Reliability of routinely collected hospital data for child maltreatment surveillance

Background: Internationally, research on child maltreatment-related injuries has been hampered by a lack of available routinely collected health data to identify cases, examine causes, identify risk factors and explore health outcomes. Routinely collected hospital separation data coded using the International Classification of Diseases and Related Health Problems (ICD) system provide an internationally standardised data source for classifying and aggregating diseases, injuries, causes of injuries and related health conditions for statistical purposes. However, there has been limited research to examine the reliability of these data for child maltreatment surveillance purposes. This study examined the reliability of coding of child maltreatment in Queensland, Australia. Methods: A retrospective medical record review and recoding methodology was used to assess the reliability of coding of child maltreatment. A stratified sample of hospitals across Queensland was selected for this study, and a stratified random sample of cases was selected from within those hospitals. Results: In 3.6% of cases the coders disagreed on whether any maltreatment code could be assigned (definite or possible) versus no maltreatment being assigned (unintentional injury), giving a sensitivity of 0.982 and specificity of 0.948. The review of these cases where discrepancies existed revealed that all cases had some indications of risk documented in the records. 15.5% of cases originally assigned a definite or possible maltreatment code, were recoded to a more or less definite strata. In terms of the number and type of maltreatment codes assigned, the auditor assigned a greater number of maltreatment types based on the medical documentation than the original coder assigned (22% of the auditor coded cases had more than one maltreatment type assigned compared to only 6% of the original coded data). The maltreatment types which were the most ‘under-coded’ by the original coder were psychological abuse and neglect. Cases coded with a sexual abuse code showed the highest level of reliability. Conclusion: Given the increasing international attention being given to improving the uniformity of reporting of child-maltreatment related injuries and the emphasis on the better utilisation of routinely collected health data, this study provides an estimate of the reliability of maltreatment-specific ICD-10-AM codes assigned in an inpatient setting.

Robust suspicious behaviour detection for smart surveillance systems

Video surveillance technology, based on Closed Circuit Television (CCTV) cameras, is one of the fastest growing markets in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. To overcome this limitation, it is necessary to have “intelligent” processes which are able to highlight the salient data and filter out normal conditions that do not pose a threat to security. In order to create such intelligent systems, an understanding of human behaviour, specifically, suspicious behaviour is required. One of the challenges in achieving this is that human behaviour can only be understood correctly in the context in which it appears. Although context has been exploited in the general computer vision domain, it has not been widely used in the automatic suspicious behaviour detection domain. So, it is essential that context has to be formulated, stored and used by the system in order to understand human behaviour. Finally, since surveillance systems could be modeled as largescale data stream systems, it is difficult to have a complete knowledge base. In this case, the systems need to not only continuously update their knowledge but also be able to retrieve the extracted information which is related to the given context. To address these issues, a context-based approach for detecting suspicious behaviour is proposed. In this approach, contextual information is exploited in order to make a better detection. The proposed approach utilises a data stream clustering algorithm in order to discover the behaviour classes and their frequency of occurrences from the incoming behaviour instances. Contextual information is then used in addition to the above information to detect suspicious behaviour. The proposed approach is able to detect observed, unobserved and contextual suspicious behaviour. Two case studies using video feeds taken from CAVIAR dataset and Z-block building, Queensland University of Technology are presented in order to test the proposed approach. From these experiments, it is shown that by using information about context, the proposed system is able to make a more accurate detection, especially those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information give critical feedback to the system designers to refine the system. Finally, the proposed modified Clustream algorithm enables the system to both continuously update the system’s knowledge and to effectively retrieve the information learned in a given context. The outcomes from this research are: (a) A context-based framework for automatic detecting suspicious behaviour which can be used by an intelligent video surveillance in making decisions; (b) A modified Clustream data stream clustering algorithm which continuously updates the system knowledge and is able to retrieve contextually related information effectively; and (c) An update-describe approach which extends the capability of the existing human local motion features called interest points based features to the data stream environment.

