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.

Decoupled image-based visual servoing for cameras obeying the unified projection model

This paper proposes a generic decoupled imagebased control scheme for cameras obeying the unified projection model. The scheme is based on the spherical projection model. Invariants to rotational motion are computed from this projection and used to control the translational degrees of freedom. Importantly we form invariants which decrease the sensitivity of the interaction matrix to object depth variation. Finally, the proposed results are validated with experiments using a classical perspective camera as well as a fisheye camera mounted on a 6-DOF robotic platform.

Empirical comparison of machine learning algorithms for image texture classification with application to vegetation management in power line corridors

This paper reports on the empirical comparison of seven machine learning algorithms in texture classification with application to vegetation management in power line corridors. Aiming at classifying tree species in power line corridors, object-based method is employed. Individual tree crowns are segmented as the basic classification units and three classic texture features are extracted as the input to the classification algorithms. Several widely used performance metrics are used to evaluate the classification algorithms. The experimental results demonstrate that the classification performance depends on the performance matrix, the characteristics of datasets and the feature used.

"Re-imagining animation : the changing face of the moving image by Paul Wells and Johnny Hardstaff" (Book Review)

Advances in digital technology have caused a radical shift in moving image culture. This has occurred in both modes of production and sites of exhibition, resulting in a blurring of boundaries that previously defined a range of creative disciplines. Re-Imagining Animation: The Changing Face of the Moving Image, by Paul Wells and Johnny Hardstaff, argues that as a result of these blurred disciplinary boundaries, the term “animation” has become a “catch all” for describing any form of manipulated moving image practice. Understanding animation predicates the need to (re)define the medium within contemporary moving image culture. Via a series of case studies, the book engages with a range of moving image works, interrogating “how the many and varied approaches to making film, graphics, visual artefacts, multimedia and other intimations of motion pictures can now be delineated and understood” (p. 7). The structure and clarity of content make this book ideally suited to any serious study of contemporary animation which accepts animation as a truly interdisciplinary medium.

Monitoring and regulatory role of the balanced scorecard in controlling organisational identities

