Mid-level concept learning with visual contextual ontologies and probabilistic inference for image annotation

To date, automatic recognition of semantic information such as salient objects and mid-level concepts from images is a challenging task. Since real-world objects tend to exist in a context within their environment, the computer vision researchers have increasingly incorporated contextual information for improving object recognition. In this paper, we present a method to build a visual contextual ontology from salient objects descriptions for image annotation. The ontologies include not only partOf/kindOf relations, but also spatial and co-occurrence relations. A two-step image annotation algorithm is also proposed based on ontology relations and probabilistic inference. Different from most of the existing work, we specially exploit how to combine representation of ontology, contextual knowledge and probabilistic inference. The experiments show that image annotation results are improved in the LabelMe dataset.

Computational modeling and psychophysics in low- and mid-level vision

This thesis addresses a series of topics related to the question of how people find the foreground objects from complex scenes. With both computer vision modeling, as well as psychophysical analyses, we explore the computational principles for low- and mid-level vision.

We first explore the computational methods of generating saliency maps from images and image sequences. We propose an extremely fast algorithm called Image Signature that detects the locations in the image that attract human eye gazes. With a series of experimental validations based on human behavioral data collected from various psychophysical experiments, we conclude that the Image Signature and its spatial-temporal extension, the Phase Discrepancy, are among the most accurate algorithms for saliency detection under various conditions.

In the second part, we bridge the gap between fixation prediction and salient object segmentation with two efforts. First, we propose a new dataset that contains both fixation and object segmentation information. By simultaneously presenting the two types of human data in the same dataset, we are able to analyze their intrinsic connection, as well as understanding the drawbacks of today’s “standard” but inappropriately labeled salient object segmentation dataset. Second, we also propose an algorithm of salient object segmentation. Based on our novel discoveries on the connections of fixation data and salient object segmentation data, our model significantly outperforms all existing models on all 3 datasets with large margins.

In the third part of the thesis, we discuss topics around the human factors of boundary analysis. Closely related to salient object segmentation, boundary analysis focuses on delimiting the local contours of an object. We identify the potential pitfalls of algorithm evaluation for the problem of boundary detection. Our analysis indicates that today’s popular boundary detection datasets contain significant level of noise, which may severely influence the benchmarking results. To give further insights on the labeling process, we propose a model to characterize the principles of the human factors during the labeling process.

The analyses reported in this thesis offer new perspectives to a series of interrelating issues in low- and mid-level vision. It gives warning signs to some of today’s “standard” procedures, while proposing new directions to encourage future research.

Mid-Level Vision and Recognition of Non-Rigid Objects

We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/ incoming regions are more salient; and that perception begins by setting a reference frame (prior to early vision), and proceeds by processing convex structures.

Observations of ice multiplication in a weakly convective cell embedded in supercooled mid-level stratus

Simultaneous observations of cloud microphysical properties were obtained by in-situ aircraft measurements and ground based Radar/Lidar. Widespread mid-level stratus cloud was present below a temperature inversion (~5 °C magnitude) at 3.6 km altitude. Localised convection (peak updraft 1.5 m s−1) was observed 20 km west of the Radar station. This was associated with convergence at 2.5 km altitude. The convection was unable to penetrate the inversion capping the mid-level stratus. The mid-level stratus cloud was vertically thin (~400 m), horizontally extensive (covering 100 s of km) and persisted for more than 24 h. The cloud consisted of supercooled water droplets and small concentrations of large (~1 mm) stellar/plate like ice which slowly precipitated out. This ice was nucleated at temperatures greater than −12.2 °C and less than −10.0 °C, (cloud top and cloud base temperatures, respectively). No ice seeding from above the cloud layer was observed. This ice was formed by primary nucleation, either through the entrainment of efficient ice nuclei from above/below cloud, or by the slow stochastic activation of immersion freezing ice nuclei contained within the supercooled drops. Above cloud top significant concentrations of sub-micron aerosol were observed and consisted of a mixture of sulphate and carbonaceous material, a potential source of ice nuclei. Particle number concentrations (in the size range 0.1mid-level stratus evaporated before reaching the surface, whereas rates of up to 1 mm h−1 were observed below the convective feature. There is strong evidence for the Hallett-Mossop (HM) process of secondary ice particle production leading to the formation of the precipitation observed. This includes (1) Ice concentrations in the convective feature were more than an order of magnitude greater than the concentration of primary ice in the overlaying stratus, (2) Large concentrations of small pristine columns were observed at the ~−5 °C level together with liquid water droplets and a few rimed ice particles, (3) Columns were larger and increasingly rimed at colder temperatures. Calculated ice splinter production rates are consistent with observed concentrations if the condition that only droplets greater than 24 μm are capable of generating secondary ice splinters is relaxed. This case demonstrates the importance of understanding the formation of ice at slightly supercooled temperatures, as it can lead to secondary ice production and the formation of precipitation in clouds which may not otherwise be considered as significant precipitation sources.

