Thesis (Ph.D.)--Texas Christian University, 2007. / Title from dissertation title page (viewed Jul. 27, 2007). Includes abstract. Includes bibliographical references.

This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the saliency of image regions and to provide an efficient short cut for object detection and recognition. The scene is represented by means of a low-dimensional global description obtained from low-level features. The global scene features are then used to predict the probability of presence of the target object in the scene, and its location and scale, before exploring the image. Scene information can then be used to modulate the saliency of image regions early during the visual processing in order to provide an efficient short cut for object detection and recognition.

Current computer vision techniques can effectively monitor gross activities in sparse environments. Unfortunately, visual stimulus is often not sufficient for reliably discriminating between many types of activity. In many cases where the visual information required for a particular task is extremely subtle or non-existent, there is often audio stimulus that is extremely salient for a particular classification or anomaly detection task. Unfortunately unlike visual events, independent sounds are often very ambiguous and not sufficient to define useful events themselves. Without an effective method of learning causally-linked temporal sequences of sound events that are coupled to the visual events, these sound events are generally only useful for independent anomalous sounds detection, e.g., detecting a gunshot or breaking glass. This paper outlines a method for automatically detecting a set of audio events and visual events in a particular environment, for determining statistical anomalies, for automatically clustering these detected events into meaningful clusters, and for learning salient temporal relationships between the audio and visual events. This results in a compact description of the different types of compound audio-visual events in an environment.

