Traffic State Estimation (TSE) is a vital component in traffic control which requires an accurate viewof the current traffic situation. Since there is no full sensor coverage and the collected measurementsare inflicted with random noise, statistical estimation techniques are necessary to accomplish this.Common methods, which have been used in highway applications for several decades, are state-spacemodels in the form of Kalman Filters and Particle Filters. These methods are forms of BayesianFilters, and rely on transition models to describe the system dynamics, and observation models torelate collected measurements to the current state. Reliable estimation of traffic in urban environmentshas been considered more difficult than in highways owing to the increased complexity.This MsC thesis build upon previous research studying the use of non-parametric Gaussian Processtransition and measurement models in an extended Kalman Filter to achieve short-term TSE. To dothis, models requiring different feature sets are developed and analysed, as well as a hybrid approchcombining non-parametric and parametric models through an analytical mean function based on vehicleconservation law. The data used to train and test the models was collected in a simulated signalizedintersection constructed in SUMO.The presented results show that the proposed method has potential to performing short-term TSE inthis context. A strength in the proposed framework comes from the probabilistic nature of the GaussianProcesses, as it removes the need to manually calibrate the filter parameters of the Kalman Filter. Themean absolute error (MAE) lies between one and five vehicles for estimation of a one hour long dataseries with varying traffic demand. More importantly, the method has desirable characteristics andcaptures short-term fluctuations as well as larger scale demand changes better than a previously proposedmodel using the same underlying framework. In the cases with poorer performance, the methodprovided estimates unrelated to the system dynamics as well as large error bounds. While the causefor this was not determined, several hypotheses are presented and analysed. These results are takento imply that the combination of BF and GP models has potential for short-term TSE in a signalizedintersection, but that more work is necessary to provide reliable algorithms with known bounds. In particular,the relative ease of augmenting an available analytical model, built on conventional knowledgein traffic modelling, with a non-parametric GP is highlighted.

Les êtres humains définissent naturellement leur espace quotidien en unités discrètes. Par exemple, nous sommes capables d'identifier le lieu où nous sommes (e.g. le bureau 205) et sa catégorie (i.e. un bureau), sur la base de leur seule apparence visuelle. Les travaux récents en reconnaissance de lieux sémantiques, visent à doter les robots de capacités similaires. Ces unités, appelées "lieux sémantiques", sont caractérisées par une extension spatiale et une unité fonctionnelle, ce qui distingue ce domaine des travaux habituels en cartographie. Nous présentons nos travaux dans le domaine de la reconnaissance de lieux sémantiques. Ces derniers ont plusieurs originalités par rapport à l'état de l'art. Premièrement, ils combinent la caractérisation globale d'une image, intéressante car elle permet de s'affranchir des variations locales de l'apparence des lieux, et les méthodes basées sur les mots visuels, qui reposent sur la classification non-supervisée de descripteurs locaux. Deuxièmement, et de manière intimement reliée, ils tirent parti du flux d'images fourni par le robot en utilisant des méthodes bayésiennes d'intégration temporelle. Dans un premier modèle, nous ne tenons pas compte de l'ordre des images. Le mécanisme d'intégration est donc particulièrement simple mais montre des difficultés à repérer les changements de lieux. Nous élaborons donc plusieurs mécanismes de détection des transitions entre lieux qui ne nécessitent pas d'apprentissage supplémentaire. Une deuxième version enrichit le formalisme classique du filtrage bayésien en utilisant l'ordre local d'apparition des images. Nous comparons nos méthodes à l'état de l'art sur des tâches de reconnaissance d'instances et de catégorisation, en utilisant plusieurs bases de données. Nous étudions l'influence des paramètres sur les performances et comparons les différents types de codage employés sur une même base.Ces expériences montrent que nos méthodes sont supérieures à l'état de l'art, en particulier sur les tâches de catégorisation. / Human beings naturally organize their space as composed of discrete units. Those units, called "semantic places", are characterized by their spatial extend and their functional unity. Moreover, we are able to quickly recognize a given place (e.g. office 205) and its category (i.e. an office), solely on their visual appearance. Recent works in semantic place recognition seek to endow the robot with similar capabilities. Contrary to classical localization and mapping work, this problem is usually tackled as a supervised learning problem. Our contributions are two fold. First, we combine global image characterization, which captures the global organization of the image, and visual words methods which are usually based unsupervised classification of local signatures. Our second but closely related, contribution is to use several images for recognition by using Bayesian methods for temporal integration. Our first model don't use the natural temporal ordering of images. Temporal integration is very simple but has difficulties when the robot moves from one place to another.We thus develop several mechanisms to detect place transitions. Those mechanisms are simple and don't require additional learning. A second model augment the classical Bayesian filtering approach by using the local order among images. We compare our methods to state-of-the-art algorithms on place recognition and place categorization tasks.We study the influence of system parameters and compare the different global characterization methods on the same dataset. These experiments show that our approach while being simple leads to better results especially on the place categorization task.