The interaction of moist convection and mid-level dry air in the advance of the onset of the Indian monsoon

The advance of the onset of the Indian monsoon is here explained in terms of a balance between the low-level monsoon flow and an over-running intrusion of mid-tropospheric dry air. The monsoon advances, over a period of about 6 weeks, from the south of the country to the northwest. Given that the low-level monsoon winds are westerly or southwesterly, and the midlevel winds northwesterly, the monsoon onset propagates upwind relative to midlevel flow, and perpendicular to the low-level flow, and is not directly caused by moisture flux toward the northwest. Lacking a conceptual model for the advance means that it has been hard to understand and correct known biases in weather and climate prediction models. The mid-level northwesterlies form a wedge of dry air that is deep in the far northwest of India and over-runs the monsoon flow. The dry layer is moistened from below by shallow cumulus and congestus clouds, so that the profile becomes much closer to moist adiabatic, and the dry layer is much shallower in the vertical, toward the southeast of India. The profiles associated with this dry air show how the most favourable environment for deep convection occurs in the south, and onset occurs here first. As the onset advances across India, the advection of moisture from the Arabian Sea becomes stronger, and the mid-level dry air is increasingly moistened from below. This increased moistening makes the wedge of dry air shallower throughout its horizontal extent, and forces the northern limit of moist convection to move toward the northwest. Wetting of the land surface by rainfall will further reinforce the north-westward progression, by sustaining the supply of boundary layer moisture and shallow cumulus. The local advance of the monsoon onset is coincident with weakening of the mid-level northwesterlies, and therefore weakened mid-level dry advection.

Performance and emissions testing of a small two stroke engine using mid-level ethanol blends

With the introduction of the mid-level ethanol blend gasoline fuel for commercial sale, the compatibility of different off-road engines is needed. This report details the test study of using one mid-level ethanol fuel in a two stroke hand held gasoline engine used to power line trimmers. The study sponsored by E3 is to test the effectiveness of an aftermarket spark plug from E3 Spark Plug when using a mid-level ethanol blend gasoline. A 15% ethanol by volume (E15) is the test mid-level ethanol used and the 10% ethanol by volume (E10) was used as the baseline fuel. The testing comprises running the engine at different load points and throttle positions to evaluate the cylinder head temperature, exhaust temperature and engine speed. Raw gas emissions were also measured to determine the impact of the performance spark plug. The low calorific value of the E15 fuel decreased the speed of the engine along with reduction in the fuel consumption and exhaust gas temperature. The HC emissions for E15 fuel and E3 spark plug increased when compared to the base line in most of the cases and NO formation was dependent on the cylinder head temperature. The E3 spark plug had a tendency to increase the temperature of the cylinder head irrespective of fuel type while reducing engine speed.

O papel da burocracia no processo de implantação dos Institutos Federais de Educação, Ciência e Tecnologia (IFs): o caso do IF de Passos (MG)

Pós-graduação em Planejamento e Análise de Políticas Públicas - FCHS

Work engagement and its antecedents in high-risk occupations : a police service case study

