100Hz onboard vision for quadrotor state estimation

This paper introduces a high-speed, 100Hz, visionbased state estimator that is suitable for quadrotor control in close quarters manoeuvring applications. We describe the hardware and algorithms for estimating the state of the quadrotor. Experimental results for position, velocity and yaw angle estimators are presented and compared with motion capture data. Quantitative performance comparison with state-of-the-art achievements are also presented.

Airborne collision scenario flight tests : impact of angle measurement errors on reactive vision-based avoidance control

The future emergence of many types of airborne vehicles and unpiloted aircraft in the national airspace means collision avoidance is of primary concern in an uncooperative airspace environment. The ability to replicate a pilot’s see and avoid capability using cameras coupled with vision based avoidance control is an important part of an overall collision avoidance strategy. But unfortunately without range collision avoidance has no direct way to guarantee a level of safety. Collision scenario flight tests with two aircraft and a monocular camera threat detection and tracking system were used to study the accuracy of image-derived angle measurements. The effect of image-derived angle errors on reactive vision-based avoidance performance was then studied by simulation. The results show that whilst large angle measurement errors can significantly affect minimum ranging characteristics across a variety of initial conditions and closing speeds, the minimum range is always bounded and a collision never occurs.

V1-inspired features induce a weighted margin in SVMs

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.

Submission to the Queensland Department of Communities Review of the Juvenile Justices Act 1992 Issues Paper 2007

This submission addresses the Queensland Government’s Department of Communities Issues Paper regarding the Review of the Juvenile Justice Act 1992 (August 2007). The Queensland University of Technology Faculty of Law has a Criminal Justice Program within the Law and Justice Research Centre. The members of this Program wish to participate in the debate on these issues which are critically important to the Queensland community at large but especially to our young people.

Could mobile telephony be harnessed for development in Papua New Guinea?

Could mobile telephony be harnessed for development in Papua New Guinea (PNG)? Could mobile phones be utilised to enhance the security and prosperity of rural communities? Could mobile phones be a useful tool in the achievement of the PNG 2050 Vision targets? This paper is based on literature review around use of mobile phones in development in Asia, Africa, and the Caribbean. It also draws on discussions with key players in PNG, such as NGOs, UN agencies, donor partners, telecommunication companies and the government of PNG. Anticipated benefits of mobile phone availability have not been fully realised in rural areas of PNG to date due to pricing, difficulties with recharging handset batteries in communities which do not have mains electricity supply, and also concerns about negative social changes related to mobile telephony, for example parental stress over youth forming unsuitable relationships. Nonetheless, there are manifest possible ways for mobile phone technology to change user communication patterns positively regarding economic output. In sectors as diverse as health, education and law and justice, discussions are currently underway to establish how mobile phones could be used to increase service delivery, particularly to rural and marginal communities.

Translating vision research into policy and practice to improve visibility, and hence safety, of road workers at night

This case study report describes the stages involved in the translation of research on night-time visibility into standards for the safety clothing worn by roadworkers. Vision research demonstrates that when lights are placed on the moveable joints of the body and the person moves in a dark setting, the phenomenon known as “biological motion or biomotion” occurs, enabling rapid and accurate recognition of the human form although only the lights can be seen. QUT was successful in gaining funding from the Australian Research Council for a Linkage grant due to the support of the predecessors of the Queensland Department of Transport and Main Roads (TMR) to research the biomotion effect in on-road settings using materials that feature in roadworker clothing. Although positive results were gained, the process of translating the research results into policy, practices and standards relied strongly on the supportive efforts of TMR staff engaged in the review and promulgation of national standards. The ultimate result was the incorporation of biomotion marking into AS/NZS 4602.1 2011. The experiences gained in this case provide insights into the processes involved in translating research into practice.

A Summative Evaluation of the Stronger Smarter Learning Communities Project : Vol 1 and Vol 2

This is a summative evaluation of the Stronger Smarter Learning Communities (SSLC) project that examines whether and how the SSLC project had an impact on Australian state schools which adopted its models and approaches. Drawing from qualitative and quantitative data sets, it also presents the largest scale and most comprehensive analysis of Indigenous education practices and outcomes to date. It includes empirical findings on: success in changing school ethos and community engagement; challenges in progress at closure of the 'gap' in conventionally measured achievement and performance; schools' and principals' choices in curriculum and instruction; profiles of teachers' and principals' training and views on teacher education; and a strong emphasis on community and school Indigenoous voices and views on Indigenous education.

