Improving level crossing safety through enhanced data recording and reporting : The CRC for Rail Innovation’s Baseline Rail Level Crossing Video project

This paper describes the work being conducted in the baseline rail level crossing project, supported by the Australian rail industry and the Cooperative Research Centre for Rail Innovation. The paper discusses the limitations of near-miss data for analysis obtained using current level crossing occurrence reporting practices. The project is addressing these limitations through the development of a data collection and analysis system with an underlying level crossing accident causation model. An overview of the methodology and improved data recording process are described. The paper concludes with a brief discussion of benefits this project is expected to provide the Australian rail industry.

Automatically detecting pain in video through facial action units

In a clinical setting, pain is reported either through patient self-report or via an observer. Such measures are problematic as they are: 1) subjective, and 2) give no specific timing information. Coding pain as a series of facial action units (AUs) can avoid these issues as it can be used to gain an objective measure of pain on a frame-by-frame basis. Using video data from patients with shoulder injuries, in this paper, we describe an active appearance model (AAM)-based system that can automatically detect the frames in video in which a patient is in pain. This pain data set highlights the many challenges associated with spontaneous emotion detection, particularly that of expression and head movement due to the patient's reaction to pain. In this paper, we show that the AAM can deal with these movements and can achieve significant improvements in both the AU and pain detection performance compared to the current-state-of-the-art approaches which utilize similarity-normalized appearance features only.

Video analytics for the detection of near-miss incidents on approach to railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand causal factors that contribute to these accidents, the Cooperative Research Centre for Rail Innovation is running a project entitled Baseline Level Crossing Video. The project aims to improve the recording of level crossing safety data by developing an intelligent system capable of detecting near-miss incidents and capturing quantitative data around these incidents. To detect near-miss events at railway level crossings a video analytics module is being developed to analyse video footage obtained from forward-facing cameras installed on trains. This paper presents a vision base approach for the detection of these near-miss events. The video analytics module is comprised of object detectors and a rail detection algorithm, allowing the distance between a detected object and the rail to be determined. An existing publicly available Histograms of Oriented Gradients (HOG) based object detector algorithm is used to detect various types of vehicles in each video frame. As vehicles are usually seen from a sideway view from the cabin’s perspective, the results of the vehicle detector are verified using an algorithm that can detect the wheels of each detected vehicle. Rail detection is facilitated using a projective transformation of the video, such that the forward-facing view becomes a bird’s eye view. Line Segment Detector is employed as the feature extractor and a sliding window approach is developed to track a pair of rails. Localisation of the vehicles is done by projecting the results of the vehicle and rail detectors on the ground plane allowing the distance between the vehicle and rail to be calculated. The resultant vehicle positions and distance are logged to a database for further analysis. We present preliminary results regarding the performance of a prototype video analytics module on a data set of videos containing more than 30 different railway level crossings. The video data is captured from a journey of a train that has passed through these level crossings.

Participation and social order in the playground

This study investigates the everyday practices of young children acting in their social worlds within the context of the school playground. It employs an ethnographic ethnomethodological approach using conversation analysis. In the context of child participation rights advanced by the United Nations Convention on the Rights of the Child (UNCRC) and childhood studies, the study considers children’s social worlds and their participation agendas. The participants of the study were a group of young children in a preparatory year setting in a Queensland school. These children, aged 4 to 6 years, were videorecorded as they participated in their day-to-day activities in the classroom and in the playground. Data collection took place over a period of three months, with a total of 26 hours of video data. Episodes of the video-recordings were shown to small groups of children and to the teacher to stimulate conversations about what they saw on the video. The conversations were audio-recorded. This method acknowledged the child’s standpoint and positioned children as active participants in accounting for their relationships with others. These accounts are discussed as interactionally built comments on past joint experiences and provided a starting place for analysis of the video-recorded interaction. Four data chapters are presented in this thesis. Each data chapter investigates a different topic of interaction. The topics include how children use “telling” as a tactical tool in the management of interactional trouble, how children use their “ideas” as possessables to gain ownership of a game and the interactional matters that follow, how children account for interactional matters and bid for ownership of “whose idea” for the game and finally, how a small group of girls orientated to a particular code of conduct when accounting for their actions in a pretend game of “school”. Four key themes emerged from the analysis. The first theme addresses two arenas of action operating in the social world of children, pretend and real: the “pretend”, as a player in a pretend game, and the “real”, as a classroom member. These two arenas are intertwined. Through inferences to explicit and implicit “codes of conduct”, moral obligations are invoked as children attempt to socially exclude one another, build alliances and enforce their own social positions. The second theme is the notion of shared history. This theme addresses the history that the children reconstructed, and acts as a thread that weaves through their interactions, with implications for present and future relationships. The third theme is around ownership. In a shared context, such as the playground, ownership is a highly contested issue. Children draw on resources such as rules, their ideas as possessables, and codes of behaviour as devices to construct particular social and moral orders around owners of the game. These themes have consequences for children’s participation in a social group. The fourth theme, methodological in nature, shows how the researcher was viewed as an outsider and novice and was used as a resource by the children. This theme is used to inform adult-child relationships. The study was situated within an interest in participation rights for children and perspectives of children as competent beings. Asking children to account for their participation in playground activities situates children as analysers of their own social worlds and offers adults further information for understanding how children themselves construct their social interactions. While reporting on the experiences of one group of children, this study opens up theoretical questions about children’s social orders and these influences on their everyday practices. This thesis uncovers how children both participate in, and shape, their everyday social worlds through talk and interaction. It investigates the consequences that taken-for-granted activities of “playing the game” have for their social participation in the wider culture of the classroom. Consideration of this significance may assist adults to better understand and appreciate the social worlds of young children in the school playground.