Super-resolved faces for improved face recognition from surveillance video advances in biometrics

Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for computers and human operators to identify individuals from these videos. To overcome this problem, super-resolution can be used in conjunction with an automated face recognition system to enhance the spatial resolution of video frames containing the subject and narrow down the number of manual verifications performed by the human operator by presenting a list of most likely candidates from the database. As the super-resolution reconstruction process is ill-posed, visual artifacts are often generated as a result. These artifacts can be visually distracting to humans and/or affect machine recognition algorithms. While it is intuitive that higher resolution should lead to improved recognition accuracy, the effects of super-resolution and such artifacts on face recognition performance have not been systematically studied. This paper aims to address this gap while illustrating that super-resolution allows more accurate identification of individuals from low-resolution surveillance footage. The proposed optical flow-based super-resolution method is benchmarked against Baker et al.’s hallucination and Schultz et al.’s super-resolution techniques on images from the Terrascope and XM2VTS databases. Ground truth and interpolated images were also tested to provide a baseline for comparison. Results show that a suitable super-resolution system can improve the discriminability of surveillance video and enhance face recognition accuracy. The experiments also show that Schultz et al.’s method fails when dealing surveillance footage due to its assumption of rigid objects in the scene. The hallucination and optical flow-based methods performed comparably, with the optical flow-based method producing less visually distracting artifacts that interfered with human recognition.

Feasibility of using health data sources to inform product safety surveillance in Queensland : a report for the Queensland Injury Prevention Council

This report provides an evaluation of the current available evidence-base for identification and surveillance of product-related injuries in children in Queensland. While the focal population was children in Queensland, the identification of information needs and data sources for product safety surveillance has applicability nationally for all age groups. The report firstly summarises the data needs of product safety regulators regarding product-related injury in children, describing the current sources of information informing product safety policy and practice, and documenting the priority product surveillance areas affecting children which have been a focus over recent years in Queensland. Health data sources in Queensland which have the potential to inform product safety surveillance initiatives were evaluated in terms of their ability to address the information needs of product safety regulators. Patterns in product-related injuries in children were analysed using routinely available health data to identify areas for future intervention, and the patterns in product-related injuries in children identified in health data were compared to those identified by product safety regulators. Recommendations were made for information system improvements and improved access to and utilisation of health data for more proactive approaches to product safety surveillance in the future.

A suspicious behaviour detection using a context space model for smart surveillance systems

Video surveillance systems using Closed Circuit Television (CCTV) cameras, is one of the fastest growing areas in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. This work attempts to address these problems by proposing an automatic suspicious behaviour detection which utilises contextual information. The utilisation of contextual information is done via three main components: a context space model, a data stream clustering algorithm, and an inference algorithm. The utilisation of contextual information is still limited in the domain of suspicious behaviour detection. Furthermore, it is nearly impossible to correctly understand human behaviour without considering the context where it is observed. This work presents experiments using video feeds taken from CAVIAR dataset and a camera mounted on one of the buildings Z-Block) at the Queensland University of Technology, Australia. From these experiments, it is shown that by exploiting contextual information, the proposed system is able to make more accurate detections, especially of those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information gives critical feedback to the system designers to refine the system.

A Context Space Model for Detecting Anomalous Behaviour in Video Surveillance

Having a good automatic anomalous human behaviour detection is one of the goals of smart surveillance systems’ domain of research. The automatic detection addresses several human factor issues underlying the existing surveillance systems. To create such a detection system, contextual information needs to be considered. This is because context is required in order to correctly understand human behaviour. Unfortunately, the use of contextual information is still limited in the automatic anomalous human behaviour detection approaches. This paper proposes a context space model which has two benefits: (a) It provides guidelines for the system designers to select information which can be used to describe context; (b)It enables a system to distinguish between different contexts. A comparative analysis is conducted between a context-based system which employs the proposed context space model and a system which is implemented based on one of the existing approaches. The comparison is applied on a scenario constructed using video clips from CAVIAR dataset. The results show that the context-based system outperforms the other system. This is because the context space model allows the system to considering knowledge learned from the relevant context only.

