Hessian-based affine adaptation of salient local image features

Affine covariant local image features are a powerful tool for many applications, including matching and calibrating wide baseline images. Local feature extractors that use a saliency map to locate features require adaptation processes in order to extract affine covariant features. The most effective extractors make use of the second moment matrix (SMM) to iteratively estimate the affine shape of local image regions. This paper shows that the Hessian matrix can be used to estimate local affine shape in a similar fashion to the SMM. The Hessian matrix requires significantly less computation effort than the SMM, allowing more efficient affine adaptation. Experimental results indicate that using the Hessian matrix in conjunction with a feature extractor that selects features in regions with high second order gradients delivers equivalent quality correspondences in less than 17% of the processing time, compared to the same extractor using the SMM.

Towards semantic search and inference in electronic medical records : an approach using concept-based information retrieval

Background This paper presents a novel approach to searching electronic medical records that is based on concept matching rather than keyword matching. Aim The concept-based approach is intended to overcome specific challenges we identified in searching medical records. Method Queries and documents were transformed from their term-based originals into medical concepts as defined by the SNOMED-CT ontology. Results Evaluation on a real-world collection of medical records showed our concept-based approach outperformed a keyword baseline by 25% in Mean Average Precision. Conclusion The concept-based approach provides a framework for further development of inference based search systems for dealing with medical data.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

Integrated vision-based attitude estimation

For many years, computer vision has lured researchers with promises of a low-cost, passive, lightweight and information-rich sensor suitable for navigation purposes. The prime difficulty in vision-based navigation is that the navigation solution will continually drift with time unless external information is available, whether it be cues from the appearance of the scene, a map of features (whether built online or known a priori), or from an externally-referenced sensor. It is not merely position that is of interest in the navigation problem. Attitude (i.e. the angular orientation of a body with respect to a reference frame) is integral to a visionbased navigation solution and is often of interest in its own right (e.g. flight control). This thesis examines vision-based attitude estimation in an aerospace environment, and two methods are proposed for constraining drift in the attitude solution; one through a novel integration of optical flow and the detection of the sky horizon, and the other through a loosely-coupled integration of Visual Odometry and GPS position measurements. In the first method, roll angle, pitch angle and the three aircraft body rates are recovered though a novel method of tracking the horizon over time and integrating the horizonderived attitude information with optical flow. An image processing front-end is used to select several candidate lines in a image that may or may not correspond to the true horizon, and the optical flow is calculated for each candidate line. Using an Extended Kalman Filter (EKF), the previously estimated aircraft state is propagated using a motion model and a candidate horizon line is associated using a statistical test based on the optical flow measurements and location of the horizon in the image. Once associated, the selected horizon line, along with the associated optical flow, is used as a measurement to the EKF. To evaluate the accuracy of the algorithm, two flights were conducted, one using a highly dynamic Uninhabited Airborne Vehicle (UAV) in clear flight conditions and the other in a human-piloted Cessna 172 in conditions where the horizon was partially obscured by terrain, haze and smoke. The UAV flight resulted in pitch and roll error standard deviations of 0.42° and 0.71° respectively when compared with a truth attitude source. The Cessna 172 flight resulted in pitch and roll error standard deviations of 1.79° and 1.75° respectively. In the second method for estimating attitude, a novel integrated GPS/Visual Odometry (GPS/VO) navigation filter is proposed, using a structure similar to a classic looselycoupled GPS/INS error-state navigation filter. Under such an arrangement, the error dynamics of the system are derived and a Kalman Filter is developed for estimating the errors in position and attitude. Through similar analysis to the GPS/INS problem, it is shown that the proposed filter is capable of recovering the complete attitude (i.e. pitch, roll and yaw) of the platform when subjected to acceleration not parallel to velocity for both the monocular and stereo variants of the filter. Furthermore, it is shown that under general straight line motion (e.g. constant velocity), only the component of attitude in the direction of motion is unobservable. Numerical simulations are performed to demonstrate the observability properties of the GPS/VO filter in both the monocular and stereo camera configurations. Furthermore, the proposed filter is tested on imagery collected using a Cessna 172 to demonstrate the observability properties on real-world data. The proposed GPS/VO filter does not require additional restrictions or assumptions such as platform-specific dynamics, map-matching, feature-tracking, visual loop-closing, gravity vector or additional sensors such as an IMU or magnetic compass. Since no platformspecific dynamics are required, the proposed filter is not limited to the aerospace domain and has the potential to be deployed in other platforms such as ground robots or mobile phones.

