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.

Eight weeks of episodic visual navigation inside a non-stationary environment using adaptive spherical views

This paper presents a long-term experiment where a mobile robot uses adaptive spherical views to localize itself and navigate inside a non-stationary office environment. The office contains seven members of staff and experiences a continuous change in its appearance over time due to their daily activities. The experiment runs as an episodic navigation task in the office over a period of eight weeks. The spherical views are stored in the nodes of a pose graph and they are updated in response to the changes in the environment. The updating mechanism is inspired by the concepts of long- and short-term memories. The experimental evaluation is done using three performance metrics which evaluate the quality of both the adaptive spherical views and the navigation over time.

Constructing a clinical decision-making framework for image-guided radiotherapy using a Bayesian Network

A decision-making framework for image-guided radiotherapy (IGRT) is being developed using a Bayesian Network (BN) to graphically describe, and probabilistically quantify, the many interacting factors that are involved in this complex clinical process. Outputs of the BN will provide decision-support for radiation therapists to assist them to make correct inferences relating to the likelihood of treatment delivery accuracy for a given image-guided set-up correction. The framework is being developed as a dynamic object-oriented BN, allowing for complex modelling with specific sub-regions, as well as representation of the sequential decision-making and belief updating associated with IGRT. A prototype graphic structure for the BN was developed by analysing IGRT practices at a local radiotherapy department and incorporating results obtained from a literature review. Clinical stakeholders reviewed the BN to validate its structure. The BN consists of a sub-network for evaluating the accuracy of IGRT practices and technology. The directed acyclic graph (DAG) contains nodes and directional arcs representing the causal relationship between the many interacting factors such as tumour site and its associated critical organs, technology and technique, and inter-user variability. The BN was extended to support on-line and off-line decision-making with respect to treatment plan compliance. Following conceptualisation of the framework, the BN will be quantified. It is anticipated that the finalised decision-making framework will provide a foundation to develop better decision-support strategies and automated correction algorithms for IGRT.

Analysis of bilinear pairing-based accumulator for identity escrowing

An accumulator based on bilinear pairings was proposed at CT-RSA'05. Here, it is first demonstrated that the security model proposed by Lan Nguyen does lead to a cryptographic accumulator that is not collision resistant. Secondly, it is shown that collision-resistance can be provided by updating the adversary model appropriately. Finally, an improvement on Nguyen's identity escrow scheme, with membership revocation based on the accumulator, by removing the trusted third party is proposed.

Dictionary learning and sparse coding on Grassmann manifolds : an extrinsic solution

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graph-embedding Grassmann discriminant analysis.

An adaptive spherical view representation for navigation in changing environments

Real-world environments such as houses and offices change over time, meaning that a mobile robot’s map will become out of date. In previous work we introduced a method to update the reference views in a topological map so that a mobile robot could continue to localize itself in a changing environment using omni-directional vision. In this work we extend this longterm updating mechanism to incorporate a spherical metric representation of the observed visual features for each node in the topological map. Using multi-view geometry we are then able to estimate the heading of the robot, in order to enable navigation between the nodes of the map, and to simultaneously adapt the spherical view representation in response to environmental changes. The results demonstrate the persistent performance of the proposed system in a long-term experiment.

Long-term experiments with an adaptive spherical view representation for navigation in changing environments

Real-world environments such as houses and offices change over time, meaning that a mobile robot’s map will become out of date. In this work, we introduce a method to update the reference views in a hybrid metrictopological map so that a mobile robot can continue to localize itself in a changing environment. The updating mechanism, based on the multi-store model of human memory, incorporates a spherical metric representation of the observed visual features for each node in the map, which enables the robot to estimate its heading and navigate using multi-view geometry, as well as representing the local 3D geometry of the environment. A series of experiments demonstrate the persistence performance of the proposed system in real changing environments, including analysis of the long-term stability.

Toward an object-based semantic memory for long-term operation of mobile service robots

Throughout a lifetime of operation, a mobile service robot needs to acquire, store and update its knowledge of a working environment. This includes the ability to identify and track objects in different places, as well as using this information for interaction with humans. This paper introduces a long-term updating mechanism, inspired by the modal model of human memory, to enable a mobile robot to maintain its knowledge of a changing environment. The memory model is integrated with a hybrid map that represents the global topology and local geometry of the environment, as well as the respective 3D location of objects. We aim to enable the robot to use this knowledge to help humans by suggesting the most likely locations of specific objects in its map. An experiment using omni-directional vision demonstrates the ability to track the movements of several objects in a dynamic environment over an extended period of time.