L'utilisation de systèmes multi-caméras est de plus en plus populaire et il y a un intérêt croissant à résoudre les problèmes de vision par ordinateur dans ce contexte particulier. L'objectif étant de ne pas se limiter à l'application des méthodes monoculaires mais de proposer de nouvelles approches intrinsèquement orientées vers les systèmes multi-caméras. Le travail de cette thèse a pour objectif une meilleure compréhension du problème de segmentation multi-vues, pour proposer une nouvelle approche qui tire meilleur parti de la redondance d'information inhérente à l'utilisation de plusieurs points de vue. La segmentation multi-vues est l'identification de l'objet observé simultanément dans plusieurs caméras et sa séparation de l'arrière-plan. Les approches monoculaires classiques raisonnent sur chaque image de manière indépendante et ne bénéficient pas de la présence de plusieurs points de vue. Une question clé de la segmentation multi-vues réside dans la propagation d'information sur la segmentation entres les images tout en minimisant la complexité et le coût en calcul. Dans ce travail, nous investiguons en premier lieu l'utilisation d'un ensemble épars d'échantillons de points 3D. L'algorithme proposé classe chaque point comme "vide" s'il se projette sur une région du fond et "occupé" s'il se projette sur une région avant-plan dans toutes les vues. Un modèle probabiliste est proposé pour estimer les modèles de couleur de l'avant-plan et de l'arrière-plan, que nous testons sur plusieurs jeux de données de l'état de l'art. Deux extensions du modèle sont proposées. Dans la première, nous montrons la flexibilité de la méthode proposée en intégrant les mélanges de Gaussiennes comme modèles d'apparence. Cette intégration est possible grâce à l'utilisation de l'inférence variationelle. Dans la seconde, nous montrons que le modèle bayésien basé sur les échantillons 3D peut aussi être utilisé si des mesures de profondeur sont présentes. Les résultats de l'évaluation montrent que les problèmes de robustesse, typiquement causés par les ambigüités couleurs entre fond et forme, peuvent être au moins partiellement résolus en utilisant cette information de profondeur. A noter aussi qu'une approche multi-vues reste meilleure qu'une méthode monoculaire utilisant l'information de profondeur. Les différents tests montrent aussi les limitations de la méthode basée sur un échantillonnage éparse. Cela a montré la nécessité de proposer un modèle reposant sur une description plus riche de l'apparence dans les images, en particulier en utilisant les superpixels. L'une des contributions de ce travail est une meilleure modélisation des contraintes grâce à un schéma par coupure de graphes liant les régions d'images aux échantillons 3D. Dans le cas statique, les résultats obtenus rivalisent avec ceux de l'état de l'art mais sont obtenus avec beaucoup moins de points de vue. Les résultats dans le cas dynamique montrent l'intérêt de la propagation de l'information de segmentation à travers la géométrie et le mouvement. Enfin, la dernière partie de cette thèse explore la possibilité d'améliorer le suivi dans les systèmes multi-caméras non calibrés. Un état de l'art sur le suivi monoculaire et multi-caméras est présenté et nous explorons l'utilisation des matrices d'autosimilarité comme moyen de décrire le mouvement et de le comparer entre plusieurs caméras. / There has been a growing interest for multi-camera systems and many interesting works have tried to tackle computer vision problems in this particular configuration. The general objective is to propose new multi-view oriented methods instead of applying limited monocular approaches independently for each viewpoint. The work in this thesis is an attempt to have a better understanding of the multi-view object segmentation problem and to propose an alternative approach making maximum use of the available information from different viewpoints. Multiple view segmentation consists in segmenting objects simultaneously in several views. Classic monocular segmentation approaches reason on a single image and do not benefit from the presence of several viewpoints. A key issue in that respect is to ensure propagation of segmentation information between views while minimizing complexity and computational cost. In this work, we first investigate the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve this goal. The proposed algorithm softly assigns each of these 3D samples to the scene background if it projects on the background region in at least one view, or to the foreground if it projects on foreground region in all views. A complete probabilistic framework is proposed to estimate foreground/background color models and the method is tested on various datasets from state of the art. Two different extensions of the sparse 3D sampling segmentation framework are proposed in two scenarios. In the first, we show the flexibility of the sparse sampling framework, by using variational inference to integrate Gaussian mixture models as appearance models. In the second scenario, we propose a study of how to incorporate depth measurements in multi-view segmentation. We present a quantitative evaluation, showing that typical color-based segmentation robustness issues due to color-space ambiguity between foreground and background, can be at least partially mitigated by using depth, and that multi-view color depth segmentation also improves over monocular color depth segmentation strategies. The various tests also showed the limitations of the proposed 3D sparse sampling approach which was the motivation to propose a new method based on a richer description of image regions using superpixels. This model, that expresses more subtle relationships of the problem trough a graph construction linking superpixels and 3D samples, is one of the contributions of this work. In this new framework, time related information is also integrated. With static views, results compete with state of the art methods but they are achieved with significantly fewer viewpoints. Results on videos demonstrate the benefit of segmentation propagation through geometric and temporal cues. Finally, the last part of the thesis explores the possibilities of tracking in uncalibrated multi-view scenarios. A summary of existing methods in this field is presented, in both mono-camera and multi-camera scenarios. We investigate the potential of using self-similarity matrices to describe and compare motion in the context of multi-view tracking.

