As demand for real-time image processing increases, the need to improve the efficiency of image processing systems is growing. The process of image segmentation is often used in preprocessing stages of computer vision systems to reduce image data and increase processing efficiency. This dissertation introduces a novel image segmentation approach known as leap segmentation, which applies a flexible definition of adjacency to allow groupings of pixels into segments which need not be spatially contiguous and thus can more accurately correspond to large surfaces in the scene. Experiments show that leap segmentation correctly preserves an average of 20% more original scene pixels than traditional approaches, while using the same number of segments, and significantly improves execution performance (executing 10x - 15x faster than leading approaches). Further, leap segmentation is shown to improve the efficiency of a high-level vision application for scene layout analysis within 3D scene reconstruction. The benefits of applying image segmentation in preprocessing are not limited to single-frame image processing. Segmentation is also often applied in the preprocessing stages of video analysis applications. In the second contribution of this dissertation, the fast, single-frame leap segmentation approach is extended into the temporal domain to develop a highly-efficient method for multiple-frame segmentation, called video leap segmentation. This approach is evaluated for use on mobile platforms where processing speed is critical using moving-camera traffic sequences captured on busy, multi-lane highways. Video leap segmentation accurately tracks segments across temporal bounds, maintaining temporal coherence between the input sequence frames. It is shown that video leap segmentation can be applied with high accuracy to the task of salient segment transformation detection for alerting drivers to important scene changes that may affect future steering decisions. Finally, while research efforts in the field of image segmentation have often recognized the need for efficient implementations for real-time processing, many of today’s leading image segmentation approaches exhibit processing times which exceed their camera frame periods, making them infeasible for use in real-time applications. The third research contribution of this dissertation focuses on developing fast implementations of the single-frame leap segmentation approach for use on both single-core and multi-core platforms as well as on both high-performance and resource-constrained systems. While the design of leap segmentation lends itself to efficient implementations, the efficiency achieved by this algorithm, as in any algorithm, is can be improved with careful implementation optimizations. The leap segmentation approach is analyzed in detail and highly optimized implementations of the approach are presented with in-depth studies, ranging from storage considerations to realizing parallel processing potential. The final implementations of leap segmentation for both serial and parallel platforms are shown to achieve real-time frame rates even when processing very high resolution input images. Leap segmentation’s accuracy and speed make it a highly competitive alternative to today’s leading segmentation approaches for modern, real-time computer vision systems.

The Klein Karoo National Arts Festival (KKNK) is one of the most popular arts festivals in South Africa, but ticket sales have alarmingly declined since 2005 resulting in the Festival already being in a decline phase of its product life cycle. This has a negative impact on the Festival's economic impact and future sustainability. It is therefore vital to increase the ticket sales in order for the Festival to maintain a steady growth rate. Market segmentation can assist the Festival's marketers/organisers to address this problem by identifying the high spending segment at the Festival since they stay longer and are keener to buy tickets supporting the Festivals shows/productions. Market segmentation is the process of dividing the festival market into smaller, more clearly defined groups that share similar, needs, wants and characteristics. The more detailed the knowledge of the needs and motives of potential visitors, the closer the Festival can get to a customised festival program creating greater satisfaction, long-term relationships, repeat visits and an increase in tickets supporting the shows/productions. The main purpose of this study was therefore to determine the spending behaviour of visitors the KKNK by means of establishing the determinants which influence visitor's expenditure and by applying expenditure-based segmentation in order to determine the high spending segment at the Festival. To determine the above goal, the study is divided into 2 articles. Research for both the articles was undertaken at the Festival and data obtained from 2005 to 2008 were used. Questionnaires were interview-administered and distributed randomly during the course of the Festival. In total 1940 questionnaires have been completed in the visitor survey since 2005. Article 1 is titled: "Socio-demographic and behavioural determinants of visitor spending at the Klein Karoo National Arts Festival." The main purpose of this article was to identify the various socio-demographic and behavioural determinants that influence visitor spending at the KKNK. This was done in order to determine which visitors spend most at the Festival and which determinants are most significant in determining their expenditure levels. A regression analysis was used as an instrument to achieve the mentioned goal. Results indicated that occupation, distance travelled, length of stay, the reason for attending the Festival and preferred type of shows/productions were significant determinants that influence the amount of money visitors spent at the Festival. These results generated strategic insights on marketing for the festival in order to increase visitor spending especially on purchasing more tickets for shows/productions. Article 2 is titled: "Expenditure-based segmentation of visitors at the Klein Karoo National Arts festival." The main purpose of this article was to apply expenditure-based segmentation to visitors at the KKNK in order to identify the high spending segment at the festival. An analysis of variance (ANOVA) was used to determine whether there were significant differences between the different expenditure groups. The Festival's market was divided into high, medium and low expenditure groups. Results revealed that the high spenders at the Festival were distinguishable from the low spenders based on their longer length of stay, older age, higher income, main reason to attend the Festival and preferred type of shows/productions. These results were used to compile a complete profile of the high spenders and how the Festival's appeal can be maximised in order to attract more high spenders. This research therefore revealed that certain socio-demographic determinants influence visitor's spending behaviour at the Klein Karoo National Arts Festival. There are further two distinct expenditure groups at the Festival, namely a high and low expenditure group. Knowledge of the determinants which influence visitor spending can be used in combination with the profile of the high spenders to maximise the Festival's appeal in order to attract more high spenders who buy tickets supporting the Festivals shows/productions. This will lead to an increase in ticket sales, a greater economic impact and ultimately to the continuous sustainability of the Klein Karoo National Arts Festival. / Thesis (M.A. (Tourism))--North-West University, Potchefstroom Campus, 2009.