Very high resolution optical satellites for DEM generation : a review

The advent of very high resolution (VHR) optical satellites capable of producing stereo images led to a new era in extracting digital elevation model which commenced with the launch of IKONOS. The special specifications of VHR optical satellites besides, the significant economic profit stimulated other countries and companies to have their constellations such as EROS-A1 and EROS-B1 as the cooperation between Israel and ImageSat. QuickBird, WorldView-1 and WorldVew-2 were launched by DigitalGlobe. ALOS and GeoEye-1 were offered by Japan and GeoEye Respectively. In addition to aforementioned satellites, Indian and South Korea initiated their own constellation by launching CartoSat-1 and KOPOSAT-2 respectively.The availability of all so-called satellites make a huge market of stereo images for extracting of digital elevation model and other correspondent applications such as, producing orthorectifcatin images and updating maps. Therefore, there is a need for a comprehensive comparison for scientific and commercial clients to choose appropriate satellite images and methods of generating digital elevation model to obtain optimum results. This paper will thus give a review about the specifications of VHR optical satellites. Then it will discuss the automatic elaborating of digital elevation model. Finally an overview of studies and corresponding results is reported.

Refining user and item profiles based on multidimensional data for top-n item recommendation

In recommender systems based on multidimensional data, additional metadata provides algorithms with more information for better understanding the interaction between users and items. However, most of the profiling approaches in neighbourhood-based recommendation approaches for multidimensional data merely split or project the dimensional data and lack the consideration of latent interaction between the dimensions of the data. In this paper, we propose a novel user/item profiling approach for Collaborative Filtering (CF) item recommendation on multidimensional data. We further present incremental profiling method for updating the profiles. For item recommendation, we seek to delve into different types of relations in data to understand the interaction between users and items more fully, and propose three multidimensional CF recommendation approaches for top-N item recommendations based on the proposed user/item profiles. The proposed multidimensional CF approaches are capable of incorporating not only localized relations of user-user and/or item-item neighbourhoods but also latent interaction between all dimensions of the data. Experimental results show significant improvements in terms of recommendation accuracy.

Novel non-linear elastic structural analysis with generalised transverse element loads using a refined finite element

In the finite element modelling of structural frames, external loads such as wind loads, dead loads and imposed loads usually act along the elements rather than at the nodes only. Conventionally, when an element is subjected to these general transverse element loads, they are usually converted to nodal forces acting at the ends of the elements by either lumping or consistent load approaches. In addition, it is especially important for an element subjected to the first- and second-order elastic behaviour, to which the steel structure is critically prone to; in particular the thin-walled steel structures, when the stocky element section may be generally critical to the inelastic behaviour. In this sense, the accurate first- and second-order elastic displacement solutions of element load effect along an element is vitally crucial, but cannot be simulated using neither numerical nodal nor consistent load methods alone, as long as no equilibrium condition is enforced in the finite element formulation, which can inevitably impair the structural safety of the steel structure particularly. It can be therefore regarded as a unique element load method to account for the element load nonlinearly. If accurate displacement solution is targeted for simulating the first- and second-order elastic behaviour on an element on the basis of sophisticated non-linear element stiffness formulation, the numerous prescribed stiffness matrices must indispensably be used for the plethora of specific transverse element loading patterns encountered. In order to circumvent this shortcoming, the present paper proposes a numerical technique to include the transverse element loading in the non-linear stiffness formulation without numerous prescribed stiffness matrices, and which is able to predict structural responses involving the effect of first-order element loads as well as the second-order coupling effect between the transverse load and axial force in the element. This paper shows that the principle of superposition can be applied to derive the generalized stiffness formulation for element load effect, so that the form of the stiffness matrix remains unchanged with respect to the specific loading patterns, but with only the magnitude of the loading (element load coefficients) being needed to be adjusted in the stiffness formulation, and subsequently the non-linear effect on element loadings can be commensurate by updating the magnitude of element load coefficients through the non-linear solution procedures. In principle, the element loading distribution is converted into a single loading magnitude at mid-span in order to provide the initial perturbation for triggering the member bowing effect due to its transverse element loads. This approach in turn sacrifices the effect of element loading distribution except at mid-span. Therefore, it can be foreseen that the load-deflection behaviour may not be as accurate as those at mid-span, but its discrepancy is still trivial as proved. This novelty allows for a very useful generalised stiffness formulation for a single higher-order element with arbitrary transverse loading patterns to be formulated. Moreover, another significance of this paper is placed on shifting the nodal response (system analysis) to both nodal and element response (sophisticated element formulation). For the conventional finite element method, such as the cubic element, all accurate solutions can be only found at node. It means no accurate and reliable structural safety can be ensured within an element, and as a result, it hinders the engineering applications. The results of the paper are verified using analytical stability function studies, as well as with numerical results reported by independent researchers on several simple frames.

