Wide-baseline keypoint detection and matching with wide-angle images for vision based localisation

This thesis addresses the problem of detecting and describing the same scene points in different wide-angle images taken by the same camera at different viewpoints. This is a core competency of many vision-based localisation tasks including visual odometry and visual place recognition. Wide-angle cameras have a large field of view that can exceed a full hemisphere, and the images they produce contain severe radial distortion. When compared to traditional narrow field of view perspective cameras, more accurate estimates of camera egomotion can be found using the images obtained with wide-angle cameras. The ability to accurately estimate camera egomotion is a fundamental primitive of visual odometry, and this is one of the reasons for the increased popularity in the use of wide-angle cameras for this task. Their large field of view also enables them to capture images of the same regions in a scene taken at very different viewpoints, and this makes them suited for visual place recognition. However, the ability to estimate the camera egomotion and recognise the same scene in two different images is dependent on the ability to reliably detect and describe the same scene points, or ‘keypoints’, in the images. Most algorithms used for this purpose are designed almost exclusively for perspective images. Applying algorithms designed for perspective images directly to wide-angle images is problematic as no account is made for the image distortion. The primary contribution of this thesis is the development of two novel keypoint detectors, and a method of keypoint description, designed for wide-angle images. Both reformulate the Scale- Invariant Feature Transform (SIFT) as an image processing operation on the sphere. As the image captured by any central projection wide-angle camera can be mapped to the sphere, applying these variants to an image on the sphere enables keypoints to be detected in a manner that is invariant to image distortion. Each of the variants is required to find the scale-space representation of an image on the sphere, and they differ in the approaches they used to do this. Extensive experiments using real and synthetically generated wide-angle images are used to validate the two new keypoint detectors and the method of keypoint description. The best of these two new keypoint detectors is applied to vision based localisation tasks including visual odometry and visual place recognition using outdoor wide-angle image sequences. As part of this work, the effect of keypoint coordinate selection on the accuracy of egomotion estimates using the Direct Linear Transform (DLT) is investigated, and a simple weighting scheme is proposed which attempts to account for the uncertainty of keypoint positions during detection. A word reliability metric is also developed for use within a visual ‘bag of words’ approach to place recognition.

Revisiting 'how we learn' in academia : practice-based learning exchanges in three Australian universities

Ideas of 'how we learn' in formal academic settings have changed markedly in recent decades. The primary position that universities once held on shaping what constitutes learning has come into question from a range of experience-led and situated learning models. Drawing on findings from a study conducted across three Australian universities, the article focuses on the multifarious learning experiences indicative of practice-based learning exchanges such as student placements. Building on both experiential and situated learning theories, the authors found that students can experience transformative and emotional elucidations of learning, that can challenge tacit assumptions and transform the ways they understand the world. It was found that all participants (hosts, students, academics) both teach and learn in these educative scenarios and that, contrary to common (mis)perceptions that academics live in 'ivory towers', they play a crucial role in contributing to learning that takes place in the so-called 'real world'.

Analytical and numerical solutions for the time and space-symmetric fractional diffusion equation

We consider a time and space-symmetric fractional diffusion equation (TSS-FDE) under homogeneous Dirichlet conditions and homogeneous Neumann conditions. The TSS-FDE is obtained from the standard diffusion equation by replacing the first-order time derivative by a Caputo fractional derivative, and the second order space derivative by a symmetric fractional derivative. First, a method of separating variables expresses the analytical solution of the TSS-FDE in terms of the Mittag--Leffler function. Second, we propose two numerical methods to approximate the Caputo time fractional derivative: the finite difference method; and the Laplace transform method. The symmetric space fractional derivative is approximated using the matrix transform method. Finally, numerical results demonstrate the effectiveness of the numerical methods and to confirm the theoretical claims.