Introduction: Work engagement is a recent application of positive psychology and refers to a positive, fulfilling, work-related state of mind characterized by vigor, dedication and absorption. Despite theoretical assumptions, there is little published research on work engagement, due primarily to its recent emergence as a psychological construct. Furthermore, examining work engagement among high-stress occupations, such as police, is useful because police officers are generally characterized as having a high level of work engagement. Previous research has identified job resources (e.g. social support) as antecedents of work engagement. However detailed evaluation of job demands as an antecedent of work engagement within high-stress occupations has been scarce. Thus our second aim was to test job demands (i.e. monitoring demands and problem-solving demands) and job resources (i.e. time control, method control, supervisory support, colleague support, and friend and family support) as antecedents of work engagement among police officers. Method: Data were collected via a self-report online survey from one Australian state police service (n = 1,419). Due to the high number of hypothesized antecedent variables, hierarchical multiple regression analysis was employed rather than structural equation modelling. Results: Work engagement reported by police officers was high. Female officers had significantly higher levels of work engagement than male officers, while officers at mid-level ranks (sergeant) reported the lowest levels of work engagement. Job resources (method control, supervisor support and colleague support) were significant antecedents of three dimensions of work engagement. Only monitoring demands were significant antecedent of the absorption. Conclusion: Having healthy and engaged police officers is important for community security and economic growth. This study identified some common factors which influence work engagement experienced by police officers. However, we also note that excessive work engagement can yield negative outcomes such as psychological distress.

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.

Mediators of the relationship between person-organisation fit and individual outcomes

To date, research on P-O fit has focused heavily on the effect of P-O fit on individual and organisational outcomes. Few studies have attempted to explain how or why P-O fit leads to these outcomes. Meglino, Ravlin, and Adkins (1989) and Schein (1985) identified several intervening mechanisms for explaining fit-outcome relationships but only few of these explanations have been tested empirically (Cable & Edwards, 2004; Edwards & Cable, 2009; Kalliath, Bluedorn, & Strube, 1999). This thesis investigates role conflict, cognitive style and organisational justice as three potential mediating mechanisms in the relationship between P-O fit (defined as fit between personal and organisational values – value congruence or value fit) and outcomes including job satisfaction, job performance, service performance, affective commitment and continuance commitment. The study operationalised P-O fit using three measures: subjective fit, perceived fit and objective fit. The mediation model of subjective fit was tested using a Mplus analytical technique, while the mediation models of both perceived and objective fit were tested by modeling the difference between two scores (that is, between personal values and organisational values) using a polynomial regression and response surface analysis (Edwards, 1993). A survey of 558 mid-level managers from seven Brunei public sector organisations provided the data. Our results showed that the relationship between P-O fit and outcomes was partially mediated by organisational justice and cognitive style - for all the three measures of fit, while role conflict had no mediating effects. The findings from this research therefore have both theoretical and practical implications. This research contributes to the literature by combining these theoretical explanations for value congruence effects into one integrated model, and by providing evidence on the partial mediating effects of organisational justice and cognitive style. Future research needs to address and investigate other potential mechanisms by which value congruence affects individual and organisational outcomes. In addition, the study is considered to be the first to test these mediating roles for a value fit-outcomes relationship using three different measures of fit in a non-Western context.

Content-based video indexing for sports applications using integrated multi-modal approach

To sustain an ongoing rapid growth of video information, there is an emerging demand for a sophisticated content-based video indexing system. However, current video indexing solutions are still immature and lack of any standard. This doctoral consists of a research work based on an integrated multi-modal approach for sports video indexing and retrieval. By combining specific features extractable from multiple audio-visual modalities, generic structure and specific events can be detected and classified. During browsing and retrieval, users will benefit from the integration of high-level semantic and some descriptive mid-level features such as whistle and close-up view of player(s).

Recontextualising policy discourses : a Bernsteinian perspective on policy interpretation, translation, enactment

This paper contributes to critical policy research by theorising one aspect of policy enactment, the meaning making work of a cohort of mid-level policy actors. Specifically, we propose that Basil Bernstein’s work on the structuring of pedagogic discourse, in particular, the concept of recontextualisation, may add to understandings of the policy work of interpretation and translation. Recontextualisation refers to the relational processes of selecting and moving knowledge from one context to another, as well as to the distinctive re-organisation of knowledge as an instructional and regulative or moral discourse. Processes of recontextualisation necessitate an analysis of power and control relations, and therefore add to the Foucauldian theorisations of power that currently dominate the critical policy literature. A process of code elaboration (decoding and recoding) takes place in various recontextualising agencies, responsible for the production of professional development materials, teaching guidelines and curriculum resources. We propose that mid-level policy actors are crucial to the work of policy interpretation and translation because they are engaged in elaborating the condensed codes of policy texts to an imagined logic of teachers’ practical work. To illustrate our theoretical points we draw on data; collected for an Australian research project on the accounts of mid-level policy actors responsible for the interpretation of child protection and safety policies for staff in Queensland schools.

