Kernel analysis on Grassmann manifolds for action recognition

Modelling video sequences by subspaces has recently shown promise for recognising human actions. Subspaces are able to accommodate the effects of various image variations and can capture the dynamic properties of actions. Subspaces form a non-Euclidean and curved Riemannian manifold known as a Grassmann manifold. Inference on manifold spaces usually is achieved by embedding the manifolds in higher dimensional Euclidean spaces. In this paper, we instead propose to embed the Grassmann manifolds into reproducing kernel Hilbert spaces and then tackle the problem of discriminant analysis on such manifolds. To achieve efficient machinery, we propose graph-based local discriminant analysis that utilises within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, respectively. Experiments on KTH, UCF Sports, and Ballet datasets show that the proposed approach obtains marked improvements in discrimination accuracy in comparison to several state-of-the-art methods, such as the kernel version of affine hull image-set distance, tensor canonical correlation analysis, spatial-temporal words and hierarchy of discriminative space-time neighbourhood features.

The Citizen’s Round Table process : canvassing public opinion on energy technologies to mitigate climate change

This study draws on communication accommodation theory, social identity theory and cognitive dissonance theory to drive a ‘Citizen’s Round Table’ process that engages community audiences on energy technologies and strategies that potentially mitigate climate change. The study examines the effectiveness of the process in determining the strategies that engage people in discussion. The process is designed to canvas participants’ perspectives and potential reactions to the array of renewable and non-renewable energy sources, in particular, underground storage of CO2. Ninety-five people (12 groups) participated in the process. Questionnaires were administered three times to identify changes in attitudes over time, and analysis of video, audio-transcripts and observer notes enabled an evaluation of level of engagement and communication among participants. The key findings of this study indicate that the public can be meaningfully engaged in discussion on the politically sensitive issue of CO2 capture and storage (CCS) and other low emission technologies. The round table process was critical to participants’ engagement and led to attitude change towards some methods of energy production. This study identifies a process that can be used successfully to explore community attitudes on politically-sensitive topics and encourages an examination of attitudes and potential attitude change.

Investigation of the airborne submicrometer particles emitted by dredging vessels using a plume capture method

This paper presents a method for investigating ship emissions, the plume capture and analysis system (PCAS), and its application in measuring airborne pollutant emission factors (EFs) and particle size distributions. The current investigation was conducted in situ, aboard two dredgers (Amity: a cutter suction dredger and Brisbane: a hopper suction dredger) but the PCAS is also capable of performing such measurements remotely at a distant point within the plume. EFs were measured relative to the fuel consumption using the fuel combustion derived plume CO2. All plume measurements were corrected by subtracting background concentrations sampled regularly from upwind of the stacks. Each measurement typically took 6 minutes to complete and during one day, 40 to 50 measurements were possible. The relationship between the EFs and plume sample dilution was examined to determine the plume dilution range over which the technique could deliver consistent results when measuring EFs for particle number (PN), NOx, SO2, and PM2.5 within a targeted dilution factor range of 50-1000 suitable for remote sampling. The EFs for NOx, SO2, and PM2.5 were found to be independent of dilution, for dilution factors within that range. The EF measurement for PN was corrected for coagulation losses by applying a time dependant particle loss correction to the particle number concentration data. For the Amity, the EF ranges were PN: 2.2 - 9.6 × 1015 (kg-fuel)-1; NOx: 35-72 g(NO2).(kg-fuel)-1, SO2 0.6 - 1.1 g(SO2).(kg-fuel)-1and PM2.5: 0.7 – 6.1 g(PM2.5).(kg-fuel)-1. For the Brisbane they were PN: 1.0 – 1.5 x 1016 (kg-fuel)-1, NOx: 3.4 – 8.0 g(NO2).(kg-fuel)-1, SO2: 1.3 – 1.7 g(SO2).(kg-fuel)-1 and PM2.5: 1.2 – 5.6 g(PM2.5).(kg-fuel)-1. The results are discussed in terms of the operating conditions of the vessels’ engines. Particle number emission factors as a function of size as well as the count median diameter (CMD), and geometric standard deviation of the size distributions are provided. The size distributions were found to be consistently uni-modal in the range below 500 nm, and this mode was within the accumulation mode range for both vessels. The representative CMDs for the various activities performed by the dredgers ranged from 94-131 nm in the case of the Amity, and 58-80 nm for the Brisbane. A strong inverse relationship between CMD and EF(PN) was observed.