Analytical and numerical solutions for the time and space-symmetric fractional diffusion equation

We consider a time and space-symmetric fractional diffusion equation (TSS-FDE) under homogeneous Dirichlet conditions and homogeneous Neumann conditions. The TSS-FDE is obtained from the standard diffusion equation by replacing the first-order time derivative by the Caputo fractional derivative and the second order space derivative by the symmetric fractional derivative. Firstly, a method of separating variables is used to express the analytical solution of the tss-fde in terms of the Mittag–Leffler function. Secondly, we propose two numerical methods to approximate the Caputo time fractional derivative, namely, the finite difference method and the Laplace transform method. The symmetric space fractional derivative is approximated using the matrix transform method. Finally, numerical results are presented to demonstrate the effectiveness of the numerical methods and to confirm the theoretical claims.

Implications for the design of a digital stethoscope for anaesthetic preadmission consultations

Background This research addresses the development of a digital stethoscope for use with a telehealth communications network to allow doctors to examine patients remotely (a digital telehealth stethoscope). A telehealth stethoscope would allow remote auscultation of patients who do not live near a major hospital. Travelling from remote areas to major hospitals is expensive for patients and a telehealth stethoscope could result in significant cost savings. Using a stethoscope requires great skill. To design a telehealth stethoscope that meets doctors’ expectations, the use of existing stethoscopes in clinical contexts must be examined. Method Observations were conducted of 30 anaesthetic preadmission consultations. The observations were video- taped. Interaction between doctor, patient and non-human elements in the consultation were “coded” to transform the video into data. The data were analysed to reveal essential aspects of the interactions. Results The analysis has shown that the doctor controls the interaction during auscultation. The conduct of auscultation draws heavily on the doctor’s tacit knowledge, allowing the doctor to treat the acoustic stethoscope as infrastructure – that is, the stethoscope sinks into the background and becomes completely transparent in use. Conclusion Two important, and related, implications for the design of a telehealth stethoscope have arisen from this research. First, as a telehealth stethoscope will be a shared device, doctors will not be able to make use of their existing expertise in using their own stethoscopes. Very simply, a telehealth stethoscope will sound different to a doctor’s own stethoscope. Second, the collaborative interaction required to use a telehealth stethoscope will have to be invented and refined. A telehealth stethoscope will need to be carefully designed to address these issues and result in successful use. This research challenges the concept of a telehealth stethoscope by raising questions about the ease and confidence with which doctors could use such a device.