Primary students’ interpretation of maps : gesture use and mapping knowledge

Maps are used to represent three-dimensional space and are integral to a range of everyday experiences. They are increasingly used in mathematics, being prominent both in school curricula and as a form of assessing students understanding of mathematics ideas. In order to successfully interpret maps, students need to be able to understand that maps: represent space, have their own perspective and scale, and their own set of symbols and texts. Despite the fact that maps have an increased prevalence in society and school, there is evidence to suggest that students have difficulty interpreting maps. This study investigated 43 primary-aged students’ (aged 9-12 years) verbal and gestural behaviours as they engaged with and solved map tasks. Within a multiliteracies framework that focuses on spatial, visual, linguistic, and gestural elements, the study investigated how students interpret map tasks. Specifically, the study sought to understand students’ skills and approaches used to solving map tasks and the gestural behaviours they utilised as they engaged with map tasks. The investigation was undertaken using the Knowledge Discovery in Data (KDD) design. The design of this study capitalised on existing research data to carry out a more detailed analysis of students’ interpretation of map tasks. Video data from an existing data set was reorganised according to two distinct episodes—Task Solution and Task Explanation—and analysed within the multiliteracies framework. Content Analysis was used with these data and through anticipatory data reduction techniques, patterns of behaviour were identified in relation to each specific map task by looking at task solution, task correctness and gesture use. The findings of this study revealed that students had a relatively sound understanding of general mapping knowledge such as identifying landmarks, using keys, compass points and coordinates. However, their understanding of mathematical concepts pertinent to map tasks including location, direction, and movement were less developed. Successful students were able to interpret the map tasks and apply relevant mathematical understanding to navigate the spatial demands of the map tasks while the unsuccessful students were only able to interpret and understand basic map conventions. In terms of their gesture use, the more difficult the task, the more likely students were to exhibit gestural behaviours to solve the task. The most common form of gestural behaviour was deictic, that is a pointing gesture. Deictic gestures not only aided the students capacity to explain how they solved the map tasks but they were also a tool which assisted them to navigate and monitor their spatial movements when solving the tasks. There were a number of implications for theory, learning and teaching, and test and curriculum design arising from the study. From a theoretical perspective, the findings of the study suggest that gesturing is an important element of multimodal engagement in mapping tasks. In terms of teaching and learning, implications include the need for students to utilise gesturing techniques when first faced with new or novel map tasks. As students become more proficient in solving such tasks, they should be encouraged to move beyond a reliance on such gesture use in order to progress to more sophisticated understandings of map tasks. Additionally, teachers need to provide students with opportunities to interpret and attend to multiple modes of information when interpreting map tasks.

High resolution tiled display walls

Scalable high-resolution tiled display walls are becoming increasingly important to decision makers and researchers because high pixel counts in combination with large screen areas facilitate content rich, simultaneous display of computer-generated visualization information and high-definition video data from multiple sources. This tutorial is designed to cater for new users as well as researchers who are currently operating tiled display walls or 'OptiPortals'. We will discuss the current and future applications of display wall technology and explore opportunities for participants to collaborate and contribute in a growing community. Multiple tutorial streams will cover both hands-on practical development, as well as policy and method design for embedding these technologies into the research process. Attendees will be able to gain an understanding of how to get started with developing similar systems themselves, in addition to becoming familiar with typical applications and large-scale visualisation techniques. Presentations in this tutorial will describe current implementations of tiled display walls that highlight the effective usage of screen real-estate with various visualization datasets, including collaborative applications such as visualcasting, classroom learning and video conferencing. A feature presentation for this tutorial will be given by Jurgen Schulze from Calit2 at the University of California, San Diego. Jurgen is an expert in scientific visualization in virtual environments, human-computer interaction, real-time volume rendering, and graphics algorithms on programmable graphics hardware.

