Search For:

Displaying 1-36 out of 36 total
FNS and HEIV: Relating Two Vision Parameter Estimation Frameworks
Found in: Image Analysis and Processing, International Conference on
By Wojciech Chojnacki, Michael J. Brooks, Anton van den Hengel, Darren Gawley
Issue Date:September 2003
pp. 152
Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here it is shown that FNS and a ...
 
Toward a Digital Ecosystem: International Symposium on Ubiquitous Virtual Reality 2010
Found in: IEEE Pervasive Computing
By Hyoseok Yoon, Anton van den Hengel, Gerhard Reitmayr, Joshua Lifton, Sung-Hee Lee, Woontack Woo
Issue Date:April 2011
pp. 90-93
<p>The International Symposium on Ubiquitous Virtual Reality (ISUVR) series continues to provide an interdisciplinary forum for leading researchers and graduate students, especially in the areas of ubiquitous computing, virtual reality, and augmented...
 
From FNS to HEIV: A Link between Two Vision Parameter Estimation Methods
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wojciech Chojnacki, Michael J. Brooks, Anton van den Hengel, Darren Gawley
Issue Date:January 2004
pp. 264-268
<p><b>Abstract</b>—Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV sche...
 
Revisiting Hartley's Normalized Eight-Point Algorithm
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wojciech Chojnacki, Michael J. Brooks, Anton van den Hengel, Darren Gawley
Issue Date:September 2003
pp. 1172-1177
<p><b>Abstract</b>—Hartley's eight-point algorithm has maintained an important place in computer vision, notably as a means of providing an initial value of the fundamental matrix for use in iterative estimation methods. In this paper, a ...
 
Middleware for Distributed Video Surveillance
Found in: IEEE Distributed Systems Online
By Henry Detmold, Anton van den Hengel, Anthony Dick, Katrina Falkner, David S. Munro, Ron Morrison
Issue Date:February 2008
pp. 1
Future generations of automated video surveillance systems must be scalable and evolvable, and they demand sophisticated middleware support. This middleware approach partitions systems according to an activity topology—a graph describing activity observed ...
 
A Statistical Rationalisation of Hartley?s Normalised Eight-Point Algorithm
Found in: Image Analysis and Processing, International Conference on
By Wojciech Chojnacki, Michael J. Brooks, Anton van den Hengel, Darren Gawley
Issue Date:September 2003
pp. 334
The eight-point algorithm of Hartley occupies an important place in computer vision, notably as a means of providing an initial value of the fundamental matrix for use in iterative estimation methods. In this paper, a novel explanation is given for the imp...
 
RATSAC: An Adaptive Method for Accelerated Robust Estimation and its Application to Video Synchronisation
Found in: Digital Image Computing: Techniques and Applications
By Daniel Pooley, Michael Brooks, Anton van den Hengel
Issue Date:December 2007
pp. 294-300
A new method for robust estimation is introduced. The presented algorithm seeks to unify adjustable per-iteration speedup methods with an adaptive assumption regarding the number of inliers. This is achieved by assuming a prior distribution on the true num...
 
Activity Topology Estimation for Large Networks of Cameras
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Anton van den Hengel, Anthony Dick, Rhys Hill
Issue Date:November 2006
pp. 44
Estimating the paths that moving objects can take through the fields of view of possibly non-overlapping cameras, also known as their activity topology, is an important step in the effective interpretation of surveillance video. Existing approaches to this...
 
Scalable Surveillance Software Architecture
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Henry Detmold, Anthony Dick, Katrina Falkner, David S. Munro, Anton van den Hengel, Ron Morrison
Issue Date:November 2006
pp. 103
Video surveillance is a key technology for enhanced protection of facilities such as airports and power stations from various types of threat. Networks of thousands of IP-based cameras are now possible, but current surveillance methodologies become increas...
 
Fast Global Kernel Density Mode Seeking with Application to Localisation and Tracking
Found in: Computer Vision, IEEE International Conference on
By Chunhua Shen, Michael J. Brooks, Anton van den Hengel
Issue Date:October 2005
pp. 1516-1523
<p>We address the problem of seeking the global mode of a density function using the mean shift algorithm. Mean shift, like other gradient ascent optimisation methods, is susceptible to local maxima, and hence often fails to find the desired global m...
 
Experiences with Simulated Robot Soccer as a Teaching Tool
Found in: Information Technology and Applications, International Conference on
By Rhys Hill, Anton van den Hengel
Issue Date:July 2005
pp. 387-390
<p>The development of assignments for undergraduate teaching typically requires a compromise between what is achievable by an average student and what will engage the interest of a more advanced member of the class. Selecting a suitable compromise is...
 
