The probability hypothesis density (PHD), popularized by Ronald Mahler, presents a novel and theoretically-rigorous approach to multitarget, multisensor tracking. Based on random set theory, the PHD is the first moment of a point process of a random track set, and it can be propagated by Bayesian prediction and observation equations to form a multitarget, multisensor tracking filter. The advantage of the PHD filter lies in its ability to estimate automatically the expected number of targets present, to fuse easily different kinds of data observations, and to locate targets without performing any explicit report-to-track association. We apply a particle-filter implementation of the PHD filter to realistic multitarget, multisensor tracking using passive coherent location (PCL) systems that exploit illuminators of opportunity such as FM radio stations. The objective of this dissertation is to enhance the usefulness of the PHD particle filter for multitarget, multisensor tracking, in general, and within the context of PCL, in particular. This involves a number of thrusts, including: 1) devising intelligent proposal densities for particle placement, 2) devising a peak-extraction algorithm for extracting information from the PHD, 3) incorporating realistic probabilities of detection and signal-to-noise ratios (including multipath effects) to model realistic PCL scenarios, 4) using range, Doppler, and direction of arrival (DOA) observations to test the target detection and data fusion capabilities of the PHD filter, and 5) clarifying the concepts behind FISST and the PHD to make them more accessible to the practicing engineer. A goal of this dissertation is to serve as a tutorial for anyone interested in becoming familiar with the probability hypothesis density and associated PHD particle filter. It is hoped that, after reading this thesis, the reader will have gained a clearer understanding of the PHD and the functionality and effectiveness of the PHD particle filter.

Thesis (Ph. D.)--University of Missouri-Columbia, 2000. / Typescript. Vita. Includes bibliographical references (leaves 113-117). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2000. / Typescript. Vita. Includes bibliographical references (leaves 113-117). Also available on the Internet.

Cette thèse s'inscrit dans la thématique classique de l'homogénéisation des milieux hétérogènes linéaires et a pour but l'étude et la prédiction du comportement optique de couches de peintures. L'objectif est double : d'une part caractériser et modéliser la microstructure hétérogène des matériaux utilisés dans les revêtements de peinture, d'autre part prédire le comportement optique de ces matériaux par des moyens numériques, et étudier l'influence de la morphologie sur les propriétés optiques. Ces travaux ont été faits dans le cadre du projet LIMA (Lumière Interaction Matière Aspect), soutenu par l'Agence Nationale de la Recherche et en partenariat avec le groupe PSA. Des images acquises par microscopie électronique à balayage (MEB) sont obtenues de différentes couches de peintures. On y distingue différentes échelles pigmentaires : microscopique et nanoscopique. Des images représentatives des échelles sont alors sélectionnées et segmentées, pour permettre la prise de mesures morphologiques. Ces mesures permettent l'élaboration de modèles aléatoires propres à chacune des échelles. Ces modèles sont ensuite validés, et optimisés pour le cas du modèle nanoscopique à deux échelles. La prédiction du comportement optique des modèles aléatoires de matériaux hétérogènes se fait ici avec l'utilisation de méthodes utilisant les transformées de Fourier rapides (FFT). La théorie de l'optique des milieux composites est rappelée, ainsi que les contraintes et limites des méthodes FFT. L'approximation quasi-statique est une contrainte, impliquant l'application de la méthode FFT au seul modèle nanoscopique. Le comportement optique du modèle nanoscopique optimisé est calculé numériquement, et comparé à celui mesuré de la peinture qui a servi de référence. Les fonctions diélectriques des matériaux constituants de la peinture ont été mesurées à l'ellipsomètre spectroscopique au Musée de Minéralogie des Mines de Paris. Les réponses mesurée et calculées sont comparées entre elles et à des estimations analytiques. Une caractérisation statistique est également faite sur le modèle aléatoire et sur les champs locaux de déplacement diélectrique, par le calcul du volume élémentaire représentatif (VER). / This work presents a numerical and theoretical study of the optical properties of paint layers, in the classical framework of homogenization of heterogeneous media. Objectives are : describing and modeling the heterogenous microstructures used in paint coatings, and predicting the optical response of such materials by numerical ways, depending of the pigments morphology. This work was carried out as part of the LIMA project (Light Interaction Materials Aspect), in partnership with the Agence Nationale de la Recherche and the PSA company. Images of differents paint layers are acquired by scanning electron microscopy (SEM). Different length scales are considered for the microstructures and pigments : microscopic and nanoscopic. Representatives images of these scales are chosen and segmented in order to estimate morphological measurements. Using these measurements, random models are developed depending on the scales. These models, of a multiscale nature, are optimized and validated. The prediction of the optical behaviour of random models describing heterogenous materials is carried out using numerical process based on fast Fourier transforms (FFT). Optics of composite materials theory is introduced, as well as the limits of FFT methods. The quasi-static approximation is a constraint which implies the use of the FFT method on the nanoscopic model only. Dielectric functions of the components of the paint have been measured on macroscopic samples at the Museum of Mineralogy of Mines de Paris by spectroscopic ellipsometry. The optical response of the optimized nanoscopic model is computed and compared to ellipsometry measurements carried out on a reference paint layer. The computed and measured responses are also compared with analytical estimates. In addition, a statistical characterization is made on the random model and the local dielectrical displacement fields, by using the representative volume element (RVE).

