Automatically Recovering Geometry and Texture from Large Sets of Calibrated Images

Three-dimensional models which contain both geometry and texture have numerous applications such as urban planning, physical simulation, and virtual environments. A major focus of computer vision (and recently graphics) research is the automatic recovery of three-dimensional models from two-dimensional images. After many years of research this goal is yet to be achieved. Most practical modeling systems require substantial human input and unlike automatic systems are not scalable. This thesis presents a novel method for automatically recovering dense surface patches using large sets (1000's) of calibrated images taken from arbitrary positions within the scene. Physical instruments, such as Global Positioning System (GPS), inertial sensors, and inclinometers, are used to estimate the position and orientation of each image. Essentially, the problem is to find corresponding points in each of the images. Once a correspondence has been established, calculating its three-dimensional position is simply a matter of geometry. Long baseline images improve the accuracy. Short baseline images and the large number of images greatly simplifies the correspondence problem. The initial stage of the algorithm is completely local and scales linearly with the number of images. Subsequent stages are global in nature, exploit geometric constraints, and scale quadratically with the complexity of the underlying scene. We describe techniques for: 1) detecting and localizing surface patches; 2) refining camera calibration estimates and rejecting false positive surfels; and 3) grouping surface patches into surfaces and growing the surface along a two-dimensional manifold. We also discuss a method for producing high quality, textured three-dimensional models from these surfaces. Some of the most important characteristics of this approach are that it: 1) uses and refines noisy calibration estimates; 2) compensates for large variations in illumination; 3) tolerates significant soft occlusion (e.g. tree branches); and 4) associates, at a fundamental level, an estimated normal (i.e. no frontal-planar assumption) and texture with each surface patch.

Automated Placement of Cameras in a Floorplan to Satisfy Task-Specific Constraints

In many multi-camera vision systems the effect of camera locations on the task-specific quality of service is ignored. Researchers in Computational Geometry have proposed elegant solutions for some sensor location problem classes. Unfortunately, these solutions utilize unrealistic assumptions about the cameras' capabilities that make these algorithms unsuitable for many real-world computer vision applications: unlimited field of view, infinite depth of field, and/or infinite servo precision and speed. In this paper, the general camera placement problem is first defined with assumptions that are more consistent with the capabilities of real-world cameras. The region to be observed by cameras may be volumetric, static or dynamic, and may include holes that are caused, for instance, by columns or furniture in a room that can occlude potential camera views. A subclass of this general problem can be formulated in terms of planar regions that are typical of building floorplans. Given a floorplan to be observed, the problem is then to efficiently compute a camera layout such that certain task-specific constraints are met. A solution to this problem is obtained via binary optimization over a discrete problem space. In preliminary experiments the performance of the resulting system is demonstrated with different real floorplans.

Tracking a Large Number of Objects from Multiple Views

We propose a multi-object multi-camera framework for tracking large numbers of tightly-spaced objects that rapidly move in three dimensions. We formulate the problem of finding correspondences across multiple views as a multidimensional assignment problem and use a greedy randomized adaptive search procedure to solve this NP-hard problem efficiently. To account for occlusions, we relax the one-to-one constraint that one measurement corresponds to one object and iteratively solve the relaxed assignment problem. After correspondences are established, object trajectories are estimated by stereoscopic reconstruction using an epipolar-neighborhood search. We embedded our method into a tracker-to-tracker multi-view fusion system that not only obtains the three-dimensional trajectories of closely-moving objects but also accurately settles track uncertainties that could not be resolved from single views due to occlusion. We conducted experiments to validate our greedy assignment procedure and our technique to recover from occlusions. We successfully track hundreds of flying bats and provide an analysis of their group behavior based on 150 reconstructed 3D trajectories.

Object Matching in Distributed Video Surveillance Systems by LDA-Based Appearance Descriptors

Establishing correspondences among object instances is still challenging in multi-camera surveillance systems, especially when the cameras’ fields of view are non-overlapping. Spatiotemporal constraints can help in solving the correspondence problem but still leave a wide margin of uncertainty. One way to reduce this uncertainty is to use appearance information about the moving objects in the site. In this paper we present the preliminary results of a new method that can capture salient appearance characteristics at each camera node in the network. A Latent Dirichlet Allocation (LDA) model is created and maintained at each node in the camera network. Each object is encoded in terms of the LDA bag-of-words model for appearance. The encoded appearance is then used to establish probable matching across cameras. Preliminary experiments are conducted on a dataset of 20 individuals and comparison against Madden’s I-MCHR is reported.

