A robust structure and motion replacement for bundle adjustment

This paper demonstrates the application of a robust form of pose estimation and scene reconstruction using data from camera images. We demonstrate results that suggest the ability of the algorithm to rival methods of RANSAC based pose estimation polished by bundle adjustment in terms of solution robustness, speed and accuracy, even when given poor initialisations. Our simulated results show the behaviour of the algorithm in a number of novel simulated scenarios reflective of real world cases that show the ability of the algorithm to handle large observation noise and difficult reconstruction scenes. These results have a number of implications for the vision and robotics community, and show that the application of visual motion estimation on robotic platforms in an online fashion is approaching real-world feasibility.

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.

Applying ISOMAP to the learning of hyperspectral image

In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive. We propose the use of Isomap, a non-linear manifold learning technique combined with Expectation Maximisation in graphical probabilistic models for learning and classification. Isomap is used to find the underlying manifold of the training data. This low dimensional representation of the hyperspectral data facilitates the learning of a Gaussian Mixture Model representation, whose joint probability distributions can be calculated offline. The learnt model is then applied to the hyperspectral image at runtime and data classification can be performed.

Applying incremental EM to Bayesian classifiers in the learning of hyperspectral remote sensing data

In this paper, we apply the incremental EM method to Bayesian Network Classifiers to learn and interpret hyperspectral sensor data in robotic planetary missions. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. Many spacecraft carry spectroscopic equipment as wavelengths outside the visible light in the electromagnetic spectrum give much greater information about an object. The algorithm used is an extension to the standard Expectation Maximisation (EM). The incremental method allows us to learn and interpret the data as they become available. Two Bayesian network classifiers were tested: the Naive Bayes, and the Tree-Augmented-Naive Bayes structures. Our preliminary experiments show that incremental learning with unlabelled data can improve the accuracy of the classifier.

Building a software architecture for a human-robot team using the ORCA framework

This paper considers the problem of building a software architecture for a human-robot team. The objective of the team is to build a multi-attribute map of the world by performing information fusion. A decentralized approach to information fusion is adopted to achieve the system properties of scalability and survivability. Decentralization imposes constraints on the design of the architecture and its implementation. We show how a Component-Based Software Engineering approach can address these constraints. The architecture is implemented using Orca – a component-based software framework for robotic systems. Experimental results from a deployed system comprised of an unmanned air vehicle, a ground vehicle, and two human operators are presented. A section on the lessons learned is included which may be applicable to other distributed systems with complex algorithms. We also compare Orca to the Player software framework in the context of distributed systems.

Developments in measuring the “creative” workforce

This article outlines the contribution the ARC Centre of Excellence for Creative Industries and Innovation has made to the project to improve statistical parameters for defining the “creative” workforce. This is one approach which addresses the imprecision of official statistics in grasping the emergent nature of the creative industries. The article discusses the policy implications of the differences between emphasizing industry and occupation or workforce. It provides qualitative case studies that provide further perspectives on quantitative analysis of the creative workforce. It also outlines debates about the implications for the cultural disciplines of an evidence-based account of creative labour. The “creative trident” methodology is summarized: it is the total of creative occupations within the core creative industries (specialists), plus the creative occupations employed in other industries (embedded) plus the business and support occupations employed in creative industries who are often responsible for managing, accounting for and technically supporting creative activity (support). The method is applied to the arts workforce in Australia. An industry-facing spin-off from the centre's mapping work, Creative Business Benchmarker, is discussed. The implications of this approach to the creative workforce is raised and exemplified in case studies of design and of the health industry.

The Australian UAS Experience

Invited presentation made to the New Zealand Robotic Systems Network Conference. The presentation provides an overview of the Unmanned Aircraft Systems industry, civil applications for the technology, some current research activity and the UAS industry initiatives in the Australia.

Lumia : Art | light | motion. The Art of Kuuki.

The State Library of Queensland is delighted to present Lumia: art/light/motion, a culmination of many years of collaboration by the Kuuki collective led by Priscilla Bracks and Gavin Sade. This extraordinary exhibition not only showcases the unique talent of these Queenslanders, it also opens up a world of future possibilities while re-presenting the past and present. These contemporary new media installations sit comfortably within the walls of the library as they are the distinctive products of inquisitive and philosophical minds. In a sense the exhibition highlights the longevity and purposefulness of a cultural learning institution, through the non-traditional use of data, information, research and collection interpretation. The exhibition simultaneously articulates one of our key objectives – to progress the state’s digital agenda. Two academic essays have been commissioned for this joint Kuuki and State Library of Queensland publication. The first is by artist and writer Paul Brown, who has specialised in art, science and technology since the late 1960s and in computational and generative art since the mid 1970s. Brown investigates the history of new media, which is celebrating its 60th anniversary, and clearly places Sade and Bracks at the forefront of this genre nationally. The second essay is by arts writer Linda Carroli, who has delved deeply into the thoughts and processes of the artists to bring to light the complex workings of the artists’ minds. The publication also features an interview Carroli conducted with the artists. This exhibition is playful, informative and contemplative. The audience is invited to play, and consequently to ponder the way we live and the environmental and social implications of our choices. The exhibition tempts us to travel deep into the Antarctic, plunge into the Great Barrier Reef, be swamped by an orchestra of crickets, enter the Charmed world and travel back in time to a Victorian parlour where you can interact with a ‘new-world’ lyrebird and consider a brave new world where our only link to the animal world is with robotic representations. In essence this exhibition is about ideas and knowledge and what better institution than the State Library of Queensland to partner such a project?. State Library is committed to preserving culture, exploring new media and creating new content as a lasting legacy of Queensland for all Queenslanders.

