Variational Bayes and the reduced dependence approximation for the autologistic model on an irregular grid with applications

Discrete Markov random field models provide a natural framework for representing images or spatial datasets. They model the spatial association present while providing a convenient Markovian dependency structure and strong edge-preservation properties. However, parameter estimation for discrete Markov random field models is difficult due to the complex form of the associated normalizing constant for the likelihood function. For large lattices, the reduced dependence approximation to the normalizing constant is based on the concept of performing computationally efficient and feasible forward recursions on smaller sublattices which are then suitably combined to estimate the constant for the whole lattice. We present an efficient computational extension of the forward recursion approach for the autologistic model to lattices that have an irregularly shaped boundary and which may contain regions with no data; these lattices are typical in applications. Consequently, we also extend the reduced dependence approximation to these scenarios enabling us to implement a practical and efficient non-simulation based approach for spatial data analysis within the variational Bayesian framework. The methodology is illustrated through application to simulated data and example images. The supplemental materials include our C++ source code for computing the approximate normalizing constant and simulation studies.

An integrated approach for precise road reconstruction from aerial imagery and LiDAR data

Accurate and detailed road models play an important role in a number of geospatial applications, such as infrastructure planning, traffic monitoring, and driver assistance systems. In this thesis, an integrated approach for the automatic extraction of precise road features from high resolution aerial images and LiDAR point clouds is presented. A framework of road information modeling has been proposed, for rural and urban scenarios respectively, and an integrated system has been developed to deal with road feature extraction using image and LiDAR analysis. For road extraction in rural regions, a hierarchical image analysis is first performed to maximize the exploitation of road characteristics in different resolutions. The rough locations and directions of roads are provided by the road centerlines detected in low resolution images, both of which can be further employed to facilitate the road information generation in high resolution images. The histogram thresholding method is then chosen to classify road details in high resolution images, where color space transformation is used for data preparation. After the road surface detection, anisotropic Gaussian and Gabor filters are employed to enhance road pavement markings while constraining other ground objects, such as vegetation and houses. Afterwards, pavement markings are obtained from the filtered image using the Otsu's clustering method. The final road model is generated by superimposing the lane markings on the road surfaces, where the digital terrain model (DTM) produced by LiDAR data can also be combined to obtain the 3D road model. As the extraction of roads in urban areas is greatly affected by buildings, shadows, vehicles, and parking lots, we combine high resolution aerial images and dense LiDAR data to fully exploit the precise spectral and horizontal spatial resolution of aerial images and the accurate vertical information provided by airborne LiDAR. Objectoriented image analysis methods are employed to process the feature classiffcation and road detection in aerial images. In this process, we first utilize an adaptive mean shift (MS) segmentation algorithm to segment the original images into meaningful object-oriented clusters. Then the support vector machine (SVM) algorithm is further applied on the MS segmented image to extract road objects. Road surface detected in LiDAR intensity images is taken as a mask to remove the effects of shadows and trees. In addition, normalized DSM (nDSM) obtained from LiDAR is employed to filter out other above-ground objects, such as buildings and vehicles. The proposed road extraction approaches are tested using rural and urban datasets respectively. The rural road extraction method is performed using pan-sharpened aerial images of the Bruce Highway, Gympie, Queensland. The road extraction algorithm for urban regions is tested using the datasets of Bundaberg, which combine aerial imagery and LiDAR data. Quantitative evaluation of the extracted road information for both datasets has been carried out. The experiments and the evaluation results using Gympie datasets show that more than 96% of the road surfaces and over 90% of the lane markings are accurately reconstructed, and the false alarm rates for road surfaces and lane markings are below 3% and 2% respectively. For the urban test sites of Bundaberg, more than 93% of the road surface is correctly reconstructed, and the mis-detection rate is below 10%.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.