2D Articulated Tracking with Dynamic Bayesian Networks
Found in: Computer and Information Technology, International Conference on
By Chunhua Shen, Anton van den Hengel, Anthony Dick, Michael J. Brooks
Issue Date:September 2004
pp. 130-136
We present a novel method for tracking the motion of an articulated structure in a video sequence. The analysis of articulated motion is challenging because of the potentially large number of degrees of freedom (DOFs) of an articulated body. For particle f...
 
A General Two-Step Approach to Learning-Based Hashing
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Guosheng Lin,Chunhua Shen,David Suter,Anton van den Hengel
Issue Date:December 2013
pp. 2552-2559
Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can resul...
 
A dimensionality result for multiple homography matrices
Found in: Computer Vision, IEEE International Conference on
By Wojciech Chojnacki,Anton van den Hengel
Issue Date:November 2011
pp. 2104-2109
It is shown that the set of all I-element collections of interdependent homography matrices describing homographies induced by I planes in the 3D scene between two views has dimension 4I + 7. This improves on an earlier result which gave an upper bound for...
 
Multiple Homography Estimation with Full Consistency Constraints
Found in: Digital Image Computing: Techniques and Applications
By Wojciech Chojnacki, Zygmunt L. Szpak, Michael J. Brooks, Anton van den Hengel
Issue Date:December 2010
pp. 480-485
A novel approach is presented to estimating a set of interdependent homography matrices linked together by latent variables. The approach allows enforcement of all underlying consistency constraints while accounting for the arbitrariness of the scale of ea...
 
Contradiction and Correlation for Camera Overlap Estimation
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Alex Cichowski, Christopher Madden, Anton van den Hengel, Rhys Hill, Henry Detmold, Anthony Dick
Issue Date:September 2009
pp. 268-273
An accurate estimate of camera overlap is a key enabler for efficient network-wide surveillance processing (e.g. inter-camera tracking), especially in large-scale surveillance networks. Techniques based on contradictions in pair-wise occupancy data, such a...
 
Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Sakrapee Paisitkriangkrai,Chunhua Shen,Anton Van Den Hengel
Issue Date:December 2013
pp. 1057-1064
Many typical applications of object detection operate within a prescribed false-positive range. In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve...
 
Contextual Hypergraph Modeling for Salient Object Detection
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xi Li,Yao Li,Chunhua Shen,Anthony Dick,Anton Van Den Hengel
Issue Date:December 2013
pp. 3328-3335
Salient object detection aims to locate objects that capture human attention within images. Previous approaches often pose this as a problem of image contrast analysis. In this work, we model an image as a hyper graph that utilizes a set of hyper edges to ...
 
Graph mode-based contextual kernels for robust SVM tracking
Found in: Computer Vision, IEEE International Conference on
By Xi Li,Anthony Dick,Hanzi Wang,Chunhua Shen,Anton van den Hengel
Issue Date:November 2011
pp. 1156-1163
Visual tracking has been typically solved as a binary classification problem. Most existing trackers only consider the pairwise interactions between samples, and thereby ignore the higher-order contextual interactions, which may lead to the sensitivity to ...
 
Image Retrieval with a Visual Thesaurus
Found in: Digital Image Computing: Techniques and Applications
By Yanzhi Chen, Anthony Dick, Anton van den Hengel
Issue Date:December 2010
pp. 8-14
Current state-of-art of image retrieval methods represent images as an unordered collection of local patches, each of which is classified as a
 
Image-Based Modelling for Augmenting Reality
Found in: International Symposium on Ubiquitous Virtual Reality
By Anton van den Hengel
Issue Date:July 2010
pp. 1-4
The interaction between real and synthetic geometry is fundamental to Augmented Reality. Portraying such interactions in a manner that is convincing to the user requires 3D models of the shape of the real objects involved. The large-scale application of Au...
 
Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L<inf>1</inf> norm
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Anders Eriksson, Anton van den Hengel
Issue Date:June 2010
pp. 771-778
The calculation of a low-rank approximation of a matrix is a fundamental operation in many computer vision applications. The workhorse of this class of problems has long been the Singular Value Decomposition. However, in the presence of missing data and ou...
 
Multi-projective Parameter Estimation for Sets of Homogeneous Matrices
Found in: Digital Image Computing: Techniques and Applications
By Wojciech Chojnacki, Rhys Hill, Anton van den Hengel, Michael J. Brooks
Issue Date:December 2009
pp. 119-124
A number of problems in computer vision require the estimation of a set of matrices, each of which is defined only up to an individual scale factor and represents the parameters of a separate model, under the assumption that the models are intrinsically in...
 
