Evaluating automatic road detection across a large aerial imagery collection

The automated extraction of roads from aerial imagery can be of value for tasks including mapping, surveillance and change detection. Unfortunately, there are no public databases or standard evaluation protocols for evaluating these techniques. Many techniques are further hindered by a reliance on manual initialisation, making large scale application of the techniques impractical. In this paper, we present a public database and evaluation protocol for the evaluation of road extraction algorithms, and propose an improved automatic seed finding technique to initialise road extraction, based on a combination of geometric and colour features.

Catherine or Kate, the royal name dilemma : humour and performance in collaborative art practice

The traditional model of visual arts practice is one that privileges highly individuated reflection and research on studio based, predominately material outcomes. This archetypal approach to thinking about cultural production tends to overlook all of the conceptual and contextual collaborations that take place, both informally and formally in the process of making artworks. The aim of this practice-led research project is to creatively and critically explore the potential for actively engaging in a collaborative process for making artworks. It will focus on this approach to research and making through performance and video based works made in conjunction with Kate Woodcroft. Through doing this it aims to explore the possibilities for thinking and working beyond singular, materially based practices and develop new understandings for this as a model for generating new and unexpected creative outcomes. Key departure points for this discussion include; tertiary performance, conceptual art, and humour.

Graph-based concept weighting for medical information retrieval

This paper presents a graph-based method to weight medical concepts in documents for the purposes of information retrieval. Medical concepts are extracted from free-text documents using a state-of-the-art technique that maps n-grams to concepts from the SNOMED CT medical ontology. In our graph-based concept representation, concepts are vertices in a graph built from a document, edges represent associations between concepts. This representation naturally captures dependencies between concepts, an important requirement for interpreting medical text, and a feature lacking in bag-of-words representations. We apply existing graph-based term weighting methods to weight medical concepts. Using concepts rather than terms addresses vocabulary mismatch as well as encapsulates terms belonging to a single medical entity into a single concept. In addition, we further extend previous graph-based approaches by injecting domain knowledge that estimates the importance of a concept within the global medical domain. Retrieval experiments on the TREC Medical Records collection show our method outperforms both term and concept baselines. More generally, this work provides a means of integrating background knowledge contained in medical ontologies into data-driven information retrieval approaches.

Heteroscedastic probabilistic linear discriminant analysis for manifold learning in video-based face recognition

To recognize faces in video, face appearances have been widely modeled as piece-wise local linear models which linearly approximate the smooth yet non-linear low dimensional face appearance manifolds. The choice of representations of the local models is crucial. Most of the existing methods learn each local model individually meaning that they only anticipate variations within each class. In this work, we propose to represent local models as Gaussian distributions which are learned simultaneously using the heteroscedastic probabilistic linear discriminant analysis (PLDA). Each gallery video is therefore represented as a collection of such distributions. With the PLDA, not only the within-class variations are estimated during the training, the separability between classes is also maximized leading to an improved discrimination. The heteroscedastic PLDA itself is adapted from the standard PLDA to approximate face appearance manifolds more accurately. Instead of assuming a single global within-class covariance, the heteroscedastic PLDA learns different within-class covariances specific to each local model. In the recognition phase, a probe video is matched against gallery samples through the fusion of point-to-model distances. Experiments on the Honda and MoBo datasets have shown the merit of the proposed method which achieves better performance than the state-of-the-art technique.

Pieces of a city : the art of making speculative cities, bodies, & texts

This practice-led doctorate involved the development of a collection – a bricolage – of interwoven fragments of literary texts and visual imagery explor-ing questions of speculative fiction, urban space and embodiment. As a sup-plement to the creative work, I also developed an exegesis, using a combina-tion of theoretical and contextual analysis combined with critical reflections on my creative process and outputs. An emphasis on issues of creative practice and a sustained investigation into an aesthetics of fragmentation and assem-blage is organised around the concept and methodology of bricolage, the eve-ryday art of ‘making do’. The exegesis also addresses my interest in the city and urban forms of subjectivity and embodiment through the use of a range of theorists, including Michel de Certeau and Elizabeth Grosz.

