The ECOS Project. An interactive simulation to promote an ECO-friendly universe.

Custom designed for display on the Cube Installation situated in the new Science and Engineering Centre (SEC) at QUT, the ECOS project is a playful interface that uses real-time weather data to simulate how a five-star energy building operates in climates all over the world. In collaboration with the SEC building managers, the ECOS Project incorporates energy consumption and generation data of the building into an interactive simulation, which is both engaging to users and highly informative, and which invites play and reflection on the roles of green buildings. ECOS focuses on the principle that humans can have both a positive and negative impact on ecosystems with both local and global consequence. The ECOS project draws on the practice of Eco-Visualisation, a term used to encapsulate the important merging of environmental data visualization with the philosophy of sustainability. Holmes (2007) uses the term Eco-Visualisation (EV) to refer to data visualisations that ‘display the real time consumption statistics of key environmental resources for the goal of promoting ecological literacy’. EVs are commonly artifacts of interaction design, information design, interface design and industrial design, but are informed by various intellectual disciplines that have shared interests in sustainability. As a result of surveying a number of projects, Pierce, Odom and Blevis (2008) outline strategies for designing and evaluating effective EVs, including ‘connecting behavior to material impacts of consumption, encouraging playful engagement and exploration with energy, raising public awareness and facilitating discussion, and stimulating critical reflection.’ Consequently, Froehlich (2010) and his colleagues also use the term ‘Eco-feedback technology’ to describe the same field. ‘Green IT’ is another variation which Tomlinson (2010) describes as a ‘field at the juncture of two trends… the growing concern over environmental issues’ and ‘the use of digital tools and techniques for manipulating information.’ The ECOS Project team is guided by these principles, but more importantly, propose an example for how these principles may be achieved. The ECOS Project presents a simplified interface to the very complex domain of thermodynamic and climate modeling. From a mathematical perspective, the simulation can be divided into two models, which interact and compete for balance – the comfort of ECOS’ virtual denizens and the ecological and environmental health of the virtual world. The comfort model is based on the study of psychometrics, and specifically those relating to human comfort. This provides baseline micro-climatic values for what constitutes a comfortable working environment within the QUT SEC buildings. The difference between the ambient outside temperature (as determined by polling the Google Weather API for live weather data) and the internal thermostat of the building (as set by the user) allows us to estimate the energy required to either heat or cool the building. Once the energy requirements can be ascertained, this is then balanced with the ability of the building to produce enough power from green energy sources (solar, wind and gas) to cover its energy requirements. Calculating the relative amount of energy produced by wind and solar can be done by, in the case of solar for example, considering the size of panel and the amount of solar radiation it is receiving at any given time, which in turn can be estimated based on the temperature and conditions returned by the live weather API. Some of these variables can be altered by the user, allowing them to attempt to optimize the health of the building. The variables that can be changed are the budget allocated to green energy sources such as the Solar Panels, Wind Generator and the Air conditioning to control the internal building temperature. These variables influence the energy input and output variables, modeled on the real energy usage statistics drawn from the SEC data provided by the building managers.

A computer image analysis system for microvessel density measurement in solid tumours

Microvessel density (MVD) is a widely used surrogate measure of angiogenesis in pathological specimens and tumour models. Measurement of MVD can be achieved by several methods. Automation of counting methods aims to increase the speed, reliability and reproducibility of these techniques. The image analysis system described here enables MVD measurement to be carried out with minimal expense in any reasonably equipped pathology department or laboratory. It is demonstrated that the system translates easily between tumour types which are suitably stained with minimal calibration. The aim of this paper is to offer this technique to a wider field of researchers in angiogenesis.

