Vision-based tracking for sports performance analysis

With the world of professional sports shifting towards employing better sport analytics, the demand for vision-based performance analysis is growing increasingly in recent years. In addition, the nature of many sports does not allow the use of any kind of sensors or other wearable markers attached to players for monitoring their performances during competitions. This provides a potential application of systematic observations such as tracking information of the players to help coaches to develop their visual skills and perceptual awareness needed to make decisions about team strategy or training plans. My PhD project is part of a bigger ongoing project between sport scientists and computer scientists involving also industry partners and sports organisations. The overall idea is to investigate the contribution technology can make to the analysis of sports performance on the example of team sports such as rugby, football or hockey. A particular focus is on vision-based tracking, so that information about the location and dynamics of the players can be gained without any additional sensors on the players. To start with, prior approaches on visual tracking are extensively reviewed and analysed. In this thesis, methods to deal with the difficulties in visual tracking to handle the target appearance changes caused by intrinsic (e.g. pose variation) and extrinsic factors, such as occlusion, are proposed. This analysis highlights the importance of the proposed visual tracking algorithms, which reflect these challenges and suggest robust and accurate frameworks to estimate the target state in a complex tracking scenario such as a sports scene, thereby facilitating the tracking process. Next, a framework for continuously tracking multiple targets is proposed. Compared to single target tracking, multi-target tracking such as tracking the players on a sports field, poses additional difficulties, namely data association, which needs to be addressed. Here, the aim is to locate all targets of interest, inferring their trajectories and deciding which observation corresponds to which target trajectory is. In this thesis, an efficient framework is proposed to handle this particular problem, especially in sport scenes, where the players of the same team tend to look similar and exhibit complex interactions and unpredictable movements resulting in matching ambiguity between the players. The presented approach is also evaluated on different sports datasets and shows promising results. Finally, information from the proposed tracking system is utilised as the basic input for further higher level performance analysis such as tactics and team formations, which can help coaches to design a better training plan. Due to the continuous nature of many team sports (e.g. soccer, hockey), it is not straightforward to infer the high-level team behaviours, such as players’ interaction. The proposed framework relies on two distinct levels of performance analysis: low-level performance analysis, such as identifying players positions on the play field, as well as a high-level analysis, where the aim is to estimate the density of player locations or detecting their possible interaction group. The related experiments show the proposed approach can effectively explore this high-level information, which has many potential applications.

Anisotropy-based performance analysis of linear discrete time invariant control systems

The anisotropic norm of a linear discrete-time-invariant system measures system output sensitivity to stationary Gaussian input disturbances of bounded mean anisotropy. Mean anisotropy characterizes the degree of predictability (or colouredness) and spatial non-roundness of the noise. The anisotropic norm falls between the H-2 and H-infinity norms and accommodates their loss of performance when the probability structure of input disturbances is not exactly known. This paper develops a method for numerical computation of the anisotropic norm which involves linked Riccati and Lyapunov equations and an associated special type equation.

Repeater vs. Bridge-based hybrid wired/wireless PROFIBUS networks: a comparative performance analysis

In the last years, several solutions have been proposed to extend PROFIBUS in order to support wired and wireless network stations in the same network. In this paper we compare two of those solutions, one in which the interconnection between wired and wireless stations is made by repeaters and another in which the interconnection is made by bridges. The comparison is both qualitative and numerical, based on simulation models of both architectures.

Performance Analysis of IEEE 802.15.6 Contention-based MAC Protocol

IEEE International Conference on Communications (IEEE ICC 2015). 8 to 12, Jun, 2015, IEEE ICC 2015 - Communications QoS, Reliability and Modeling, London, United Kingdom.

Performance analysis of an SRI screen based on employment quality in high and low capital industries: International evidence

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Finance from the NOVA – School of Business and Economics and Maastricht University School of Business and Economics

Development of a systematic computer vision-based method to analyse and compare images of false identity documents for forensic intelligence purposes-Part I: acquisition, calibration and validation issues

Following their detection and seizure by police and border guard authorities, false identity and travel documents are usually scanned, producing digital images. This research investigates the potential of these images to classify false identity documents, highlight links between documents produced by a same modus operandi or same source, and thus support forensic intelligence efforts. Inspired by previous research work about digital images of Ecstasy tablets, a systematic and complete method has been developed to acquire, collect, process and compare images of false identity documents. This first part of the article highlights the critical steps of the method and the development of a prototype that processes regions of interest extracted from images. Acquisition conditions have been fine-tuned in order to optimise reproducibility and comparability of images. Different filters and comparison metrics have been evaluated and the performance of the method has been assessed using two calibration and validation sets of documents, made up of 101 Italian driving licenses and 96 Portuguese passports seized in Switzerland, among which some were known to come from common sources. Results indicate that the use of Hue and Edge filters or their combination to extract profiles from images, and then the comparison of profiles with a Canberra distance-based metric provides the most accurate classification of documents. The method appears also to be quick, efficient and inexpensive. It can be easily operated from remote locations and shared amongst different organisations, which makes it very convenient for future operational applications. The method could serve as a first fast triage method that may help target more resource-intensive profiling methods (based on a visual, physical or chemical examination of documents for instance). Its contribution to forensic intelligence and its application to several sets of false identity documents seized by police and border guards will be developed in a forthcoming article (part II).