Vision based control for micro aerial vehicles : Application to sense and avoid

This work presents a collision avoidance approach based on omnidirectional cameras that does not require the estimation of range between two platforms to resolve a collision encounter. Our method achieves minimum separation between the two vehicles involved by maximising the view-angle given by the omnidirectional sensor. Only visual information is used to achieve avoidance under a bearing- only visual servoing approach. We provide theoretical problem formulation, as well as results from real flights using small quadrotors

Mailed versus frozen transport of nasal swabs for surveillance of respiratory bacteria in remote Indigenous communities in Australia

Background Surveillance programs and research for acute respiratory infections in remote Australian communities are complicated by difficulties in the storage and transport of frozen samples to urban laboratories for testing. This study assessed the sensitivity of a simple method for transporting nasal swabs from a remote setting for bacterial polymerase chain reaction (PCR) testing. Methods We sampled every individual who presented to a remote community clinic over a three week period in August at a time of low influenza and no respiratory syncytial virus activity. Two anterior nasal swabs were collected from each participant. The left nare specimen was mailed to the laboratory via routine postal services. The right nare specimen was transported frozen. Testing for six bacterial species was undertaken using real-time PCR. Results One hundred and forty participants were enrolled who contributed 150 study visits and paired specimens for testing. Respiratory illnesses accounted for 10% of the reasons for presentation. Bacteria were identified in 117 (78%) presentations for 110 (79.4%) individuals; Streptococcus pneumoniae and Haemophilus influenzae were the most common (each identified in 58% of episodes). The overall sensitivity for any bacterium detected in mailed specimens was 82.2% (95% CI 73.6, 88.1) compared to 94.8% (95% CI 89.4, 98.1) for frozen specimens. The sensitivity of the two methods varied by species identified. Conclusion The mailing of unfrozen nasal specimens from remote communities appears to influence the utility of the specimen for bacterial studies, with a loss in sensitivity for the detection of any species overall. Further studies are needed to confirm our finding and to investigate the possible mechanisms of effect. Clinical trial registration Australia and New Zealand Clinical Trials Registry Number: ACTRN12609001006235. Keywords: Respiratory bacteria; RT-PCR; Specimen transport; Laboratory methods

‘Connect and create’ : young people, YouTube and graffiti communities

Dominant discourses around young people and social networking in the mass media are littered with negative connotations and moral panics. While some scholars challenge this negativity, their focus has predominantly been upon the formation of friendships, the construction of identity and the presentation of the self online. We argue that as well as engaging in such areas, young people are also appropriating social networking sites, such as YouTube, as spaces in which they can engage in what Jean Burgess terms, ‘Vernacular Creativity’ – a way of describing and surfacing creative practices that emerge from non-elite, specific everyday contexts. Using case study material we consider the processes of Vernacular Creativity as engaged with by young people in relation to doing graffiti with YouTube. Through this, and given that graffiti is a cultural practise traditionally associated with physical space, we also consider points of continuity and discontinuity in relation to Vernacular Creativity mediated with YouTube and the significance of such things in enabling young people to connect and create with like-minded others.

Making space and place for knowledge communities : lessons for Australian practice

This paper aims to shed light on the planning and development processes of the knowledge-based urban development phenomenon, with respect to the construction of knowledge community precincts. We undertake policy and best practice analyses to learn from the planning and development processes of internationally renowned knowledge community precincts—from Copenhagen, Eindhoven and Singapore. In the light of this, we scrutinise major Australian knowledge community precinct initiatives—from Sydney, Melbourne and Brisbane—to better understand the dynamics of national practices, and benchmark them against the international best practice cases. The paper concludes with a discussion on the study findings and successfully establishing space and place for both knowledge economy and society in Australian cities.

Investigative Essentials for Journalists in Multicultural and Diverse Communities

This chapter describes how investigative journalism can uncover news that often goes unreported about personalities, problems, ways of life and pressing issues in ethnic and religious sub-communities. While investigative journalism is traditionally understood as reporting that exposes corrupt, inefficient, incompetent or other inappropriate conduct in politics and business circles, investigative reporters do far more than that. They also map human activities, landmarks, patterns and changes in the landscape, and connections across the whole of society. This type of investigative journalism can improve reporting of ethnic and religious sub-communities via identification, deep observation and analysis of trends, events, and issues that would otherwise remain hidden or obscured. The chapter includes details of techniques that investigative journalists can employ to identify interesting topics, find sources of information, analyse data and issues, and report compelling stories.

Vision-only autonomous navigation using topometric maps

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph --- as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

Vision-based place recognition : how low can you go?

In this paper we use the algorithm SeqSLAM to address the question, how little and what quality of visual information is needed to localize along a familiar route? We conduct a comprehensive investigation of place recognition performance on seven datasets while varying image resolution (primarily 1 to 512 pixel images), pixel bit depth, field of view, motion blur, image compression and matching sequence length. Results confirm that place recognition using single images or short image sequences is poor, but improves to match or exceed current benchmarks as the matching sequence length increases. We then present place recognition results from two experiments where low-quality imagery is directly caused by sensor limitations; in one, place recognition is achieved along an unlit mountain road by using noisy, long-exposure blurred images, and in the other, two single pixel light sensors are used to localize in an indoor environment. We also show failure modes caused by pose variance and sequence aliasing, and discuss ways in which they may be overcome. By showing how place recognition along a route is feasible even with severely degraded image sequences, we hope to provoke a re-examination of how we develop and test future localization and mapping systems.