A comparison of the histochemical and image-derived proteoglycan content of articular cartilage

There are several methods for determining the proteoglycan content of cartilage in biomechanics experiments. Many of these include assay-based methods and the histochemistry or spectrophotometry protocol where quantification is biochemically determined. More recently a method based on extracting data to quantify proteoglycan content has emerged using the image processing algorithms, e.g., in ImageJ, to process histological micrographs, with advantages including time saving and low cost. However, it is unknown whether or not this image analysis method produces results that are comparable to those obtained from the biochemical methodology. This paper compares the results of a well-established chemical method to those obtained using image analysis to determine the proteoglycan content of visually normal (n=33) and their progressively degraded counterparts with the protocols. The results reveal a strong linear relationship with a regression coefficient (R2) = 0.9928, leading to the conclusion that the image analysis methodology is a viable alternative to the spectrophotometry.

Creating a Sustainability Scorecard as a predictive tool for measuring the complex social, economic and environmental impacts of industries, a case study : assessing the viability and sustainability of the dairy industry

Sustainability is a key driver for decisions in the management and future development of industries. The World Commission on Environment and Development (WCED, 1987) outlined imperatives which need to be met for environmental, economic and social sustainability. Development of strategies for measuring and improving sustainability in and across these domains, however, has been hindered by intense debate between advocates for one approach fearing that efforts by those who advocate for another could have unintended adverse impacts. Studies attempting to compare the sustainability performance of countries and industries have also found ratings of performance quite variable depending on the sustainability indices used. Quantifying and comparing the sustainability of industries across the triple bottom line of economy, environment and social impact continues to be problematic. Using the Australian dairy industry as a case study, a Sustainability Scorecard, developed as a Bayesian network model, is proposed as an adaptable tool to enable informed assessment, dialogue and negotiation of strategies at a global level as well as being suitable for developing local solutions.

Image segmentation and pose estimation of humans in video

This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.

Dealing with shadows : capturing intrinsic scene appearance for image-based outdoor localisation

In outdoor environments shadows are common. These typically strong visual features cause considerable change in the appearance of a place, and therefore confound vision-based localisation approaches. In this paper we describe how to convert a colour image of the scene to a greyscale invariant image where pixel values are a function of underlying material property not lighting. We summarise the theory of shadow invariant images and discuss the modelling and calibration issues which are important for non-ideal off-the-shelf colour cameras. We evaluate the technique with a commonly used robotic camera and an autonomous car operating in an outdoor environment, and show that it can outperform the use of ordinary greyscale images for the task of visual localisation.

Optimal camera planning under versatile user constraints in multi-camera image processing systems

The selection of optimal camera configurations (camera locations, orientations, etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we propose a statistical framework of the problem as well as propose a trans-dimensional simulated annealing algorithm to effectively deal with it. We compare our approach with a state-of-the-art method based on binary integer programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than two alternative heuristics designed to deal with the scalability issue of BIP. Last, we show the versatility of our approach using a number of specific scenarios.

Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Using image quality metrics to detect smoke-affected laser data

Field robots often rely on laser range finders (LRFs) to detect obstacles and navigate autonomously. Despite recent progress in sensing technology and perception algorithms, adverse environmental conditions, such as the presence of smoke, remain a challenging issue for these robots. In this paper, we investigate the possibility to improve laser-based perception applications by anticipating situations when laser data are affected by smoke, using supervised learning and state-of-the-art visual image quality analysis. We propose to train a k-nearest-neighbour (kNN) classifier to recognise situations where a laser scan is likely to be affected by smoke, based on visual data quality features. This method is evaluated experimentally using a mobile robot equipped with LRFs and a visual camera. The strengths and limitations of the technique are identified and discussed, and we show that the method is beneficial if conservative decisions are the most appropriate.

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.

Towards training-free appearance-based localization : probabilistic models for whole-image descriptors

Whole image descriptors have recently been shown to be remarkably robust to perceptual change especially compared to local features. However, whole-image-based localization systems typically rely on heuristic methods for determining appropriate matching thresholds in a particular environment. These environment-specific tuning requirements and the lack of a meaningful interpretation of these arbitrary thresholds limits the general applicability of these systems. In this paper we present a Bayesian model of probability for whole-image descriptors that can be seamlessly integrated into localization systems designed for probabilistic visual input. We demonstrate this method using CAT-Graph, an appearance-based visual localization system originally designed for a FAB-MAP-style probabilistic input. We show that using whole-image descriptors as visual input extends CAT-Graph’s functionality to environments that experience a greater amount of perceptual change. We also present a method of estimating whole-image probability models in an online manner, removing the need for a prior training phase. We show that this online, automated training method can perform comparably to pre-trained, manually tuned local descriptor methods.