L’audition est une modalité utile pour aider un robot à explorer et comprendre son environnement sonore. Dans cette thèse, nous nous intéressons à la tâche de localiser une ou plusieurs sources sonores mobiles et intermittentes à l’aide d’un robot mobile équipé d’une antenne de microphones en exploitant la mobilité du robot pour améliorer la localisation. Nous proposons d’abord un modèle bayésien pour localiser une seule source mobile intermittente. Ce modèle estime conjointement la position et l’activité de la source au cours du temps et s’applique à tout type d’antenne. Grâce au mouvement du robot, il peut estimer la distance de la source et résoudre l’ambiguïté avant-arrière qui apparaît dans le cas des antennes linéaires. Nous proposons deux implémentations de ce modèle, l’une à l’aide d’un filtre de Kalman étendu basé sur des mélanges de gaussiennes et l’autre à l’aide d’un filtre à particules, que nous comparons en termes de performance et de temps de calcul. Nous étendons ensuite notre modèle à plusieurs sources intermittentes et mobiles. En combinant notre filtre avec un joint probability data association filter (JPDAF), nous pouvons estimer conjointement les positions et activités de deux sources sonores dans un environnement réverbérant. Enfin nous faisons une contribution à la planification de mouvement pour réduire l’incertitude sur la localisation d’une source sonore. Nous définissons une fonction de coût avec l’alternative entre deux critères: l’entropie de Shannon ou l’écart-type sur l’estimation de la position. Ces deux critères sont intégrés dans le temps avec un facteur d’actualisation. Nous adaptons alors l’algorithme de Monte-Carlo tree search (MCTS) pour trouver, efficacement, le mouvement du robot qui minimise notre fonction de coût. Nos expériences montrent que notre méthode surpasse, sur le long terme, d’autres méthodes de planification pour l’audition robotique / Robot audition provides hearing capability for robots and helps them explore and understand their sound environment. In this thesis, we focus on the task of sound source localization for a single or multiple, intermittent, possibly moving sources using a mobile robot and exploiting robot motion to improve the source localization. We propose a Bayesian filtering framework to localize the position of a single, intermittent, possibly moving sound source. This framework jointly estimates the source location and its activity over time and is applicable to any micro- phone array geometry. Thanks to the movement of the robot, it can estimate the distance to the source and solve the front-back ambiguity which appears in the case of a linear microphone array. We propose two implementations of this framework based on an extended mixture Kalman filter (MKF) and on a particle filter, that we compare in terms of performance and computation time. We then extend our model to the context of multiple, intermittent, possibly moving sources. By implementing an extended MKF with joint probabilistic data association filter (JPDAF), we can jointly estimate the locations of two sources and their activities over time. Lastly, we make a contribution on long-term robot motion planning to optimally reduce the uncertainty in the source location. We define a cost function with two alternative criteria: the Shannon entropy or the standard deviation of the estimated belief. These entropies or standard deviations are integrated over time with a discount factor. We adapt the Monte Carlo tree search (MCTS) method for efficiently finding the optimal robot motion that will minimize the above cost function. Experiments show that the proposed method outperforms other robot motion planning methods for robot audition in the long run

Estimating the state of a system from noisy measurements is a problem which arises in a variety of scientific and industrial areas which include signal processing, communications, statistics and econometrics. Recursive filtering is one way to achieve this by incorporating noisy observations as they become available with prior knowledge of the system model. Bayesian methods provide a general framework for dynamic state estimation problems. The central idea behind this recursive Bayesian estimation is computing the probability density function of the state vector of the system conditioned on the measurements. However, the optimal solution to this problem is often intractable because it requires high-dimensional integration. Although we can use the Kalman lter in the case of a linear state space model with Gaussian noise, this method is not optimum for a non-linear and non-Gaussian system model. There are many new methods of filtering for the general case. The main emphasis of this thesis is on one such recently developed filter, the particle lter [2,3,6]. In this thesis, a detailed introduction to particle filters is provided as well as some guidelines for the efficient implementation of the particle lter. The application of particle lters to various communication channels like detection of symbols over the channels, capacity calculation of the channel are discussed.

