Design and evaluation of decision and control strategies for autonomous vision-based see and avoid systems

This paper details the design and performance assessment of a unique collision avoidance decision and control strategy for autonomous vision-based See and Avoid systems. The general approach revolves around re-positioning a collision object in the image using image-based visual servoing, without estimating range or time to collision. The decision strategy thus involves determining where to move the collision object, to induce a safe avoidance manuever, and when to cease the avoidance behaviour. These tasks are accomplished by exploiting human navigation models, spiral motion properties, expected image feature uncertainty and the rules of the air. The result is a simple threshold based system that can be tuned and statistically evaluated by extending performance assessment techniques derived for alerting systems. Our results demonstrate how autonomous vision-only See and Avoid systems may be designed under realistic problem constraints, and then evaluated in a manner consistent to aviation expectations.

Complete-linkage clustering for voice activity detection in audio and visual speech

We propose a novel technique for conducting robust voice activity detection (VAD) in high-noise recordings. We use Gaussian mixture modeling (GMM) to train two generic models; speech and non-speech. We then score smaller segments of a given (unseen) recording against each of these GMMs to obtain two respective likelihood scores for each segment. These scores are used to compute a dissimilarity measure between pairs of segments and to carry out complete-linkage clustering of the segments into speech and non-speech clusters. We compare the accuracy of our method against state-of-the-art and standardised VAD techniques to demonstrate an absolute improvement of 15% in half-total error rate (HTER) over the best performing baseline system and across the QUT-NOISE-TIMIT database. We then apply our approach to the Audio-Visual Database of American English (AVDBAE) to demonstrate the performance of our algorithm in using visual, audio-visual or a proposed fusion of these features.

Incorporating visual information for spoken term detection

Spoken term detection (STD) is the task of looking up a spoken term in a large volume of speech segments. In order to provide fast search, speech segments are first indexed into an intermediate representation using speech recognition engines which provide multiple hypotheses for each speech segment. Approximate matching techniques are usually applied at the search stage to compensate the poor performance of automatic speech recognition engines during indexing. Recently, using visual information in addition to audio information has been shown to improve phone recognition performance, particularly in noisy environments. In this paper, we will make use of visual information in the form of lip movements of the speaker in indexing stage and will investigate its effect on STD performance. Particularly, we will investigate if gains in phone recognition accuracy will carry through the approximate matching stage to provide similar gains in the final audio-visual STD system over a traditional audio only approach. We will also investigate the effect of using visual information on STD performance in different noise environments.

Cross database training of audio-visual hidden Markov models for phone recognition

Speech recognition can be improved by using visual information in the form of lip movements of the speaker in addition to audio information. To date, state-of-the-art techniques for audio-visual speech recognition continue to use audio and visual data of the same database for training their models. In this paper, we present a new approach to make use of one modality of an external dataset in addition to a given audio-visual dataset. By so doing, it is possible to create more powerful models from other extensive audio-only databases and adapt them on our comparatively smaller multi-stream databases. Results show that the presented approach outperforms the widely adopted synchronous hidden Markov models (HMM) trained jointly on audio and visual data of a given audio-visual database for phone recognition by 29% relative. It also outperforms the external audio models trained on extensive external audio datasets and also internal audio models by 5.5% and 46% relative respectively. We also show that the proposed approach is beneficial in noisy environments where the audio source is affected by the environmental noise.

Cultural factors: Understanding culture to design organisation structures and systems to optimise safety

Safety culture is a term with numerous definitions in the literature. Many authors advocate a prescriptive approach to safety culture in which if an organisation has certain levels of externally prescribed systems and structures in place it has a “good safety culture”. Conversely, other researchers suggest an anthropological approach of exploring deep meanings and understandings present within an organisation’s workforce. In a recent published review, the authors presented an alternative view to safety culture, in which the anthropological aspects of safety culture interact with the structures and systems in place within an organisation to result in behavioural patterns. This can be viewed as a human factors approach to safety culture in which, through understanding the specific interactions between the culture of a workforce and external organisational elements, organisational structures and systems can be optimised in order to shape worker behaviour and improve safety. This paper presents findings from a recent investigation of safety culture in the Australian heavy vehicle (transport) industry. Selected results are discussed to explore how understanding culture can provide direction to the optimisation of organisational structures and systems to match worker culture and thus improve safety. Specifically the value placed on personal experience and stories, as well as on both time and money are discussed, and interventions that are suited to these aspects of the culture are discussed. These findings demonstrate the importance of shifting beyond mere prescriptive and interpretive approaches to safety culture and instead to focus on the interaction between cultural and contextual elements to optimise organisational structures and systems.