A database for person re-identification in multi-camera surveillance networks

Person re-identification involves recognising individuals in different locations across a network of cameras and is a challenging task due to a large number of varying factors such as pose (both subject and camera) and ambient lighting conditions. Existing databases do not adequately capture these variations, making evaluations of proposed techniques difficult. In this paper, we present a new challenging multi-camera surveillance database designed for the task of person re-identification. This database consists of 150 unscripted sequences of subjects travelling in a building environment though up to eight camera views, appearing from various angles and in varying illumination conditions. A flexible XML-based evaluation protocol is provided to allow a highly configurable evaluation setup, enabling a variety of scenarios relating to pose and lighting conditions to be evaluated. A baseline person re-identification system consisting of colour, height and texture models is demonstrated on this database.

Surveillance of dengue fever virus: a review of epidemiological models and early warning systems

Dengue fever is one of the world’s most important vector-borne diseases. The transmission area of this disease continues to expand due to many factors including urban sprawl, increased travel and global warming. Current preventative techniques are primarily based on controlling mosquito vectors as other prophylactic measures, such as a tetravalent vaccine are unlikely to be available in the foreseeable future. However, the continually increasing dengue incidence suggests that this strategy alone is not sufficient. Epidemiological models attempt to predict future outbreaks using information on the risk factors of the disease. Through a systematic literature review, this paper aims at analyzing the different modeling methods and their outputs in terms of accurately predicting disease outbreaks. We found that many previous studies have not sufficiently accounted for the spatio-temporal features of the disease in the modeling process. Yet with advances in technology, the ability to incorporate such information as well as the socio-environmental aspect allowed for its use as an early warning system, albeit limited geographically to a local scale.

Efficient real-time face detection for high resolution surveillance applications

This paper presents an efficient face detection method suitable for real-time surveillance applications. Improved efficiency is achieved by constraining the search window of an AdaBoost face detector to pre-selected regions. Firstly, the proposed method takes a sparse grid of sample pixels from the image to reduce whole image scan time. A fusion of foreground segmentation and skin colour segmentation is then used to select candidate face regions. Finally, a classifier-based face detector is applied only to selected regions to verify the presence of a face (the Viola-Jones detector is used in this paper). The proposed system is evaluated using 640 x 480 pixels test images and compared with other relevant methods. Experimental results show that the proposed method reduces the detection time to 42 ms, where the Viola-Jones detector alone requires 565 ms (on a desktop processor). This improvement makes the face detector suitable for real-time applications. Furthermore, the proposed method requires 50% of the computation time of the best competing method, while reducing the false positive rate by 3.2% and maintaining the same hit rate.

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.

Design, simulation and analysis of a parallel hybrid electric propulsion system for unmanned aerial vehicles

Aerial Vehicles (UAV) has become a significant growing segment of the global aviation industry. These vehicles are developed with the intention of operating in regions where the presence of onboard human pilots is either too risky or unnecessary. Their popularity with both the military and civilian sectors have seen the use of UAVs in a diverse range of applications, from reconnaissance and surveillance tasks for the military, to civilian uses such as aid relief and monitoring tasks. Efficient energy utilisation on an UAV is essential to its functioning, often to achieve the operational goals of range, endurance and other specific mission requirements. Due to the limitations of the space available and the mass budget on the UAV, it is often a delicate balance between the onboard energy available (i.e. fuel) and achieving the operational goals. This paper presents the development of a parallel Hybrid Electric Propulsion System (HEPS) on a small fixed-wing UAV incorporating an Ideal Operating Line (IOL) control strategy. A simulation model of an UAV was developed in the MATLAB Simulink environment, utilising the AeroSim Blockset and the in-built Aerosonde UAV block and its parameters. An IOL analysis of an Aerosonde engine was performed, and the most efficient (i.e. provides greatest torque output at the least fuel consumption) points of operation for this engine were determined. Simulation models of the components in a HEPS were designed and constructed in the MATLAB Simulink environment. It was demonstrated through simulation that an UAV with the current HEPS configuration was capable of achieving a fuel saving of 6.5%, compared to the ICE-only configuration. These components form the basis for the development of a complete simulation model of a Hybrid-Electric UAV (HEUAV).