Mother and child sharing through drawing: Intergenerational collaborative processes for making artworks

This paper presents a preliminary study into collaborated processes for art-making, undertaken by a young child and an adult. The study explores collaborative drawing in the context of sociocultural research into early childhood education. The study particularly examines whether childhood techniques for making marks, creative processing and art-making could be ‘re-learned’ by the adult, while new opportunities for expanding on extant repertoire could be available to the child. In this context the child teaches and learns from the adult, and the adult teaches and learns from the child. The study utilised video-data-recording to facilitate microanalysis of the researchers in action, enabling the adult researcher to present a discourse into the dynamics of how the visual, mark-making repertoires of an adult and child can be co-developed. Preliminary findings help contribute to the various discourses available into sociocultural research that supports processes for exploring and making art, and which allows a challenge to the role of the adult educator as a provider or director of what is learned.

SAIVT-QUT@TRECVid 2012 : interactive surveillance event detection

In this paper, we propose an approach which attempts to solve the problem of surveillance event detection, assuming that we know the definition of the events. To facilitate the discussion, we first define two concepts. The event of interest refers to the event that the user requests the system to detect; and the background activities are any other events in the video corpus. This is an unsolved problem due to many factors as listed below: 1) Occlusions and clustering: The surveillance scenes which are of significant interest at locations such as airports, railway stations, shopping centers are often crowded, where occlusions and clustering of people are frequently encountered. This significantly affects the feature extraction step, and for instance, trajectories generated by object tracking algorithms are usually not robust under such a situation. 2) The requirement for real time detection: The system should process the video fast enough in both of the feature extraction and the detection step to facilitate real time operation. 3) Massive size of the training data set: Suppose there is an event that lasts for 1 minute in a video with a frame rate of 25fps, the number of frames for this events is 60X25 = 1500. If we want to have a training data set with many positive instances of the event, the video is likely to be very large in size (i.e. hundreds of thousands of frames or more). How to handle such a large data set is a problem frequently encountered in this application. 4) Difficulty in separating the event of interest from background activities: The events of interest often co-exist with a set of background activities. Temporal groundtruth typically very ambiguous, as it does not distinguish the event of interest from a wide range of co-existing background activities. However, it is not practical to annotate the locations of the events in large amounts of video data. This problem becomes more serious in the detection of multi-agent interactions, since the location of these events can often not be constrained to within a bounding box. 5) Challenges in determining the temporal boundaries of the events: An event can occur at any arbitrary time with an arbitrary duration. The temporal segmentation of events is difficult and ambiguous, and also affected by other factors such as occlusions.

GrabCutSFM : how 3D information improves unsupervised object segmentation

In this paper, we present an unsupervised graph cut based object segmentation method using 3D information provided by Structure from Motion (SFM), called Grab- CutSFM. Rather than focusing on the segmentation problem using a trained model or human intervention, our approach aims to achieve meaningful segmentation autonomously with direct application to vision based robotics. Generally, object (foreground) and background have certain discriminative geometric information in 3D space. By exploring the 3D information from multiple views, our proposed method can segment potential objects correctly and automatically compared to conventional unsupervised segmentation using only 2D visual cues. Experiments with real video data collected from indoor and outdoor environments verify the proposed approach.

Get real : the development, implementation and evaluation of an intervention for primary aged children with High Functioning Autism

Children with Autism Spectrum Disorder experience difficulty in communication and in understanding the social world which can have negative consequences for their relationships, in managing emotions, and generally dealing with the challenges of everyday life. This thesis examines the effectiveness of the Active and Reflective components of the Get REAL program through the assessment of the detailed coding of video-recorded observations and longitudinal quantitative analysis. The aim of Get REAL is to increase the social, emotional, and cognitive learning of children with High Functioning Autism (HFA). Get REAL is a group program designed specifically for use in inclusive primary school settings. The Get REAL program was designed in response to the mixed success of generalisation of learning to new contexts of existing social skills programs. The theoretical foundation of Get REAL is based upon pedagogical theory and learning theory to facilitate transfer of learning, combined with experiential, individualised, evaluative and organisational approaches. This thesis is by publication and consists of four refereed journal papers; 1 accepted for publication and 3 that are under review. Paper 1 describes the development and theoretical basis of the Get REAL program and provides detail of the program structure and learning cycle. The focus of Paper 1 reflects the first question of interest in the thesis which is about the extent to which learning derived from participation in the program can be generalised to other contexts. Participants are 16 children with HFA ranging in age from 8-13 years. Results provided support for the generalisability of learning from Get REAL to home and school evidenced by parent and teacher data collected pre and post participation in Get REAL. Following establishment of the generalisation of learning from Get REAL, Papers 2 and 3 focus on the Active and Reflective components of the program in order to examine how individual and group learning takes place. Participants (N = 12) in the program are video-taped during the Active and Reflective Sessions. Using identical coding protocols of video data, improvements in prosocial behaviour and diminishing of inappropriate behaviours were apparent with the exception of perspective taking. Data also revealed that 2 of the participants had atypical trajectories. An in-depth case study analysis was then conducted with these 2 participants in Paper 4. Data included reports from health care and education professionals within the school and externally (e.g., paediatrician) and identified the multi-faceted nature of care needed for children with comorbid diagnoses and extremely challenging family circumstances as a complex task to effect change. Results of this research support the effectiveness of the Get REAL program in promoting pro social behaviours such as improvements in engaging with others and emotional regulation, and in diminishing unwanted behaviours such as conduct problems. Further, the gains made by the participating children were found to be generalisable beyond Get REAL to home and other school settings. The research contained in the thesis adds to current knowledge about how learning can take place for children with HFA. Results show that an experiential learning framework with a focus on social cognition, together with explicit teaching, scaffolded with video feedback, are key ingredients for the generalisation of social learning to broader contexts.