Thesis (M.A. (Tourism))--North-West University, Potchefstroom Campus, 2009.

No description available.

In brachytherapy, radiation therapy is performed by placing the radiation source into or very close to the tumour. When calculating the absorbed dose, water is often used as the radiation transport and dose scoring medium for soft tissues and this leads to inaccuracies. The iterative reconstruction algorithm DIRA is under development at the Center for Medical Imaging Science and Visualization, Linköping University. DIRA uses dual-energy CT to decompose tissues into different doublets and triplets of base components for a better absorbed dose estimation. To accurately determine mass fractions of these base components for different tissues, the tissues needs to be identified in the image. The aims of this master thesis are: (i) Find an automated segmentation algorithm in CT that best segments the male pelvis. (ii) Implement a segmentation algorithm that can be used in DIRA. (iii) Implement a fully automatic segmentation algorithm. Seven segmentation methods were tested in Matlab using images obtained from Linköping University Hospital. The methods were: active contours, atlas based registration, graph cuts, level set, region growing, thresholding and watershed. Four segmentation algorithms were selected for further analysis: phase based atlas registration, region growing, thresholding and active contours without edges. The four algorithms were combined and supplemented with other image analysis methods to form a fully automated segmentation algorithm that was implemented in DIRA. The newly developed algorithm (named MK2014) was sufficiently stable for pelvic image segmentation with a mean computational time of 45.3 s and a mean Dice similarity coefficient of 0.925 per 512×512 image. The performance of MK2014 tested on a simplified anthropomorphic phantom in DIRA gave promising result. Additional tests with more realistic phantoms are needed to confirm the general applicability of MK2014 in DIRA.

The haptic exploration of 2-D images is a challenging problem in computer haptics. Research on the topic has primarily been focused on the exploration of maps and curves. This thesis describes the design and implementation of a system for the haptic exploration of photographs. The system builds on various research directions related to assistive technology, computer haptics, and image segmentation. An object-level segmentation hierarchy is generated from the source photograph to be rendered haptically as a contour image at multiple levels-of-detail. A tool for the authoring of object-level hierarchies was developed, as well as an innovative type of user interaction by region selection for accurate and efficient image segmentation. According to an objective benchmark measuring how the new method compares with other interactive image segmentation algorithms shows that our region selection interaction is a viable alternative to marker-based interaction. The hierarchy authoring tool combined with precise algorithms for image segmentation can build contour images of the quality necessary for the images to be understood by touch with our system. The system was evaluated with a user study of 24 sighted participants divided in different groups. The first part of the study had participants explore images using haptics and answer questions about them. The second part of the study asked the participants to identify images visually after haptic exploration. Results show that using a segmentation hierarchy supporting multiple levels-of-detail of the same image is beneficial to haptic exploration. As the system gains maturity, it is our goal to make it available to blind users.