Strategizing public sector human resource management : the implications of working network

Networks have come to the fore as a means by which government can achieve its strategic objectives, particularly when addressing complex or “wicked” issues. Such joined-up arrangements differ in their operations from other forms of organizing as they require collaborative effort to deliver the collaborative advantage. Strategic Human Resource Management is concerned with the matching of human resource practices to the strategic direction of organizations. It is argued that the strategic direction of government has been towards network involvement and that, as a result, a reconfiguration of Human Resource Management practices is needed to support this new direction. Drawing on eight network case studies findings are presented in relation to the roles government is expected to play in networks and conclusions are drawn about what types of human resource management practices would best support those roles. Implications for Strategic Human Resource Management are posited.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

Can you describe him for me? A technique for semantic person search in video

From a law enforcement standpoint, the ability to search for a person matching a semantic description (i.e. 1.8m tall, red shirt, jeans) is highly desirable. While a significant research effort has focused on person re-detection (the task of identifying a previously observed individual in surveillance video), these techniques require descriptors to be built from existing image or video observations. As such, person re-detection techniques are not suited to situations where footage of the person of interest is not readily available, such as a witness reporting a recent crime. In this paper, we present a novel framework that is able to search for a person based on a semantic description. The proposed approach uses size and colour cues, and does not require a person detection routine to locate people in the scene, improving utility in crowded conditions. The proposed approach is demonstrated with a new database that will be made available to the research community, and we show that the proposed technique is able to correctly localise a person in a video based on a simple semantic description.

Analysis of genome survey sequences and SSR marker development for Siamese Mud Carp, Henicorhynchus siamensis, using 454 Pyrosequencing

Siamese mud carp (Henichorynchus siamensis) is a freshwater teleost of high economic importance in the Mekong River Basin. However, genetic data relevant for delineating wild stocks for management purposes currently are limited for this species. Here, we used 454 pyrosequencing to generate a partial genome survey sequence (GSS) dataset to develop simple sequence repeat (SSR) markers from H. siamensis genomic DNA. Data generated included a total of 65,954 sequence reads with average length of 264 nucleotides, of which 2.79% contain SSR motifs. Based on GSS-BLASTx results, 10.5% of contigs and 8.1% singletons possessed significant similarity (E value < 10–5) with the majority matching well to reported fish sequences. KEGG analysis identified several metabolic pathways that provide insights into specific potential roles and functions of sequences involved in molecular processes in H. siamensis. Top protein domains detected included reverse transcriptase and the top putative functional transcript identified was an ORF2-encoded protein. One thousand eight hundred and thirty seven sequences containing SSR motifs were identified, of which 422 qualified for primer design and eight polymorphic loci have been tested with average observed and expected heterozygosity estimated at 0.75 and 0.83, respectively. Regardless of their relative levels of polymorphism and heterozygosity, microsatellite loci developed here are suitable for further population genetic studies in H. siamensis and may also be applicable to other related taxa.

Spatial and temporal distribution of falciparum malaria in China

Background: Falciparum malaria is the most deadly among the four main types of human malaria. Although great success has been achieved since the launch of the National Malaria Control Programme in 1955, malaria remains a serious public health problem in China. This paper aimed to analyse the geographic distribution, demographic patterns and time trends of falciparum malaria in China. Methods: The annual numbers of falciparum malaria cases during 1992–2003 and the individual case reports of each clinical falciparum malaria during 2004–2005 were extracted from communicable disease information systems in China Center for Diseases Control and Prevention. The annual number of cases and the annual incidence were mapped by matching them to corresponding province- and county-level administrative units in a geographic information system. The distribution of falciparum malaria by age, gender and origin of infection was analysed. Time-series analysis was conducted to investigate the relationship between the falciparum malaria in the endemic provinces and the imported falciparum malaria in non-endemic provinces. Results: Falciparum malaria was endemic in two provinces of China during 2004–05. Imported malaria was reported in 26 non-endemic provinces. Annual incidence of falciparum malaria was mapped at county level in the two endemic provinces of China: Yunnan and Hainan. The sex ratio (male vs. female) for the number of cases in Yunnan was 1.6 in the children of 0–15 years and it reached 5.7 in the adults over 15 years of age. The number of malaria cases in Yunnan was positively correlated with the imported malaria of concurrent months in the non-endemic provinces. Conclusion: The endemic area of falciparum malaria in China has remained restricted to two provinces, Yunnan and Hainan. Stable transmission occurs in the bordering region of Yunnan and the hilly-forested south of Hainan. The age and gender distribution in the endemic area is characterized by the predominance of adult men cases. Imported falciparum malaria in the non-endemic area of China, affected mainly by the malaria transmission in Yunnan, has increased both spatially and temporally. Specific intervention measures targeted at the mobile population groups are warranted.