An architecture for agent-enhanced network service provisioning through SLA negotiation

This paper focuses on two main areas. We first investigate various aspects of subscription and session Service Level Agreement (SLA) issues such as negotiating and setting up network services with Quality of Service (QoS) and pricing preferences. We then introduce an agent-enhanced service architecture that facilitates these services. A prototype system consisting of real-time agents that represent various network stakeholders was developed. A novel approach is presented where the agent system is allowed to communicate with a simulated network. This allows functional and dynamic behaviour of the network to be investigated under various agent-supported scenarios. This paper also highlights the effects of SLA negotiation and dynamic pricing in a competitive multi-operator networks environment.

A Data Model for Content Modelling of Temporal Media

This paper describes a data model for content representation of temporal media in an IP based sensor network. The model is formed by introducing the idea of semantic-role from linguistics into the underlying concepts of formal event representation with the aim of developing a common event model. The architecture of a prototype system for a multi camera surveillance system, based on the proposed model is described. The important aspects of the proposed model are its expressiveness, its ability to model content of temporal media, and its suitability for use with a natural language interface. It also provides a platform for temporal information fusion, as well as organizing sensor annotations by help of ontologies.

Real-time GPU color-based segmentation of football players

In this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex color patterns, a Gaussian Mixture Models (GMM) is applied as segmentation paradigm, in order to analyze sport live images and video. Optimization techniques have also been applied over the C++ implementation using profiling tools focused on high performance. Time consuming tasks were implemented over NVIDIA's CUDA platform, and later restructured and enhanced, speeding up the whole process significantly. Our resulting code is around 4-11 times faster on a low cost GPU than a highly optimized C++ version on a central processing unit (CPU) over the same data. Real time has been obtained processing until 64 frames per second. An important conclusion derived from our study is the scalability of the application to the number of cores on the GPU. © 2011 Springer-Verlag.

Ventilação mista em edifícios de habitação

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Civil na Área de Especialização de Edificações

Calibration de systèmes de caméras et projecteurs dans des applications de création multimédia

Ce mémoire s'intéresse à la vision par ordinateur appliquée à des projets d'art technologique. Le sujet traité est la calibration de systèmes de caméras et de projecteurs dans des applications de suivi et de reconstruction 3D en arts visuels et en art performatif. Le mémoire s'articule autour de deux collaborations avec les artistes québécois Daniel Danis et Nicolas Reeves. La géométrie projective et les méthodes de calibration classiques telles que la calibration planaire et la calibration par géométrie épipolaire sont présentées pour introduire les techniques utilisées dans ces deux projets. La collaboration avec Nicolas Reeves consiste à calibrer un système caméra-projecteur sur tête robotisée pour projeter des vidéos en temps réel sur des écrans cubiques mobiles. En plus d'appliquer des méthodes de calibration classiques, nous proposons une nouvelle technique de calibration de la pose d'une caméra sur tête robotisée. Cette technique utilise des plans elliptiques générés par l'observation d'un seul point dans le monde pour déterminer la pose de la caméra par rapport au centre de rotation de la tête robotisée. Le projet avec le metteur en scène Daniel Danis aborde les techniques de calibration de systèmes multi-caméras. Pour son projet de théâtre, nous avons développé un algorithme de calibration d'un réseau de caméras wiimotes. Cette technique basée sur la géométrie épipolaire permet de faire de la reconstruction 3D d'une trajectoire dans un grand volume à un coût minime. Les résultats des techniques de calibration développées sont présentés, de même que leur utilisation dans des contextes réels de performance devant public.

Vidéosurveillance intelligente pour la détection de chutes chez les personnes âgées