This thesis tackles the visual tracking problem as a target contour estimation problem in the face of corrupted measurements. The major aim is to design robust recursive curve filters for accurate contour-based tracking. The state-space representation adopted comprises of a group component and a shape component describing the rigid motion and the non-rigid shape deformation respectively; filtering strategies on each component are then decoupled. The thesis considers two implicit curve descriptors, a classification probability field and the traditional signed distance function, and aims to develop an optimal probabilistic contour observer and locally optimal curve filters. For the former, introducing a novel probabilistic shape description simplifies the filtering problem on the infinite-dimensional space of closed curves to a series of point-wise filtering tasks. The definition and justification of a novel update model suited to the shape space, the derivation of the filtering equations and the relation to Kalman filtering are studied. In addition to the temporal consistency provided by the filtering, extensions involving distributed filtering methods are considered in order to maintain spatial consistency. For the latter, locally optimal closed curve filtering strategies involving curve velocities are explored. The introduction of a local, linear description for planar curve variation and curve uncertainty enables the derivation of a mechanism for estimating the optimal gain associated to the curve filtering process, given quantitative uncertainty levels. Experiments on synthetic and real sequences of images validate the filtering designs.

The problem of object detection deals with determining whether an instance of a given class of object is present or not. There are robust, supervised learning based algorithms available for object detection in an image. These image object detectors (image-based object detectors) use characteristics learnt from the training samples to find object and non-object regions. The characteristics used are such that the detectors work under a variety of conditions and hence are very robust. Object detection in video can be performed by using such a detector on each frame of the video sequence. This approach checks for presence of an object around each pixel, at different scales. Such a frame-based approach completely ignores the temporal continuity inherent in the video. The detector declares presence of the object independent of what has happened in the past frames. Also, various visual cues such as motion and color, which give hints about the location of the object, are not used. The current work is aimed at building a generic framework for using a supervised learning based image object detector for video that exploits temporal continuity and the presence of various visual cues. We use temporal continuity and visual cues to speed up the detection and improve detection accuracy by considering past detection results. We propose a generic framework, based on Experiential Sampling [1], which considers temporal continuity and visual cues to focus on a relevant subset of each frame. We determine some key positions in each frame, called attention samples, and object detection is performed only at scales with these positions as centers. These key positions are statistical samples from a density function that is estimated based on various visual cues, past experience and temporal continuity. This density estimation is modeled as a Bayesian Filtering problem and is carried out using Sequential Monte Carlo methods (also known as Particle Filtering), where a density is represented by a weighted sample set. The experiential sampling framework is inspired by Neisser’s perceptual cycle [2] and Itti-Koch’s static visual attention model[3]. In this work, we first use Basic Experiential Sampling as presented in[1]for object detection in video and show its limitations. To overcome these limitations, we extend the framework to effectively combine top-down and bottom-up visual attention phenomena. We use learning based detector’s response, which is a top-down cue, along with visual cues to improve attention estimate. To effectively handle multiple objects, we maintain a minimum number of attention samples per object. We propose to use motion as an alert cue to reduce the delay in detecting new objects entering the field of view. We use an inhibition map to avoid revisiting already attended regions. Finally, we improve detection accuracy by using a particle filter based detection scheme [4], also known as Track Before Detect (TBD). In this scheme, we compute likelihood of presence of the object based on current and past frame data. This likelihood is shown to be approximately equal to the product of average sample weights over past frames. Our framework results in a significant reduction in overall computation required by the object detector, with an improvement in accuracy while retaining its robustness. This enables the use of learning based image object detectors in real time video applications which otherwise are computationally expensive. We demonstrate the usefulness of this framework for frontal face detection in video. We use Viola-Jones’ frontal face detector[5] and color and motion visual cues. We show results for various cases such as sequences with single object, multiple objects, distracting background, moving camera, changing illumination, objects entering/exiting the frame, crossing objects, objects with pose variation and sequences with scene change. The main contributions of the thesis are i) We give an experiential sampling formulation for object detection in video. Many concepts like attention point and attention density which are vague in[1] are precisely defined. ii) We combine detector’s response along with visual cues to estimate attention. This is inspired by a combination of top-down and bottom-up attention maps in visual attention models. To the best of our knowledge, this is used for the first time for object detection in video. iii) In case of multiple objects, we highlight the problem with sample based density representation and solve by maintaining a minimum number of attention samples per object. iv) For objects first detected by the learning based detector, we propose to use a TBD scheme for their subsequent detections along with the learning based detector. This improves accuracy compared to using the learning based detector alone. This thesis is organized as follows . Chapter 1: In this chapter we present a brief survey of related work and define our problem. . Chapter 2: We present an overview of biological models that have motivated our work. . Chapter 3: We give the experiential sampling formulation as in previous work [1], show results and discuss its limitations. . Chapter 4: In this chapter, which is on Enhanced Experiential Sampling, we suggest enhancements to overcome limitations of basic experiential sampling. We propose track-before-detect scheme to improve detection accuracy. . Chapter 5: We conclude the thesis and give possible directions for future work in this area. . Appendix A: A description of video database used in this thesis. . Appendix B: A list of commonly used abbreviations and notations.