Evaluation of MegaVoltage Cone Beam CT image quality with an unmodified Elekta Precise Linac and EPID : a feasibility study

In order to increase the accuracy of patient positioning for complex radiotherapy treatments various 3D imaging techniques have been developed. MegaVoltage Cone Beam CT (MVCBCT) can utilise existing hardware to implement a 3D imaging modality to aid patient positioning. MVCBCT has been investigated using an unmodified Elekta Precise linac and 15 iView amorphous silicon electronic portal imaging device (EPID). Two methods of delivery and acquisition have been investigated for imaging an anthropomorphic head phantom and quality assurance phantom. Phantom projections were successfully acquired and CT datasets reconstructed using both acquisition methods. Bone, tissue and air were 20 clearly resolvable in both phantoms even with low dose (22 MU) scans. The feasibility of MegaVoltage Cone beam CT was investigated using a standard linac, amorphous silicon EPID and a combination of a free open source reconstruction toolkit as well as custom in-house software written in Matlab. The resultant image quality has 25 been assessed and presented. Although bone, tissue and air were resolvable 2 in all scans, artifacts are present and scan doses are increased when compared with standard portal imaging. The feasibility of MVCBCT with unmodified Elekta Precise linac and EPID has been considered as well as the identification of possible areas for future development in artifact correction techniques to 30 further improve image quality.

Moulding them in the industry's image : journalism education's impact on students' professional views

Long-running debates over the value of university-based journalism education have suffered from a lack of empirical foundation, leading to a wide range of assertions both from those who see journalism education playing a crucial role in moulding future journalists and those who do not. Based on a survey of 320 Australian journalism students from six universities across the country, this study provides an account of the professional views these future journalists hold. Findings show that students hold broadly similar priorities in their role perceptions, albeit to different intensities from working journalists. The results point to a relationship between journalism education and the way in which students' views of journalism's watchdog role and its market orientation change over the course of their degree – to the extent that, once they are near completion of their degree, students have been moulded in the image of industry professionals.

Learning detectors quickly with stationary statistics

Computer vision is increasingly becoming interested in the rapid estimation of object detectors. The canonical strategy of using Hard Negative Mining to train a Support Vector Machine is slow, since the large negative set must be traversed at least once per detector. Recent work has demonstrated that, with an assumption of signal stationarity, Linear Discriminant Analysis is able to learn comparable detectors without ever revisiting the negative set. Even with this insight, the time to learn a detector can still be on the order of minutes. Correlation filters, on the other hand, can produce a detector in under a second. However, this involves the unnatural assumption that the statistics are periodic, and requires the negative set to be re-sampled per detector size. These two methods differ chie y in the structure which they impose on the co- variance matrix of all examples. This paper is a comparative study which develops techniques (i) to assume periodic statistics without needing to revisit the negative set and (ii) to accelerate the estimation of detectors with aperiodic statistics. It is experimentally verified that periodicity is detrimental.

Real-time image classification for adaptive mission planning using an Autonomous Underwater Vehicle

Real-time image analysis and classification onboard robotic marine vehicles, such as AUVs, is a key step in the realisation of adaptive mission planning for large-scale habitat mapping in previously unexplored environments. This paper describes a novel technique to train, process, and classify images collected onboard an AUV used in relatively shallow waters with poor visibility and non-uniform lighting. The approach utilises Förstner feature detectors and Laws texture energy masks for image characterisation, and a bag of words approach for feature recognition. To improve classification performance we propose a usefulness gain to learn the importance of each histogram component for each class. Experimental results illustrate the performance of the system in characterisation of a variety of marine habitats and its ability to operate onboard an AUV's main processor suitable for real-time mission planning.