Aproximando conceitos como Teatro Documental (Erwin Psicator), Biodrama (Vivi Tellas), autoficção (Serge Doubrovsky) e espetáculos contemporâneos previamente selecionados por suas proximidades discursivas, a pesquisa investiga práticas que tratama memória como agenciadora de criações teatrais. O interesse principal da investigação é refletir como esta memórias e torna uma possibilidade virtual para a problematização e potencialização do "real" na cena, criando mecanismos de composição espetaculares, que aqui se define como Biopoéticas Teatrais. Este processo mnemônico é problematizado neste trabalho tal qual catalisador da cena, inserindo-se em esferas de caráter pessoal, em atos de exposição, pela experiência do revelar-se a si e ao outro em cena. Assim, procura-se evidenciar uma cena que transite entre o individual e o coletivo, criando uma manutenção própria de organização. Busca-se ainda identificar aportes da prática desta construção que se utiliza de si para criação cênica, evidenciando o confronto entre autor e cena, real e ficcional. Para tanto, serão enfocadas as estratégias de criação de três espetáculos: Luís Antônio-Gabriela (direção de Nelson Baskerville), Natalício Cavalo (direção de Patrícia Fagundes) e Br-Trans (criação de Silvero Pereira), que nascem a partir da memória, de relatos, fotografias, vontades, fracassos, etc, para compreender e levantar potencialidades que possibilitem reflexões cênicas, práticas sobre a multiplicidade da vida posta no palco, potencializando produções singulares no teatro. / Approaching concepts such as Documentary Theatre (Erwin Psicator), Biodrama (ViviTellas), autofiction (Serge Doubrovsky) and contemporary shows previously selected by their proximity discursive, this research investigates practices that treat memory as a mediator theatrical creations. The main interest of this research is to understand how this memory becomes a virtual possibility for questioning and enhancement of "real" in the scene, creating spectacular composition mechanisms that here is defined as BioPoetic Theater. This mnemonic process is questioned in this work just like catalyst scene by entering into personal spheres, in acts of exposure, the experience prove to themselves and to each other on stage. So, we try to highlight a scene that transit between the individual and the collective, creating its own maintenance organization. It also seeks to identify practical contributions of this construction that uses itself to scenic creation, highlighting the confrontation between author and scene, real and fictional. Therefore, strategies for creating three shows will be analyzed: Luis Antonio - Gabriela (directed by Nelson Baskerville), Natalício Horse (directed by Patricia Fagundes) and Br -Trans (creating Silvero Pereira), born from memory, reports, photographs, wills, failures, etc., to understand and lift capabilities that enable scenic reflections, practices on the multiplicity of life put on stage, leveraging unique productions at the theater.

This research, situated at the intersection of sociology, science and technology studies and police studies, provides the first sociological account of Crime Scene Investigator (CSI) training in England and Wales. Focusing on the acquisition and everyday enactment of CSI expertise, this qualitative, ethnographic investigation asks (1) what are the roles, practices and expertise of the CSI and (2) how is the CSI’s expertise developed in training and enacted in everyday work. These questions are explored through participant observation at the main training centre for UK CSIs, observation at crime scenes, interviews with trainees during and after their training and visual methods. By unpicking the visible and invisible components of CSI work, I analyse how CSIs are trained to document crime scenes and explore the practices of transforming a potentially relevant object from these locations into artefacts that meet the requirements of courtroom scrutiny. I demonstrate how CSIs engage actively and reflexively with the requirements of different conceptions of objectivity and the changing demands placed on them. They continually and performatively negotiate and delimit multiple boundaries, from the very literal in demarcating a crime scene to claiming their position within the investigative hierarchy in each interaction. Unlike other discussions of boundary work, for the CSI this is iterative, requires constant effort and is embedded in their routine practice. Within police environments, the CSI has scope for such boundary work. In the courtroom, however, crime scene investigation is narrowly defined. This thesis develops our understanding of the CSI and crime scene investigation as a practice. It stresses the significance of taking this actor seriously in any account of forensic science and investigative practices. By viewing the CSI as simply an evidence collector, or not considering her work at all, the expertise and pivotal role of this actor in the meaningful and efficient use of science in policing is blackboxed. My detailed qualitative analysis of the CSI’s role, work and specialist expertise contributes a necessary account of a key actor in the police and criminal justice system.