Introducing Design History Lectures 2015

This compilation of slides from eleven lectures spans the core content themes about design history including: what, when, how, where, who, why, heritage and future history. Examples are drawn for these design disciplines: architecture, fashion, industrial design, interactive & visual design, interior design, and landscape architecture.

Pars pro toto: Experimental exhibition design and curatorial paradigms

'Pars pro toto: Experimental Exhibition Design and Curatorial Paradigms' is situated within the ongoing debate over the conflation of art and curating, and the subsequent tension between artistic autonomy and curatorial intervention. This practice-led research project acclimates these polarities using a collaborative and discursive curatorial methodology in the creation of two exhibitions. Both exhibitions, one digital and one primarily physical, investigated how the temporary exhibition can operate as a site for provocation, how the suggested methodology facilitates the relationship between artist and curator within this paradigm, and outlines factors that assist in expanding the definition of the contemporary curatorial role.

Overcoming language barriers in healthcare: A protocol for investigating safe and effective communication when patients or clinicians use a second language

Background Miscommunication in the healthcare sector can be life-threatening. The rising number of migrant patients and foreign-trained staff means that communication errors between a healthcare practitioner and patient when one or both are speaking a second language are increasingly likely. However, there is limited research that addresses this issue systematically. This protocol outlines a hospital-based study examining interactions between healthcare practitioners and their patients who either share or do not share a first language. Of particular interest are the nature and efficacy of communication in language-discordant conversations, and the degree to which risk is communicated. Our aim is to understand language barriers and miscommunication that may occur in healthcare settings between patients and healthcare practitioners, especially where at least one of the speakers is using a second (weaker) language. Methods/Design Eighty individual interactions between patients and practitioners who speak either English or Chinese (Mandarin or Cantonese) as their first language will be video recorded in a range of in- and out-patient departments at three hospitals in the Metro South area of Brisbane, Australia. All participants will complete a language background questionnaire. Patients will also complete a short survey rating the effectiveness of the interaction. Recordings will be transcribed and submitted to both quantitative and qualitative analyses to determine elements of the language used that might be particularly problematic and the extent to which language concordance and discordance impacts on the quality of the patient-practitioner consultation. Discussion Understanding the role that language plays in creating barriers to healthcare is critical for healthcare systems that are experiencing an increasing range of culturally and linguistically diverse populations both amongst patients and practitioners. The data resulting from this study will inform policy and practical solutions for communication training, provide an agenda for future research, and extend theory in health communication.

Visual openness in urban environments: Measuring visual openness and visibility to natural landscapes in a changing urban landscape in Gold Coast, Australia

The visual characteristics of urban environments have been changing dramatically with the growth of cities around the world. Protection and enhancement of landscape character in urban environments have been one of the challenges for policy makers in addressing sustainable urban growth. Visual openness and enclosure in urban environments are important attributes in perception of visual space which affect the human interaction with physical space and which can be often modified by new developments. Measuring visual openness in urban areas results in more accurate, reliable, and systematic approach to manage and control visual qualities in growing cities. Recent advances in techniques in geographic information systems (GIS) and survey systems make it feasible to measure and quantify this attribute with a high degree of realism and precision. Previous studies in this field do not take full advantage of these improvements. This paper proposes a method to measure the visual openness and enclosure in a changing urban landscape in Australia, on the Gold Coast, by using the improved functionality in GIS. Using this method, visual openness is calculated and described for all publicly accessible areas in the selected study area. A final map is produced which shows the areas with highest visual openness and visibility to natural landscape resources. The output of this research can be used by planners and decision-makers in managing and controlling views in complex urban landscapes. Also, depending on the availability of GIS data, this method can be applied to any region including non-urban landscapes to help planners and policy-makers manage views and visual qualities.

Digital design interventions for creating new presentations of self in public urban places

During everyday urban life, people spend time in public urban places waiting for specific events to occur. During these times, people sometimes tend to engage with their information and communication technology (ICT) devices in a way that shuts off interactions with collocated people. These devices could also be used to better connect with the urban space and collocated people within. This chapter presents and discusses the impact of three design interventions on the urban user experience enabling collocated people to share lightweight, non-privacy-sensitive data in the urban space. We investigate and discuss the impact on the urban experience under the notions of people, place, and technology with an emphasis on how the sharing of non-privacy-sensitive data can positively transform anonymous public urban places in various ways through anonymous digital augmentations.