Reverse immigration

This book (256 pages, written in Korean) is a critical essay that reviews, questions, and criticises Korean and Eastern immigrants’ thinking and behaviour styles in Australia from their cultural perspectives, and discuss and proposes a creative cultural dimension for their better life in a multicultural context. Multiculturalism is not supportive of Eastern cultures because of individualistic collection of cultures, while transculturalism facilitates nurture of their culture in a community-oriented way within multicultural circumstances. Korean and Eastern immigrants, sharing oriental cultural systems and values, should approach to the Australian multicultural context with transculturalism which allows creating new cultural values in collaboration with and by participation into local communities. ------------------------------------------------------------ Many Eastern immigrants live in their own ethnic communities without or less interacting with Australian (communities). The author defines this phenomenon as “reverse immigration”. Reverse immigration refers to re-immigrating to their ethnic community in Australia or to their birth country despite they did not anticipate that this would happen to them before immigration to Australia. The author argues that Easterners’ collectivistic culture often devalues individuality and vice versa. Cultural clash between West and East often forces the immigrants to choose reverse immigration because of their lack of understanding of Western culture and their cultural characteristics such as low individuality, high power distance, and high uncertainty avoidance. For example, a vague boundary between individualist and collectivist in a collectivistic context (within their ethnic group) often leads to maladjustment to local communities and enhancement of cultural conservatism. The author proposes that the cultural clash can be overcome by cross-cultural activities named “transculturalism”. To Eastern immigrants, transculturalism can be achieved by acculturation of their two predominant cultures, the third-person perspective and generalised others. In a multicultural context, the former refers to the ability to share another person's feelings and emotions as if they were your own, and the latter does the ability to manage community and public expectations. When both cultural values are used for quality interactions between East and West, they allow Eastern immigrants to be more creative and critical and Australian to be more socially inclusive and culturally tolerant. With these discussions, the author discusses cultural differences throughout the book with four topics (chapters) and proposes transculturalism as a solution to the reverse immigration. ------------------------------------------------------------ Chapter 1 criticises Koreans’ attitudes and methods towards learning English that is less pragmatic and practical, but more likely to be a scholarly study. The author explains that Koreans’ non-pragmatic towards learning English has been firmly built based on their traditional systems and values that Koreans view English as a discipline and an aim of academic achievements rather than a means of communication. Within their cultural context, English can be perceived as more than a language, but something like vastly superior to their language and culture. Their collectivistic culture regards English as an unreachable and heterogeneous one that may threaten their cultural identity, so that “scholarly studying” is only the way to achieve (not learn) it. This discourages the immigrants to engage and involve in daily dialogues by “using” English as a second language. The author further advises the readers to be aware of Eastern collectivistic culture in communication and interaction that sometimes completely reverses private and public topics in a Western context. This leads them to feel that they have no content to talk to natives. ------------------------------------------------------------ Chapter 2 compares between Korea and Australia in terms of their educational systems and values, and proposes how Eastern overseas students can achieve critical and creative thinking within a Western educational setting. Interestingly, this chapter includes an explanation of why Eastern overseas students easily fail assessments including essay writing, oral presentations and discussions. One of the reasons the author explains is that Eastern students are not familiar to criticise others and think creatively, especially when they recognise that their words and ideas may harm the collectivistic harmony. Western educational systems focuses on enhancement of individuality such as self-confidence, self-esteem, and self-expression, while Eastern educational systems foster group-oriented values such as interpersonal relationship, and strong moral and spiritual values. Yet, the author argues that the collectivistic approach to criticism and creativity is often more critical and creative than Western individuals when they know what they are supposed to do for a group (or a community). Therefore, Eastern students need to think their cultural merits and demerits by using an individual perspective rather than generalised others’ perspective. The latter often discourages individual participation in a community, and the generalised others in a Western culture is weaker than Eastern. Furthermore, Western educational systems do not educate students to transform (loose) their individuality to fit into a group or a community. Rather they cultivate individuality for community prosperity. ------------------------------------------------------------ Chapter 3 introduces various cases of reverse immigration in workplaces that many immigrants return to their country or their ethnic community after many trials for acculturation. Reverse immigration is unexpected and not planned before immigration, so that its emotional embarrassment increases such severe social loneliness. Most Eastern immigrant workers have tried to adjust themselves in this new cultural environment at the early stages of immigration. However, their cultural features of collectivism, high power distance, high uncertainty avoidance, and long-term oriented cultures suppress individual initiative and eliminate the space for experiments in ways of acculturation. The author argues that returning to their ethnic community (physically and psychologically) leads to two significant problems: their distorted parenting and becoming more conservatives. The former leads the first generation of immigrants to pressure their children to pursue extrinsic or materialist values, such as financial success, fame and physical appearance, rather than on intrinsic values, while the latter refers to their isolated conservative characters because of their remoteness from the changes of their own country. The author also warns that their ethnic and religious groups actively strengthens immigrants’ social loneliness and systematically discourages immigrants’ interests and desire to be involving into local communities. The ethnic communities and leaders have not been interacting with Australian local communities and, as a result, are eager to conserve outdated cultural systems values. Even they have a tendency to weed out those people who wish to settle down within Australian local communities. They believe that those people can threaten their community’s survival and continuity. ------------------------------------------------------------ Chapter 4 titled multiculturalism argues that Korean and Eastern immigrants should more precisely understand Australia as a multicultural society in a way of collaboratively creating new cultural values. The author introduces multiculturalism with its definitions and history in Australia and argues the limitations of multiculturalism from an Easterner’s perspective. With well known tragedies of the second generations of U.S. immigrants, Cho Seung-Hui, a university student, massacred 32 people on the Virginia Tech before committing suicide and Hidal Hassan, an Army psychiatrist, killed 13 people at Fort Hood and the responses of ethnic community, the author explains that their mental illness may be derived from their parents’ (or ethnic group) culturally isolated attitude and socially static viewpoint of U.S. (Western system and values). The author insists that multiculturalism may restrict Eastern immigrants’ engagement and involvement in local communities. Multiculturalism has been systematically and historically developed based on Western systems and cultural values. In other words, multiculturalism requires high self-confidence and self-esteem that Eastern immigrants less prioritise them. It has been generally known that Easterners put more weight on human relationship than Westerners, but the author claims that this is not true. Within an individualistic culture, Westerners are more interested in building person-to-person connections and relationships. While Easterners are more interested in how individuals can achieve a sense of belonging within a group and a community. Therefore, multiculturalism is an ideology which forces Eastern immigrants to discard their strong desire to be part of a group and does not give a sense of belonging. In a consequence, the author advises that Eastern immigrants should aim towards “transculturalism” which allows them to actively participate in and contribute to their multicultural community. Transculturalism does not ask Easterners to discard their cultural values, but enables them to be a collectivistic individualist (a community leader) who is capable of developing new cultural values in a more creative and productive way. Furthermore, transculturalism encourages Western Australians in a multicultural context to collaborate with ethnic minorities to build a better community.

