Multi-object auctions differ in an important way from single-object auctions. When bidders have multi-object demand, equilibria can exist in which bids decrease as values increase! Consider a model with n bidders who receive affiliated one-dimensional types t and whose marginal values are non-decreasing in t and strictly increasing in own type ti. In the first-price auction of a single object, all equilibria are monotone (over the range of types that win with positive probability) in that each bidder's equilibrium bid is non-decreasing in type. On the other hand, some or all equilibria may be non-monotone in many multi-object auctions. In particular, examples are provided for the as-bid and uniform-price auctions of identical objects in which (i) some bidder reduces his bids on all units as his type increases in all equilibria and (ii) symmetric bidders all reduce their bids on some units in all equilibria, and for the as-bid auction of non-identical objects in which (iii) bidders have independent types and some bidder reduces his bids on some packages in all equilibria. Fundamentally, this difference in the structure of equilibria is due to the fact that payoffs fail to satisfy strategic complementarity and/or modularity in these multi-object auctions.

For several years multi-object spectroscopy systems have been available for carrying out survey work in the visible region, but until very recently there has not been a system for the near infrared region. This thesis describes the design, manufacture and commissioning of the first multi-object fibre system for near infrared spectroscopy. SMIRFS (Spectroscopic Multi-object Infrared Fibre System) is a prototype system that has been designed at the Department of Physics in Durham to couple the Cassegrain focus of the United Kingdom InfraRed Telescope (UKIRT) to a cooled long slit infrared spectrograph (CGS4). Two different fibre bundles are available, each containing 14 fibres. One bundle is made from zirconium fluoride fibres, for K band spectroscopy and the second bundle is made from silica fibres, for J and H band spectroscopy. During the design process of SMIRFS a number of issues were addressed. These included; the characteristics of infrared fibres, in particular their throughput and FRD, atmospheric features in the near infra-red and suitable sky subtraction techniques, fibre preparation and evaluation, the use of microlenses for coupling slow focal ratio beams with fibres, and the thermal emissions from the warm material of the instrument. These, along with the design, manufacture and testing of the SMIRFS are described in detail, including the fibre evaluation results and estimates for throughput, instrument thermal background derived from the commissioning run data. Finally, there is a brief discussion on the development of infrared fibre system for astronomy.

Nowadays, researchers have shown convolutional neural network (CNN) can achieve an improved performance in multi-object tracking (MOT) by performing detection and re-identification (ReID) simultaneously. Many models have been created to overcome challenges and bring the state-of-the-art performance to a new level. However, due to the fact the CNN models only utilize feature from a local region, the potential of the model has not been fully utilized. The long range dependencies in spatial domain are usually difficult for a network to capture. Hence, how to obtain such dependencies has become the new focus in MOT field. One approach is to adopt the self-attention mechanism named transformer. Since it was successfully transferred from natural language processing to computer vision, many recent works have implemented it to their trackers. With the introduce of global information, the trackers become more robust and stable. There are also traditional methods which are re-designed in the manner of CNN and achieve satisfying performance such as optical flow. It can generate a correlated relation between feature maps and also obtain non-local information. However, the introduces of these mechanism usually causes a significant surge in computational power and memory. They also requires huge amount of epochs to train thus the training time is largely increased. To solve this issue, we propose a new method to gather non-local information based on the existing self-attention methods, we named it dual attention with regional-representation, which significantly reduces the training time as well as the inference time, but only causes a small increase in computational memory and are able to run with a reasonable speed. Our experiments shows this module can help the ReID be more stable to improve the performance in different tasks. / Thesis / Master of Applied Science (MASc)

Memoria para optar al título de Ingeniero Civil Eléctrico / En este trabajo se evaluarán distintos algoritmos de trackeo para el problema de seguimiento de peatones, donde teniendo un video obtenido de una camara de seguridad, nos interesa reconocer correctamente cada individuo a traves del tiempo, buscando minimizar la cantindad de etiquetas mal asignadas y objetos (peatones) no identificados. Para esto se ocuparán algorimos basados en el concepto de Conjuntos Aleatorios Finitos (Random Finite Sets - RFS), los cuales usan mediciones pasadas de los objetos para predecir posiciones futuras de todos ellos simultaneamente, mientras que también se consideran los casos de nacimientos y muertes de los objetos. Estos algoritmos fueron concebidos para el trackeo de objetos con movimientos simples y predecibles en condiciones de una gran cantidad ruido en las mediciones. mientras que las condiciones en las que se evaluarán son drasticamente opuestas, con un nivel muy alto de certeza en las mediciones pero con movimientos altamente no linear y muy impredecible. Se ocupará una libreria abierta creada por el investigador Ba Tuong Vo, donde están implementados varios de los más clásicos algoritmos en esta área. Es por esto que el trabajo se basará más en el análisis de los resultados en estas nuevas condiciones y observar como se comparán a los algoritmos actuales del area de Computer Vision (CV)/ Machine Learning (ML), usando tanto métricas de RFS como del área de CV.