LED lighting design strategies to enhance window appearance and increase energy savings in daylit office spaces

Vertical windows are the most common and simplest method to introduce daylight to interior spaces of office buildings, while also providing a view and connection to the outside. However, high contrast ratios between windows and surrounding surfaces can cause visual discomfort for occupants and can negatively influence their health and productivity. Consequently, building occupants may try to adapt their working environment through closing blinds and turning on lights in order to improve indoor visual comfort. Such interventions defeat the purpose of daylight harvesting systems and can increase the forecast electric lighting consumption in buildings that include such systems. A simple strategy to prevent these problematic consequences is to reduce the luminance contrasts presented by the window wall by increasing the luminance of areas surrounding the window through the sparing use of energy-efficient supplementary lighting, such light emitting diodes (LEDs). This paper presents the result of a pilot study in typical office in Brisbane, Australia that tests the effectiveness of a supplementary LED lighting system. The study shows an improvement in the appraisal of the visual environment is achieved using the supplementary system, along with up to 88% reductions in luminance contrast at the window wall. Also observed is a 36% reduction in the likelihood of user interventions that would increase energy usage. These results are used as the basis of an annual energy simulation of the test office and indicate that supplementary systems could be used to save energy beyond what is typically realised in side lit office spaces.

The root locus method: application to linear stability analysis and design of cooperative car-following models

A global framework for linear stability analyses of traffic models, based on the dispersion relation root locus method, is presented and is applied taking the example of a broad class of car-following (CF) models. This approach is able to analyse all aspects of the dynamics: long waves and short wave behaviours, phase velocities and stability features. The methodology is applied to investigate the potential benefits of connected vehicles, i.e. V2V communication enabling a vehicle to send and receive information to and from surrounding vehicles. We choose to focus on the design of the coefficients of cooperation which weights the information from downstream vehicles. The coefficients tuning is performed and different ways of implementing an efficient cooperative strategy are discussed. Hence, this paper brings design methods in order to obtain robust stability of traffic models, with application on cooperative CF models

A CCG virtual system for big data application communication costs analysis

Network topology and routing are two important factors in determining the communication costs of big data applications at large scale. As for a given Cluster, Cloud, or Grid system, the network topology is fixed and static or dynamic routing protocols are preinstalled to direct the network traffic. Users cannot change them once the system is deployed. Hence, it is hard for application developers to identify the optimal network topology and routing algorithm for their applications with distinct communication patterns. In this study, we design a CCG virtual system (CCGVS), which first uses container-based virtualization to allow users to create a farm of lightweight virtual machines on a single host. Then, it uses software-defined networking (SDN) technique to control the network traffic among these virtual machines. Users can change the network topology and control the network traffic programmingly, thereby enabling application developers to evaluate their applications on the same system with different network topologies and routing algorithms. The preliminary experimental results through both synthetic big data programs and NPB benchmarks have shown that CCGVS can represent application performance variations caused by network topology and routing algorithm.

Integrating LED lighting design strategies with side daylighting systems to improve interior lighting design of office buildings

A high contrast ratio between windows and surrounding walls may lead to office workers visual discomfort that could negatively affect their satisfaction and productivity. Consequently, occupants may try to adapt their working environment by closing blinds and/ or turning on the lights to enhance indoor visual comfort, which can reduce predicted energy savings. The hypothesis of this study is that reducing luminance contrast ratio on the window wall will improve window appearance which potentially will reduce visual discomfort and decrease workers interventions. Thus, this PhD research proposes a simple strategy to diminish the luminance contrast on the window wall by increasing the luminance of the areas surrounding the windows using supplementary light emitting diode (LED) systems. To test the hypothesis, this investigation will involve three experiments in different office layouts with various window types and orientations in Brisbane, Australia. It will assess user preferences for different luminance patterns in windowed offices featuring flexible, lowpower LED lighting installations that allows multiple lighting design options on the window wall. Detailed luminance and illuminance measures will be used to match quantitative lighting design assessment to user preferences.

“I understand. I am a participant”: Navigating the ‘fuzzy’ boundaries of visual methods in qualitative longitudinal research

In this chapter we discuss how utilising the participatory visual methodology, photovoice, in an aged care context with its unique communal setting raised several ‘fuzzy boundary’ ethical dilemmas. To illustrate these challenges, we draw on immersive field notes from an ongoing qualitative longitudinal research (QLR) exploring the lived experience of aged care from the perspective of older residents, and focus on interactions with one participant, 81 year old Cassie. We explore how the camera, which is integral to the photovoice method, altered the researcher/participant ethical dynamics by becoming a continual ‘connector’ to the researcher. The camera took on a distinct agency, acting as a non-threatening ‘portal’ that lengthened contact, provided informal opportunities to alter the relationship dynamics and enabled unplanned participant revelation.