Lego robotics : an authentic problem solving tool?

With the current curriculum focus on correlating classroom problem solving lessons to real-world contexts, are LEGO robotics an effective problem solving tool? This present study was designed to investigate this question and to ascertain what problem solving strategies primary students engaged with when working with LEGO robotics and whether the students were able to effectively relate their problem solving strategies to real-world contexts. The qualitative study involved 23 Grade 6 students participating in robotics activities. The study included data collected from researcher observations of student problem solving discussions, collected software programs, and data from a student completed questionnaire. Results from the study indicated that the robotic activities assisted students to reflect on the problem-solving decisions they made. The study also highlighted that the students were able to relate their problem solving strategies to real-world contexts. The study demonstrated that while LEGO robotics can be considered useful problem solving tools in the classroom, careful teacher scaffolding needs to be implemented in regards to correlating LEGO with authentic problem solving. Further research in regards to how teachers can best embed real-world contexts into effective robotics lessons is recommended.

Adding a receding horizon to Locally Weighted Regression for learning robot control

There have been notable advances in learning to control complex robotic systems using methods such as Locally Weighted Regression (LWR). In this paper we explore some potential limits of LWR for robotic applications, particularly investigating its application to systems with a long horizon of temporal dependence. We define the horizon of temporal dependence as the delay from a control input to a desired change in output. LWR alone cannot be used in a temporally dependent system to find meaningful control values from only the current state variables and output, as the relationship between the input and the current state is under-constrained. By introducing a receding horizon of the future output states of the system, we show that sufficient constraint is applied to learn good solutions through LWR. The new method, Receding Horizon Locally Weighted Regression (RH-LWR), is demonstrated through one-shot learning on a real Series Elastic Actuator controlling a pendulum.

The digital Dark Ages : a retro-speculative history of possible futures

The Dark Ages are generally held to be a time of technological and intellectual stagnation in western development. But that is not necessarily the case. Indeed, from a certain perspective, nothing could be further from the truth. In this paper we draw historical comparisons, focusing especially on the thirteenth and fourteenth centuries, between the technological and intellectual ruptures in Europe during the Dark Ages, and those of our current period. Our analysis is framed in part by Harold Innis’s2 notion of "knowledge monopolies". We give an overview of how these were affected by new media, new power struggles, and new intellectual debates that emerged in thirteenth and fourteenth century Europe. The historical salience of our focus may seem elusive. Our world has changed so much, and history seems to be an increasingly far-from-favoured method for understanding our own period and its future potentials. Yet our seemingly distant historical focus provides some surprising insights into the social dynamics that are at work today: the fracturing of established knowledge and power bases; the democratisation of certain "sacred" forms of communication and knowledge, and, conversely, the "sacrosanct" appropriation of certain vernacular forms; challenges and innovations in social and scientific method and thought; the emergence of social world-shattering media practices; struggles over control of vast networks of media and knowledge monopolies; and the enclosure of public discursive and social spaces for singular, manipulative purposes. The period between the eleventh and fourteenth centuries in Europe prefigured what we now call the Enlightenment, perhaps moreso than any other period before or after; it shaped what the Enlightenment was to become. We claim no knowledge of the future here. But in the "post-everything" society, where history is as much up for sale as it is for argument, we argue that our historical perspective provides a useful analogy for grasping the wider trends in the political economy of media, and for recognising clear and actual threats to the future of the public sphere in supposedly democratic societies.

The digital Dark Ages : a retro-speculative history of possible futures

The Dark Ages are generally held to be a time of technological and intellectual stagnation in western development. But that is not necessarily the case. Indeed, from a certain perspective, nothing could be further from the truth. In this paper we draw historical comparisons, focusing especially on the thirteenth and fourteenth centuries, between the technological and intellectual ruptures in Europe during the Dark Ages, and those of our current period. Our analysis is framed in part by Harold Innis’s2 notion of "knowledge monopolies". We give an overview of how these were affected by new media, new power struggles, and new intellectual debates that emerged in thirteenth and fourteenth century Europe. The historical salience of our focus may seem elusive. Our world has changed so much, and history seems to be an increasingly far-from-favoured method for understanding our own period and its future potentials. Yet our seemingly distant historical focus provides some surprising insights into the social dynamics that are at work today: the fracturing of established knowledge and power bases; the democratisation of certain "sacred" forms of communication and knowledge, and, conversely, the "sacrosanct" appropriation of certain vernacular forms; challenges and innovations in social and scientific method and thought; the emergence of social world-shattering media practices; struggles over control of vast networks of media and knowledge monopolies; and the enclosure of public discursive and social spaces for singular, manipulative purposes. The period between the eleventh and fourteenth centuries in Europe prefigured what we now call the Enlightenment, perhaps moreso than any other period before or after; it shaped what the Enlightenment was to become. We claim no knowledge of the future here. But in the "post-everything" society, where history is as much up for sale as it is for argument, we argue that our historical perspective provides a useful analogy for grasping the wider trends in the political economy of media, and for recognising clear and actual threats to the future of the public sphere in supposedly democratic societies.