Frame-rate stereopsis using non-parametric transforms and programmable logic

A frame-rate stereo vision system, based on non-parametric matching metrics, is described. Traditional metrics, such as normalized cross-correlation, are expensive in terms of logic. Non-parametric measures require only simple, parallelizable, functions such as comparators, counters and exclusive-or, and are thus very well suited to implementation in reprogrammable logic.

Applying market design theory to 'greyfields' housing supply

This paper examines whether innovation in market design can address persistent problems of housing choice and affordability in the ageing inner and middle suburbs of Australian cities. Despite policy consensus that urban intensification of these low density, ‘greyfield’ areas should be able to deliver positive social, economic and environmental outcomes, existing models of development have not increased housing stock or delivered adequate gains in sustainability, affordability or diversity of dwellings in greyfield localities. We argue that application of smart market and matching market principles to the supply of multi-unit housing can unlock land, reduce development costs and improve design.

Candidate radial-inflow turbines and high-density working fluids for geothermal power systems

Optimisation of Organic Rankine Cycle (ORCs) for binary-cycle geothermal applications could play a major role in determining the competitiveness of low to moderate temperature geothermal resources. Part of this optimisation process is matching cycles to a given resource such that power output can be maximised. Two major and largely interrelated components of the cycle are the working fluid and the turbine. Both components need careful consideration: the selection of working fluid and appropriate operating conditions as well as optimisation of the turbine design for those conditions will determine the amount of power that can be extracted from a resource. In this paper, we present the rationale for the use of radial-inflow turbines for ORC applications and the preliminary design of several radial-inflow machines based on a number of promising ORC systems that use five different working fluids: R134a, R143a, R236fa, R245fa and n-Pentane. Preliminary meanline analysis lead to the generation of turbine designs for the various cycles with similar efficiencies (77%) but large differences in dimensions (139–289 mm rotor diameter). The highest performing cycle, based on R134a, was found to produce 33% more net power from a 150 °C resource flowing at 10 kg/s than the lowest performing cycle, based on n-Pentane.

Candidate radial-inflow turbines and high-density working fluids for geothermal power systems

Optimisation of Organic Rankine Cycles (ORCs) for binary-cycle geothermal applications could play a major role in the competitiveness of low to moderate temperature geothermal resources. Part of this optimisation process is matching cycles to a given resource such that power output can be maximised. Two major and largely interrelated components of the cycle are the working fluid and the turbine. Both components need careful consideration. Due to the temperature differences in geothermal resources a one-size-fits-all approach to surface power infrastructure is not appropriate. Furthermore, the traditional use of steam as a working fluid does not seem practical due to the low temperatures of many resources. A variety of organic fluids with low boiling points may be utilised as ORC working fluids in binary power cycle loops. Due to differences in thermodynamic properties, certain fluids are able to extract more heat from a given resource than others over certain temperature and pressure ranges. This enables the tailoring of power cycle infrastructure to best match the geothermal resource through careful selection of the working fluid and turbine design optimisation to yield the optimum overall cycle performance. This paper presents the rationale for the use of radial-inflow turbines for ORC applications and the preliminary design of several radial-inflow turbines based on a selection of promising ORC cycles using five different high-density working fluids: R134a, R143a, R236fa, R245fa and n-Pentane at sub- or trans-critical conditions. Numerous studies published compare a variety of working fluids for various ORC configurations. However, there is little information specifically pertaining to the design and implementation of ORCs using realistic radial turbine designs in terms of pressure ratios, inlet pressure, rotor size and rotational speed. Preliminary 1D analysis leads to the generation of turbine designs for the various cycles with similar efficiencies (77%) but large differences in dimensions (139289 mm rotor diameter). The highest performing cycle (R134a) was found to produce 33% more net power from a 150°C resource flowing at 10 kg/s than the lowest performing cycle (n-Pentane).

Estimating vulnerable windows of exposure to air pollution during pregnancy

Exposure to air pollution during pregnancy is a potential cause of adverse birth outcomes such as preterm birth and stillbirth. The risk of exposure may be greater during vulnerable windows of the pregnancy which might only be weeks long. We demonstrate a method to find these windows based on smoothing the risk of weekly exposure using conditional autoregression. We use incidence density sampling to match cases with adverse birth outcomes to controls whose gestation lasted at least as long as the case. This matching means that cases and controls are have equal length exposure periods, rather than comparing, for example, cases with short gestations to controls with longer gestations. We demonstrate the ability of the method to find vulnerable windows using two simulation studies. We illustrate the method by examining the association between particulate matter air pollution and stillbirth in Brisbane, Australia.