Human identification from video using advanced gait recognition techniques

The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.

Towards pose-robust face recognition on video

This thesis investigates face recognition in video under the presence of large pose variations. It proposes a solution that performs simultaneous detection of facial landmarks and head poses across large pose variations, employs discriminative modelling of feature distributions of faces with varying poses, and applies fusion of multiple classifiers to pose-mismatch recognition. Experiments on several benchmark datasets have demonstrated that improved performance is achieved using the proposed solution.

An efficient and robust system for multi-person event detection in real world indoor surveillance scenes

Due to the popularity of security cameras in public places, it is of interest to design an intelligent system that can efficiently detect events automatically. This paper proposes a novel algorithm for multi-person event detection. To ensure greater than real-time performance, features are extracted directly from compressed MPEG video. A novel histogram-based feature descriptor that captures the angles between extracted particle trajectories is proposed, which allows us to capture motion patterns of multi-person events in the video. To alleviate the need for fine-grained annotation, we propose the use of Labelled Latent Dirichlet Allocation, a “weakly supervised” method that allows the use of coarse temporal annotations which are much simpler to obtain. This novel system is able to run at approximately ten times real-time, while preserving state-of-theart detection performance for multi-person events on a 100-hour real-world surveillance dataset (TRECVid SED).

International Perspectives on Business Innovation and Disruption in the Creative Industries : Film, Video and Photography

This volume examines how disruptive innovations are reshaping industry boundaries and challenging conventional business models and practices in the industries for film, video and photography. The thirteen chapters provide a rich and diverse account of these processes from a wide range of country contexts. The book fills the gap between the study of disruption by innovation scholars in business schools and the recognition of disruption by academics and practitioners from non-business school disciplines and contexts, including the broader social sciences.

User perceived video quality modelling on mobile devices for Vp9 and H265 encoders

This study constructs performance prediction models to estimate the end-user perceived video quality on mobile devices for the latest video encoding techniques –VP9 and H.265. Both subjective and objective video quality assessments were carried out for collecting data and selecting the most desirable predictors. Using statistical regression, two models were generated to achieve 94.5% and 91.5% of prediction accuracies respectively, depending on whether the predictor derived from the objective assessment is involved. These proposed models can be directly used by media industries for video quality estimation, and will ultimately help them to ensure a positive end-user quality of experience on future mobile devices after the adaptation of the latest video encoding technologies.

All about that base : differing player experiences in video game genres and the unique case of MOBA games

Video games provide unique interactive player experiences (PX) often categorised into different genres. Prior research has looked at different game genres, but rarely through a PX lens. Especially, PX in the emerging area of massive online battle arena (MOBA) games is not well understood by researchers in the field. We address this knowledge gap by presenting a PX study of different game genres, which we followed up with a second semi-structured interview study about PX in MOBA games. Among the results of our analyses are that games that are likely played with other players, such as MOBA games, stimulate less immersion and presence for players. Additionally, while challenge and frustration are significantly higher in this genre, players get a sense of satisfaction from teamwork, competition and mastery of complex gameplay interactions. Our study is the first to contribute a comprehensive insight into key motivators of MOBA players and how PX in this genre is different from other genres.

Using augmented video to test in-car user experiences of context analog HUDs

Automotive interactive technologies represent an exemplar challenge for user experience (UX) designers, as the concerns for aesthetics, functionality and usability add up to the compelling issues of safety and cognitive demand. This extended abstract presents a methodology for the user-centred creation and evaluation of novel in-car applications, involving real users in realistic use settings. As a case study, we present the methodologies of an ideation workshop in a simulated environment and the evaluation of six design idea prototypes for in-vehicle head up display (HUD) applications using a semi-naturalistic drive. Both methods rely on video recordings of real traffic situations that the users are familiar with and/or experienced themselves. The extended abstract presents experiences and results from the evaluation and reflection on our methods.

Using viewer’s facial expression and heart rate for sports video highlights detection

Viewer interests, evoked by video content, can potentially identify the highlights of the video. This paper explores the use of facial expressions (FE) and heart rate (HR) of viewers captured using camera and non-strapped sensor for identifying interesting video segments. The data from ten subjects with three videos showed that these signals are viewer dependent and not synchronized with the video contents. To address this issue, new algorithms are proposed to effectively combine FE and HR signals for identifying the time when viewer interest is potentially high. The results show that, compared with subjective annotation and match report highlights, ‘non-neutral’ FE and ‘relatively higher and faster’ HR is able to capture 60%-80% of goal, foul, and shot-on-goal soccer video events. FE is found to be more indicative than HR of viewer’s interests, but the fusion of these two modalities outperforms each of them.