Speech Endpoint Detection, also known as Speech Segmentation, is an unsolved problem in speech processing that affects numerous applications including robust speech recognition. This task is not as trivial as it appears, and most of the existing algorithms degrade at low signal-to-noise ratios (SNRs). Most of the previous research approaches have focused on the development of robust algorithms with special attention being paid to the derivation and study of noise robust features and decision rules. This research tackles the endpoint detection problem in a different way, and proposes a novel speech endpoint detection algorithm which has been derived from Chan-Vese algorithm for image segmentation. The proposed algorithm has the ability to fuse multi features extracted from the speech signal to enhance the detection accuracy. The algorithm performance has been evaluated and compared to two widely used speech detection algorithms under various noise environments with SNR levels ranging from 0 dB to 30 dB. Furthermore, the proposed algorithm has also been applied to different types of American English phonemes. The experiments show that, even under conditions of severe noise contamination, the proposed algorithm is more efficient as compared to the reference algorithms.

Dans ce travail nous nous intéressons à la segmentation d’image 3D. Le but est de définir un cadre permettant, étant donnée une problématique de segmentation, de développer rapidement un algorithme apportant une solution à cette problématique. Afin de ne pas être restreint à un sous ensemble des types de problématique de segmentation, ce cadre doit permettre de mettre en oeuvre efficacement les différentes méthodes et les différents critères de segmentation existants, dans le but de les combiner pour définir les nouveaux algorithmes. Ce cadre doit reposer sur un modèle de structuration d’image qui représente la topologie et la géométrie d’une partition et permet d’en extraire efficacement les informations requises. Dans ce document, les différentes méthodes de segmentation existantes sont présentées afin de définir un ensemble d’opération nécessaire à leur implémentation. Une présentation des modèles existants est faite pour en déterminer avantages et inconvénients, puis le nouveau modèle est ensuite défini. Sa mise en oeuvre complète est détaillée ainsi qu’une analyse de sa complexité en temps et en mémoire pour l’ensemble des opérations précédemment définies. Des exemples d’utilisation du modèle sur des cas concrets sont ensuite décrits, ainsi que les possibilités d’extension du modèle et d’implémentation sur architecture parallèle. / In this work we focus on 3D image segmentation. The aim consists in defining a framework which, given a segmentation problem, allows to design efficiently an algorithm solving this problem. Since this framework has to be unspecific according to the kind of segmentation problem, it has to allow an efficient implementation of most segmentation techniques and criteria, in order to combine them to define new algorithms. This framework has to rely on a structuring model both representing the topology and the geometry of the partition of an image, in order to efficiently extract required information. In this document, different segmentation techniques are presented in order to define a set of primitives required for their implementation. Existing models are presented with their advantages and drawbacks, then the new structuring model is defined. Its whole implementation including details of its memory consumption and time complexity for each primitives of the previously defined set of requirements is given. Some examples of use with real image analysis problems are described, with also possible extensions of the model and its implementation on parallel architecture.

