Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Older adults’ safety perceptions of driving situations: Towards a new driving self-regulation scale

The term ‘driving self-restriction’ is used in the road safety literature to describe the behaviour of some older drivers. It includes the notion that older drivers will avoid driving in specific, usually self-identified situations, such as those in which safety is compromised. We sought to identify the situations that older drivers report avoiding; and, to determine the adequacy of a key measure of such behaviour. A sample of 75 drivers aged 65 years and older completed Baldock et al.’s modification of the Driving Habits Questionnaire avoidance items (Baldock et al., 2006), the Driving Behaviour Questionnaire, and open-ended items that elicited written descriptions of the most and least safe driving situation. Consistent with previous results, we found a relatively low level of driving self-restriction and infrequent episodes of aggressive violations. However, when combined with the situation descriptions, these data suggest that Driving Habits Questionnaire did not cover all of the situations that older drivers might choose avoid. We suggest that a new avoidance scale is needed and we present a new item pool that may be used for this purpose.

Randomised controlled trial of an automated, interactive telephone intervention to improve type 2 diabetes self-management (Telephone-Linked Care Diabetes Project) : study protocol

Background: An estimated 285 million people worldwide have diabetes and its prevalence is predicted to increase to 439 million by 2030. For the year 2010, it is estimated that 3.96 million excess deaths in the age group 20-79 years are attributable to diabetes around the world. Self-management is recognised as an integral part of diabetes care. This paper describes the protocol of a randomised controlled trial of an automated interactive telephone system aiming to improve the uptake and maintenance of essential diabetes self-management behaviours. ---------- Methods/Design: A total of 340 individuals with type 2 diabetes will be randomised, either to the routine care arm, or to the intervention arm in which participants receive the Telephone-Linked Care (TLC) Diabetes program in addition to their routine care. The intervention requires the participants to telephone the TLC Diabetes phone system weekly for 6 months. They receive the study handbook and a glucose meter linked to a data uploading device. The TLC system consists of a computer with software designed to provide monitoring, tailored feedback and education on key aspects of diabetes self-management, based on answers voiced or entered during the current or previous conversations. Data collection is conducted at baseline (Time 1), 6-month follow-up (Time 2), and 12-month follow-up (Time 3). The primary outcomes are glycaemic control (HbA1c) and quality of life (Short Form-36 Health Survey version 2). Secondary outcomes include anthropometric measures, blood pressure, blood lipid profile, psychosocial measures as well as measures of diet, physical activity, blood glucose monitoring, foot care and medication taking. Information on utilisation of healthcare services including hospital admissions, medication use and costs is collected. An economic evaluation is also planned.---------- Discussion: Outcomes will provide evidence concerning the efficacy of a telephone-linked care intervention for self-management of diabetes. Furthermore, the study will provide insight into the potential for more widespread uptake of automated telehealth interventions, globally.

A Taxonomy of image matching techniques for stereo vision

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Applications of stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics, industrial automation and stereomicroscopy. A key issue in stereo vision is that of image matching, or identifying corresponding points in a stereo pair. The difference in the positions of corresponding points in image coordinates is termed the parallax or disparity. When the orientation of the two cameras is known, corresponding points may be projected back to find the location of the original object point in world coordinates. Matching techniques are typically categorised according to the nature of the matching primitives they use and the matching strategy they employ. This report provides a detailed taxonomy of image matching techniques, including area based, transform based, feature based, phase based, hybrid, relaxation based, dynamic programming and object space methods. A number of area based matching metrics as well as the rank and census transforms were implemented, in order to investigate their suitability for a real-time stereo sensor for mining automation applications. The requirements of this sensor were speed, robustness, and the ability to produce a dense depth map. The Sum of Absolute Differences matching metric was the least computationally expensive; however, this metric was the most sensitive to radiometric distortion. Metrics such as the Zero Mean Sum of Absolute Differences and Normalised Cross Correlation were the most robust to this type of distortion but introduced additional computational complexity. The rank and census transforms were found to be robust to radiometric distortion, in addition to having low computational complexity. They are therefore prime candidates for a matching algorithm for a stereo sensor for real-time mining applications. A number of issues came to light during this investigation which may merit further work. These include devising a means to evaluate and compare disparity results of different matching algorithms, and finding a method of assigning a level of confidence to a match. Another issue of interest is the possibility of statistically combining the results of different matching algorithms, in order to improve robustness.