Transforming people, place, and technology : towards re-creative city

This session is titled TRANSFORM! Opportunities and Challenges of Digital Content for Creative Economy. Some of the key concepts for this session include: 1. City / Economy 2. Creativity 3. Digital content 4. Transformation All of us would agree that these terms describe pertinent characteristics of contemporary world, the epithet of which is the ‘network era.’ I was thinking about what I would like to discuss here and what you, leading experts in divergent fields, would be interested to hear about. As the keynote for this session and as one of the first speakers for the entire conference, I see my role as an initiator for imagination, the wilder the better, posing questions rather than answers. Also given the session title Transform!, I wish to change this slightly to Transforming People, Place, and Technology: Towards Re-­creative City in an attempt to take us away a little from the usual image depicted by the given topic. Instead, I intend to sketch a more holistic picture by reflecting on and extrapolating the four key concepts from the urban informatics point of view. To do so, I use ‘city’ as the primary guiding concept for my talk rather than probably more expected ‘digital media’ or ‘creative economy.’ You may wonder what I mean by re-­creative city. I will explain this in time by looking at the key concepts from these four respective angles: 1. Living city 2. Creative city 3. Re-­‐creative city 4. Opportunities and Challenges to arrive at a speculative yet probable image of the city that we may aspire to transform our current cities into. First let us start by considering the ‘living city.’

Differential roles of the pRb and Arf/p53 pathways in murine naevus and melanoma genesis

We report on a systematic analysis of genotype-specific melanocyte (MC) UVR responses in transgenic mouse melanoma models along with tumour penetrance and comparative histopathology. pRb or p53 pathway mutations cooperated with NrasQ61K to transform MCs. We previously reported that MCs migrate from the follicular outer root sheath into the epidermis after neonatal UVR. Here, we found that Arf or p53 loss markedly diminished this response. Despite this, mice carrying these mutations developed melanoma with very early age of onset after neonatal UVR. Cdk4R24C did not affect the MC migration. Instead, independent of UVR exposure, interfollicular dermal MCs were more prevalent in Cdk4R24C mice. Subsequently, in adulthood, these mutants developed dermal MC proliferations reminiscent of superficial congenital naevi. Two types of melanoma were observed in this model. The location and growth pattern of the first was consistent with derivation from the naevi, while the second appeared to be of deep dermal origin. In animals carrying the Arf or p53 defects, no naevi were detected, with all tumours ostensibly skipping the benign precursor stage in progression.

