Towards robust night and day place recognition using visible and thermal imaging

The chief challenge facing persistent robotic navigation using vision sensors is the recognition of previously visited locations under different lighting and illumination conditions. The majority of successful approaches to outdoor robot navigation use active sensors such as LIDAR, but the associated weight and power draw of these systems makes them unsuitable for widespread deployment on mobile robots. In this paper we investigate methods to combine representations for visible and long-wave infrared (LWIR) thermal images with time information to combat the time-of-day-based limitations of each sensing modality. We calculate appearance-based match likelihoods using the state-of-the-art FAB-MAP [1] algorithm to analyse loop closure detection reliability across different times of day. We present preliminary results on a dataset of 10 successive traverses of a combined urban-parkland environment, recorded in 2-hour intervals from before dawn to after dusk. Improved location recognition throughout an entire day is demonstrated using the combined system compared with methods which use visible or thermal sensing alone.

The competing-complementarity engagement of news media with online social media

The rapid growth of online social media networks like Facebook and Twitter is strongly influencing news media to engage with such networks for generating newsworthy content, accessing mass audiences for news consumption and using the platforms for news distribution. While both media’s complement each other as sources of news and information, they also compete against each other as news repositories and are observed vying for the same audiences. We call this phenomenon the competing-complementarity (C-C) engagement. To investigate the C-C relationship we use Fidler’s “mediamorphosis” concept to explain the metamorphosis of news media in the online domain. We make two contributions to Fidler’s concept by offering an additional principle “mass user migration” to address the characteristics of metamorphosis and an additional driver “transcended social engagement” to show the force that propels it. Besides, we also propose four accelerators that influence metamorphosis. Theoretical analysis of news media’s metamorphosis indicates its affinity to online social media. We apply niche and gratification theories to explain complementarity, and displacement effects on media consumption habits to trace competition between both media’s.

The provision of online counselling for young people

A substantial group of young people experience mental health problems which impact on their educational development and subsequent wellbeing. Of those who do suffer from mental health issues, a minority of these seek appropriate professional assistance. This paucity of help seeking behaviours among young people is a challenge for counsellors. Whereas adults who suffer mental health issues have increasingly turned to the internet for assistance, it is interesting that when young people whose social lives are increasingly dependent on the communication technologies, are not catered for as much as adults by online counselling. One small online counselling pilot program conducted at a Queensland secondary school for three years from 2005-2007 (Glasheen & Campbell, 2009) offered anonymous live-time counselling from the school counsellor (via a secure chat room) to students through the school’s website. Findings indicated that boys were more likely to use the service than girls. All participants transitioned to face-to-face counselling, and all reported it was beneficial. This pilot study attested to the potential of an online counselling. However, school counsellors as a professional group have been hesitant to utilise online counselling as part of their service delivery to young people in schools. This chapter concludes by identifying reasons for this reluctance and the possible initiatives to increase online support for young people in schools.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

Promoting Staywild: An examination of promotional strategies for a niche online

This paper will provide an overview of a joint research initiative by the Queensland University of Technology in conjunction with the Australian Smart Services Cooperative Research Centre into the development and analysis of online communities (OLCs). This project aimed to create an exciting and innovative web space (Staywild.com.au) around the concept of adventure travel. This paper considers the literature on promoting and building online communities. It also discusses methods for promotion and encouraging participation. These methods emerged from the literature and the results of a Staywild user survey. In our research for this paper we found little work that focused on promoting and building OLCs for non-profit organisations. This paper thus contributes to the field in its work towards developing a standardised method of marketing and promotion that can be applied to niche non-profit communities.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

Buy, boycott or blog : exploring online consumer power to share, discuss and distribute controversial advertising messages

The availability of new media as a universal communication tool has an impact on the power of the general public to comment on a variety of issues. This paper examines this increase in consumer power with respect to bloggers. The research context is controversial advertising, and specifically Tourism Australia’s “Where the bloody hell are you?” campaign. By utilising Denegri-Knott’s (2006) four on-line power strategies, a content analysis of weblogs reveals that consumers are distributing information, opinion and even banned advertising material, thereby forming power hubs of like-minded people, with the potential to become online pressure groups. The consequences and implications of this augmented power on regulators, advertisers and bloggers are explored. The findings contribute to the understanding of blogs as a new communication platform and bloggers as a new demographic of activists in the process of advertising.

The development of teacher assessment identity through participation in online moderation

Teachers’ professional conversations regarding the qualities evidenced in student work provide opportunities to develop a shared understanding of achievement standards. This research investigates social moderation conducted in a synchronous online mode as a specific form of professional conversation. The discussion considers the different factors that influenced these conversations which included the technologic medium of the meeting. The focus of the discussion is how participation in online moderation can support teachers to develop an assessment identity as one who works within a standards-based assessment system. Qualitative data were gathered from middle school teachers from different year levels, in different curriculum areas, in diverse geographic locations, and in a range of sociocultural contexts within Queensland, Australia. Analysis of the data through a sociocultural lens of becoming suggests that participation in online moderation, while challenging for teachers, can also provide opportunities to construct and to negotiate an identity as an assessor of student work.

Online multiple profile manager for eHealth information sharing

Online social networks connect millions of people around the globe. These electronic bonds make individuals comfortable with their behaviours. Such positive signs of sharing information is useful phenomena requires consideration to establish a socio-scientific effect. Recently, many web users have more than one social networking account. This means a user may hold multiple profiles which are stored in different Social Network Sites (SNNs). Maintaining these multiple online social network profiles is cumbersome and time-consuming [1]. In this paper we will propose a framework for the management of a user's multiple profiles. A demonstrator, called Multiple Profile Manager (MPM), will be showcased to illustrate how effective the framework will be.

Quality based frame selection for video face recognition

Quality based frame selection is a crucial task in video face recognition, to both improve the recognition rate and to reduce the computational cost. In this paper we present a framework that uses a variety of cues (face symmetry, sharpness, contrast, closeness of mouth, brightness and openness of the eye) to select the highest quality facial images available in a video sequence for recognition. Normalized feature scores are fused using a neural network and frames with high quality scores are used in a Local Gabor Binary Pattern Histogram Sequence based face recognition system. Experiments on the Honda/UCSD database shows that the proposed method selects the best quality face images in the video sequence, resulting in improved recognition performance.

Tell me what you see : Pre-service teachers' recognition of exemplary digital pedagogy

How do you identify "good" teaching practice in the complexity of a real classroom? How do you know that beginning teachers can recognise effective digital pedagogy when they see it? How can teacher educators see through their students’ eyes? The study in this paper has arisen from our interest in what pre-service teachers “see” when observing effective classroom practice and how this might reveal their own technological, pedagogical and content knowledge. We asked 104 pre-service teachers from Early Years, Primary and Secondary cohorts to watch and comment upon selected exemplary videos of teachers using ICT (information and communication technologies) in Science. The pre-service teachers recorded their observations using a simple PMI (plus, minus, interesting) matrix which were then coded using the SOLO Taxonomy to look for evidence of their familiarity with and judgements of digital pedagogies. From this, we determined that the majority of preservice teachers we surveyed were using a descriptive rather than a reflective strategy, that is, not extending beyond what was demonstrated in the teaching exemplar or differentiating between action and purpose. We also determined that this method warrants wider trialling as a means of evaluating students’ understandings of the complexity of the digital classroom.