The role of assisted self-help in services for alcohol-related disorders

Potentially harmful substance use is common, but many affected people do not receive treatment. Brief face-to-face treatments show impact, as do strategies to assist self-help remotely, by using bibliotherapies, computers or mobile phones. Remotely delivered treatments offer more sustained and multifaceted support than brief interventions, and they show a substantial cost advantage as users increase in number. They may also build skills, confidence and treatment fidelity in providers who use them in sessions. Engagement and retention remain challenges, but electronic treatments show promise in engaging younger populations. Recruitment may be assisted by integration with community campaigns or brief opportunistic interventions. However, routine use of assisted self-help by standard services faces significant challenges. Strategies to optimize adoption are discussed. ----- ----- Research Highlights: ► Many people with risky or problematic drinking do not currently receive treatment. ► Assisted self-help has a significant impact and can be delivered at low cost. ► Maximal effects from assisted self-help require engagement of potential users. ► Marketing campaigns and integration into existing service models may assist.

Applying ISOMAP to the learning of hyperspectral image

In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive. We propose the use of Isomap, a non-linear manifold learning technique combined with Expectation Maximisation in graphical probabilistic models for learning and classification. Isomap is used to find the underlying manifold of the training data. This low dimensional representation of the hyperspectral data facilitates the learning of a Gaussian Mixture Model representation, whose joint probability distributions can be calculated offline. The learnt model is then applied to the hyperspectral image at runtime and data classification can be performed.

meso-Porphyrinylphosphine Oxides: Mono- and Bidentate Ligands for Supramolecular Chemistry and the Crystal Structures of Monomeric [10,20-Diphenylporphyrinatonickel(II)-5,15-diyl]-bis-[P(O)Ph2] and Polymeric Self-Coordinated ([10,20-Diphenylporphyrinatozinc(II)-5,15-diyl]-bis-[P(O)Ph2])

A series of porphyrins substituted in one or two meso-positions by diphenylphosphine oxide groups has been prepared by the palladium catalysed reaction of diphenylphosphine or its oxide with the corresponding bromoporphyrins. Compounds {MDPP-[P(O)Ph2]n} (M = H2, Ni, Zn; H2DPP = 5,15-diphenylporphyrin; n = 1, 2) were isolated in yields of 60-95%. The reaction is believed to proceed via the conventional oxidative addition, phosphination and reductive elimination steps, as the stoichiometric reaction of η1-palladio(II) porphyrin [PdBr(H2DPP)(dppe)] (H2DPP = 5,15-diphenylporphyrin; dppe = 1,2-bis(diphenylphosphino)ethane) with diphenylphosphine oxide also results in the desired mono-porphyrinylphosphine oxide [H2DPP-P(O)Ph2]. Attempts to isolate the tertiary phosphines failed due to their extreme air-sensitivity. Variable temperature 1H NMR studies of [H2DPP-P(O)Ph2] revealed an intrinsic lack of symmetry, while fluorescence spectroscopy showed that the phosphine oxide group does not behave as a "heavy atom" quencher. The electron withdrawing effect of the phosphine oxide group was confirmed by voltammetry. The ligands were characterised by multinuclear NMR and UV-visible spectroscopy as well as mass spectrometry. Single crystal X-ray crystallography showed that the bis(phosphine oxide) nickel(II) complex {[NiDPP-[P(O)Ph2]2} is monomeric in the solid state, with a ruffled porphyrin core and the two P=O fragments on the same side of the average plane of the molecule. On the other hand, the corresponding zinc(II) complex formed infinite chains through coordination of one Ph2PO substituent to the neighbouring zinc porphyrin through an almost linear P=O---Zn unit, leaving the other Ph2PO group facing into a parallel channel filled with disordered water molecules. These new phosphine oxides are attractive ligands for supramolecular porphyrin chemistry.

