Single camera vision-only SLAM on a suburban road network

Simultaneous Localization And Mapping (SLAM) is one of the major challenges in mobile robotics. Probabilistic techniques using high-end range finding devices are well established in the field, but recent work has investigated vision only approaches. This paper presents a method for generating approximate rotational and translation velocity information from a single vehicle-mounted consumer camera, without the computationally expensive process of tracking landmarks. The method is tested by employing it to provide the odometric and visual information for the RatSLAM system while mapping a complex suburban road network. RatSLAM generates a coherent map of the environment during an 18 km long trip through suburban traffic at speeds of up to 60 km/hr. This result demonstrates the potential of ground based vision-only SLAM using low cost sensing and computational hardware.

Towards improved speech recognition for resource poor languages

In recent times, the improved levels of accuracy obtained by Automatic Speech Recognition (ASR) technology has made it viable for use in a number of commercial products. Unfortunately, these types of applications are limited to only a few of the world’s languages, primarily because ASR development is reliant on the availability of large amounts of language specific resources. This motivates the need for techniques which reduce this language-specific, resource dependency. Ideally, these approaches should generalise across languages, thereby providing scope for rapid creation of ASR capabilities for resource poor languages. Cross Lingual ASR emerges as a means for addressing this need. Underpinning this approach is the observation that sound production is largely influenced by the physiological construction of the vocal tract, and accordingly, is human, and not language specific. As a result, a common inventory of sounds exists across languages; a property which is exploitable, as sounds from a resource poor, target language can be recognised using models trained on resource rich, source languages. One of the initial impediments to the commercial uptake of ASR technology was its fragility in more challenging environments, such as conversational telephone speech. Subsequent improvements in these environments has gained consumer confidence. Pragmatically, if cross lingual techniques are to considered a viable alternative when resources are limited, they need to perform under the same types of conditions. Accordingly, this thesis evaluates cross lingual techniques using two speech environments; clean read speech and conversational telephone speech. Languages used in evaluations are German, Mandarin, Japanese and Spanish. Results highlight that previously proposed approaches provide respectable results for simpler environments such as read speech, but degrade significantly when in the more taxing conversational environment. Two separate approaches for addressing this degradation are proposed. The first is based on deriving better target language lexical representation, in terms of the source language model set. The second, and ultimately more successful approach, focuses on improving the classification accuracy of context-dependent (CD) models, by catering for the adverse influence of languages specific phonotactic properties. Whilst the primary research goal in this thesis is directed towards improving cross lingual techniques, the catalyst for investigating its use was based on expressed interest from several organisations for an Indonesian ASR capability. In Indonesia alone, there are over 200 million speakers of some Malay variant, provides further impetus and commercial justification for speech related research on this language. Unfortunately, at the beginning of the candidature, limited research had been conducted on the Indonesian language in the field of speech science, and virtually no resources existed. This thesis details the investigative and development work dedicated towards obtaining an ASR system with a 10000 word recognition vocabulary for the Indonesian language.

The potential to mitigate global warming with no-tillage management is only realized when practised in the long term

No-tillage (NT) management has been promoted as a practice capable of offsetting greenhouse gas (GHG) emissions because of its ability to sequester carbon in soils. However, true mitigation is only possible if the overall impact of NT adoption reduces the net global warming potential (GWP) determined by fluxes of the three major biogenic GHGs (i.e. CO2, N2O, and CH4). We compiled all available data of soil-derived GHG emission comparisons between conventional tilled (CT) and NT systems for humid and dry temperate climates. Newly converted NT systems increase GWP relative to CT practices, in both humid and dry climate regimes, and longer-term adoption (>10 years) only significantly reduces GWP in humid climates. Mean cumulative GWP over a 20-year period is also reduced under continuous NT in dry areas, but with a high degree of uncertainty. Emissions of N2O drive much of the trend in net GWP, suggesting improved nitrogen management is essential to realize the full benefit from carbon storage in the soil for purposes of global warming mitigation. Our results indicate a strong time dependency in the GHG mitigation potential of NT agriculture, demonstrating that GHG mitigation by adoption of NT is much more variable and complex than previously considered, and policy plans to reduce global warming through this land management practice need further scrutiny to ensure success.