A context sensitive model for querying linked scientific data

This thesis provides a query model suitable for context sensitive access to a wide range of distributed linked datasets which are available to scientists using the Internet. The model is designed based on scientific research standards which require scientists to provide replicable methods in their publications. Although there are query models available that provide limited replicability, they do not contextualise the process whereby different scientists select dataset locations based on their trust and physical location. In different contexts, scientists need to perform different data cleaning actions, independent of the overall query, and the model was designed to accommodate this function. The query model was implemented as a prototype web application and its features were verified through its use as the engine behind a major scientific data access site, Bio2RDF.org. The prototype showed that it was possible to have context sensitive behaviour for each of the three mirrors of Bio2RDF.org using a single set of configuration settings. The prototype provided executable query provenance that could be attached to scientific publications to fulfil replicability requirements. The model was designed to make it simple to independently interpret and execute the query provenance documents using context specific profiles, without modifying the original provenance documents. Experiments using the prototype as the data access tool in workflow management systems confirmed that the design of the model made it possible to replicate results in different contexts with minimal additions, and no deletions, to query provenance documents.

CAT-SLAM : probabilistic localisation and mapping using a continuous appearance-based trajectory

This paper describes a new system, dubbed Continuous Appearance-based Trajectory Simultaneous Localisation and Mapping (CAT-SLAM), which augments sequential appearance-based place recognition with local metric pose filtering to improve the frequency and reliability of appearance-based loop closure. As in other approaches to appearance-based mapping, loop closure is performed without calculating global feature geometry or performing 3D map construction. Loop-closure filtering uses a probabilistic distribution of possible loop closures along the robot’s previous trajectory, which is represented by a linked list of previously visited locations linked by odometric information. Sequential appearance-based place recognition and local metric pose filtering are evaluated simultaneously using a Rao–Blackwellised particle filter, which weights particles based on appearance matching over sequential frames and the similarity of robot motion along the trajectory. The particle filter explicitly models both the likelihood of revisiting previous locations and exploring new locations. A modified resampling scheme counters particle deprivation and allows loop-closure updates to be performed in constant time for a given environment. We compare the performance of CAT-SLAM with FAB-MAP (a state-of-the-art appearance-only SLAM algorithm) using multiple real-world datasets, demonstrating an increase in the number of correct loop closures detected by CAT-SLAM.

Re-engaging marginalized youth through digital music production: performance, audience and evaluation

This paper presents two case studies of marginalised youth experimenting with digital music production in flexible education settings. The cases were drawn from a three-year study of alternative assessment in flexible learning centres that enrol 650+ students who have left formal schooling in Queensland, Australia. The cases are framed in reference to the literature on cultural studies approaches to education and the digital arts. Each case describes the student’s histories, cultural background and experiences, music productions, evidence of learning and re-engagement with education. Findings document how digital music production can re-engage and extend participation among students who have left formal education. They do so by theorising the online judgements and blog comments about the digital music production as a social field of exchange. It also raises critical questions about the adequacy of current approaches to evaluating and accounting for the learning and development of such youth, especially where this has occurred through creative arts and digital production.

Exploring information experience using social media during the 2011 Queensland floods : a pilot study

Social media networks have emerged as a powerful tool in allowing collaboration and sharing of information during times of crisis (Bruns, The Centre for Creative Industries Blog, comment posted on January 19,2011). The 2011 Queensland floods provided a unique opportunity to explore social media use during an emergency. This paper presents the findings of a pilot study that explored the information experiences of people using social media during the flooding of the Brisbane River. Analysis of data from four interviews supported the emergence of four categories of information experience. Examination of the categories revealed variation between the way in which individuals experienced social media and the point of the flooding at which each category of experience occurred. Information regarding individual’s use of social media has the potential to inform the development of social media platforms that can provide relevant and accessible information for the general public in event of a natural disaster.