Co-production of actions and activities at airport security screening

In this paper we will examine passenger actions and activities at the security screening points of Australian domestic and international airports. Our findings and analysis provide a more complete understanding of the current airport passenger security screening experience. Data in this paper is comprised of field studies conducted at two Australian airports, one domestic and one international. Video data was collected by cameras situated either side of the security screening point. A total of one hundred and ninety-six passengers were observed. Two methods of analysis are used. First, the activities of passengers are coded and analysed to reveal the common activities at domestic and international security regimes and between quiet and busy periods. Second, observation of passenger activities is used to reveal uncommon aspects. The results show that passengers do more at security screening that being passively scanned. Passengers queue, unpack the required items from their bags and from their pockets, walk through the metal-detector, re-pack and occasionally return to be re-screened. For each of these activities, passengers must understand the procedures at the security screening point and must co-ordinate various actions and objects in time and space. Through this coordination passengers are active participants in making the security checkpoint function – they are co-producers of the security screening process.

Introduction to the special issue on next generation network architectures, protocols, theory, systems and applications

This special issue of Networking Science focuses on Next Generation Network (NGN) that enables the deployment of access independent services over converged fixed and mobile networks. NGN is a packet-based network and uses the Internet protocol (IP) to transport the various types of traffic (voice, video, data and signalling). NGN facilitates easy adoption of distributed computing applications by providing high speed connectivity in a converged networked environment. It also makes end user devices and applications highly intelligent and efficient by empowering them with programmability and remote configuration options. However, there are a number of important challenges in provisioning next generation network technologies in a converged communication environment. Some preliminary challenges include those that relate to QoS, switching and routing, management and control, and security which must be addressed on an urgent or emergency basis. The consideration of architectural issues in the design and pro- vision of secure services for NGN deserves special attention and hence is the main theme of this special issue.

Summarisation of short-term and long-term videos using texture and colour

We present a novel approach to video summarisation that makes use of a Bag-of-visual-Textures (BoT) approach. Two systems are proposed, one based solely on the BoT approach and another which exploits both colour information and BoT features. On 50 short-term videos from the Open Video Project we show that our BoT and fusion systems both achieve state-of-the-art performance, obtaining an average F-measure of 0.83 and 0.86 respectively, a relative improvement of 9% and 13% when compared to the previous state-of-the-art. When applied to a new underwater surveillance dataset containing 33 long-term videos, the proposed system reduces the amount of footage by a factor of 27, with only minor degradation in the information content. This order of magnitude reduction in video data represents significant savings in terms of time and potential labour cost when manually reviewing such footage.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Near-miss event detection at railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand the causal factors of these accidents, a video analytics application is being developed to automatically detect near-miss incidents using forward facing videos from trains. As near-miss events occur more frequently than collisions, by detecting these occurrences there will be more safety data available for analysis. The application that is being developed will improve the objectivity of near-miss reporting by providing quantitative data about the position of vehicles at level crossings through the automatic analysis of video footage. In this paper we present a novel method for detecting near-miss occurrences at railway level crossings from video data of trains. Our system detects and localizes vehicles at railway level crossings. It also detects the position of railways to calculate the distance of the detected vehicles to the railway centerline. The system logs the information about the position of the vehicles and railway centerline into a database for further analysis by the safety data recording and analysis system, to determine whether or not the event is a near-miss. We present preliminary results of our system on a dataset of videos taken from a train that passed through 14 railway level crossings. We demonstrate the robustness of our system by showing the results of our system on day and night videos.