Aproximando conceitos como Teatro Documental (Erwin Psicator), Biodrama (Vivi Tellas), autoficção (Serge Doubrovsky) e espetáculos contemporâneos previamente selecionados por suas proximidades discursivas, a pesquisa investiga práticas que tratama memória como agenciadora de criações teatrais. O interesse principal da investigação é refletir como esta memórias e torna uma possibilidade virtual para a problematização e potencialização do "real" na cena, criando mecanismos de composição espetaculares, que aqui se define como Biopoéticas Teatrais. Este processo mnemônico é problematizado neste trabalho tal qual catalisador da cena, inserindo-se em esferas de caráter pessoal, em atos de exposição, pela experiência do revelar-se a si e ao outro em cena. Assim, procura-se evidenciar uma cena que transite entre o individual e o coletivo, criando uma manutenção própria de organização. Busca-se ainda identificar aportes da prática desta construção que se utiliza de si para criação cênica, evidenciando o confronto entre autor e cena, real e ficcional. Para tanto, serão enfocadas as estratégias de criação de três espetáculos: Luís Antônio-Gabriela (direção de Nelson Baskerville), Natalício Cavalo (direção de Patrícia Fagundes) e Br-Trans (criação de Silvero Pereira), que nascem a partir da memória, de relatos, fotografias, vontades, fracassos, etc, para compreender e levantar potencialidades que possibilitem reflexões cênicas, práticas sobre a multiplicidade da vida posta no palco, potencializando produções singulares no teatro. / Approaching concepts such as Documentary Theatre (Erwin Psicator), Biodrama (ViviTellas), autofiction (Serge Doubrovsky) and contemporary shows previously selected by their proximity discursive, this research investigates practices that treat memory as a mediator theatrical creations. The main interest of this research is to understand how this memory becomes a virtual possibility for questioning and enhancement of "real" in the scene, creating spectacular composition mechanisms that here is defined as BioPoetic Theater. This mnemonic process is questioned in this work just like catalyst scene by entering into personal spheres, in acts of exposure, the experience prove to themselves and to each other on stage. So, we try to highlight a scene that transit between the individual and the collective, creating its own maintenance organization. It also seeks to identify practical contributions of this construction that uses itself to scenic creation, highlighting the confrontation between author and scene, real and fictional. Therefore, strategies for creating three shows will be analyzed: Luis Antonio - Gabriela (directed by Nelson Baskerville), Natalício Horse (directed by Patricia Fagundes) and Br -Trans (creating Silvero Pereira), born from memory, reports, photographs, wills, failures, etc., to understand and lift capabilities that enable scenic reflections, practices on the multiplicity of life put on stage, leveraging unique productions at the theater.

Aproximando conceitos como Teatro Documental (Erwin Psicator), Biodrama (Vivi Tellas), autoficção (Serge Doubrovsky) e espetáculos contemporâneos previamente selecionados por suas proximidades discursivas, a pesquisa investiga práticas que tratama memória como agenciadora de criações teatrais. O interesse principal da investigação é refletir como esta memórias e torna uma possibilidade virtual para a problematização e potencialização do "real" na cena, criando mecanismos de composição espetaculares, que aqui se define como Biopoéticas Teatrais. Este processo mnemônico é problematizado neste trabalho tal qual catalisador da cena, inserindo-se em esferas de caráter pessoal, em atos de exposição, pela experiência do revelar-se a si e ao outro em cena. Assim, procura-se evidenciar uma cena que transite entre o individual e o coletivo, criando uma manutenção própria de organização. Busca-se ainda identificar aportes da prática desta construção que se utiliza de si para criação cênica, evidenciando o confronto entre autor e cena, real e ficcional. Para tanto, serão enfocadas as estratégias de criação de três espetáculos: Luís Antônio-Gabriela (direção de Nelson Baskerville), Natalício Cavalo (direção de Patrícia Fagundes) e Br-Trans (criação de Silvero Pereira), que nascem a partir da memória, de relatos, fotografias, vontades, fracassos, etc, para compreender e levantar potencialidades que possibilitem reflexões cênicas, práticas sobre a multiplicidade da vida posta no palco, potencializando produções singulares no teatro. / Approaching concepts such as Documentary Theatre (Erwin Psicator), Biodrama (ViviTellas), autofiction (Serge Doubrovsky) and contemporary shows previously selected by their proximity discursive, this research investigates practices that treat memory as a mediator theatrical creations. The main interest of this research is to understand how this memory becomes a virtual possibility for questioning and enhancement of "real" in the scene, creating spectacular composition mechanisms that here is defined as BioPoetic Theater. This mnemonic process is questioned in this work just like catalyst scene by entering into personal spheres, in acts of exposure, the experience prove to themselves and to each other on stage. So, we try to highlight a scene that transit between the individual and the collective, creating its own maintenance organization. It also seeks to identify practical contributions of this construction that uses itself to scenic creation, highlighting the confrontation between author and scene, real and fictional. Therefore, strategies for creating three shows will be analyzed: Luis Antonio - Gabriela (directed by Nelson Baskerville), Natalício Horse (directed by Patricia Fagundes) and Br -Trans (creating Silvero Pereira), born from memory, reports, photographs, wills, failures, etc., to understand and lift capabilities that enable scenic reflections, practices on the multiplicity of life put on stage, leveraging unique productions at the theater.