Improving the measurement and surveillance of child abuse in Queensland emergency departments

There are no population studies of prevalence or incidence of child maltreatment in Australia. Child protection data gives some understanding but is restricted by system capacity and definitional issues across jurisdictions. Child protection data currently suggests that numbers of reports are increasing yearly, and the child protection system then becomes focussed on investigating all reports and diluting available resources for those children who are most in need of intervention. A public health response across multiple agencies enables responses to child safety across the entire population. All families are targeted at the primary level; examples include ensuring all parents know the dangers of shaking a baby or teaching children to say no if a situation makes them uncomfortable. The secondary level of prevention targets families with a number of risk factors, for example subsidised child care so children aren't left unsupervised after school when both parents have to be at work or home visiting for drug-addicted parents to ensure children are cared for. The tertiary response then becomes the responsibility of the child protection system and is reserved for those children where abuse and neglect are identified. This model requires that child safety is seen in a broader context than just the child protection system, and increasingly health professionals are being identified as an important component in the public health framework. If all injury is viewed as preventable and considered along a continuum of 'accidental' through to 'inflicted', it becomes possible to conceptualise child maltreatment in an injury context. Parental intent may not be to cause harm to the child, but by lack of insight or concern about risk, the potential for injury is high. The mechanisms for unintentional and intentional injury overlap and some suggest that by segregating child abuse (with the possible exception of sexual abuse) from unintentional injury, child abuse is excluded from the broader injury prevention initiative that is gaining momentum in the community. This research uses a public health perspective, specifically that of injury prevention, to consider the problem of child abuse. This study employed a mixed method design that incorporates secondary data analysis, data linkage and structured interviews of different professional groups. Datasets from the Queensland Injury Surveillance Unit (QISU) and The Department of Child Safety (DCS) were evaluated. Coded injury data was grouped according to intent of injury according to those with a code that indicated the ED presentation was due to child abuse, a code indicating that the injury was possibly due to abuse or, in the third group, the intent code indicated that the injury was unintentional and not due to abuse. Primary data collection from ED records was undertaken and information recoded to assess reliability and completeness. Emergency department data (QISU) was linked to Department of Child Safety Data to examine concordance and data quality. Factors influencing the collection and collation of these data were identified through structured interview methodology and analysed using qualitative methods. Secondary analysis of QISU data indicated that codes lacking specific information on the injury event were more likely to also have an intent code indicating abuse than those records where there was specific information on the injury event. Codes for abuse appeared in only 1.2% of the 84,765 records analysed. Unintentional injury was the most commonly coded intent (95.3%). In the group with a definite abuse code assigned at triage, 83% linked to a record with DCS and cases where documentation indicated police involvement were significantly more likely to be associated with a DCS record than those without such documentation. In those coded with an unintentional injury code, 22% linked to a DCS record with cases assigned an urgent triage category more likely to link than those with a triage category for resuscitation and children who presented to regional or remote hospitals more likely to link to a DCS record than those presenting to urban hospitals. Twenty-nine per cent of cases with a code indicating possible abuse linked to a DCS record. In documentation that indicated police involvement in the case, a code for unspecified activity when compared to cases with a code indicating involvement in a sporting activity and children less than 12 months of age compared to those in the 13-17 year old age group were all variables significantly associated with linkage to a DCS record. Only 13% of records contained documentation indicating that child abuse and neglect were considered in the diagnosis of the injury despite almost half of the sample having a code of abuse or possible abuse. Doctors and nurses were confident in their knowledge of the process of reporting child maltreatment but less confident about identifying child abuse and neglect and what should be reported. Many were concerned about implications of reporting, for the child and family and for themselves. A number were concerned about the implications of not reporting, mostly for the wellbeing of the child and a few in terms of their legal obligations as mandatory reporters. The outcomes of this research will help improve the knowledge of barriers to effective surveillance of child abuse in emergency departments. This will, in turn, ensure better identification and reporting practises; more reliable official statistical collections and the potential of flagging high-risk cases to ensure adequate departmental responses have been initiated.