This thesis presents a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "contextual" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of the proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Additionally, in order to increase the sensitivity of the object detector, a new approach is presented that propagates previous frame detections into each new frame using optical flow. These are treated as added object proposals which are then classified as objects. A new traffic monitoring dataset is also provided, which includes naturalistic video footage from current infrastructure cameras in Virginia Beach City with a variety of vehicle density and environment conditions. Experimental evaluation demonstrates the efficacy of the proposed approaches on the provided dataset and the popular MOT Challenge Benchmark. / Master of Science / This thesis presents a novel method for Multi-Object Tracking (MOT) in videos, with the main goal of associating objects between frames. The proposed method is based on a Deep Neural Network Architecture operating on a Graph Structure. The Graph based approach makes it possible to use both appearance and geometry of detected objects to retrieve high level information about their characteristics and interaction. The framework includes the Sinkhorn algorithm, which can be embedded in the training phase to satisfy MOT constraints, such as the 1 to 1 matching between previous and new objects. Another approach is also proposed to improve the sensitivity of the object detector by using previous frame detections as a guide to detect objects in each new frame, resulting in less missed objects. Alongside the new methods, a new dataset is also provided which includes naturalistic video footage from current infrastructure cameras in Virginia Beach City with a variety of vehicle density and environment conditions. Experimental evaluation demonstrates the efficacy of the proposed approaches on the provided dataset and the popular MOT Challenge Benchmark.

This study aimed to better understand visuomotor tracking and spatial visual imagery. 101 Participants performed four tasks: A Manual Tracking Task (MTT), in which participants mouse-tracked the path of a circle, sometimes with occlusion. A Multi-Object Tracking task (MOT), in which participants tracked several objects simultaneously. The Sussex Cognitive Styles Questionnaire (SCSQ), in which participants self-reported their experience with imagery. A Mental Rotation Task (MRT) in which participants mentally rotate Tetris-like objects. The results demonstrated a significant correlation between the technical/spatial subscale of the SCSQ and the occluded MTT, the MRT, the MOT but not the visible MTT. A multiple regression showed that occluded MTT and the MRT together significantly predicted the spatial/technical subscale of the SCSQ above visible MTT and MOT. These findings support the claim that the cognitive resources behind mental imagery may also be recruited during other tasks that arguably draw on the need for internal visualization.