Building an Australian user community for VIVO

The Australian National Data Service (ANDS) was established in 2008 and aims to: influence national policy in the area of data management in the Australian research community; inform best practice for the curation of data, and, transform the disparate collections of research data around Australia into a cohesive collection of research resources One high profile ANDS activity is to establish the population of Research Data Australia, a set of web pages describing data collections produced by or relevant to Australian researchers. It is designed to promote visibility of research data collections in search engines, in order to encourage their re-use. As part of activities associated with the Australian National Data Service, an increasing number of Australian Universities are choosing to implement VIVO, not as a platform to profile information about researchers, but as a 'metadata store' platform to profile information about institutional research data sets, both locally and as part of a national data commons. To date, the University of Melbourne, Griffith University, the Queensland University of Technology, and the University of Western Australia have all chosen to implement VIVO, with interest from other Universities growing.

Incorporating authentic assessment into different university learning scenarios

There is a current requirement for universities to prepare graduates who are skilled in practical as well as theoretical knowledge of the workplace. It is argued in this paper that assessment, as integral to the teaching/learning process, should also relate to the real world context of the workplace, in that students are able to transform, use and apply the knowledge that they learn into these contexts. While assessment authentic for students in a university setting is often a difficult task for lecturers. This paper discusses three different learning contexts that involved different assessment experiences linked in some way to real world learning and application of the theory. The results of the trial indicated that as contexts became close to a real world experience, the sustainability of the assessment became more problematic. While acknowledging the difficulty of these practices, it is suggested that there is a need for a continuous cycle of evaluation amid some creative and innovative approaches to assessment practice.

The social work & human services workforce : report from a national study of education, training and workforce needs

This report analyses the national curriculum and workforce needs of the social work and human services workforce. Australia’s community and health services are among the fastest growing sectors of employment in the nation but the sustainability of an appropriately qualified workforce is threatened. Yet there is little integration of education and workforce planning for the community services sector. This contrasts markedly with the health services sector, where key stakeholders are collaboratively addressing workforce challenges. Our research confirmed rapid growth in the social work and human services workforce and it also identified: • an undersupply of professionally qualified social work and human service practitioners to meet workforce demand; • the rapid ageing of the workforce with many workers approaching retirement; • limited career and salary structures creating disincentives to retention; • a highly diverse qualification base across the workforce. This diversity is inconsistent with the specialist knowledge and skills required of practitioners in many domains of community service provision. Our study revealed a lack of co-ordination across VET and higher education to meet the educational needs of the social work and human services workforce. Our analysis identified: • strong representation of equity groups in social work and related human service programs, although further participation of these groups is still needed; • the absence of clear articulation pathways between VET and higher education programs due the absence of co-ordination and planning between these sectors; • substantial variation in the content of the diverse range of social work and human service programs, with accredited programs conforming to national standards and some others in social and behavioural sciences lacking any external validation; • financial obstacles and disincentives to social work and human service practitioners in achieving postgraduate level qualifications. We recommend that: • DEEWR identify accredited social work and human services courses as a national education priority (similar to education and nursing). This will help ensure the supply of professional workers to this sector; • VET and higher education providers are encouraged to collaboratively develop clear and accessible educational pathways across the educational sectors; • DEEWR undertake a national workforce analysis and planning processes in collaboration with CSDMAC, and all social and community services stakeholders, to ensure workforce sustainability; and • COAG develop a national regulation framework for the social and community services workforce. This would provide sound accountability systems, and rigorous practice and educational standards necessary for quality service provision. It will also ensure much needed public confidence in this workforce.

Developing a knowledge-based urban development analysis framework : the case of multimedia super corridor, Malaysia