Improving wound management for residents in Residential Aged Care Facilities: National dissemination and implementation of the evidence based Champions for Skin Integrity Program

Overview The incidence of skin tears, pressure injuries and chronic wounds increases with age [1-4] and therefore is a serious issue for staff and residents in Residential Aged Care Facilities (RACFs). A pilot project funded in Round 2 of the Encouraging Best Practice in Residential Aged Care (EBPRAC) program by the then Australian Government Department of Health and Ageing found that a substantial proportion of residents in aged care facilities experienced pressure injuries, skin tears or chronic wounds. It also found the implementation of the evidence based Champions for Skin Integrity (CSI) model of wound care was successful in significantly decreasing the prevalence and severity of wounds in residents, improving staff skills and knowledge of evidence based wound management, increasing staff confidence with wound management, increasing implementation of evidence based wound management and prevention strategies, and increasing staff awareness of their roles in evidence based wound care at all levels [5]. Importantly, during the project, the project team developed a resource kit on evidence based wound management. Two critical recommendations resulting from the project were that: - The CSI model or a similar strategic approach should be implemented in RACFs to facilitate the uptake of evidence based wound management and prevention - The resource kit on evidence based wound management should be made available to all Residential Aged Care Facilities and interested parties A proposal to disseminate or rollout the CSI model of wound care to all RACFs across Australia was submitted to the department in 2012. The department approved funding from the Aged Care Services Improvement Healthy Ageing Grant (ACSIHAG) at the same time as the Round 3 of the Encouraging Better Practice in Aged Care (EBPAC) program. The dissemination involved two crucial elements: 1. The updating, refining and distribution of a Champions for Skin Integrity Resource Kit, more commonly known as a CSI Resource Kit and 2. The presentation of intensive one day Promoting Healthy Skin “Train the Trainer” workshops in all capital cities and major regional towns across Australia Due to demand, the department agreed to fund a second round of workshops focussing on regional centres and the completion date was extended to accommodate the workshops. Later, the department also decided to host a departmental website for a number of clinical domains, including wound management, so that staff from the residential aged care sector had easy access to a central repository of helpful clinical resource material that could be used for improving the health and wellbeing of their older adults, consumers and carers. CSI Resource Kit Upgrade and Distribution: At the start of the project, a full evidence review was carried out on the material produced during the EBPRAC-CSI Stage 1 project and the relevant evidence based changes were made to the documentation. At the same time participants in the EBPRAC-CSI Stage 1 project were interviewed for advice on how to improve the resource material. Following this the documentation, included in the kit, was sent to independent experts for peer review. When this process was finalised, a learning designer and QUT’s Visual Communications Services were engaged to completely refine and update the design of the resources, and combined resource kit with the goal of keeping the overall size of the kit suitable for bookshelf mounting and the cost at reasonable levels. Both goals were achieved in that the kit is about the same size as a 25 mm A4 binder and costs between $19.00 and $28.00 per kit depending on the size of the print run. The dissemination of the updated CSI resource kit was an outstanding success. Demand for the kits was so great that a second print run of 2,000 kits was arranged on top of the initial print run of 4,000 kits. All RACFs across Australia were issued with a kit, some 2,740 in total. Since the initial distribution another 1,100 requests for kits has been fulfilled as well as 1,619 kits being distributed to participants at the Promoting Healthy Skin workshops. As the project was winding up a final request email was sent to all workshop participants asking if they required additional kits or resources to distribute the remaining kits and resources. This has resulted in requests for 200 additional kits and resources. Feedback from the residential aged care sector and other clinical providers who have interest in wound care has been very positive regarding the utility of the kit, (see Appendix 4). Promoting Healthy Skin Workshops The workshops also exceeded the project team’s initial objective. Our goal of providing workshop training for staff from one in four facilities and 450 participants was exceeded, with overwhelming demand for workshop places resulting in the need to provide a second round of workshops across Australia. At the completion of the second round, 37 workshops had been given, with 1286 participants, representing 835 facilities. A number of strategies were used to promote the workshops ranging from invitations included in the kit, to postcard mail-outs, broadcast emailing to all facilities and aged care