In this thesis, we propose a new representation, which we name Interaction Bisector Surface (IBS), that can describe the general nature of spatial relationship. We show that the IBS can be applied in 3D scene analysis, retrieval and synthesis. Despite the fact that the spatial relationship between different objects plays a significant role in describing the context, few works have focused on elaborating a representation that can describe arbitrary interactions between different objects. Previous methods simply concatenate the individual state vectors to produce a joint space, or only use simple representations such as relative vectors or contacts to describe the context. Such representations do not contain detailed information of spatial relationships. They cannot describe complex interactions such as hooking and enclosure. The IBS is a data structure with rich information about the interaction. It provides the topological, geometric and correspondence features that can be used to classify and recognize interactions. The topological features are at the most abstract level and it can be used to recognize spatial relationships such as enclosure, hooking and surrounding. The geometric features encode the fine details of interactions. The correspondence feature describes which parts of the scene elements contribute to the interaction and is especially useful for recognizing character-object interactions. We show examples of successful classification and retrieval of different types of data including indoor static scenes and dynamic scenes which contain character-object interactions. We also conduct an exhaustive comparison which shows that our method outperforms existing approaches. We also propose a novel approach to automatically synthesizing new interactions from example scenes and new objects. Given an example scene composed of two objects, the open space between the objects is abstracted by the IBS. Then, an translation, rotation and scale equivariant feature called shape coverage feature, which encodes how the point in the open space is surrounded by the environment, is computed near the IBS and around the open space of the new objects. Finally, a novel scene is synthesized by conducting a partial matching of the open space around the new objects with the IBS. Using our approach, new scenes can be automatically synthesized from example scenes and new objects without relying on label information, which is especially useful when the data of scenes and objects come from multiple sources.

Scene parsing, or segmenting all the objects in an image and identifying their categories, is one of the core problems of computer vision. In order to achieve an object-level semantic segmentation, we build upon the recent superparsing approach by Tighe and Lazebnik, which is a nonparametric solution to the image labeling problem. Superparsing consists of four steps. For a new query image, the most similar images from the training dataset of labeled images is retrieved based on global features. In the second step, the query image is segmented into superpxiels and 20 di erent local features are computed for each superpixel. We propose to use the SLICO segmentation method to allow control of the size, shape and compactness of the superpixels because SLICO is able to produce accurate boundaries. After all superpixel features have been extracted, feature-based matching of superpixels is performed to nd the nearest-neighbour superpixels in the retrieval set for each query superpxiel. Based on the neighbouring superpixels a likelihood score for each class is calculated. Finally, we formulate a Conditional Random Field (CRF) using the likelihoods and a pairwise cost both computed from nonparametric estimation to optimize the labeling of the image. Speci cally, we de ne a novel pairwise cost to provide stronger semantic contextual constraints by incorporating the similarity of adjacent superpixels depending on local features. The optimized labeling obtained with the CRF results in superpixels with the same labels grouped together to generate segmentation results which also identify the categories of objects in an image. We evaluate our improvements to the superparsing approach using segmentation evaluation measures as well as the per-pixel rate and average per-class rate in a labeling evaluation. We demonstrate the success of our modi ed approach on the SIFT Flow dataset, and compare our results with the basic superparsing methods proposed by Tighe and Lazebnik.