Les caméras de surveillance sont de plus en plus fréquemment présentes dans notre environnement (villes, supermarchés, aéroports, entrepôts, etc.). Ces caméras sont utilisées, entre autres, afin de pouvoir détecter des comportements suspects (intrusion par exemple) ou de reconnaître une catégorie d'objets ou de personnes (détection de genre, détection de plaques d'immatriculation par exemple). D'autres applications concernent également l'établissement de statistiques de fréquentation ou de passage (comptage d'entrée/sortie de personnes ou de véhicules) ou bien le suivi d'un ou plusieurs objets se déplaçant dans le champ de vision de la caméra (trajectoires d'objets, analyse du comportement des clients dans un magasin). Compte tenu du nombre croissant de caméras et de la difficulté à réaliser ces traitements manuellement, un ensemble de méthodes d'analyse vidéo ont été développées ces dernières années afin de pouvoir automatiser ces tâches. Dans cette thèse, nous nous concentrons essentiellement sur les tâches de détection et de suivi des objets mobiles à partir d'une caméra fixe. Contrairement aux méthodes basées uniquement sur les images acquises par les caméras, notre approche consiste à intégrer un certain nombre d'informations contextuelles à l'observation afin de pouvoir mieux interpréter ces images. Ainsi, nous proposons de construire un modèle géométrique et géolocalisé de la scène et de la caméra. Ce modèle est construit directement à partir des études de prédéploiement des caméras et peut notamment utiliser les données OpenStreetMap afin d'établir les modèles 3d des bâtiments proches de la caméra. Nous avons complété ce modèle en intégrant la possibilité de prédire la position du Soleil tout au long de la journée et ainsi pouvoir calculer les ombres projetées des objets de la scène. Cette prédiction des ombres a été mise à profit afin d'améliorer la segmentation des piétons par modèle de fond en supprimant les ombres du masque de mouvement. Concernant le suivi des objets mobiles, nous utilisons le formalisme des automates finis afin de modéliser efficacement les états et évolutions possibles d'un objet. Ceci nous permet d'adapter le traitement de chaque objet selon son état. Nous gérons les occultations inter-objets à l'aide d'un mécanisme de suivi collectif (suivi en groupe) des objets le temps de l'occultation et de ré-identification de ceux-ci à la fin de l'occultation. Notre algorithme s'adapte à n'importe quel type d'objet se déplaçant au sol (piétons, véhicules, etc.) et s'intègre naturellement au modèle de scène développé. Nous avons également développé un ensemble de "rétro-actions" tirant parti de la connaissance des objets suivis afin d'améliorer les détections obtenues à partir d'un modèle de fond. En particulier, nous avons abordé le cas des objets stationnaires, souvent intégrés à tort dans le fond, et avons revisité la méthode de suppression des ombres du masque de mouvement en tirant parti de la connaissance des objets suivis. L'ensemble des solutions proposées a été implémenté dans le logiciel de l'entreprise Foxstream et est compatible avec la contrainte d'exécution en temps réel nécessaire en vidéosurveillance. / Video-surveillance cameras are increasingly used in our environment. They are indeed present almost everywhere in the cities, supermarkets, airports, warehouses, etc. These cameras are used, among other things, in order to detect suspect behavior (an intrusion for instance) or to recognize a specific category of object or person (gender detection, license plates detection). Other applications also exist to count and/or track people in order to analyze their behavior. Due to the increasing number of cameras and the difficulty to achieve these tasks manually, several video analysis methods have been developed in order to address them automatically. In this thesis, we mainly focus on the detection and tracking of moving objects from a fixed camera. Unlike methods based solely on images captured by cameras, our approach integrates contextual pieces of information in order better interpret these images. Thus we propose to build a geometric and geolocalized model of the scene and the camera. This model is built directly from the pre-deployment studies of the cameras and uses the OpenStreetMap geographical database to build 3d models of buildings near the camera. We added to this model the ability to predict the position of the sun throughout the day and the resulting shadows in the scene. By predicting the shadows, and deleting them from the foreground mask, our method is able to improve the segmentation of pedestrians. Regarding the tracking of multiple mobile objects, we use the formalism of finite state machines to effectively model the states and possible transitions that an object is allowed to take. This allows us to tailor the processing of each object according to its state. We manage the inter-object occlusion using a collective tracking strategy. When taking part in an occlusion, objects are regrouped and tracked collectively. At the end of the occlusion, each object is re-identified and individual tracking resume. Our algorithm adapts to any type of ground-moving object (pedestrians, vehicles, etc.) and seamlessly integrates in the developed scene model. We have also developed several retro-actions taking advantage of the knowledge of tracked objects to improve the detections obtained with the background model. In particular, we tackle the issue of stationary objects often integrated erroneously in the background and we revisited the initial proposal regarding shadow removal. All proposed solutions have been implemented in the Foxstream products and are able to run in real-time.

Le filtrage multiobjet est une technique de résolution du problème de détection et/ou suivi dans un contexte multicible. Cette thèse s'intéresse au filtre PHD (Probability Hypothesis Density), une célèbre approximation du filtre RFS (Random Finite Set) adaptée au cas où les observations sont le fruit d'un seul capteur. La première partie propose une construction rigoureuse du filtre PHD multicapteur exact et son expression simplifiée, sans approximation, grâce à un partitionnement joint de l'espace d'état des cibles et des capteurs. Avec cette nouvelle méthode, la solution exacte du filtre PHD multicapteur peut être propagée dans des scénarios de surveillance simples. La deuxième partie aborde le problème de gestion des capteurs dans le cadre du PHD. A chaque itération, le BET (Balanced Explorer and Tracker) construit une prédiction du PHD multicapteur a posteriori grâce au PIMS (Predicted Ideal Measurement Set) et définit un contrôle multicapteur en respectant quelques critères opérationnels simples adaptés aux missions de surveillance / The aim of multi-object filtering is to address the multiple target detection and/or tracking problem. This thesis focuses on the Probability Hypothesis Density (PHD) filter, a well-known tractable approximation of the Random Finite Set (RFS) filter when the observation process is realized by a single sensor. The first part proposes the rigorous construction of the exact multi-sensor PHD filter and its simplified expression, without approximation, through a joint partitioning of the target state space and the sensors. With this new method, the exact multi-sensor PHD can be propagated in simple surveillance scenarii. The second part deals with the sensor management problem in the PHD framework. At each iteration, the Balanced Explorer and Tracker (BET) builds a prediction of the posterior multi-sensor PHD thanks to the Predicted Ideal Measurement Set (PIMS) and produces a multi-sensor control according to a few simple operational principles adapted to surveillance activities