networks and to articles and paid advertising in aged care journals. The most effective method, by far, was directly phoning the facilities. This enabled the caller to contact the relevant staff member and enlist their support for the workshop. As this is a labour intensive exercise, it was only used where numbers needed bolstering, with one venue rising from 3 registrants before the calls to 53 registrants after. The workshops were aimed at staff who had the interest and the capability of implementing evidence-based wound management within their facility or organisation. This targeting was successful in that a large proportion (68%) of participants were Registered Nurses, Nurse Managers, Educators or Consultants. Twenty percent were Endorsed Enrolled Nurses with the remaining 12% being made up of Personal Care Workers or Allied Health Professionals. To facilitate long term sustainability, the workshop employed train-the-trainer strategies. Feedback from the EBPRAC-CSI Stage 1 interviews was used in the development of workshop content. In addition, feedback from the workshop conducted at the end of the EBPRAC-CSI Stage 1 project suggested that change management and leadership training should be included in the workshops. The program was trialled in the first workshop conducted in Brisbane and then rolled out across Australia. Participants were asked to complete pre and post workshop surveys at the beginning and end of the workshop to determine how knowledge and confidence improved over the day. Results from the pre and post surveys showed significant improvements in the level of confidence in attendees’ ability to implement evidence based wound management. The results also indicated a significant increase in the level of confidence in ability to implement change within their facility or organisation. This is an important indication that the inclusion of change management/leadership training with clinical instruction can increase staff capacity and confidence in translating evidence into practice. To encourage the transfer of the evidence based content of the workshop into practice, participants were asked to prepare an Action Plan to be followed by a simple one page progress report three months after the workshop. These reports ranged from simple (e.g. skin moisturising to prevent skin tears), to complex implementation plans for introducing the CSI model across the whole organisation. Outcomes described in the project reports included decreased prevalence of skin tears, pressure injuries and chronic wounds, along with increased staff and resident knowledge and resident comfort. As stated above, some organisations prepared large, complex plans to roll out the CSI model across their organisation. These plans included a review of the organisation’s wound care system, policies and procedures, the creation of new processes, the education of staff and clients, uploading education and resource material onto internal electronic platforms and setting up formal review and evaluation processes. The CSI Resources have been enthusiastically sought and incorporated into multiple health care settings, including aged care, acute care, Medicare Local intranets (e.g. Map of Medicine e-pathways), primary health care, community and home care organisations, education providers and New Zealand aged and community health providers. Recommendations: Recommendations for RACFs, aged care and health service providers and government  Skin integrity and the evidence-practice gap in this area should be recognised as a major health issue for health service providers for older adults, with wounds experienced by up to 50% of residents in aged care settings (Edwards et al. 2010). Implementation of evidence based wound care through the Champions for Skin Integrity model in this and the pilot project has demonstrated the prevalence of wounds, wound healing times and wound infections can be halved.  A national program and Centre for Evidence Based Wound Management should be established to: - expand the reach of the model to other aged care facilities and health service providers for older adults - sustain the uptake of models such as the Champions for Skin Integrity (CSI) model - ensure current resources, expertise and training are available for consumers and health care professionals to promote skin integrity for all older adults  Evidence based resources for the CSI program and similar projects should be reviewed and updated every 3 – 4 years as per NH&MRC recommendations  Leadership and change management training is fundamental to increasing staff capacity, at all levels, to promote within-organisation dissemination of skills and knowledge gained from projects providing evidence based training Recommendations for future national dissemination projects  A formal program of opportunities for small groups of like projects to share information and resources, coordinate activities and synergise education programs interactively would benefit future national dissemination projects - Future workshop programs could explore an incentive program to optimise attendance and reduce ‘no shows’ - Future projects should build in the capacity and funding for increased follow-up with workshop attendees, to explore the reasons behind those who are unable to translate workshop learnings into the workplace and identify factors to address these barriers.