Image based visual servo control for fixed wing UAVs tracking linear infrastructure in wind

This paper presents an Image Based Visual Servo control design for Fixed Wing Unmanned Aerial Vehicles tracking locally linear infrastructure in the presence of wind using a body fixed imaging sensor. Visual servoing offers improved data collection by posing the tracking task as one of controlling a feature as viewed by the inspection sensor, although is complicated by the introduction of wind as aircraft heading and course angle no longer align. In this work it is shown that the effects of wind alter the desired line angle required for continuous tracking to equal the wind correction angle as would be calculated to set a desired course. A control solution is then sort by linearizing the interaction matrix about the new feature pose such that kinematics of the feature can be augmented with the lateral dynamics of the aircraft, from which a state feedback control design is developed. Simulation results are presented comparing no compensation, integral control and the proposed controller using the wind correction angle, followed by an assessment of response to atmospheric disturbances in the form of turbulence and wind gusts

The naturally imperfect form : investigations of the application of digital sculpting methods - extracted art : incorporating and translating ‘found art’ into the medium of digital sculpture

This dissertation analyses how physical objects are translated into digital artworks using techniques which can lead to ‘imperfections’ in the resulting digital artwork that are typically removed to arrive at a ‘perfect’ final representation. The dissertation discusses the adaptation of existing techniques into an artistic workflow that acknowledges and incorporates the imperfections of translation into the final pieces. It presents an exploration of the relationship between physical and digital artefacts and the processes used to move between the two. The work explores the 'craft' of digital sculpting and the technology used in producing what the artist terms ‘a naturally imperfect form’, incorporating knowledge of traditional sculpture, an understanding of anatomy and an interest in the study of bones (Osteology). The outcomes of the research are presented as a series of digital sculptural works, exhibited as a collection of curiosities in multiple mediums, including interactive game spaces, augmented reality (AR), rapid prototype prints (RP) and video displays.

A topic based document relevance ranking model

Topic modelling has been widely used in the fields of information retrieval, text mining, machine learning, etc. In this paper, we propose a novel model, Pattern Enhanced Topic Model (PETM), which makes improvements to topic modelling by semantically representing topics with discriminative patterns, and also makes innovative contributions to information filtering by utilising the proposed PETM to determine document relevance based on topics distribution and maximum matched patterns proposed in this paper. Extensive experiments are conducted to evaluate the effectiveness of PETM by using the TREC data collection Reuters Corpus Volume 1. The results show that the proposed model significantly outperforms both state-of-the-art term-based models and pattern-based models.

Pattern-based topics for document modelling in information filtering

Many mature term-based or pattern-based approaches have been used in the field of information filtering to generate users’ information needs from a collection of documents. A fundamental assumption for these approaches is that the documents in the collection are all about one topic. However, in reality users’ interests can be diverse and the documents in the collection often involve multiple topics. Topic modelling, such as Latent Dirichlet Allocation (LDA), was proposed to generate statistical models to represent multiple topics in a collection of documents, and this has been widely utilized in the fields of machine learning and information retrieval, etc. But its effectiveness in information filtering has not been so well explored. Patterns are always thought to be more discriminative than single terms for describing documents. However, the enormous amount of discovered patterns hinder them from being effectively and efficiently used in real applications, therefore, selection of the most discriminative and representative patterns from the huge amount of discovered patterns becomes crucial. To deal with the above mentioned limitations and problems, in this paper, a novel information filtering model, Maximum matched Pattern-based Topic Model (MPBTM), is proposed. The main distinctive features of the proposed model include: (1) user information needs are generated in terms of multiple topics; (2) each topic is represented by patterns; (3) patterns are generated from topic models and are organized in terms of their statistical and taxonomic features, and; (4) the most discriminative and representative patterns, called Maximum Matched Patterns, are proposed to estimate the document relevance to the user’s information needs in order to filter out irrelevant documents. Extensive experiments are conducted to evaluate the effectiveness of the proposed model by using the TREC data collection Reuters Corpus Volume 1. The results show that the proposed model significantly outperforms both state-of-the-art term-based models and pattern-based models

Revolving kaleidoscope : site-specificity and the part object in contemporary installation art

This practice-led research project explores the possibilities for restaging and reconfiguring contemporary art installations in multiple and different locations. By exploring ideas and art that demonstrate a kaleidoscopic approach to creative practice, this project examines how analysing artists' particular processes can achieve new understandings and experiences of installation art. This project achieves this through reflection on, and analysis of creative works made throughout the research, and a critical examination of contemporary art practices.