Le suivi multi-objets, malgré les avancées récentes en détection d'objets, présente encore plusieurs difficultés spécifiques et reste ainsi une problématique difficile. Au cours de cette thèse nous proposons d'examiner l'emploi de représentations parcimonieuses au sein de méthodes de suivi multi-objets, dans le but d'améliorer les performances de ces dernières. La première contribution de cette thèse consiste à employer des représentations parcimonieuses collaboratives dans un système de suivi en ligne pour distinguer au mieux les cibles. Des représentations parcimonieuses structurées sont ensuite considérées pour s'adapter plus spécifiquement aux approches de suivi à fenêtre glissante. Une dernière contribution consiste à employer des dictionnaires denses, prenant en considération un grand nombre de positions non détectées au sein des images, de manière à être plus robuste vis-à-vis de la performance du détecteur d'objets employé. / Despite recent advances in object detection, multi-object tracking still raises some specific issues and therefore remains a challenging problem. In this thesis, we propose to investigate the use of sparse representations within multi-object tracking approaches in order to gain in performances. The first contribution of this thesis consists in designing an online tracking approach that takes advantage of collaborative sparse representations to better distinguish between the targets. Then, structured sparse representations are considered in order to be more suited to traking approaches based on a sliding window. In order to rely less on the object detector quality, we consider for the last contribution of this thesis to use dense dictionaries that are taking into account a large number of undetected locations inside each frame.

Les systèmes de surveillance modernes doivent coordonner leurs stratégies d’observation pour améliorer l’information obtenue lors de leurs futures mesures afin d’estimer avec précision les états des objets d’intérêt (emplacement, vitesse, apparence, etc.). Par conséquent, la gestion adaptative des capteurs consiste à déterminer les stratégies de mesure des capteurs exploitant les informations a priori afin de déterminer les actions de détection actuelles. L’une des applications la plus connue de la gestion des capteurs est le suivi multi-objet, qui fait référence au problème de l’estimation conjointe du nombre d’objets et de leurs états ou trajectoires à partir de mesures bruyantes. Cette thèse porte sur les stratégies de gestion des capteurs en temps réel afin de résoudre le problème du suivi multi-objet dans le cadre de l’approche RFS labélisée. La première contribution est la formulation théorique rigoureuse du filtre mono-capteur LPHD avec son implémentation Gaussienne. La seconde contribution est l’extension du filtre LPHD pour le cas multi-capteurs. La troisième contribution est le développement de la méthode de gestion de capteurs basée sur la minimisation du risque Bayes et formulée dans les cadres POMDP et LRFS. En outre, des analyses et des simulations des approches de gestion de capteurs existantes pour le suivi multi-objets sont fournies / Modern surveillance systems must coordinate their observation strategies to enhance the information obtained by their future measurements in order to accurately estimate the states of objects of interest (location, velocity, appearance, etc). Therefore, adaptive sensor management consists of determining sensor measurement strategies that exploit a priori information in order to determine current sensing actions. One of the most challenging applications of sensor management is the multi-object tracking, which refers to the problem of jointly estimating the number of objects and their states or trajectories from noisy sensor measurements. This thesis focuses on real-time sensor management strategies formulated in the POMDP framework to address the multi-object tracking problem within the LRFS approach. The first key contribution is the rigorous theoretical formulation of the mono-sensor LPHD filter with its Gaussian-mixture implementation. The second contribution is the extension of the mono-sensor LPHD filter for superpositional sensors, resulting in the theoretical formulation of the multi-sensor LPHD filter. The third contribution is the development of the Expected Risk Reduction (ERR) sensor management method based on the minimization of the Bayes risk and formulated in the POMDP and LRFS framework. Additionally, analyses and simulations of the existing sensor management approaches for multi-object tracking, such as Task-based, Information-theoretic, and Risk-based sensor management, are provided.