This thesis employs the theoretical fusion of disciplinary knowledge, interlacing an analysis from both functional and interpretive frameworks and applies these paradigms to three concepts—organisational identity, the balanced scorecard performance measurement system, and control. As an applied thesis, this study highlights how particular public sector organisations are using a range of multi-disciplinary forms of knowledge constructed for their needs to achieve practical outcomes. Practical evidence of this study is not bound by a single disciplinary field or the concerns raised by academics about the rigorous application of academic knowledge. The study’s value lies in its ability to explore how current communication and accounting knowledge is being used for practical purposes in organisational life. The main focus of this thesis is on identities in an organisational communication context. In exploring the theoretical and practical challenges, the research questions for this thesis were formulated as: 1. Is it possible to effectively control identities in organisations by the use of an integrated performance measurement system—the balanced scorecard—and if so, how? 2. What is the relationship between identities and an integrated performance measurement system—the balanced scorecard—in the identity construction process? Identities in the organisational context have been extensively discussed in graphic design, corporate communication and marketing, strategic management, organisational behaviour, and social psychology literatures. Corporate identity is the self-presentation of the personality of an organisation (Van Riel, 1995; Van Riel & Balmer, 1997), and organisational identity is the statement of central characteristics described by members (Albert & Whetten, 2003). In this study, identity management is positioned as a strategically complex task, embracing not only logo and name, but also multiple dimensions, levels and facets of organisational life. Responding to the collaborative efforts of researchers and practitioners in identity conceptualisation and methodological approaches, this dissertation argues that analysis can be achieved through the use of an integrated framework of identity products, patternings and processes (Cornelissen, Haslam, & Balmer, 2007), transforming conceptualisations of corporate identity, organisational identity and identification studies. Likewise, the performance measurement literature from the accounting field now emphasises the importance of ‘soft’ non-financial measures in gauging performance—potentially allowing the monitoring and regulation of ‘collective’ identities (Cornelissen et al., 2007). The balanced scorecard (BSC) (Kaplan & Norton, 1996a), as the selected integrated performance measurement system, quantifies organisational performance under the four perspectives of finance, customer, internal process, and learning and growth. Broadening the traditional performance measurement boundary, the BSC transforms how organisations perceived themselves (Vaivio, 2007). The rhetorical and communicative value of the BSC has also been emphasised in organisational self-understanding (Malina, Nørreklit, & Selto, 2007; Malmi, 2001; Norreklit, 2000, 2003). Thus, this study establishes a theoretical connection between the controlling effects of the BSC and organisational identity construction. Common to both literatures, the aspects of control became the focus of this dissertation, as ‘the exercise or act of achieving a goal’ (Tompkins & Cheney, 1985, p. 180). This study explores not only traditional technical and bureaucratic control (Edwards, 1981), but also concertive control (Tompkins & Cheney, 1985), shifting the locus of control to employees who make their own decisions towards desired organisational premises (Simon, 1976). The controlling effects on collective identities are explored through the lens of the rhetorical frames mobilised through the power of organisational enthymemes (Tompkins & Cheney, 1985) and identification processes (Ashforth, Harrison, & Corley, 2008). In operationalising the concept of control, two guiding questions were developed to support the research questions: 1.1 How does the use of the balanced scorecard monitor identities in public sector organisations? 1.2 How does the use of the balanced scorecard regulate identities in public sector organisations? This study adopts qualitative multiple case studies using ethnographic techniques. Data were gathered from interviews of 41 managers, organisational documents, and participant observation from 2003 to 2008, to inform an understanding of organisational practices and members’ perceptions in the five cases of two public sector organisations in Australia. Drawing on the functional and interpretive paradigms, the effective design and use of the systems, as well as the understanding of shared meanings of identities and identifications are simultaneously recognised. The analytical structure guided by the ‘bracketing’ (Lewis & Grimes, 1999) and ‘interplay’ strategies (Schultz & Hatch, 1996) preserved, connected and contrasted the unique findings from the multi-paradigms. The ‘temporal bracketing’ strategy (Langley, 1999) from the process view supports the comparative exploration of the analysis over the periods under study. The findings suggest that the effective use of the BSC can monitor and regulate identity products, patternings and processes. In monitoring identities, the flexible BSC framework allowed the case study organisations to monitor various aspects of finance, customer, improvement and organisational capability that included identity dimensions. Such inclusion legitimises identity management as organisational performance. In regulating identities, the use of the BSC created a mechanism to form collective identities by articulating various perspectives and causal linkages, and through the cascading and alignment of multiple scorecards. The BSC—directly reflecting organisationally valued premises and legitimised symbols—acted as an identity product of communication, visual symbols and behavioural guidance. The selective promotion of the BSC measures filtered organisational focus to shape unique identity multiplicity and characteristics within the cases. Further, the use of the BSC facilitated the assimilation of multiple identities by controlling the direction and strength of identifications, engaging different groups of members. More specifically, the tight authority of the BSC framework and systems are explained both by technical and bureaucratic controls, while subtle communication of organisational premises and information filtering is achieved through concertive control. This study confirms that these macro top-down controls mediated the sensebreaking and sensegiving process of organisational identification, supporting research by Ashforth, Harrison and Corley (2008). This study pays attention to members’ power of self-regulation, filling minor premises of the derived logic of their organisation through the playing out of organisational enthymemes (Tompkins & Cheney, 1985). Members are then encouraged to make their own decisions towards the organisational premises embedded in the BSC, through the micro bottom-up identification processes including: enacting organisationally valued identities; sensemaking; and the construction of identity narratives aligned with those organisationally valued premises. Within the process, the self-referential effect of communication encouraged members to believe the organisational messages embedded in the BSC in transforming collective and individual identities. Therefore, communication through the use of the BSC continued the self-producing of normative performance mechanisms, established meanings of identities, and enabled members’ self-regulation in identity construction. Further, this research establishes the relationship between identity and the use of the BSC in terms of identity multiplicity and attributes. The BSC framework constrained and enabled case study organisations and members to monitor and regulate identity multiplicity across a number of dimensions, levels and facets. The use of the BSC constantly heightened the identity attributes of distinctiveness, relativity, visibility, fluidity and manageability in identity construction over time. Overall, this research explains the reciprocal controlling relationships of multiple structures in organisations to achieve a goal. It bridges the gap among corporate and organisational identity theories by adopting Cornelissen, Haslam and Balmer’s (2007) integrated identity framework, and reduces the gap in understanding between identity and performance measurement studies. Parallel review of the process of monitoring and regulating identities from both literatures synthesised the theoretical strengths of both to conceptualise and operationalise identities. This study extends the discussion on positioning identity, culture, commitment, and image and reputation measures in integrated performance measurement systems as organisational capital. Further, this study applies understanding of the multiple forms of control (Edwards, 1979; Tompkins & Cheney, 1985), emphasising the power of organisational members in identification processes, using the notion of rhetorical organisational enthymemes. This highlights the value of the collaborative theoretical power of identity, communication and performance measurement frameworks. These case studies provide practical insights about the public sector where existing bureaucracy and desired organisational identity directions are competing within a large organisational setting. Further research on personal identity and simple control in organisations that fully cascade the BSC down to individual members would provide enriched data. The extended application of the conceptual framework to other public and private sector organisations with a longitudinal view will also contribute to further theory building.

Attraction and image for the Australian rail industry

Despite the global financial downturn, the Australian rail industry is in a period of expansion. Reports indicate that the industry is not attracting sufficient entry level and mid-career engineers and skilled technicians from within the Australian labour market and is facing widespread retirements from an ageing workforce. This paper reports on a completed qualitative study that explores the perceptions of engineering students, their lecturers, careers advisors and recruitment consultants regarding rail as a brand and of careers in the rail industry. Findings are presented about career knowledge, job characteristic preferences, branding and image and indicate that rail as a brand has a dated image, that young people and their influencers have little knowledge of rail careers and that rail could better focus its image and recruitment strategies. Conclusions include suggestions for more effective attraction and image strategies for the industry and for further research.

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.

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.

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.