“That you would post such a thing implies that you are a despicable human being”: spectatorship, social media, & the struggle for meaning in disability performance

Artists with disabilities working in Live Art paradigms often present performances which replay the social attitudes they are subject to in daily life as guerilla theatre in public spaces – including online spaces. In doing so, these artists draw spectators’ attention to the way their responses to disabled people contribute to the social construction of disability. They provide different theatrical, architectural or technological devices to encourage spectators to articulate their response to themselves and others. But – the use of exaggeration, comedy and confrontation in these practices notwithstanding – their blurry boundaries mean some spectators experience confusion as to whether they are responding to real life or a representation of it. This results in conflicted responses which reveal as much about the politics of disability as the performances themselves. In this paper, I examine how these conflicted responses play out in online forums. I discuss diverse examples, from blog comments on Liz Crow’s Resistance on the Plinth on YouTube, to Aaron Williamson and Katherine Araneillo’s Disabled Avant-Garde clips on YouTube, to Ju Gosling’s Letter Writing Project on her website, to segments of UK Channel 4’s mock reality show Cast Offs on YouTube. I demonstrate how online forums become a place not just for recording memories of an original performance (which posters may not have seen), but for a new performance, which goes well beyond re-membering/remediating the original. I identify trends in the way experience, memory and meaningmaking play out in these performative forums – moving from clarification of the original act’s parameters, to claims of disgust, insult or offense, to counter-claims confirming the comic or political efficacy of the act, often linked disclosure of personal memory or experience of disability. I examine the way these encounters at the interstices of live and/or online performance, memory, technology and public/private history negotiate ideas about disability, and what they tell us about the ethics and efficacy of the specific modes of performance and spectatorship these artists with disabilities are invoking.

OpenFABMAP : an open source toolbox for appearance-based loop closure detection

Appearance-based loop closure techniques, which leverage the high information content of visual images and can be used independently of pose, are now widely used in robotic applications. The current state-of-the-art in the field is Fast Appearance-Based Mapping (FAB-MAP) having been demonstrated in several seminal robotic mapping experiments. In this paper, we describe OpenFABMAP, a fully open source implementation of the original FAB-MAP algorithm. Beyond the benefits of full user access to the source code, OpenFABMAP provides a number of configurable options including rapid codebook training and interest point feature tuning. We demonstrate the performance of OpenFABMAP on a number of published datasets and demonstrate the advantages of quick algorithm customisation. We present results from OpenFABMAP’s application in a highly varied range of robotics research scenarios.

Relaxed phylogenetics and dating with confidence

In phylogenetics, the unrooted model of phylogeny and the strict molecular clock model are two extremes of a continuum. Despite their dominance in phylogenetic inference, it is evident that both are biologically unrealistic and that the real evolutionary process lies between these two extremes. Fortunately, intermediate models employing relaxed molecular clocks have been described. These models open the gate to a new field of “relaxed phylogenetics.” Here we introduce a new approach to performing relaxed phylogenetic analysis. We describe how it can be used to estimate phylogenies and divergence times in the face of uncertainty in evolutionary rates and calibration times. Our approach also provides a means for measuring the clocklikeness of datasets and comparing this measure between different genes and phylogenies. We find no significant rate autocorrelation among branches in three large datasets, suggesting that autocorrelated models are not necessarily suitable for these data. In addition, we place these datasets on the continuum of clocklikeness between a strict molecular clock and the alternative unrooted extreme. Finally, we present analyses of 102 bacterial, 106 yeast, 61 plant, 99 metazoan, and 500 primate alignments. From these we conclude that our method is phylogenetically more accurate and precise than the traditional unrooted model while adding the ability to infer a timescale to evolution.

Activity analysis in complicated scenes using DFT coefficients of particle trajectories

Modelling activities in crowded scenes is very challenging as object tracking is not robust in complicated scenes and optical flow does not capture long range motion. We propose a novel approach to analyse activities in crowded scenes using a “bag of particle trajectories”. Particle trajectories are extracted from foreground regions within short video clips using particle video, which estimates long range motion in contrast to optical flow which is only concerned with inter-frame motion. Our applications include temporal video segmentation and anomaly detection, and we perform our evaluation on several real-world datasets containing complicated scenes. We show that our approaches achieve state-of-the-art performance for both tasks.