Humanitarianism or self-serving hypocrisy? : the provision of aid to South Africa under the Hawke-Keating and Howard governments

General perceptions of foreign aid commonly engender images of humanitarianism and altruism, whereby the humanitarian needs of the recipient of development assistance are of the utmost priority of the aid donor. However, the Australian governments led by Hawke, Keating and Howard often gave humanitarianism a low emphasis, frequently placing Australia’s own foreign policy and economic concerns at the forefront of aid allocation – often unashamedly. This self-interest met through aid meant that most was provided to Australia’s regional neighbourhood, neglecting some of the poorest, most struggling states, including South Africa. Other issues and events, including the Cold War, apartheid, terrorism and HIV/AIDS also affected Australia’s aid policy; mostly, they were used as excuses to limit aid to states like South Africa.

Digital image processing techniques for pavement macro-texture analysis

Road surface macro-texture is an indicator used to determine the skid resistance levels in pavements. Existing methods of quantifying macro-texture include the sand patch test and the laser profilometer. These methods utilise the 3D information of the pavement surface to extract the average texture depth. Recently, interest in image processing techniques as a quantifier of macro-texture has arisen, mainly using the Fast Fourier Transform (FFT). This paper reviews the FFT method, and then proposes two new methods, one using the autocorrelation function and the other using wavelets. The methods are tested on pictures obtained from a pavement surface extending more than 2km's. About 200 images were acquired from the surface at approx. 10m intervals from a height 80cm above ground. The results obtained from image analysis methods using the FFT, the autocorrelation function and wavelets are compared with sensor measured texture depth (SMTD) data obtained from the same paved surface. The results indicate that coefficients of determination (R2) exceeding 0.8 are obtained when up to 10% of outliers are removed.

Effects of reduced contrast on the perception and control of speed when driving

Misperception of speed under low-contrast conditions has been identified as a possible contributor to motor vehicle crashes in fog. To test this hypothesis, we investigated the effects of reduced contrast on drivers’ perception and control of speed while driving under real-world conditions. Fourteen participants drove around a 2.85 km closed road course under three visual conditions: clear view and with two levels of reduced contrast created by diffusing filters on the windscreen and side windows. Three dependent measures were obtained, without view of the speedometer, on separate laps around the road course: verbal estimates of speed; adjustment of speed to instructed levels (25 to 70 km h-1); and estimation of minimum stopping distance. The results showed that drivers traveled more slowly under low-contrast conditions. Reduced contrast had little or no effect on either verbal judgments of speed or estimates of minimum stopping distance. Speed adjustments were significantly slower under low-contrast than clear conditions, indicating that, contrary to studies of object motion, drivers perceived themselves to be traveling faster under conditions of reduced contrast. Under real-world driving conditions, drivers’ ability to perceive and control their speed was not adversely affected by large variations in the contrast of their surroundings. These findings suggest that perceptions of self-motion and object motion involve neural processes that are differentially affected by variations in stimulus contrast as encountered in fog.

The role of mother-centered factors influencing the complex social behaviour of breastfeeding : social support and self-efficacy

This research investigated the role of mother-centred issues that influence breastfeeding behaviours. The need for social marketing research for breastfeeding is indicated by the fact that despite evidence of the health benefits to both the infant and mother of longer breastfeeding duration, rates in developed countries have failed to increase in recent decades. Breastfeeding is a complex behaviour that for many women involves barriers that influence their commitment to continue breastfeeding. Structural equation modelling was used on a sample of 405 respondents to an online survey. The analysis revealed that personal social support had a significant impact on breastfeeding self-efficacy, which in turn had a significant impact on breastfeeding behaviour. The findings and implications for both social marketing theory and practice are discussed.