Les pays industrialisés comme le Canada doivent faire face au vieillissement de leur population. En particulier, la majorité des personnes âgées, vivant à domicile et souvent seules, font face à des situations à risques telles que des chutes. Dans ce contexte, la vidéosurveillance est une solution innovante qui peut leur permettre de vivre normalement dans un environnement sécurisé. L’idée serait de placer un réseau de caméras dans l’appartement de la personne pour détecter automatiquement une chute. En cas de problème, un message pourrait être envoyé suivant l’urgence aux secours ou à la famille via une connexion internet sécurisée. Pour un système bas coût, nous avons limité le nombre de caméras à une seule par pièce ce qui nous a poussé à explorer les méthodes monoculaires de détection de chutes. Nous avons d’abord exploré le problème d’un point de vue 2D (image) en nous intéressant aux changements importants de la silhouette de la personne lors d’une chute. Les données d’activités normales d’une personne âgée ont été modélisées par un mélange de gaussiennes nous permettant de détecter tout événement anormal. Notre méthode a été validée à l’aide d’une vidéothèque de chutes simulées et d’activités normales réalistes. Cependant, une information 3D telle que la localisation de la personne par rapport à son environnement peut être très intéressante pour un système d’analyse de comportement. Bien qu’il soit préférable d’utiliser un système multi-caméras pour obtenir une information 3D, nous avons prouvé qu’avec une seule caméra calibrée, il était possible de localiser une personne dans son environnement grâce à sa tête. Concrêtement, la tête de la personne, modélisée par une ellipsoide, est suivie dans la séquence d’images à l’aide d’un filtre à particules. La précision de la localisation 3D de la tête a été évaluée avec une bibliothèque de séquence vidéos contenant les vraies localisations 3D obtenues par un système de capture de mouvement (Motion Capture). Un exemple d’application utilisant la trajectoire 3D de la tête est proposée dans le cadre de la détection de chutes. En conclusion, un système de vidéosurveillance pour la détection de chutes avec une seule caméra par pièce est parfaitement envisageable. Pour réduire au maximum les risques de fausses alarmes, une méthode hybride combinant des informations 2D et 3D pourrait être envisagée.

Métriques de routage dans les réseaux maillés sans fil

Ces dernières années, les technologies sans fil ont connu un essor fulgurant. Elles ont permis la mise en place de réseaux sans fil à hautes performances. Les réseaux maillées sans fil (RMSF) sont une nouvelle génération de réseaux sans fil qui offrent des débits élevés par rapport aux réseaux Wi-Fi (Wireless Fidelity) classiques et aux réseaux ad-hoc. Ils présentent de nombreux avantages telles que leur forte tolérance aux pannes, leur robustesse, leur faible coût etc. Les routeurs des RMSF peuvent disposer de plusieurs interfaces radio et chaque interface peut opérer sur plusieurs canaux distincts, c’est des RMSF multiples-radios, multiples-canaux. Ce type de réseau peut accroître de manière considérable les performances des RMSF. Cependant plusieurs problèmes subsistent et doivent être résolus notamment celui du routage. Le routage dans les RMSF demeure un défi majeur. Le but des protocoles de routage est de trouver les meilleures routes i.e. des routes qui maximisent les débits et minimisent les délais, lors de l’acheminement du trafic. La qualité des routes dans les RMSF peut être fortement affectée par les interférences, les collisions, les congestions etc. Alors les protocoles doivent être en mesure de détecter ces problèmes pour pouvoir en tenir compte lors de la sélection des routes. Plusieurs études ont été dédiées aux métriques et aux protocoles de routage dans les RMSF afin de maximiser les performances de celles ci. Mais la plupart ne prennent pas en considération toutes les contraintes telles que les interférences, le problème des stations cachées etc. Ce mémoire propose une nouvelle métrique de routage pour RMSF. Nous avons mis en place une nouvelle métrique de routage pour RMSF appelée MBP (Metric Based on Probabilities). Cette métrique est destinée aux RMSF mono-radio ou multiples-radios. Elle permet d’éviter les routes à forte ii interférence. Les résultats des simulations ont montré que MBP présente des améliorations par rapport à certaines métriques : ETT, WCETT et iAWARE qui sont connues dans le domaine.

Evaluation of probabilistic occupancy map people detection for surveillance systems

In this paper, we evaluate the Probabilistic Occupancy Map (POM) pedestrian detection algorithm on the PETS 2009 benchmark dataset. POM is a multi-camera generative detection method, which estimates ground plane occupancy from multiple background subtraction views. Occupancy probabilities are iteratively estimated by fitting a synthetic model of the background subtraction to the binary foreground motion. Furthermore, we test the integration of this algorithm into a larger framework designed for understanding human activities in real environments. We demonstrate accurate detection and localization on the PETS dataset, despite suboptimal calibration and foreground motion segmentation input.

