main themes. It is also assembled la...
     
"GrabCut": interactive foreground extraction using iterated graph cuts
Found in: ACM Transactions on Graphics (TOG)
By Andrew Blake, Carsten Rother, Vladimir Kolmogorov
Issue Date:August 2004
pp. 309-314
The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (colour) information, e.g. Magic Wand, or edge (contrast) info...
     
Poisson image editing
Found in: ACM SIGGRAPH 2003 Papers (SIGGRAPH '03)
By Andrew Blake, Michel Gangnet, Patrick Perez
Issue Date:July 2003
pp. 56-ff
Using generic interpolation machinery based on solving Poisson equations, a variety of novel tools are introduced for seamless editing of image regions. The first set of tools permits the seamless importation of both opaque and transparent source image reg...
     
Visual tracking and pose recovery for special effects
Found in: ACM SIGGRAPH 97 Visual Proceedings: The art and interdisciplinary programs of SIGGRAPH '97 (SIGGRAPH '97)
By Andrew Blake, Michael Isard
Issue Date:August 1997
pp. 224
This paper describes a physically-based rendering system tailored to the demands of lighting design and architecture. The simulation uses a light-backwards ray-tracing method with extensions to efficiently solve the rendering equation under most conditions...
     
Automatic video tracking by probabilistic propagation
Found in: ACM SIGGRAPH 96 Visual Proceedings: The art and interdisciplinary programs of SIGGRAPH '96 (SIGGRAPH '96)
By Andrew Blake, Michael Isard
Issue Date:August 1996
pp. 139
This paper describes a physically-based rendering system tailored to the demands of lighting design and architecture. The simulation uses a light-backwards ray-tracing method with extensions to efficiently solve the rendering equation under most conditions...
     
3D position, attitude and shape input using video tracking of hands and lips
Found in: Proceedings of the 21st annual conference on Computer graphics and interactive techniques (SIGGRAPH '94)
By Andrew Blake, Michael Isard
Issue Date:July 1994
pp. 185-192
Recent developments in video-tracking allow the outlines of moving, natural objects in a video-camera input stream to be tracked live, at full video-rate. Previous systems have been available to do this for specially illuminated objects or for naturally il...
     
 1