Experiments in visual localisation around underwater structures

Localisation of an AUV is challenging and a range of inspection applications require relatively accurate positioning information with respect to submerged structures. We have developed a vision based localisation method that uses a 3D model of the structure to be inspected. The system comprises a monocular vision system, a spotlight and a low-cost IMU. Previous methods that attempt to solve the problem in a similar way try and factor out the effects of lighting. Effects, such as shading on curved surfaces or specular reflections, are heavily dependent on the light direction and are difficult to deal with when using existing techniques. The novelty of our method is that we explicitly model the light source. Results are shown of an implementation on a small AUV in clear water at night.

Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping

Probabilistic robotics, most often applied to the problem of simultaneous localisation and mapping (SLAM), requires measures of uncertainly to accompany observations of the environment. This paper describes how uncertainly can be characterised for a vision system that locates coloured landmark in a typical laboratory environment. The paper describes a model of the uncertainly in segmentation, the internal camera model and the mounting of the camera on the robot. It =plains the implementation of the system on a laboratory robot, and provides experimental results that show the coherence of the uncertainly model,

Playpolis : transyouth and urban networking in Seoul

The overarching aim of this study is to create new knowledge about how playful interactions (re)create the city via ubiquitous technologies, with an outlook to apply the knowledge for pragmatic innovations in relevant fields such as urban planning and technology development in the future. The study looks at the case of transyouth, the in-between demographic bridging youth and adulthood in Seoul, one of the most connected, densely populated, and quickly transforming metropolises in the world. To unravel the elusiveness of ‘play’ as a subject and the complexity of urban networks, this study takes a three-tier transdisciplinary approach comprised of an extensive literature review, Shared Visual Ethnography (SVE), and interviews with leading industry representatives who design and develop the playscape for Seoul transyouth. Through these methodological tools, the study responds to the following four research aims: 1. Examine the sociocultural, technological, and architectural context of Seoul 2. Investigate Seoul transyouth’s perception of the self and their technosocial environment 3. Identify the pattern of their playful interaction through which meanings of the self and the city are recreated 4. Develop an analytical framework for enactment of play This thesis argues that the city is a contested space that continuously changes through multiple interactions among its constituents on the seam of control and freedom. At the core of this interactive (re)creation process is play. Play is a phenomenon that is enacted at the centre of three inter-related elements of pressure, possibility, and pleasure, the analytical framework this thesis puts forward as a conceptual apparatus for studying play across disciplines. The thesis concludes by illustrating possible trajectories for pragmatic application of the framework for envisioning and building the creative, sustainable, and seductive city.

Measuring costs of sustainability issues in highway infrastructure : perception of stakeholders in Australia

With increasing pressure to deliver environmentally friendly and socially responsible highway infrastructure projects, stakeholders are also putting significant focus on the early identification of financial viability and outcomes for these projects. Infrastructure development typically requires major capital input, which may cause serious financial constraints for investors. The push for sustainability has added new dimensions to the evaluation of highway projects, particularly on the cost front. Comprehensive analysis of the cost implications of implementing place sustainable measures in highway infrastructure throughout its lifespan is highly desirable and will become an essential part of the highway development process and a primary concern for decision makers. This paper discusses an ongoing research which seeks to identify cost elements and issues related to sustainable measures for highway infrastructure projects. Through life-cycle costing analysis (LCCA), financial implications of pursuing sustainability, which are highly concerned by the construction stakeholders, have been assessed to aid the decision making when contemplating the design, development and operation of highway infrastructure. An extensive literature review and evaluation of project reports from previous Australian highway projects was first conducted to reveal all potential cost elements. This provided the foundation for a questionnaire survey, which helped identify those specific issues and related costs that project stakeholders consider to be most critical in the Australian industry context. Through the survey, three key stakeholders in highway infrastructure development, namely consultants, contractors and government agencies, provided their views on the specific selection and priority ranking of the various categories. Findings of the survey are being integrated into proven LCCA models for further enhancement. A new LCCA model will be developed to assist the stakeholders to evaluate costs and investment decisions and reach optimum balance between financial viability and sustainability deliverables.

Dynamic visual features for audio-visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state-of-the-art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the visual speech recognition application also provide similar improvements for visual speaker recognition. A further study is conducted comparing synchronous HMM (SHMM) based fusion of CAB visual features and traditional perceptual linear predictive (PLP) acoustic features to show that higher complexity inherit in the SHMM approach does not appear to provide any improvement in the final audio-visual speaker verification system over simpler utterance level score fusion.