La thèse a visé à mieux comprendre les représentations sociales (RS) culinaires de cuisiniers domestiques (cuisiniers non professionnels). Existe-t-il différentes RS de la préparation culinaire ? Si oui, comment identifier ces groupes ayant des RS différentes ? Ainsi, nous nous sommes penchés sur le concept de distance à l’objet (DAO), qui, en interrogeant l’individu sur son niveau de pratique, de connaissance et d’implication, permet d’éclairer le lien entretenu par l’individu avec l’objet (qui est ici la « préparation culinaire ») en soulignant que ce lien est soumis à des variables sociales et psychosociales.Nous nous sommes alors questionnés sur l’intérêt de l’utilisation de la DAO comme variable de segmentation de l’échantillon ad hoc, et en quoi cette DAO serait un dispositif pertinent pour analyser les RS, les pratiques et leur lien étroit.Pour répondre à ces interrogations, avec une stratégie de triangulation, nous avons procédé en deux étapes. La première étape portait sur l’étude des RS de la préparation culinaire et l’impact de la DAO sur celles-ci. La seconde étape portait sur l’étude de la préparation culinaire comme « pratique signifiante » et de l’impact de la DAO sur celles-ci. Elle s’est faite par le biais d’une methode innovante basée sur des observations filmées de cuisiniers domestiques préparant un plat, suivies d’entretiens d’explicitations.L’ensemble de nos résultats nous a permis de mettre en lumière l’intérêt de la DAO comme moyen de segmentation de l’échantillon, ainsi que l’impact de la DAO sur le contenu et l’organisation des RS culinaires. Nos résultats sont discutés au regard des apports théoriques et opérationnels concernant les RS et la DAO. / The thesis aimed to understanding social representations (SR) of domestic culinary chefs (non-professional cooks). Are there different SR of culinary preparation? If so, how to identify these groups with different SR? So we focused on the concept of distance to the object (DO), which, by interviewing the individual on his level of practice, knowledge and involvement, sheds light on the link between the individual and the object (which is here the "culinary preparation") emphasizing that this link is submitted to social and psychosocial variables.We then asked about the interest of the use of DO as ad hoc segmentation variable of the sample, and how this DO would be an appropriate system to analyze SR, practices and their close connectionTo answer these questions, with a strategy of triangulation, we proceeded in two steps. The first step was the study of social representations of culinary preparation and the impact of the distance to the object (DO) on them. The second step was the study of the culinary preparation as "signifying practice" and the impact of CAD on them. It is made through an innovative method based on observations filmed domestic chefs preparing a dish, followed by explications of interviews.All our results allowed us to highlight the interest of the DAO as a means of sample segmenting, and the impact of the distance to the object on the content and structure of culinary social representations. Our results are discussed in terms of theoretical and operational contributions about social representations and distance to the object

L’urbanisation est un phénomène qui modifie l’environnement et les conditions de vie sur tous les continents. Depuis 2007, plus de la moitié de la population mondiale habite en ville. Or, beaucoup de villes de taille petite ou moyenne notamment d’Afrique, connaissent une croissance non planifiée, avec pour conséquence d’exposer les populations à de nombreux dangers environnementaux aux conséquences sanitaires complexes et donc assez mal connues. En développant un programme de recherche sur la ville de Bobo-Dioulasso, seconde ville du Burkina Faso, où les relations entre l’urbanisation et la santé ont été très peu analysées, notamment par les géographes de la santé, nous avions l’ambition d’analyser la production des inégalités de santé au regard du processus de l’urbanisation par le biais d’une approche méthodologique originale. Plusieurs indicateurs de santé ont été utilisés, du paludisme aux états nutritionnels, à la fois sur des adultes de 35 à 59 ans et sur les enfants de 6 à 59 mois, issus de quartiers choisis pour illustrer la diversité urbaine et maximiser ainsi l’amplitude des différences de santé entre les quartiers, mais aussi au sein même des quartiers.Notre travail se pose en préalable d’analyses plus élaborées des relations entre les processus d’urbanisation et les inégalités de santé en vue d’en comprendre les constructions socio-territoriales. Il a permis des avancées méthodologiques importantes en matière d’échantillonnage de l’espace urbain et il pose les bases d’une typologie de la ville montrant que sa segmentation est au cœur de la production des inégalités de santé. / The urbanization is a phenomenon which modifies the living conditions and the environment on all the continents. Since 2007, more half of the world population lives in urban areas. However, much of cities of the developing countries are growing without control, exposing the populations to many environmental risks which have complex medical consequences, rather badly known. It is particularly the case of the small and medium-sized cities of Africa.By developing a research program on the town of Bobo-Dioulasso, the second city of Burkina Faso, where the relations between urbanization and health were sparsely analyzed, particularly by the medical geographers, we aim to analyze the production of the inequalities of health taking into account urbanization process according to an original methodological approach. Several health indicators were used, among them malaria and nutritional states, both on adults from 35 to 59 years and on children from 6 to 59 months, resulting from districts which have been chosen to illustrate urban diversity in order to thus maximize the amplitude of the differences in health between the districts but also within the districts. Our work constitutes the bases of more elaborate analyses of the relations between the processes of urbanization and the inequalities of health in order to understand socio-territorial constructions of them. It allowed important methodological projections as regards sampling of urban space and it introduces a typology of the city showing that its segmentation is implied in the production of the inequalities of health.