Bayesian modelling of surveillance and proof of freedom : the mathematical, logical & psychological challenges

Keeping exotic plant pests out of our country relies on good border control or quarantine. However with increasing globalization and mobilization some things slip through. Then the back up systems become important. This can include an expensive form of surveillance that purposively targets particular pests. A much wider net is provided by general surveillance, which is assimilated into everyday activities, like farmers checking the health of their crops. In fact farmers and even home gardeners have provided a front line warning system for some pests (eg European wasp) that could otherwise have wreaked havoc. Mathematics is used to model how surveillance works in various situations. Within this virtual world we can play with various surveillance and management strategies to "see" how they would work, or how to make them work better. One of our greatest challenges is estimating some of the input parameters : because the pest hasn't been here before, it's hard to predict how well it might behave: establishing, spreading, and what types of symptoms it might express. So we rely on experts to help us with this. This talk will look at the mathematical, psychological and logical challenges of helping experts to quantify what they think. We show how the subjective Bayesian approach is useful for capturing expert uncertainty, ultimately providing a more complete picture of what they think... And what they don't!

Distributed low-power image processing in wireless sensor networks for intelligent video surveillance applications

Distributed Wireless Smart Camera (DWSC) network is a special type of Wireless Sensor Network (WSN) that processes captured images in a distributed manner. While image processing on DWSCs sees a great potential for growth, with its applications possessing a vast practical application domain such as security surveillance and health care, it suffers from tremendous constraints. In addition to the limitations of conventional WSNs, image processing on DWSCs requires more computational power, bandwidth and energy that presents significant challenges for large scale deployments. This dissertation has developed a number of algorithms that are highly scalable, portable, energy efficient and performance efficient, with considerations of practical constraints imposed by the hardware and the nature of WSN. More specifically, these algorithms tackle the problems of multi-object tracking and localisation in distributed wireless smart camera net- works and optimal camera configuration determination. Addressing the first problem of multi-object tracking and localisation requires solving a large array of sub-problems. The sub-problems that are discussed in this dissertation are calibration of internal parameters, multi-camera calibration for localisation and object handover for tracking. These topics have been covered extensively in computer vision literatures, however new algorithms must be invented to accommodate the various constraints introduced and required by the DWSC platform. A technique has been developed for the automatic calibration of low-cost cameras which are assumed to be restricted in their freedom of movement to either pan or tilt movements. Camera internal parameters, including focal length, principal point, lens distortion parameter and the angle and axis of rotation, can be recovered from a minimum set of two images of the camera, provided that the axis of rotation between the two images goes through the camera's optical centre and is parallel to either the vertical (panning) or horizontal (tilting) axis of the image. For object localisation, a novel approach has been developed for the calibration of a network of non-overlapping DWSCs in terms of their ground plane homographies, which can then be used for localising objects. In the proposed approach, a robot travels through the camera network while updating its position in a global coordinate frame, which it broadcasts to the cameras. The cameras use this, along with the image plane location of the robot, to compute a mapping from their image planes to the global coordinate frame. This is combined with an occupancy map generated by the robot during the mapping process to localised objects moving within the network. In addition, to deal with the problem of object handover between DWSCs of non-overlapping fields of view, a highly-scalable, distributed protocol has been designed. Cameras that follow the proposed protocol transmit object descriptions to a selected set of neighbours that are determined using a predictive forwarding strategy. The received descriptions are then matched at the subsequent camera on the object's path using a probability maximisation process with locally generated descriptions. The second problem of camera placement emerges naturally when these pervasive devices are put into real use. The locations, orientations, lens types etc. of the cameras must be chosen in a way that the utility of the network is maximised (e.g. maximum coverage) while user requirements are met. To deal with this, a statistical formulation of the problem of determining optimal camera configurations has been introduced and a Trans-Dimensional Simulated Annealing (TDSA) algorithm has been proposed to effectively solve the problem.