Towards robust automatic affective classification of images using facial expressions for practical applications

Affect is an important feature of multimedia content and conveys valuable information for multimedia indexing and retrieval. Most existing studies for affective content analysis are limited to low-level features or mid-level representations, and are generally criticized for their incapacity to address the gap between low-level features and high-level human affective perception. The facial expressions of subjects in images carry important semantic information that can substantially influence human affective perception, but have been seldom investigated for affective classification of facial images towards practical applications. This paper presents an automatic image emotion detector (IED) for affective classification of practical (or non-laboratory) data using facial expressions, where a lot of “real-world” challenges are present, including pose, illumination, and size variations etc. The proposed method is novel, with its framework designed specifically to overcome these challenges using multi-view versions of face and fiducial point detectors, and a combination of point-based texture and geometry. Performance comparisons of several key parameters of relevant algorithms are conducted to explore the optimum parameters for high accuracy and fast computation speed. A comprehensive set of experiments with existing and new datasets, shows that the method is effective despite pose variations, fast, and appropriate for large-scale data, and as accurate as the method with state-of-the-art performance on laboratory-based data. The proposed method was also applied to affective classification of images from the British Broadcast Corporation (BBC) in a task typical for a practical application providing some valuable insights.

Feature integration in human vision

The earliest stages of human cortical visual processing can be conceived as extraction of local stimulus features. However, more complex visual functions, such as object recognition, require integration of multiple features. Recently, neural processes underlying feature integration in the visual system have been under intensive study. A specialized mid-level stage preceding the object recognition stage has been proposed to account for the processing of contours, surfaces and shapes as well as configuration. This thesis consists of four experimental, psychophysical studies on human visual feature integration. In two studies, classification image a recently developed psychophysical reverse correlation method was used. In this method visual noise is added to near-threshold stimuli. By investigating the relationship between random features in the noise and observer s perceptual decision in each trial, it is possible to estimate what features of the stimuli are critical for the task. The method allows visualizing the critical features that are used in a psychophysical task directly as a spatial correlation map, yielding an effective "behavioral receptive field". Visual context is known to modulate the perception of stimulus features. Some of these interactions are quite complex, and it is not known whether they reflect early or late stages of perceptual processing. The first study investigated the mechanisms of collinear facilitation, where nearby collinear Gabor flankers increase the detectability of a central Gabor. The behavioral receptive field of the mechanism mediating the detection of the central Gabor stimulus was measured by the classification image method. The results show that collinear flankers increase the extent of the behavioral receptive field for the central Gabor, in the direction of the flankers. The increased sensitivity at the ends of the receptive field suggests a low-level explanation for the facilitation. The second study investigated how visual features are integrated into percepts of surface brightness. A novel variant of the classification image method with brightness matching task was used. Many theories assume that perceived brightness is based on the analysis of luminance border features. Here, for the first time this assumption was directly tested. The classification images show that the perceived brightness of both an illusory Craik-O Brien-Cornsweet stimulus and a real uniform step stimulus depends solely on the border. Moreover, the spatial tuning of the features remains almost constant when the stimulus size is changed, suggesting that brightness perception is based on the output of a single spatial frequency channel. The third and fourth studies investigated global form integration in random-dot Glass patterns. In these patterns, a global form can be immediately perceived, if even a small proportion of random dots are paired to dipoles according to a geometrical rule. In the third study the discrimination of orientation structure in highly coherent concentric and Cartesian (straight) Glass patterns was measured. The results showed that the global form was more efficiently discriminated in concentric patterns. The fourth study investigated how form detectability depends on the global regularity of the Glass pattern. The local structure was either Cartesian or curved. It was shown that randomizing the local orientation deteriorated the performance only with the curved pattern. The results give support for the idea that curved and Cartesian patterns are processed in at least partially separate neural systems.