Reliability analysis of transform-based stereo matching techniques, and a new matching constraint

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. Practical applications for stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics and industrial automation. The initial motivation behind this work was to produce a stereo vision sensor for mining automation applications. For such applications, the input stereo images would consist of close range scenes of rocks. A fundamental problem faced by matching algorithms is the matching or correspondence problem. This problem involves locating corresponding points or features in two images. For this application, speed, reliability, and the ability to produce a dense depth map are of foremost importance. This work implemented a number of areabased matching algorithms to assess their suitability for this application. Area-based techniques were investigated because of their potential to yield dense depth maps, their amenability to fast hardware implementation, and their suitability to textured scenes such as rocks. In addition, two non-parametric transforms, the rank and census, were also compared. Both the rank and the census transforms were found to result in improved reliability of matching in the presence of radiometric distortion - significant since radiometric distortion is a problem which commonly arises in practice. In addition, they have low computational complexity, making them amenable to fast hardware implementation. Therefore, it was decided that matching algorithms using these transforms would be the subject of the remainder of the thesis. An analytic expression for the process of matching using the rank transform was derived from first principles. This work resulted in a number of important contributions. Firstly, the derivation process resulted in one constraint which must be satisfied for a correct match. This was termed the rank constraint. The theoretical derivation of this constraint is in contrast to the existing matching constraints which have little theoretical basis. Experimental work with actual and contrived stereo pairs has shown that the new constraint is capable of resolving ambiguous matches, thereby improving match reliability. Secondly, a novel matching algorithm incorporating the rank constraint has been proposed. This algorithm was tested using a number of stereo pairs. In all cases, the modified algorithm consistently resulted in an increased proportion of correct matches. Finally, the rank constraint was used to devise a new method for identifying regions of an image where the rank transform, and hence matching, are more susceptible to noise. The rank constraint was also incorporated into a new hybrid matching algorithm, where it was combined a number of other ideas. These included the use of an image pyramid for match prediction, and a method of edge localisation to improve match accuracy in the vicinity of edges. Experimental results obtained from the new algorithm showed that the algorithm is able to remove a large proportion of invalid matches, and improve match accuracy.

Automatic speaker recognition under adverse conditions

Speaker verification is the process of verifying the identity of a person by analysing their speech. There are several important applications for automatic speaker verification (ASV) technology including suspect identification, tracking terrorists and detecting a person’s presence at a remote location in the surveillance domain, as well as person authentication for phone banking and credit card transactions in the private sector. Telephones and telephony networks provide a natural medium for these applications. The aim of this work is to improve the usefulness of ASV technology for practical applications in the presence of adverse conditions. In a telephony environment, background noise, handset mismatch, channel distortions, room acoustics and restrictions on the available testing and training data are common sources of errors for ASV systems. Two research themes were pursued to overcome these adverse conditions: Modelling mismatch and modelling uncertainty. To directly address the performance degradation incurred through mismatched conditions it was proposed to directly model this mismatch. Feature mapping was evaluated for combating handset mismatch and was extended through the use of a blind clustering algorithm to remove the need for accurate handset labels for the training data. Mismatch modelling was then generalised by explicitly modelling the session conditions as a constrained offset of the speaker model means. This session variability modelling approach enabled the modelling of arbitrary sources of mismatch, including handset type, and halved the error rates in many cases. Methods to model the uncertainty in speaker model estimates and verification scores were developed to address the difficulties of limited training and testing data. The Bayes factor was introduced to account for the uncertainty of the speaker model estimates in testing by applying Bayesian theory to the verification criterion, with improved performance in matched conditions. Modelling the uncertainty in the verification score itself met with significant success. Estimating a confidence interval for the "true" verification score enabled an order of magnitude reduction in the average quantity of speech required to make a confident verification decision based on a threshold. The confidence measures developed in this work may also have significant applications for forensic speaker verification tasks.

Disability, deinstitutionalisation and discourse : an analysis of institutional reform policies in Queensland, 1994-1996

The closure of large institutions for people with intellectual disability and the subsequent shift to community living has been a feature of social policies in most western democracies for more than two decades. While the move from congregated settings to homes in the community has been heralded as a positive and desirable strategy, deinstitutionalisation has continued to be a controversial policy and practice. This research critically analyses the implementation of a deinstitutionalisation policy called Institutional Reform in the state of Queensland from May 1994 until it was dismantled under a new government in the middle of 1996. A trajectory study of the policy from early conceptualisation through its development, implementation and final extinction was undertaken. Several methods were utilised in the research including the textual analyis of policy documents, discussion papers and newspaper articles, interviews with stakeholders and participant observation. The research draws on theories of discourse and focuses on how discourses of disability shape policy and practice. The thesis outlines a number of implications for policy implementation more generally as well as for disability services. In particular, the theoretical framework builds on Fulcher's (1989) disabling discourses - medical, charity, lay and rights - and identifies two additional discourses of economics and inclusion. The thesis argues that competing disability discourses operated in powerful ways to shape the implementation of the policy and illustrates how older discourses based on fear and prejudice were promoted to positions of dominance and power.

On the data consumption benefits of accepting increased uncertainty

In the context of learning paradigms of identification in the limit, we address the question: why is uncertainty sometimes desirable? We use mind change bounds on the output hypotheses as a measure of uncertainty, and interpret ‘desirable’ as reduction in data memorization, also defined in terms of mind change bounds. The resulting model is closely related to iterative learning with bounded mind change complexity, but the dual use of mind change bounds — for hypotheses and for data — is a key distinctive feature of our approach. We show that situations exists where the more mind changes the learner is willing to accept, the lesser the amount of data it needs to remember in order to converge to the correct hypothesis. We also investigate relationships between our model and learning from good examples, set-driven, monotonic and strong-monotonic learners, as well as class-comprising versus class-preserving learnability.

The monster chronicles : the role of children’s stories featuring monsters in managing childhood fears and promoting empowerment

Children’s fascination with monsters is a normal part of childhood development. Children’s literature reflects this with a wealth of stories featuring monsters, ranging from fairy tales to picture books to books for independent readers. These stories can raise concerns from educators, parents and other sections of the community such as political and religious institutions on the basis that they could be disturbing or harmful to children. In contrast, there is evidence to indicate the potential for managing fears and enhancing feelings of empowerment in children through the reading of stories featuring monsters. A reappraisal of these stories from a predominantly therapeutic perspective reveals that they may act as agents of positive change in six ways – catharsis, naming, taming, integration, transformation and moral empowerment. Two of these functions, transformation and moral empowerment, are examined further in three case studies of stories for the older reader that feature monsters, Wolf Brother by Michelle Paver, Monster Blood Tattoo, Book One: Foundling by D.M. Cornish and my manuscript, ‘The Monster Chronicles’. The insights from this research have been used to inform the writing and editing of ‘The Monster Chronicles’ and inherent to that, my goal of creating a children’s story featuring monsters that is sensitive to children’s fears and their desire for empowerment.