Water drinking influences eye length and IOP in young healthy subjects

This study aimed to investigate the influence of water loading upon intraocular pressure (IOP), ocular pulse amplitude (OPA) and axial length. Twenty one young adult subjects who were classified based on their spherical equivalent refraction as either myopes (n=11), or emmetropes (n=10) participated. Measures of IOP, OPA and ocular biometrics were collected before, and then 10, 15, 25 and 30 minutes following the ingestion of 1000 ml of water. Significant increases in both IOP and OPA were found to occur following water loading (p<0.0001), with peaks in both parameters occurring at 10 minutes after water loading (mean ± SEM increase of 2.24 ± 0.31 mmHg in IOP and 0.46 ± 0.06 mmHg in OPA). Axial length was found to reduce significantly following water loading (p=0.0005), with the largest reduction in axial length evident 10 minutes after water drinking (mean decrease 12 ± 3 µm). A significant time by refractive error group interaction (p=0.048) was found in axial length, indicative of a different pattern of change in eye length following water loading between the myopic and emmetropic populations. The largest difference in axial length change was evident at 10 minutes after water loading with a 17 ± 5 µm reduction in axial length evident in the myopes and only a 6 ± 2 µm reduction in the emmetropes. These findings illustrate significant changes in ocular parameters in young adult subjects following water loading.

Lateral shearing interferometry, dynamic wavefront sensing, and high-speed videokeratoscopy for noninvasive assessment of tear film surface characteristics : a comparitive study

There are several noninvasive techniques for assessing the kinetics of tear film, but no comparative studies have been conducted to evaluate their efficacies. Our aim is to test and compare techniques based on high-speed videokeratoscopy (HSV), dynamic wavefront sensing (DWS), and lateral shearing interferometry (LSI). Algorithms are developed to estimate the tear film build-up time TBLD, and the average tear film surface quality in the stable phase of the interblink interval TFSQAv. Moderate but significant correlations are found between TBLD measured with LSI and DWS based on vertical coma (Pearson's r2=0.34, p<0.01) and higher order rms (r2=0.31, p<0.01), as well as between TFSQAv measured with LSI and HSV (r2=0.35, p<0.01), and between LSI and DWS based on the rms fit error (r2=0.40, p<0.01). No significant correlation is found between HSV and DWS. All three techniques estimate tear film build-up time to be below 2.5 sec, and they achieve a remarkably close median value of 0.7 sec. HSV appears to be the most precise method for measuring tear film surface quality. LSI appears to be the most sensitive method for analyzing tear film build-up.

Who makes the news : Australia : global media monitoring project 2010 national report

The Australian report for the Global Media Monitoring Project 2010 (GMMP 2010) involved a study of 374 stories that were sampled from 26 Australian newspapers, radio and television stations, and internet news services on 10 November 2009. This snapshot of reporting on that day suggests that women are under-represented in the Australian news media as both the sources and creators of news. Females made up only 24% of the 1012 news sources who were heard, read about or seen in the stories that were studied. Neglect of female sources was particularly noticeable in sports news. Women made up only 1% of the 142 sources who were talked about or quoted in sports stories. Female sources of news were disproportionately portrayed as celebrities and victims. Although women made up only 24% of sources overall, they comprised 44% of victims of crimes, accidents, war, health problems, or discrimination. Unsurprisingly, women made up 32% of sources in stories about violent crimes and 29% in stories about disasters, accidents or emergencies – usually in the role of victim. Females were commonly defined in terms of their status as a mother, daughter, wife, sister or other family relationship. Family status was mentioned for 33% of women quoted or discussed in the news stories compared to only 13% of male sources. Women also made up 75% of sources described as homemakers or parents. The Australian GMMP 2010 study also indicates a gender division among the journalists who wrote or presented the news. Only 32% of the stories were written or presented by female reporters and newsreaders. The gender inequality was again most evident in sports journalism. Findings from the Australian report also contributed to the GMMP 2010 Global Report and the Pacific GMMP 2010 Regional Report, which are available at http://whomakesthenews.org/gmmp/gmmp-reports/gmmp-2010-reports