Abstract In this work, statistical machine learning and pattern recognition methods were developed and applied to sensor-based human context recognition. More precisely, we concentrated on an effective discriminative learning framework, where input-output mapping is learned directly from a labeled dataset. Non-parametric discriminative classification and regression models based on kernel methods were applied. They include support vector machines (SVM) and Gaussian processes (GP), which play a central role in modern statistical machine learning. Based on these established models, we propose various extensions for handling structured data that usually arise from real-life applications, for example, in a field of context-aware computing. We applied both SVM and GP techniques to handle data with multiple classes in a structured multi-sensor domain. Moreover, a framework for combining data from several sources in this setting was developed using multiple classifiers and fusion rules, where kernel methods are used as base classifiers. We developed two novel methods for handling sequential input and output data. For sequential time-series data, a novel kernel based on graphical presentation, called a weighted walk-based graph kernel (WWGK), is introduced. For sequential output labels, discriminative temporal smoothing (DTS) is proposed. Again, the proposed algorithms are modular, so different kernel classifiers can be used as base models. Finally, we propose a group of techniques based on Gaussian process regression (GPR) and particle filtering (PF) to learn to track multiple targets. We applied the proposed methodology to three different human-motion-based context recognition applications: person identification, person tracking, and activity recognition, where floor (pressure-sensitive and binary switch) and wearable acceleration sensors are used to measure human motion and gait during walking and other activities. Furthermore, we extracted a useful set of specific high-level features from raw sensor measurements based on time, frequency, and spatial domains for each application. As a result, we developed practical extensions to kernel-based discriminative learning to handle many kinds of structured data applied to human context recognition. / Tiivistelmä Tässä työssä kehitettiin ja sovellettiin tilastollisen koneoppimisen ja hahmontunnistuksen menetelmiä anturipohjaiseen ihmiseen liittyvän tilannetiedon tunnistamiseen. Esitetyt menetelmät kuuluvat erottelevan oppimisen viitekehykseen, jossa ennustemalli sisääntulomuuttujien ja vastemuuttujan välille voidaan oppia suoraan tunnetuilla vastemuuttujilla nimetystä aineistosta. Parametrittomien erottelevien mallien oppimiseen käytettiin ydinmenetelmiä kuten tukivektorikoneita (SVM) ja Gaussin prosesseja (GP), joita voidaan pitää yhtenä modernin tilastollisen koneoppimisen tärkeimmistä menetelmistä. Työssä kehitettiin näihin menetelmiin liittyviä laajennuksia, joiden avulla rakenteellista aineistoa voidaan mallittaa paremmin reaalimaailman sovelluksissa, esimerkiksi tilannetietoisen laskennan sovellusalueella. Tutkimuksessa sovellettiin SVM- ja GP-menetelmiä moniluokkaisiin luokitteluongelmiin rakenteellisen monianturitiedon mallituksessa. Useiden tietolähteiden käsittelyyn esitetään menettely, joka yhdistää useat opetetut luokittelijat päätöstason säännöillä lopulliseksi malliksi. Tämän lisäksi aikasarjatiedon käsittelyyn kehitettiin uusi graafiesitykseen perustuva ydinfunktio sekä menettely sekventiaalisten luokkavastemuuttujien käsittelyyn. Nämä voidaan liittää modulaarisesti ydinmenetelmiin perustuviin erotteleviin luokittelijoihin. Lopuksi esitetään tekniikoita usean liikkuvan kohteen seuraamiseen. Menetelmät perustuvat anturitiedosta oppivaan GP-regressiomalliin ja partikkelisuodattimeen. Työssä esitettyjä menetelmiä sovellettiin kolmessa ihmisen liikkeisiin liittyvässä tilannetiedon tunnistussovelluksessa: henkilön biometrinen tunnistaminen, henkilöiden seuraaminen sekä aktiviteettien tunnistaminen. Näissä sovelluksissa henkilön asentoa, liikkeitä ja astuntaa kävelyn ja muiden aktiviteettien aikana mitattiin kahdella erilaisella paineherkällä lattia-anturilla sekä puettavilla kiihtyvyysantureilla. Tunnistusmenetelmien laajennuksien lisäksi jokaisessa sovelluksessa kehitettiin menetelmiä signaalin segmentointiin ja kuvaavien piirteiden irroittamiseen matalantason anturitiedosta. Tutkimuksen tuloksena saatiin parannuksia erottelevien mallien oppimiseen rakenteellisesta anturitiedosta sekä erityisesti uusia menettelyjä tilannetiedon tunnistamiseen.