Unusual scene detection using distributed behaviour model and sparse representation

The ability to detect unusual events in surviellance footage as they happen is a highly desireable feature for a surveillance system. However, this problem remains challenging in crowded scenes due to occlusions and the clustering of people. In this paper, we propose using the Distributed Behavior Model (DBM), which has been widely used in computer graphics, for video event detection. Our approach does not rely on object tracking, and is robust to camera movements. We use sparse coding for classification, and test our approach on various datasets. Our proposed approach outperforms a state-of-the-art work which uses the social force model and Latent Dirichlet Allocation.

Confrontation and cooptation : a brief history of Australian political blogs

The history of political blogging in Australia does not entirely match the development of blogospheres in other countries. Even at its beginning, blogging was not an entirely alternative endeavour – one of the first news or political blogs was Margo Kingston’s Webdiary, hosted by the Sydney Morning Herald. In the United States, whose political blogosphere has been examined most comprehensively in the literature (see e.g. Adamic & Glance, 2005; Drezner & Farrell, 2008; Shaw & Benkler, 2012; Tremayne, 2007; Wallsten, 2008), blogging had a clear historical trajectory from alternative to mainstream medium. The Australian blogosphere, by contrast, has seen early and continued involvement from representatives of the mainstream media, blogging both for their employers and independently (Garden, 2010). Coupled with the incorporation of blog-like technologies into news websites, as well as with obvious differences in the size of the available talent pool and potential audience for political blogging in Australia, this recognition of blogging by the mainstream media may be one reason why, in political and news discussions at least, Australian bloggers did not bring about their own, local equivalents to the resignations of Dan Rather or Trent Lott in the U.S. –events which were commonly attributed in part to the work of bloggers (Simons, 2007). However, the acceptance of the blogging concept by the mainstream media has been accompanied by a comparative lack of acceptance towards individual bloggers. Analyses and commentary published by bloggers have been attacked by journalists, creating an at times antagonistic relationship between the mainstream media and bloggers (Flew & Wilson, 2010; Young, 2011). In this article, we examine the historical development of blogging in Australia, focussing primarily on political and news blogs. In particular, we review who the bloggers are and how the connections between different blogs and other titles have changed over the past decade. The paper tracks the evolution of individual and group blogs, independent and mainstream media-hosted opinion sites, and the gradual convergence of these platforms and their associated contributing authors. We conclude by examining the current state of the Australian blogosphere and its likely future development, taking into account the rise of social media, and in particular Twitter, as additional spaces for public commentary.

Use of hierarchical cluster analysis to assess the representativeness of a baseline groundwater quality monitoring network: comparison of New Zealand’s national and regional groundwater monitoring programs

Baseline monitoring of groundwater quality aims to characterize the ambient condition of the resource and identify spatial or temporal trends. Sites comprising any baseline monitoring network must be selected to provide a representative perspective of groundwater quality across the aquifer(s) of interest. Hierarchical cluster analysis (HCA) has been used as a means of assessing the representativeness of a groundwater quality monitoring network, using example datasets from New Zealand. HCA allows New Zealand's national and regional monitoring networks to be compared in terms of the number of water-quality categories identified in each network, the hydrochemistry at the centroids of these water-quality categories, the proportions of monitoring sites assigned to each water-quality category, and the range of concentrations for each analyte within each water-quality category. Through the HCA approach, the National Groundwater Monitoring Programme (117 sites) is shown to provide a highly representative perspective of groundwater quality across New Zealand, relative to the amalgamated regional monitoring networks operated by 15 different regional authorities (680 sites have sufficient data for inclusion in HCA). This methodology can be applied to evaluate the representativeness of any subset of monitoring sites taken from a larger network.