Vision only pose estimation and scene reconstruction on airborne platforms

We aim to demonstrate unaided visual 3D pose estimation and map reconstruction using both monocular and stereo vision techniques. To date, our work has focused on collecting data from Unmanned Aerial Vehicles, which generates a number of significant issues specific to the application. Such issues include scene reconstruction degeneracy from planar data, poor structure initialisation for monocular schemes and difficult 3D reconstruction due to high feature covariance. Most modern Visual Odometry (VO) and related SLAM systems make use of a number of sensors to inform pose and map generation, including laser range-finders, radar, inertial units and vision [1]. By fusing sensor inputs, the advantages and deficiencies of each sensor type can be handled in an efficient manner. However, many of these sensors are costly and each adds to the complexity of such robotic systems. With continual advances in the abilities, small size, passivity and low cost of visual sensors along with the dense, information rich data that they provide our research focuses on the use of unaided vision to generate pose estimates and maps from robotic platforms. We propose that highly accurate (�5cm) dense 3D reconstructions of large scale environments can be obtained in addition to the localisation of the platform described in other work [2]. Using images taken from cameras, our algorithm simultaneously generates an initial visual odometry estimate and scene reconstruction from visible features, then passes this estimate to a bundle-adjustment routine to optimise the solution. From this optimised scene structure and the original images, we aim to create a detailed, textured reconstruction of the scene. By applying such techniques to a unique airborne scenario, we hope to expose new robotic applications of SLAM techniques. The ability to obtain highly accurate 3D measurements of an environment at a low cost is critical in a number of agricultural and urban monitoring situations. We focus on cameras as such sensors are small, cheap and light-weight and can therefore be deployed in smaller aerial vehicles. This, coupled with the ability of small aerial vehicles to fly near to the ground in a controlled fashion, will assist in increasing the effective resolution of the reconstructed maps.

Death by Drowning : Gary Bryson's Turtle [A Review]

Accused of being autobiographical, as many debut novels often are, Turtle, upon first reading and further prying, does read as a story wrenched out of Gary Bryson’s own life. In a recent interview with Mandy Sayer, however, he was quick to deny all sorts of archetypal allegations. “Any resemblance to turtles living or dead”, Bryson explained, “is entirely coincidental”. Regardless of the many parallels that align author with protagonist—both were born and raised in a grey-skied Glasgow, both grew up in self-described dysfunctional families, and both returned to the colourless city to attend their mothers’ funerals—the narrative combines bruising black comedy with moments of magic realism. The result is an unlikely but often surprising concoction of twists and turns, each of which mixes the fallibility of memory with the slippery nature of truth. This playfulness between the material world and its metaphorical counterpart raises questions, not only about the curse that poisons its characters, but about the ethical implications of blurring fact and fiction...

Rich probabilistic representations for bearing only decentralised data fusion

The aim of this paper is to demonstrate the validity of using Gaussian mixture models (GMM) for representing probabilistic distributions in a decentralised data fusion (DDF) framework. GMMs are a powerful and compact stochastic representation allowing efficient communication of feature properties in large scale decentralised sensor networks. It will be shown that GMMs provide a basis for analytical solutions to the update and prediction operations for general Bayesian filtering. Furthermore, a variant on the Covariance Intersect algorithm for Gaussian mixtures will be presented ensuring a conservative update for the fusion of correlated information between two nodes in the network. In addition, purely visual sensory data will be used to show that decentralised data fusion and tracking of non-Gaussian states observed by multiple autonomous vehicles is feasible.

Children re-read and re-write their neighborhoods : critical literacies and identity work

This chapter considers the complex literate repertoires of 21st century children in multicultural primary classrooms in Adelaide South Australia. It draws on the curricular and pedagogical work of two experienced primary school teachers who explore culture, race and class, by positioning children as textual producers across a variety of media. In particular we discuss two child-authored texts – A is for Arndale – a local alphabet book co-authored by children aged between eight and ten, and – Cooking Afghani Style - a magazine style film produced by a multi-aged class of children (aged eight to thirteen) recently arrived in Australia. In the process of making these texts, primary children engaged in reading as a cultural practice – re-reading and re-writing their neighbourhoods and identities (both individual and collective). This involved frequent excursions to local key sites, both familiar and unfamiliar to the children. They investigated how diverse children experienced and lived their lives in particular places within changing communities.