Video-based training combined with flotation tank recovery does not improve three-point shooting in basketball

Video-based training combined with flotation tank recovery may provide an additional stimulus for improving shooting in basketball. A pre-post controlled trial was conducted to assess the effectiveness of a 3 wk intervention combining video-based training and flotation tank recovery on three-point shooting performance in elite female basketball players. Players were assigned to an experimental (n=10) and control group (n=9). A 3 wk intervention consisted of 2 x 30 min float sessions a week which included 10 min of video-based training footage, followed by a 3 wk retention phase. A total of 100 three-point shots were taken from 5 designated positions on the court at each week to assess three-point shooting performance. There was no clear difference in the mean change in the number of successful three-point shots between the groups (-3%; ±18%, mean; ±90% confidence limits). Video-based training combined with flotation recovery had little effect on three-point shooting performance.

The Use of a Nitroxide Probe in DMSO to Capture Radicals in Particulate Pollution

A profluorescent nitroxide was used to evaluate the oxidative potential of pollution derived from a compression ignition engine fuelled with biodiesel. The reaction products responsible for the observed fluorescence increase when a DMSO solution of nitroxide was exposed to biodiesel exhaust were determined by using HPLC/MS. The main fluorescent species was identified as a methanesulfonamide adduct arising from the reaction of the nitroxide with DMSO-derived sulfoxyl radicals.

Heteroscedastic probabilistic linear discriminant analysis for manifold learning in video-based face recognition

To recognize faces in video, face appearances have been widely modeled as piece-wise local linear models which linearly approximate the smooth yet non-linear low dimensional face appearance manifolds. The choice of representations of the local models is crucial. Most of the existing methods learn each local model individually meaning that they only anticipate variations within each class. In this work, we propose to represent local models as Gaussian distributions which are learned simultaneously using the heteroscedastic probabilistic linear discriminant analysis (PLDA). Each gallery video is therefore represented as a collection of such distributions. With the PLDA, not only the within-class variations are estimated during the training, the separability between classes is also maximized leading to an improved discrimination. The heteroscedastic PLDA itself is adapted from the standard PLDA to approximate face appearance manifolds more accurately. Instead of assuming a single global within-class covariance, the heteroscedastic PLDA learns different within-class covariances specific to each local model. In the recognition phase, a probe video is matched against gallery samples through the fusion of point-to-model distances. Experiments on the Honda and MoBo datasets have shown the merit of the proposed method which achieves better performance than the state-of-the-art technique.

User-driven quality of experience modelling for mobile video optimisation

The increasing demand for mobile video has attracted much attention from both industry and researchers. To satisfy users and to facilitate the usage of mobile video, providing optimal quality to the users is necessary. As a result, quality of experience (QoE) becomes an important focus in measuring the overall quality perceived by the end-users, from the aspects of both objective system performance and subjective experience. However, due to the complexity of user experience and diversity of resources (such as videos, networks and mobile devices), it is still challenging to develop QoE models for mobile video that can represent how user-perceived value varies with changing conditions. Previous QoE modelling research has two main limitations: aspects influencing QoE are insufficiently considered; and acceptability as the user value is seldom studied. Focusing on the QoE modelling issues, two aims are defined in this thesis: (i) investigating the key influencing factors of mobile video QoE; and (ii) establishing QoE prediction models based on the relationships between user acceptability and the influencing factors, in order to help provide optimal mobile video quality. To achieve the first goal, a comprehensive user study was conducted. It investigated the main impacts on user acceptance: video encoding parameters such as quantization parameter, spatial resolution, frame rate, and encoding bitrate; video content type; mobile device display resolution; and user profiles including gender, preference for video content, and prior viewing experience. Results from both quantitative and qualitative analysis revealed the significance of these factors, as well as how and why they influenced user acceptance of mobile video quality. Based on the results of the user study, statistical techniques were used to generate a set of QoE models that predict the subjective acceptability of mobile video quality by using a group of the measurable influencing factors, including encoding parameters and bitrate, content type, and mobile device display resolution. Applying the proposed QoE models into a mobile video delivery system, optimal decisions can be made for determining proper video coding parameters and for delivering most suitable quality to users. This would lead to consistent user experience on different mobile video content and efficient resource allocation. The findings in this research enhance the understanding of user experience in the field of mobile video, which will benefit mobile video design and research. This thesis presents a way of modelling QoE by emphasising user acceptability of mobile video quality, which provides a strong connection between technical parameters and user-desired quality. Managing QoE based on acceptability promises the potential for adapting to the resource limitations and achieving an optimal QoE in the provision of mobile video content.