[Truncated abstract] The multi-object filtering problem is a logical and fundamental generalization of the ubiquitous single-object vector filtering problem. Multi-object filtering essentially concerns the joint detection and estimation of the unknown and time-varying number of objects present, and the dynamic state of each of these objects, given a sequence of observation sets. This problem is intrinsically challenging because, given an observation set, there is no knowledge of which object generated which measurement, if any, and the detected measurements are indistinguishable from false alarms. Multi-object filtering poses significant technical challenges, and is indeed an established area of research, with many applications in both military and commercial realms. The new and emerging approach to multi-object filtering is based on the formal theory of random finite sets, and is a natural, elegant and rigorous framework for the theory of multiobject filtering, originally proposed by Mahler. In contrast to traditional approaches, the random finite set framework is completely free of explicit data associations. The random finite set framework is adopted in this dissertation as the basis for a principled and comprehensive study of multi-object filtering. The premise of this framework is that the collection of object states and measurements at any time are treated namely as random finite sets. A random finite set is simply a finite-set-valued random variable, i.e. a random variable which is random in both the number of elements and the values of the elements themselves. Consequently, formulating the multiobject filtering problem using random finite set models precisely encapsulates the essence of the multi-object filtering problem, and enables the development of principled solutions therein. '...' The performance of the proposed algorithm is demonstrated in simulated scenarios, and shown at least in simulation to dramatically outperform traditional single-object filtering in clutter approaches. The second key contribution is a mathematically principled derivation and practical implementation of a novel algorithm for multi-object Bayesian filtering, based on moment approximations to the posterior density of the random finite set state. The performance of the proposed algorithm is also demonstrated in practical scenarios, and shown to considerably outperform traditional multi-object filtering approaches. The third key contribution is a mathematically principled derivation and practical implementation of a novel algorithm for multi-object Bayesian filtering, based on functional approximations to the posterior density of the random finite set state. The performance of the proposed algorithm is compared with the previous, and shown to appreciably outperform the previous in certain classes of situations. The final key contribution is the definition of a consistent and efficiently computable metric for multi-object performance evaluation. It is shown that the finite set theoretic state space formulation permits a mathematically rigorous and physically intuitive construct for measuring the estimation error of a multi-object filter, in the form of a metric. This metric is used to evaluate and compare the multi-object filtering algorithms developed in this dissertation.

In this thesis, new methods for proving concentration inequalities for Poisson functionals are developed. The focus is on techniques that are based on logarithmic Sobolev inequalities, but also results that are based on the convex distance for Poisson processes are presented. The general methods are applied to a variety of functionals associated with random geometric graphs. In particular, concentration inequalities for subgraph and component counts are proved. Finally, the established concentration results are used to derive strong laws of large numbers for subgraph and component counts associated with random geometric graphs.

We construct and investigate random geometric structures that are based on a homogeneous Poisson point process. We investigate the random Vietoris-Rips complex constructed as the clique complex of the well known gilbert graph as an infinite random simplicial complex and prove that every realizable finite sub-complex will occur infinitely many times almost sure as isolated complex and also in the case of percolations connected to the unique giant component. Similar results are derived for the Cech complex. We derive limit theorems for the f-vector of the Vietoris-Rips complex on the unit cube centered at the origin and provide a central limit theorem and a Poisson limit theorem based on the model parameters. Finally we investigate random polytopes that are given as convex hulls of a Poisson point process in a smooth convex body. We establish a central limit theorem for certain linear combinations of intrinsic volumes. A multivariate limit theorem involving the sequence of intrinsic volumes and the number of i-dimensional faces is derived. We derive the asymptotic normality of the oracle estimator of minimal variance for estimation of the volume of a convex body.

The thesis deals with stochastic and algebraic aspects of the integer convex hull. In the first part, the intrinsic volumes of the randomized integer convex hull are investigated. In particular, we obtained an exact asymptotic order of the expected intrinsic volumes difference in a smooth convex body and a tight inequality for the expected mean width difference. In the algebraic part, an exact formula for the Bhattacharya function of complete primary monomial ideas in two variables is given. As a consequence, we derive an effective characterization for complete monomial ideals in two variables.

We consider the distribution of the zero and typical cells of a (homogeneous) Poisson hyperplane tessellation. We give a direct proof adapted to our setting of the well known Complementary Theorem. We provide sharp bounds for the tail distribution of the number of facets. We also improve existing bounds for the tail distribution of size measurements of the cells, such as the volume or the mean width. We improve known results about the generalised D.G. Kendall's problem, which asks about the shape of large cells. We also show that cells with many facets cannot be close to a lower dimensional convex body. We tacle the much less study problem of the number of facets and the shape of small cells. In order to obtain the results above we also develop some purely geometric tools, in particular we give new results concerning the polytopal approximation of an elongated convex body.