Measuring Latency for Video Surveillance Systems
Found in: Digital Image Computing: Techniques and Applications
By Rhys Hill, Christopher Madden, Anton van den Hengel, Henry Detmold, Anthony Dick
Issue Date:December 2009
pp. 89-95
The increased flexibility and other benefits offered by IP network cameras makes them a common choice for installation in new and expanded surveillance networks. One commonly quoted limitation of IP cameras is their high latency when compared to their anal...
 
In situ image-based modeling
Found in: Mixed and Augmented Reality, IEEE / ACM International Symposium on
By Anton van den Hengel, Rhys Hill, Ben Ward, Anthony Dick
Issue Date:October 2009
pp. 107-110
We present an interactive image-based modelling method for generating 3D models within an augmented reality system. Applying real time camera tracking, and high-level automated image analysis, enables more powerful modelling interactions than have previous...
 
Thrift: Local 3D Structure Recognition
Found in: Digital Image Computing: Techniques and Applications
By Alex Flint, Anthony Dick, Anton van den Hengel
Issue Date:December 2007
pp. 182-188
This paper presents a method for describing and recognising local structure in 3D images. The method extends proven techniques for 2D object recognition in images. In particular, we propose a 3D interest point detector that is based on SURF, and a 3D descr...
 
What Value Covariance Information in Estimating Vision Parameters?
Found in: Computer Vision, IEEE International Conference on
By Michael J. Brooks, Wojciech Chojnacki, Darren Gawley, Anton van den Hengel
Issue Date:July 2001
pp. 302
Many parameter estimation methods used in computer vision are able to utilise covariance information describing the uncertainty of data measurements. This paper considers the value of this information to the estimation process when applied to measured imag...
 
On the Fitting of Surfaces to Data with Covariances
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Wojciech Chojnacki, Michael J. Brooks, Anton van den Hengel, Darren Gawley
Issue Date:November 2000
pp. 1294-1303
<p><b>Abstract</b>—We consider the problem of estimating parameters of a model described by an equation of special form. Specific models arise in the analysis of a wide class of computer vision problems, including conic fitting and estima...
 
StructBoost: Boosting Methods for Predicting Structured Output Variables
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chunhua Shen,Guosheng Lin,Anton van den Hengel
Issue Date:August 2014
pp. 1
Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), h...
 
A Hybrid Loss for Multiclass and Structured Prediction
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Qinfeng Shi,Mark Reid,Tiberio Caetano,Anton van den Hengel,Zhenhua Wang
Issue Date:February 2014
pp. 1
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient conditi...
 
Part-Based Visual Tracking with Online Latent Structural Learning
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Rui Yao,Qinfeng Shi,Chunhua Shen,Yanning Zhang,Anton van den Hengel
Issue Date:June 2013
pp. 2363-2370
Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking. Structured learning has shown good results when applied to tracking whole targets, but applying this approach to a part...
 
A Fast Semidefinite Approach to Solving Binary Quadratic Problems
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peng Wang,Chunhua Shen,Anton van den Hengel
Issue Date:June 2013
pp. 1312-1319
Many computer vision problems can be formulated as binary quadratic programs (BQPs). Two classic relaxation methods are widely used for solving BQPs, namely, spectral methods and semi definite programming (SDP), each with their own advantages and disadvant...
 
Learning Compact Binary Codes for Visual Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xi Li,Chunhua Shen,Anthony Dick,Anton van den Hengel
Issue Date:June 2013
pp. 2419-2426
A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes. To attain this robustness, increasingly complex models are used to capture appearance variations. However, such models can be difficult ...
 
Inductive Hashing on Manifolds
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Fumin Shen,Chunhua Shen,Qinfeng Shi,Anton van den Hengel,Zhenmin Tang
Issue Date:June 2013
pp. 1562-1569
Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes that preserve the Euclidean distan...
 
Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Zhenhua Wang,Qinfeng Shi,Chunhua Shen,Anton van den Hengel
Issue Date:June 2013
pp. 1690-1697
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty. However, the underlying graph structure is often manually specified, or auto...
 
A survey of appearance models in visual object tracking
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Anthony Dick, Anton Van Den Hengel, Chunhua Shen, Weiming Hu, Xi Li, Zhongfei Zhang
Issue Date:September 2013
pp. 1-48
Visual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties ...
     
 1