Hysteresis modeling of Magneto-Rheological (MR) fluid damper by self tuning fuzzy control

Magneto-rheological (MR) fluid damper is a semi-active control device that has recently received more attention by the vibration control community. But inherent nonlinear hysteresis character of magneto-rheological fluid dampers is one of the challenging aspects for utilizing this device to achieve high system performance. So the development of accurate model is necessary to take the advantage their unique characteristics. Research by others [3] has shown that a system of nonlinear differential equations can successfully be used to describe the hysteresis behavior of the MR damper. The focus of this paper is to develop an alternative method for modeling a damper in the form of centre average fuzzy interference system, where back propagation learning rules are used to adjust the weight of network. The inputs for the model are used from the experimental data. The resulting fuzzy interference system is satisfactorily represents the behavior of the MR fluid damper with reduced computational requirements. Use of the neuro-fuzzy model increases the feasibility of real time simulation.

Aurora : an illustrated novella

Aurora, an illustrated novella, is a retelling of the classic fairytale Sleeping Beauty, set on the Australian coast around the grounds of the family lighthouse. Instead of following in the footsteps of tradition, this tale focuses on the long time Aurora is cursed to sleep by the malevolent Minerva; we follow Aurora as she voyages into the unconscious. Hunted by Minerva through the shifting landscape of her dreams, Aurora is dogged by a nagging pull towards the light—there is something she has left behind. Eventually, realising she must face Minerva to break the curse, they stage a battle of the minds in which Aurora triumphs, having grasped the power of her thoughts, her words. Aurora, an Australian fairytale, is a story of self-empowerment, the ability to shape destiny and the power of the mind. The exegesis examines a two-pronged question: is the illustrated book for young adults—graphic novel—relevant to a contemporary readership, and, is the graphic novel, where text and image intersect, a suitably specular genre in which to explore the unconscious? It establishes the language of the unconscious and the meaning of the term ‘graphic novel’, before investigating the place of the illustrated book for an older readership in a contemporary market, particularly exploring visual literacy and the way text and image—a hybrid narrative—work together. It then studies the aptitude of graphic literature to representing the unconscious and looks at two pioneers of the form: Audrey Niffenegger, specifically her visual novel The Three Incestuous Sisters, and Shaun Tan, and his graphic novel The Arrival. Finally, it reflects upon the creative work, Aurora, in light of three concerns: how best to develop a narrative able to relay the dreaming story; how to bestow a certain ‘Australianess’ upon the text and images; and the dilemma of designing an illustrated book for an older readership.

A methodology for object identification and tracking in construction based on spatial modeling and image matching techniques

Understanding the motion characteristics of on-site objects is desirable for the analysis of construction work zones, especially in problems related to safety and productivity studies. This article presents a methodology for rapid object identification and tracking. The proposed methodology contains algorithms for spatial modeling and image matching. A high-frame-rate range sensor was utilized for spatial data acquisition. The experimental results indicated that an occupancy grid spatial modeling algorithm could quickly build a suitable work zone model from the acquired data. The results also showed that an image matching algorithm is able to find the most similar object from a model database and from spatial models obtained from previous scans. It is then possible to use the matched information to successfully identify and track objects.

Modeling object identification and tracking errors on image-based safety assessment of earthmoving operations

Object identification and tracking have become critical for automated on-site construction safety assessment. The primary objective of this paper is to present the development of a testbed to analyze the impact of object identification and tracking errors caused by data collection devices and algorithms used for safety assessment. The testbed models workspaces for earthmoving operations and simulates safety-related violations, including speed limit violations, access violations to dangerous areas, and close proximity violations between heavy machinery. Three different cases were analyzed based on actual earthmoving operations conducted at a limestone quarry. Using the testbed, the impacts of device and algorithm errors were investigated for safety planning purposes.