Video-based road commentary training improves hazard perception of young drivers in a dual task

This study used a video-based hazard perception dual task to compare the hazard perception skills of young drivers with middle aged, more experienced drivers and to determine if these skills can be improved with video-based road commentary training. The primary task required the participants to detect and verbally identify immediate hazard on video-based traffic scenarios while concurrently performing a secondary tracking task, simulating the steering of real driving. The results showed that the young drivers perceived fewer immediate hazards (mean = 75.2%, n = 24, 19 females) than the more experienced drivers (mean = 87.5%, n = 8, all females), and had longer hazard perception times, but performed better in the secondary tracking task. After the road commentary training, the mean percentage of hazards detected and identified by the young drivers improved to the level of the experienced drivers and was significantly higher than that of an age and driving experience matched control group. The results will be discussed in the context of psychological theories of hazard perception and in relation to road commentary as an evidence-based training intervention that seems to improve many aspects of unsafe driving behaviour in young drivers.

Total Dik - Transmedia Concept development

Total Dik! is a collaborative project between the Queensland University of Technology (QUT) and Queensland Theatre Company (QTC). Total Dik! explores transmedia storytelling in live performance from concept development to delivery and builds on works, By the Way, Meet Vera Stark, (Forrester2012), Hotel Modern’s Kamp (2005) and God’s Beard (2012) that use visual art, puppetry, music and film. The project’s first iteration enabled an interrogation of the integration of media-rich elements with live performers in a theatrical environment. Performative transmedia storytelling draws on the tenets of convergent media theory developed by Jenkins (2007, 2012), Dena (2010) and Philips (2012). This exploratory work, juxtaposing transmedia storytelling techniques with live performance, draws on Samuel Becket’s challenges to theatre orthodoxy, and touches on Brechtian notions of alienation through ‘sleight-of-hand’ or processual unpacking and deconstruction during performance. Total Dik! blends a convergence of technologies, models, green screen capture, and live dimensions of performance in one narrative allowing the work’s creators to test new combinations of transmedia storytelling techniques on a traditional performance platform.

Personality & video game genre preferences

This research has been conducted to ascertain whether people with certain personality types exhibit preferences for particular game genres. Four hundred and sixty-six participants completed an online survey in which they described their preference for various game genres and provided measures of personality. Personality types were measured using the five-factor model of personality. Significant relationships between personality types and game genres were found. The results are interpreted in the context of the features of particular game genres and possible matches between personality traits and these features.

Personality, motivation and video games

This study explored relationships between personality, video game preference and gaming experiences. Two hundred and thirty-five participants completed an online survey in which they recalled a recent gaming experience, and provided measures of personality and their gaming experience via the Player Experience of Need Satisfaction (PENS) measure. Relationships between game genre, personality and gaming experience were found. Results are interpreted with reference to the validity of the PENS, current models of video gaming motivations and enjoyment, and sub-groups of people that may be more vulnerable to possible negative effects of games.

AR Services Video

Video presented as part of the USECA 2011 workshop at WISE 2011. Real-time sales assistant service is a problematic component of remote delivery of sales support for customers. Solutions involving web pages, telephony and video support prove problematic when seeking to remotely guide customers in their sales processes, especially with transactions revolving around physically complex artefacts. This process involves a number of services that are often complex in nature, ranging from physical compatibility and configuration factors, to availability and credit services. We propose the application of a combination of virtual worlds and augmented reality to create synthetic environments suitable for remote sales of physical artefacts, right in the home of the purchaser. A high level description of the service structure involved is shown, along with a use case involving the sale of electronic goods and services within an example augmented reality application. We expect this work to have application in many sales domains involving physical objects needing to be sold over the Internet.