Using autonomous miniature air vehicles (MAVs) is a cost-effective, simple method for collecting data about the size, shape, and location characteristics of a forest fire. However, noise in measurements used to compute pose (location and attitude) of the on-board camera leads to significant errors in the processing of collected video data. Typical methods using MAVs to track fires attempt to find single geolocation estimates and filter that estimate with subsequent observations. While this is an effective method of resolving the noise to achieve a better geolocation estimate, it reduces a fire to a single point or small set of points. A georeferenced mosaic is a more effective method for presenting information about a fire to fire fighters. It provides a means of presenting size, shape, and geolocation information simultaneously. We describe a novel technique to account for uncertainty in pose estimation of the camera by converting it to the image domain. We also introduce a new concept, a Georeferenced Uncertainty Mosaic (GUM), in which we utilize a Sequential Monte Carlo method (a particle filter) to resolve that uncertainty and construct a georeferenced mosaic that simultaneously shows size, shape, geolocation, and uncertainty information about the fire.

Nowadays, satellite-based localization is a well-established technical solution to support several navigation tasks in daily life. Besides the application inside of portable devices, satellite-based positioning is used for in-vehicle navigation systems as well. Moreover, due to its global coverage and the availability of inexpensive receiver hardware it is an appealing technology for numerous applications in the area of Intelligent Transportation Systems (ITSs). However, it has to be admitted that most of the aforementioned examples either rely on modest accuracy requirements or are not sensitive to temporary integrity violations. Although technical concepts of Advanced Driver Assistance Systems (ADASs) based on Global Navigation Satellite Systems (GNSSs) have been successfully demonstrated under open sky conditions, practice reveals that such systems suffer from degraded satellite signal quality when put into urban areas. Thus, the main research objective of this thesis is to provide a reliable vehicle positioning concept which can be used in urban areas without the aforementioned limitations. Therefore, an integrated probabilistic approach which preforms fault detection & exclusion, localization and multi-sensor data fusion within one unified Bayesian framework is proposed. From an algorithmic perspective, the presented concept is based on a probabilistic data association technique with explicit handling of outlier measurements as present in urban areas. By that approach, the accuracy, integrity and availability are improved at the same time, that is, a consistent positioning solution is provided. In addition, a comprehensive and in-depth analysis of typical errors in urban areas within the pseudorange domain is performed. Based on this analysis, probabilistic models are proposed and later on used to facilitate the positioning algorithm. Moreover, the presented concept clearly targets towards mass-market applications based on low-cost receivers and hence aims to replace costly sensors by smart algorithms. The benefits of these theoretical contributions are implemented and demonstrated on the example of a real-time vehicle positioning prototype as used inside of the European research project GAlileo Interactive driviNg (GAIN). This work describes all necessary parts of this system including GNSS signal processing, fault detection and multi-sensor data fusion within one processing chain. Finally, the performance and benefits of the proposed concept are examined and validated both with simulated and comprehensive real-world sensor data from numerous test drives.