The dawn of the age of the drones:An Australian privacy law perspective

Suppose a homeowner habitually enjoys sunbathing in his or her backyard, protected by a high fence from prying eyes, including those of an adolescent neighbour. In times past such homeowners could be assured that they might go about their activities without a threat to their privacy. However, recent years have seen technological advances in the development of unmanned aerial vehicles (‘UAVs’), also known colloquially as drones, that have allowed them to become more reduced in size, complexity and price. UAVs today include models retailing to the public for less than $350 and with an ease of operation that enables them to serve as mobile platforms for miniature cameras. These machines now mean that for individuals like the posited homeowner’s adolescent neighbour, barriers such as high fences no longer constitute insuperable obstacles to their voyeuristic endeavours. Moreover, ease of access to the internet and video sharing websites provides a ready means of sharing any recordings made with such cameras with a wide audience. Persons in the homeowner’s position might understandably seek some form of redress for such egregious invasions of their privacy. Other than some kind of self-help, what alternative measures may be available?

Large scale monitoring of crowds and building utilisation: A new database and distributed approach

Public buildings and large infrastructure are typically monitored by tens or hundreds of cameras, all capturing different physical spaces and observing different types of interactions and behaviours. However to date, in large part due to limited data availability, crowd monitoring and operational surveillance research has focused on single camera scenarios which are not representative of real-world applications. In this paper we present a new, publicly available database for large scale crowd surveillance. Footage from 12 cameras for a full work day covering the main floor of a busy university campus building, including an internal and external foyer, elevator foyers, and the main external approach are provided; alongside annotation for crowd counting (single or multi-camera) and pedestrian flow analysis for 10 and 6 sites respectively. We describe how this large dataset can be used to perform distributed monitoring of building utilisation, and demonstrate the potential of this dataset to understand and learn the relationship between different areas of a building.

Identifying and forecasting the reverse salient in video game consoles: A performance gap ratio comparative analysis

This study uses the reverse salient methodology to contrast subsystems in video game consoles in order to discover, characterize, and forecast the most significant technology gap. We build on the current methodologies (Performance Gap and Time Gap) for measuring the magnitude of Reverse Salience, by showing the effectiveness of Performance Gap Ratio (PGR). The three subject subsystems in this analysis are the CPU Score, GPU core frequency, and video memory bandwidth. CPU Score is a metric developed for this project, which is the product of the core frequency, number of parallel cores, and instruction size. We measure the Performance Gap of each subsystem against concurrently available PC hardware on the market. Using PGR, we normalize the evolution of these technologies for comparative analysis. The results indicate that while CPU performance has historically been the Reverse Salient, video memory bandwidth has taken over as the quickest growing technology gap in the current generation. Finally, we create a technology forecasting model that shows how much the video RAM bandwidth gap will grow through 2019 should the current trend continue. This analysis can assist console developers in assigning resources to the next generation of platforms, which will ultimately result in longer hardware life cycles.

Maintaining our rage: Inside Australia's longest-running music video program

This research presents an insider's account of rage, Australia's longest-running music video program. The research's significance is that there has been scarce scholarly analysis of this idiosyncratic ABC program, despite its longevity and uniqueness. The thesis takes a reflective and reflexive narrative journey across rage's decades, presenting the accounts of the program makers, aided by the perspective of an embedded researcher, the program's former Series Producer. This work addresses the rage research gap and contributes to the scholarly discussion on music video and its contexts, the ABC, public service broadcasting, creative labour, and the cultural sense-making of television producers.

Improving Near-Miss Event Detection Rate at Railway Level Crossings

Even though crashes between trains and road users are rare events at railway level crossings, they are one of the major safety concerns for the Australian railway industry. Nearmiss events at level crossings occur more frequently, and can provide more information about factors leading to level crossing incidents. In this paper we introduce a video analytic approach for automatically detecting and localizing vehicles from cameras mounted on trains for detecting near-miss events. To detect and localize vehicles at level crossings we extract patches from an image and classify each patch for detecting vehicles. We developed a region proposals algorithm for generating patches, and we use a Convolutional Neural Network (CNN) for classifying each patch. To localize vehicles in images we combine the patches that are classified as vehicles according to their CNN scores and positions. We compared our system with the Deformable Part Models (DPM) and Regions with CNN features (R-CNN) object detectors. Experimental results on a railway dataset show that the recall rate of our proposed system is 29% higher than what can be achieved with DPM or R-CNN detectors.

Prototyping the self-authored video interview : Challenges and opportunities

Self-authored video- where participants are in control of the creation of their own footage- is a means of creating innovative design material and including all members of a family in design activities. This paper describes our adaptation to this process called Self Authored Video Interviews (SAVIs) that we created and prototyped to better understand how families engage with situated technology in the home. We find the methodology produces unique insights into family dynamics in the home, uncovering assumptions and tensions unlikely to be discovered using more conventional methods. The paper outlines a number of challenges and opportunities associated with the methodology, specifically, maximising the value of the insights gathered by appealing to children to champion the cause, and how to counter perceptions of the lingering presence of researchers.