Purpose: In the global knowledge economy, investment in knowledge-intensive industries and information and communication technology (ICT) infrastructures are seen as significant factors in improving the overall socio-economic fabric of cities. Consequently knowledge-based urban development (KBUD) has become a new paradigm in urban planning and development, for increasing the welfare and competitiveness of cities and regions. The paper discusses the critical connections between KBUD strategies and knowledge-intensive industries and ICT infrastructures. In particular, it investigates the application of the knowledge-based urban development concept by discussing one of South East Asia’s large scale manifestations of KBUD; Malaysia’s Multimedia Super Corridor. ----- ----- Design/methodology/approach: The paper provides a review of the KBUD concept and develops a knowledge-based urban development assessment framework to provide a clearer understanding of development and evolution of KBUD manifestations. Subsequently the paper investigates the implementation of the KBUD concept within the Malaysian context, and particularly the Multimedia Super Corridor (MSC). ----- ----- Originality/value: The paper, with its KBUD assessment framework, scrutinises Malaysia’s experince; providing an overview of the MSC project and discussion of the case findings. The development and evolution of the MSC is viewed with regard to KBUD policy implementation, infrastructural implications, and the agencies involved in the development and management of the MSC. ----- ----- Practical implications: The emergence of the knowledge economy, together with the issues of globalisation and rapid urbanisation, have created an urgent need for urban planners to explore new ways of strategising planning and development that encompasses the needs and requirements of the knowledge economy and society. In light of the literature and MSC case findings, the paper provides generic recommendations, on the orchestration of knowledge-based urban development, for other cities and regions seeking to transform to the knowledge economy.

Modal parameter estimation in the presence of non-linearities

This paper investigates the use of time-frequency techniques to assist in the estimation of power system modes which are resolvable by a Digital Fourier Transform (DFT). The limitations of linear estimation techniques in the presence of large disturbances which excite system non-linearities, particularly the swing equation non-linearity are shown. Where a nonlinearity manifests itself as time varying modal frequencies the Wigner-Ville Distribution (WVD) is used to describe the variation in modal frequencies and construct a window over which standard linear estimation techniques can be used. The error obtained even in the presence of multiple resolvable modes is better than 2%.

Linear stern waves in finite depth channels

This paper formulates an analytically tractable problem for the wake generated by a long flat bottom ship by considering the steady free surface flow of an inviscid, incompressible fluid emerging from beneath a semi-infinite rigid plate. The flow is considered to be irrotational and two-dimensional so that classical potential flow methods can be exploited. In addition, it is assumed that the draft of the plate is small compared to the depth of the channel. The linearised problem is solved exactly using a Fourier transform and the Wiener-Hopf technique, and it is shown that there is a family of subcritical solutions characterised by a train of sinusoidal waves on the downstream free surface. The amplitude of these waves decreases as the Froude number increases. Supercritical solutions are also obtained, but, in general, these have infinite vertical velocities at the trailing edge of the plate. Consideration of further terms in the expansions suggests a way of canceling the singularity for certain values of the Froude number.

A Taxonomy of image matching techniques for stereo vision

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Applications of stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics, industrial automation and stereomicroscopy. A key issue in stereo vision is that of image matching, or identifying corresponding points in a stereo pair. The difference in the positions of corresponding points in image coordinates is termed the parallax or disparity. When the orientation of the two cameras is known, corresponding points may be projected back to find the location of the original object point in world coordinates. Matching techniques are typically categorised according to the nature of the matching primitives they use and the matching strategy they employ. This report provides a detailed taxonomy of image matching techniques, including area based, transform based, feature based, phase based, hybrid, relaxation based, dynamic programming and object space methods. A number of area based matching metrics as well as the rank and census transforms were implemented, in order to investigate their suitability for a real-time stereo sensor for mining automation applications. The requirements of this sensor were speed, robustness, and the ability to produce a dense depth map. The Sum of Absolute Differences matching metric was the least computationally expensive; however, this metric was the most sensitive to radiometric distortion. Metrics such as the Zero Mean Sum of Absolute Differences and Normalised Cross Correlation were the most robust to this type of distortion but introduced additional computational complexity. The rank and census transforms were found to be robust to radiometric distortion, in addition to having low computational complexity. They are therefore prime candidates for a matching algorithm for a stereo sensor for real-time mining applications. A number of issues came to light during this investigation which may merit further work. These include devising a means to evaluate and compare disparity results of different matching algorithms, and finding a method of assigning a level of confidence to a match. Another issue of interest is the possibility of statistically combining the results of different matching algorithms, in order to improve robustness.