Charge-controlled switchable CO2 capture on boron nitride nanomaterials

Increasing concerns about the atmospheric CO2 concentration and its impact on the environment are motivating researchers to discover new materials and technologies for efficient CO2 capture and conversion. Here, we report a study of the adsorption of CO2, CH4, and H2 on boron nitride (BN) nanosheets and nanotubes (NTs) with different charge states. The results show that the process of CO2 capture/release can be simply controlled by switching on/off the charges carried by BN nanomaterials. CO2 molecules form weak interactions with uncharged BN nanomaterials and are weakly adsorbed. When extra electrons are introduced to these nanomaterials (i.e., when they are negatively charged), CO2 molecules become tightly bound and strongly adsorbed. Once the electrons are removed, CO2 molecules spontaneously desorb from BN absorbents. In addition, these negatively charged BN nanosorbents show high selectivity for separating CO2 from its mixtures with CH4 and/or H2. Our study demonstrates that BN nanomaterials are excellent absorbents for controllable, highly selective, and reversible capture and release of CO2. In addition, the charge density applied in this study is of the order of 1013 cm–2 of BN nanomaterials and can be easily realized experimentally.

Modelling users' contextual querying behaviour for web image searching

The rapid growth of visual information on Web has led to immense interest in multimedia information retrieval (MIR). While advancement in MIR systems has achieved some success in specific domains, particularly the content-based approaches, general Web users still struggle to find the images they want. Despite the success in content-based object recognition or concept extraction, the major problem in current Web image searching remains in the querying process. Since most online users only express their needs in semantic terms or objects, systems that utilize visual features (e.g., color or texture) to search images create a semantic gap which hinders general users from fully expressing their needs. In addition, query-by-example (QBE) retrieval imposes extra obstacles for exploratory search because users may not always have the representative image at hand or in mind when starting a search (i.e. the page zero problem). As a result, the majority of current online image search engines (e.g., Google, Yahoo, and Flickr) still primarily use textual queries to search. The problem with query-based retrieval systems is that they only capture users’ information need in terms of formal queries;; the implicit and abstract parts of users’ information needs are inevitably overlooked. Hence, users often struggle to formulate queries that best represent their needs, and some compromises have to be made. Studies of Web search logs suggest that multimedia searches are more difficult than textual Web searches, and Web image searching is the most difficult compared to video or audio searches. Hence, online users need to put in more effort when searching multimedia contents, especially for image searches. Most interactions in Web image searching occur during query reformulation. While log analysis provides intriguing views on how the majority of users search, their search needs or motivations are ultimately neglected. User studies on image searching have attempted to understand users’ search contexts in terms of users’ background (e.g., knowledge, profession, motivation for search and task types) and the search outcomes (e.g., use of retrieved images, search performance). However, these studies typically focused on particular domains with a selective group of professional users. General users’ Web image searching contexts and behaviors are little understood although they represent the majority of online image searching activities nowadays. We argue that only by understanding Web image users’ contexts can the current Web search engines further improve their usefulness and provide more efficient searches. In order to understand users’ search contexts, a user study was conducted based on university students’ Web image searching in News, Travel, and commercial Product domains. The three search domains were deliberately chosen to reflect image users’ interests in people, time, event, location, and objects. We investigated participants’ Web image searching behavior, with the focus on query reformulation and search strategies. Participants’ search contexts such as their search background, motivation for search, and search outcomes were gathered by questionnaires. The searching activity was recorded with participants’ think aloud data for analyzing significant search patterns. The relationships between participants’ search contexts and corresponding search strategies were discovered by Grounded Theory approach. Our key findings include the following aspects: - Effects of users' interactive intents on query reformulation patterns and search strategies - Effects of task domain on task specificity and task difficulty, as well as on some specific searching behaviors - Effects of searching experience on result expansion strategies A contextual image searching model was constructed based on these findings. The model helped us understand Web image searching from user perspective, and introduced a context-aware searching paradigm for current retrieval systems. A query recommendation tool was also developed to demonstrate how users’ query reformulation contexts can potentially contribute to more efficient searching.