Robust real-time tracking for visual surveillance

This paper describes a real-time multi-camera surveillance system that can be applied to a range of application domains. This integrated system is designed to observe crowded scenes and has mechanisms to improve tracking of objects that are in close proximity. The four component modules described in this paper are (i) motion detection using a layered background model, (ii) object tracking based on local appearance, (iii) hierarchical object recognition, and (iv) fused multisensor object tracking using multiple features and geometric constraints. This integrated approach to complex scene tracking is validated against a number of representative real-world scenarios to show that robust, real-time analysis can be performed. Copyright (C) 2007 Hindawi Publishing Corporation. All rights reserved.

Narrativising the facts: acting in screen and stage docudrama

This article presents findings and seeks to establish the theoretical markers that indicate the growing importance of fact-based drama in screen and theatre performance to the wider Anglophone culture. During the final decade of the twentieth century and the opening one of the twenty-first, television docudrama and documentary theatre have grown in visibility and importance in the UK, providing key responses to social, cultural and political change over the millennial period. Actors were the prime focus for the enquiry principally because so little research has been done into the special demands that fact-based performance makes on them. The main emphasis in actor training (in the UK at any rate) is, as it always has been, on preparation for fictional drama. Preparation in acting schools is also heavily geared towards stage performance. Our thesis was that performers called upon to play the roles of real people, in whatever medium, have added responsibilities both towards history and towards real individuals and their families. Actors must engage with ethical questions whether they like it or not, and we found them keenly aware of this. In the course of the research, we conducted 30 interviews with a selection of actors ranging from the experienced to the recently-trained. We also interviewed a few industry professionals and actor trainers. Once the interviews started it was clear that actors themselves made little or no distinction between how they set about their work for television and film. The essential disciplines for work in front of the camera, they told us, are the same whether the camera is electronic or photographic. Some adjustments become necessary, of course in the multi-camera TV studio. But much serious drama for the screen is made on film anyway. We found it was also the case that young actors now tend to get their first paid employment before a camera rather than on a stage. The screen-before-stage tendency, along with the fundamental re-shaping that has gone on in the British theatre since at least the early 1980s, had implications for actor training. We have also found that theatre work still tends to be most valued by actors. For all the actors we interviewed, theatre was what they liked doing best because it was there they could practice and develop their skills, there they could work most collectively towards performance, and there they could more directly experience audience feedback in the real time of the stage play. The current world of television has been especially constrained in regard to rehearsal time in comparison to theatre (and, to a lesser extent, film). This has also affected actors’ valuation of their work. Theatre is, and is not, the most important medium in which they find work. Theatre is most important spiritually and intellectually, because in theatre is collaborative, intensive, and involving; theatre is not as important in financial and career terms, because it is not as lucrative and not as visible to a large public as acting for the screen. Many actors took the view that, for all the industrial differences that do affect them and inevitably interest the academic, acting for the visible media of theatre, film and television involved fundamentally the same process with slightly different emphases.

The look: style, technology and televisuality in the New Who

This chapter explores the distinctive qualities of the Matt Smith era Doctor Who, focusing on how dramatic emphases are connected with emphases on visual style, and how this depends on the programme's production methods and technologies. Doctor Who was first made in the 1960s era of live, studio-based, multi-camera television with monochrome pictures. However, as technical innovations like colour filming, stereo sound, CGI and post-production effects technology have been routinely introduced into the programme, and now High Definition (HD) cameras, they have given Doctor Who’s creators new ways of making visually distinctive narratives. Indeed, it has been argued that since the 1980s television drama has become increasingly like cinema in its production methods and aesthetic aims. Viewers’ ability to view the programme on high-specification TV sets, and to record and repeat episodes using digital media, also encourage attention to visual style in television as much as in cinema. The chapter evaluates how these new circumstances affect what Doctor Who has become and engages with arguments that visual style has been allowed to override characterisation and story in the current Doctor Who. The chapter refers to specific episodes, and frames the analysis with reference to earlier years in Doctor Who’s long history. For example, visual spectacle using green-screen and CGI can function as a set-piece (at the opening or ending of an episode) but can also work ‘invisibly’ to render a setting realistically. Shooting on location using HD cameras provides a rich and detailed image texture, but also highlights mistakes and especially problems of lighting. The reduction of Doctor Who’s budget has led to Steven Moffat’s episodes relying less on visual extravagance, connecting back both to Russell T. Davies’s concern to show off the BBC’s investment in the series but also to reference British traditions of gritty and intimate social drama. Pressures to capitalise on Doctor Who as a branded product are the final aspect of the chapter’s analysis, where the role of Moffat as ‘showrunner’ links him to an American (not British) style of television production where the preservation of format and brand values give him unusual power over the look of the series.