Non-destructive structural integrity assessment of a decommissioned rail wagon system

This paper presents a multi-criteria based approach for nondestructive diagnostic structural integrity assessment of a decommissioned flatbed rail wagon (FBRW) used for road bridge superstructure rehabilitation and replacement applications. First, full-scale vibration and static test data sets are employed in a FE model of the FBRW to obtain the best ‘initial’ estimate of the model parameters. Second, the ‘final’ model parameters are predicted using sensitivity-based perturbation analysis without significant difficulties encountered. Consequently, the updated FBRW model is validated using the independent sets of full-scale laboratory static test data. Finally, the updated and validated FE model of the FBRW is used for structural integrity assessment of a single lane FBRW bridge subjected to the Australian bridge design traffic load.

Structural identification of a laboratory-based steel through truss cantilevered bridge with suspended span using a layered genetic algorithm with patternsearch step (GAPS)

Structural identification (St-Id) can be considered as the process of updating a finite element (FE) model of a structural system to match the measured response of the structure. This paper presents the St-Id of a laboratory-based steel through-truss cantilevered bridge with suspended span. There are a total of 600 degrees of freedom (DOFs) in the superstructure plus additional DOFs in the substructure. The St-Id of the bridge model used the modal parameters from a preliminary modal test in the objective function of a global optimisation technique using a layered genetic algorithm with patternsearch step (GAPS). Each layer of the St-Id process involved grouping of the structural parameters into a number of updating parameters and running parallel optimisations. The number of updating parameters was increased at each layer of the process. In order to accelerate the optimisation and ensure improved diversity within the population, a patternsearch step was applied to the fittest individuals at the end of each generation of the GA. The GAPS process was able to replicate the mode shapes for the first two lateral sway modes and the first vertical bending mode to a high degree of accuracy and, to a lesser degree, the mode shape of the first lateral bending mode. The mode shape and frequency of the torsional mode did not match very well. The frequencies of the first lateral bending mode, the first longitudinal mode and the first vertical mode matched very well. The frequency of the first sway mode was lower and that of the second sway mode was higher than the true values, indicating a possible problem with the FE model. Improvements to the model and the St-Id process will be presented at the upcoming conference and compared to the results presented in this paper. These improvements will include the use of multiple FE models in a multi-layered, multi-solution, GAPS St-Id approach.

A Model to Estimate the Population Contributing to the Wastewater Using Samples Collected on Census Day

An important uncertainty when estimating per capita consumption of, for example, illicit drugs by means of wastewater analysis (sometimes referred to as “sewage epidemiology”) relates to the size and variability of the de facto population in the catchment of interest. In the absence of a day-specific direct population count any indirect surrogate model to estimate population size lacks a standard to assess associated uncertainties. Therefore, the objective of this study was to collect wastewater samples at a unique opportunity, that is, on a census day, as a basis for a model to estimate the number of people contributing to a given wastewater sample. Mass loads for a wide range of pharmaceuticals and personal care products were quantified in influents of ten sewage treatment plants (STP) serving populations ranging from approximately 3500 to 500 000 people. Separate linear models for population size were estimated with the mass loads of the different chemical as the explanatory variable: 14 chemicals showed good, linear relationships, with highest correlations for acesulfame and gabapentin. De facto population was then estimated through Bayesian inference, by updating the population size provided by STP staff (prior knowledge) with measured chemical mass loads. Cross validation showed that large populations can be estimated fairly accurately with a few chemical mass loads quantified from 24-h composite samples. In contrast, the prior knowledge for small population sizes cannot be improved substantially despite the information of multiple chemical mass loads. In the future, observations other than chemical mass loads may improve this deficit, since Bayesian inference allows including any kind of information relating to population size.