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.

Wide-baseline keypoint detection and matching with wide-angle images for vision based localisation

This thesis addresses the problem of detecting and describing the same scene points in different wide-angle images taken by the same camera at different viewpoints. This is a core competency of many vision-based localisation tasks including visual odometry and visual place recognition. Wide-angle cameras have a large field of view that can exceed a full hemisphere, and the images they produce contain severe radial distortion. When compared to traditional narrow field of view perspective cameras, more accurate estimates of camera egomotion can be found using the images obtained with wide-angle cameras. The ability to accurately estimate camera egomotion is a fundamental primitive of visual odometry, and this is one of the reasons for the increased popularity in the use of wide-angle cameras for this task. Their large field of view also enables them to capture images of the same regions in a scene taken at very different viewpoints, and this makes them suited for visual place recognition. However, the ability to estimate the camera egomotion and recognise the same scene in two different images is dependent on the ability to reliably detect and describe the same scene points, or ‘keypoints’, in the images. Most algorithms used for this purpose are designed almost exclusively for perspective images. Applying algorithms designed for perspective images directly to wide-angle images is problematic as no account is made for the image distortion. The primary contribution of this thesis is the development of two novel keypoint detectors, and a method of keypoint description, designed for wide-angle images. Both reformulate the Scale- Invariant Feature Transform (SIFT) as an image processing operation on the sphere. As the image captured by any central projection wide-angle camera can be mapped to the sphere, applying these variants to an image on the sphere enables keypoints to be detected in a manner that is invariant to image distortion. Each of the variants is required to find the scale-space representation of an image on the sphere, and they differ in the approaches they used to do this. Extensive experiments using real and synthetically generated wide-angle images are used to validate the two new keypoint detectors and the method of keypoint description. The best of these two new keypoint detectors is applied to vision based localisation tasks including visual odometry and visual place recognition using outdoor wide-angle image sequences. As part of this work, the effect of keypoint coordinate selection on the accuracy of egomotion estimates using the Direct Linear Transform (DLT) is investigated, and a simple weighting scheme is proposed which attempts to account for the uncertainty of keypoint positions during detection. A word reliability metric is also developed for use within a visual ‘bag of words’ approach to place recognition.

Multiple camera management using wide baseline matching

Camera calibration information is required in order for multiple camera networks to deliver more than the sum of many single camera systems. Methods exist for manually calibrating cameras with high accuracy. Manually calibrating networks with many cameras is, however, time consuming, expensive and impractical for networks that undergo frequent change. For this reason, automatic calibration techniques have been vigorously researched in recent years. Fully automatic calibration methods depend on the ability to automatically find point correspondences between overlapping views. In typical camera networks, cameras are placed far apart to maximise coverage. This is referred to as a wide base-line scenario. Finding sufficient correspondences for camera calibration in wide base-line scenarios presents a significant challenge. This thesis focuses on developing more effective and efficient techniques for finding correspondences in uncalibrated, wide baseline, multiple-camera scenarios. The project consists of two major areas of work. The first is the development of more effective and efficient view covariant local feature extractors. The second area involves finding methods to extract scene information using the information contained in a limited set of matched affine features. Several novel affine adaptation techniques for salient features have been developed. A method is presented for efficiently computing the discrete scale space primal sketch of local image features. A scale selection method was implemented that makes use of the primal sketch. The primal sketch-based scale selection method has several advantages over the existing methods. It allows greater freedom in how the scale space is sampled, enables more accurate scale selection, is more effective at combining different functions for spatial position and scale selection, and leads to greater computational efficiency. Existing affine adaptation methods make use of the second moment matrix to estimate the local affine shape of local image features. In this thesis, it is shown that the Hessian matrix can be used in a similar way to estimate local feature shape. The Hessian matrix is effective for estimating the shape of blob-like structures, but is less effective for corner structures. It is simpler to compute than the second moment matrix, leading to a significant reduction in computational cost. A wide baseline dense correspondence extraction system, called WiDense, is presented in this thesis. It allows the extraction of large numbers of additional accurate correspondences, given only a few initial putative correspondences. It consists of the following algorithms: An affine region alignment algorithm that ensures accurate alignment between matched features; A method for extracting more matches in the vicinity of a matched pair of affine features, using the alignment information contained in the match; An algorithm for extracting large numbers of highly accurate point correspondences from an aligned pair of feature regions. Experiments show that the correspondences generated by the WiDense system improves the success rate of computing the epipolar geometry of very widely separated views. This new method is successful in many cases where the features produced by the best wide baseline matching algorithms are insufficient for computing the scene geometry.

Implementing an emergency department patient admission predictive tool : insights from practice

Purpose: This paper aims to show that identification of expectations and software functional requirements via consultation with potential users is an integral component of the development of an emergency department patient admissions prediction tool. ---------- Design/methodology/approach: Thematic analysis of semi-structured interviews with 14 key health staff delivered rich data regarding existing practice and future needs. Participants included emergency department staff, bed managers, nurse unit managers, directors of nursing, and personnel from health administration. ---------- Findings: Participants contributed contextual insights on the current system of admissions, revealing a culture of crisis, imbued with misplayed communication. Their expectations and requirements of a potential predictive tool provided strategic data that moderated the development of the Emergency Department Patient Admissions Prediction Tool, based on their insistence that it feature availability, reliability and relevance. In order to deliver these stipulations, participants stressed that it should be incorporated, validated, defined and timely. ---------- Research limitations/implications: Participants were envisaging a concept and use of a tool that was somewhat hypothetical. However, further research will evaluate the tool in practice. ---------- Practical implications: Participants' unsolicited recommendations regarding implementation will not only inform a subsequent phase of the tool evaluation, but are eminently applicable to any process of implementation in a healthcare setting. ---------- Originality/value: The consultative process engaged clinicians and the paper delivers an insider view of an overburdened system, rather than an outsider's observations.