'Which is the best Doctor Who story?' : a case study in value judgements outside the academy'

One of Cultural Studies' most important contributions to academic thinking about culture is the acceptance as axiomatic that we must not simply accept traditional value hierarchies in relation to cultural objects (see, for example, McGuigan, 1992: 157; Brunsdon, 1997: 5; Wark, 2001). Since Richard Hoggart and Raymond Williams took popular culture as a worthy object of study, Cultural Studies practitioners have accepted that the terms in which cultural debate had previously been conducted involved a category error. Opera is not 'better' than pop music, we believe in Cultural Studies - 'better for what?', we would ask. Similarly, Shakespeare is not 'better' than Mills and Boon, unless you can specify the purpose for which you want to use the texts. Shakespeare is indeed better than Mills and Boon for understanding seventeenth century ideas about social organisation; but Mills and Boon is unquestionably better than Shakespeare if you want slightly scandalous, but ultimately reassuring representations of sexual intercourse. The reason that we do not accept traditional hierarchies of cultural value is that we know that the culture that is commonly understood to be 'best' also happens to be that which is preferred by the most educated and most materially well-off people in any given culture (Bourdieu, 1984: 1- 2; Ross, 1989: 211). We can interpret this information in at least two ways. On the one hand, it can be read as proving that the poorer and less well-educated members of a society do indeed have tastes which are innately less worthwhile than those of the material and educational elite. On the other hand, this information can be interpreted as demonstrating that the cultural and material elite publicly represent their own tastes as being the only correct ones. In Cultural Studies, we tend to favour the latter interpretation. We reject the idea that cultural objects have innate value, in terms of beauty, truth, excellence, simply 'there' in the object. That is, we reject 'aesthetic' approaches to culture (Bourdieu, 1984: 6; 485; Hartley, 1994: 6)1. In this, Cultural Studies is similar to other postmodern institutions, where high and popular culture can be mixed in ways unfamiliar to modernist culture (Sim, 1992: 1; Jameson, 1998: 100). So far, so familiar.

Diversity in action : minority group media and social change (text-only version)

This magazine, written by Melissa Giles, features three Brisbane-based media organisations: Radio 4RPH, Queensland Pride and 98.9FM. The PDF file on this website contains a text-only version of the magazine. Contact the author if you would like a copy of the text-only EPUB file or a copy of the full digital magazine with images. An audio version of the magazine is available at http://eprints.qut.edu.au/41729/

Labyrinthine literacies : navigating cultural agency in the arrival and requiem for a beast

The OED reminds us as surely as Ovid that a labyrinth is a “structure consisting of a number of intercommunicating passages arranged in bewildering complexity, through which it is it difficult or impossible to find one’s way without guidance”. Both Shaun Tan’s The Arrival (2006) and Matt Ottley’s Requiem for a Beast: A Work for Image, Word and Music (2007) mark a kind of labyrinthine watershed in Australian children’s literature. Deploying complex, intercommunicating logics of story and literacy, these books make high demands of their reader but also offer guidance for the successful navigation of their stories; for their protagonists as surely as for readers. That the shared logic of navigation in each book is literacy as privileged form of meaning-making is not surprising in the sense that within “a culture deeply invested in myths of individualism and self-sufficiency, it is easy to see why literacy is glorified as an attribute of individual control and achievement” (Williams and Zenger 166). The extent to which these books might be read as exemplifying desired norms of contemporary Australian culture seems to be affirmed by the fact of Tan and Ottley winning the Australian “Picture Book of the Year” prize awarded by the Children’s Book Council of Australia in 2007 and 2008 respectively. However, taking its cue from Ottley’s explicit intertextual use of the myth of Theseus and from Tan’s visual rhetoric of lostness and displacement, this paper reads these texts’ engagement with tropes of “literacy” in order to consider the ways in which norms of gender and culture seemingly circulated within these texts might be undermined by constructions of “nation” itself as a labyrinth that can only partly be negotiated by a literate subject. In doing so, I argue that these picture books, to varying degrees, reveal a perpetuation of the “literacy myth” (Graff 12) as a discourse of safety and agency but simultaneously bear traces of Ariadne’s story, wherein literacy alone is insufficient for safe navigation of the labyrinth of culture.