Bluetooth and Wi-Fi MAC address based crowd data collection and monitoring : benefits, challenges and enhancement

This paper firstly presents the benefits and critical challenges on the use of Bluetooth and Wi-Fi for crowd data collection and monitoring. The major challenges include antenna characteristics, environment’s complexity and scanning features. Wi-Fi and Bluetooth are compared in this paper in terms of architecture, discovery time, popularity of use and signal strength. Type of antennas used and the environment’s complexity such as trees for outdoor and partitions for indoor spaces highly affect the scanning range. The aforementioned challenges are empirically evaluated by “real” experiments using Bluetooth and Wi-Fi Scanners. The issues related to the antenna characteristics are also highlighted by experimenting with different antenna types. Novel scanning approaches including Overlapped Zones and Single Point Multi-Range detection methods will be then presented and verified by real-world tests. These novel techniques will be applied for location identification of the MAC IDs captured that can extract more information about people movement dynamics.

1000 voices : an online public collection of life stories

1000 voices is an international web-based platform for gathering and displaying more than 1000 life stories about the lived experience of people with disability. The site contains life stories told by people with disability that are presented in multiple media and formats, including text, audio, video, graphics and visual art...

Great expectations : a project by Boxcopy for Federation Square, Next Wave Festival 2008

Part of the Next Wave MEMBRANE Project, Great Expectations draws attention to the parallels between our expectations of art and new technology to make the world a better place. The theme of the 2008 Next Wave Festival, ‘Closer Together’, refers to the way society is ― for the better or for the worse ― becoming increasingly connected by media and communication technologies. Sceptical of the acclaimed social achievements of new technologies, Boxcopy: Contemporary Art Space, a Brisbane-based artist-run initiative, explores the futility of human activities, including art production and consumption, with a collection of works created by young and emerging Brisbane artists. Works for this project include: Early machines such as the Commodore 64 were tape-based, and hence had their games distributed on ordinary cassettes (2009) by Tim Kerr & Extra Features (2008) by Tim Woodward; Spine (2008), Joseph Briekers; Whiteout (2008), Channon Goodwin; Explosive Revelations (2008), Daniel McKewen.

Topical pattern based document modelling and relevance ranking

For traditional information filtering (IF) models, it is often assumed that the documents in one collection are only related to one topic. However, in reality users’ interests can be diverse and the documents in the collection often involve multiple topics. Topic modelling was proposed to generate statistical models to represent multiple topics in a collection of documents, but in a topic model, topics are represented by distributions over words which are limited to distinctively represent the semantics of topics. Patterns are always thought to be more discriminative than single terms and are able to reveal the inner relations between words. This paper proposes a novel information filtering model, Significant matched Pattern-based Topic Model (SPBTM). The SPBTM represents user information needs in terms of multiple topics and each topic is represented by patterns. More importantly, the patterns are organized into groups based on their statistical and taxonomic features, from which the more representative patterns, called Significant Matched Patterns, can be identified and used to estimate the document relevance. Experiments on benchmark data sets demonstrate that the SPBTM significantly outperforms the state-of-the-art models.

School-based education programmes for the prevention of child sexual abuse

Background Child sexual abuse is a significant global problem in both magnitude and sequelae. The most widely used primary prevention strategy has been the provision of school-based education programmes. Although programmes have been taught in schools since the 1980s, their effectiveness requires ongoing scrutiny. Objectives To systematically assess evidence of the effectiveness of school-based education programmes for the prevention of child sexual abuse. Specifically, to assess whether: programmes are effective in improving students’ protective behaviours and knowledge about sexual abuse prevention; behaviours and skills are retained over time; and participation results in disclosures of sexual abuse, produces harms, or both. Search methods In September 2014, we searched CENTRAL, OvidMEDLINE, EMBASE and 11 other databases.We also searched two trials registers and screened the reference lists of previous reviews for additional trials. Selection criteria We selected randomised controlled trials (RCTs), cluster-RCTs, and quasi-RCTs of school-based education interventions for the prevention of child sexual abuse compared with another intervention or no intervention. Data collection and analysis Two review authors independently assessed the eligibility of trials for inclusion, extracted data, and assessed risk of bias.We summarised data for six outcomes: protective behaviours; knowledge of sexual abuse or sexual abuse prevention concepts; retention of protective behaviours over time; retention of knowledge over time; harm; and disclosures of sexual abuse. School-