Pseudoseeds : investigating long-distance, ocean seed dispersal with wireless sensors

Recent theoretical research has shown that ocean currents and wind interact to disperse seeds over long distances among isolated landmasses. Dispersal of seeds among isolated oceanic islands, by birds, oceans and man, is a well-known phenomenon, and many widespread island plants have traits that facilitate this process. Crucially, however, there have been no mechanistic vector-based models of long-distance dispersal for seeds among isolated oceanic islands based on empirical data. Here, we propose a plan to develop seed analogues, or pseudoseeds, fitted with wireless sensor technology that will enable high-fidelity tracking as they disperse across the ocean. The pseudoseeds will be precisely designed to mimic actual seed buoyancy and morphology enabling realistic and accurate, vector-based dispersal models of ocean seed dispersal over vast geographic scales.

Urban Informatics Research and Insights for Libraries, Cultural Industries and Innovation Systems

Over less than a decade, we have witnessed a seismic shift in the way knowledge is produced and exchanged. This is opening up new opportunities for civic and community engagement, entrepreneurial behaviour, sustainability initiatives and creative practices. It also has the potential to create fresh challenges in areas of privacy, cyber-security and misuse of data and personal information. The field of urban informatics focuses on the use and impacts of digital media technology in urban environments. Urban informatics is a dynamic and cross-disciplinary area of inquiry that encapsulates social media, ubiquitous computing, mobile applications and location-based services. Its insights suggest the emergence of a new economic force with the potential for driving innovation, wealth and prosperity through technological advances, digital media and online networks that affect patterns of both social and economic development. Urban informatics explores the intersections between people, place and technology, and their implications for creativity, innovation and engagement. This paper examines how the key learnings from this field can be used to position creative and cultural institutions such as galleries, libraries, archives and museums (GLAM) to take advantage of the opportunities presented by these changing social and technological developments. This paper introduces the underlying principles, concepts and research areas of urban informatics, against the backdrop of modern knowledge economies. Both theoretical ideas and empirical examples are covered in this paper. The first part discusses three challenges: a. People, and the challenge of creativity: The paper explores the opportunities and challenges of urban informatics that can lead to the design and development of new tools, methods and applications fostering participation, the democratisation of knowledge, and new creative practices. b. Technology, and the challenge of innovation: The paper examines how urban informatics can be applied to support user-led innovation with a view to promoting entrepreneurial ideas and creative industries. c. Place, and the challenge of engagement: The paper discusses the potential to establish place-based applications of urban informatics, using the example of library spaces designed to deliver community and civic engagement strategies. The discussion of these challenges is illustrated by a review of projects as examples drawn from diverse fields such as urban computing, locative media, community activism, and sustainability initiatives. The second part of the paper introduces an empirically grounded case study that responds to these three challenges: The Edge, the Queensland Government’s Digital Culture Centre which is an initiative of the State Library of Queensland to explore the nexus of technology and culture in an urban environment. The paper not only explores the new role of libraries in the knowledge economy, but also how the application of urban informatics in prototype engagement spaces such as The Edge can provide transferable insights that can inform the design and development of responsive and inclusive new library spaces elsewhere. To set the scene and background, the paper begins by drawing the bigger picture and outlining some key characteristics of the knowledge economy and the role that the creative and cultural industries play in it, grasping new opportunities that can contribute to the prosperity of Australia.

Towards automatic object segmentation with sequential multiple views

Object segmentation is one of the fundamental steps for a number of robotic applications such as manipulation, object detection, and obstacle avoidance. This paper proposes a visual method for incorporating colour and depth information from sequential multiview stereo images to segment objects of interest from complex and cluttered environments. Rather than segmenting objects using information from a single frame in the sequence, we incorporate information from neighbouring views to increase the reliability of the information and improve the overall segmentation result. Specifically, dense depth information of a scene is computed using multiple view stereo. Depths from neighbouring views are reprojected into the reference frame to be segmented compensating for imperfect depth computations for individual frames. The multiple depth layers are then combined with color information from the reference frame to create a Markov random field to model the segmentation problem. Finally, graphcut optimisation is employed to infer pixels belonging to the object to be segmented. The segmentation accuracy is evaluated over images from an outdoor video sequence demonstrating the viability for automatic object segmentation for mobile robots using monocular cameras as a primary sensor.