PERFORMANCE ANALYSIS OF A TACTICAL ASSET ALLOCATION – Evidence from the Black–Litterman model based fixed income portfolio

Over time the demand for quantitative portfolio management has increased among financial institutions but there is still a lack of practical tools. In 2008 EDHEC Risk and Asset Management Research Centre conducted a survey of European investment practices. It revealed that the majority of asset or fund management companies, pension funds and institutional investors do not use more sophisticated models to compensate the flaws of the Markowitz mean-variance portfolio optimization. Furthermore, tactical asset allocation managers employ a variety of methods to estimate return and risk of assets, but also need sophisticated portfolio management models to outperform their benchmarks. Recent development in portfolio management suggests that new innovations are slowly gaining ground, but still need to be studied carefully. This thesis tries to provide a practical tactical asset allocation (TAA) application to the Black–Litterman (B–L) approach and unbiased evaluation of B–L models’ qualities. Mean-variance framework, issues related to asset allocation decisions and return forecasting are examined carefully to uncover issues effecting active portfolio management. European fixed income data is employed in an empirical study that tries to reveal whether a B–L model based TAA portfolio is able outperform its strategic benchmark. The tactical asset allocation utilizes Vector Autoregressive (VAR) model to create return forecasts from lagged values of asset classes as well as economic variables. Sample data (31.12.1999–31.12.2012) is divided into two. In-sample data is used for calibrating a strategic portfolio and the out-of-sample period is for testing the tactical portfolio against the strategic benchmark. Results show that B–L model based tactical asset allocation outperforms the benchmark portfolio in terms of risk-adjusted return and mean excess return. The VAR-model is able to pick up the change in investor sentiment and the B–L model adjusts portfolio weights in a controlled manner. TAA portfolio shows promise especially in moderately shifting allocation to more risky assets while market is turning bullish, but without overweighting investments with high beta. Based on findings in thesis, Black–Litterman model offers a good platform for active asset managers to quantify their views on investments and implement their strategies. B–L model shows potential and offers interesting research avenues. However, success of tactical asset allocation is still highly dependent on the quality of input estimates.

Performance analysis and deployment of VoLTE mechanisms over 3GPP LTE-based networks

Long Term Evolution based networks lack native support for Circuit Switched (CS) services. The Evolved Packet System (EPS) which includes the Evolved UMTS Terrestrial Radio Access Network (E-UTRAN) and Evolved Packet Core (EPC) is a purely all-IP packet system. This introduces the problem of how to provide voice call support when a user is within an LTE network and how to ensure voice service continuity when the user moves out of LTE coverage area. Different technologies have been proposed for the purpose of providing a voice to LTE users and to ensure the service continues outside LTE networks. The aim of this paper is to analyze and evaluate the overall performance of these technologies along with Single Radio Voice Call Continuity (SRVCC) Inter-RAT handover to Universal Terrestrial Radio Access Networks/ GSM-EDGE radio access Networks (UTRAN/GERAN). The possible solutions for providing voice call and service continuity over LTE-based networks are Circuit Switched Fall Back (CSFB), Voice over LTE via Generic Access (VoLGA), Voice over LTE (VoLTE) based on IMS/MMTel with SRVCC and Over The Top (OTT) services like Skype. This paper focuses mainly on the 3GPP standard solutions to implement voice over LTE. The paper compares various aspects of these solutions and suggests a possible roadmap that mobile operators can adopt to provide seamless voice over LTE.

Optimal Workflow and Process-Based Performance Measures for Endovascular Therapy in Acute Ischemic Stroke: Analysis of the Solitaire FR Thrombectomy for Acute Revascularization Study.

BACKGROUND AND PURPOSE We report on workflow and process-based performance measures and their effect on clinical outcome in Solitaire FR Thrombectomy for Acute Revascularization (STAR), a multicenter, prospective, single-arm study of Solitaire FR thrombectomy in large vessel anterior circulation stroke patients. METHODS Two hundred two patients were enrolled across 14 centers in Europe, Canada, and Australia. The following time intervals were measured: stroke onset to hospital arrival, hospital arrival to baseline imaging, baseline imaging to groin puncture, groin puncture to first stent deployment, and first stent deployment to reperfusion. Effects of time of day, general anesthesia use, and multimodal imaging on workflow were evaluated. Patient characteristics and workflow processes associated with prolonged interval times and good clinical outcome (90-day modified Rankin score, 0-2) were analyzed. RESULTS Median times were onset of stroke to hospital arrival, 123 minutes (interquartile range, 163 minutes); hospital arrival to thrombolysis in cerebral infarction (TICI) 2b/3 or final digital subtraction angiography, 133 minutes (interquartile range, 99 minutes); and baseline imaging to groin puncture, 86 minutes (interquartile range, 24 minutes). Time from baseline imaging to puncture was prolonged in patients receiving intravenous tissue-type plasminogen activator (32-minute mean delay) and when magnetic resonance-based imaging at baseline was used (18-minute mean delay). Extracranial carotid disease delayed puncture to first stent deployment time on average by 25 minutes. For each 1-hour increase in stroke onset to final digital subtraction angiography (or TICI 2b/3) time, odds of good clinical outcome decreased by 38%. CONCLUSIONS Interval times in the STAR study reflect current intra-arterial therapy for patients with acute ischemic stroke. Improving workflow metrics can further improve clinical outcome. CLINICAL TRIAL REGISTRATION: URL http://www.clinicaltrials.gov. Unique identifier: NCT01327989.

Vision-based vehicle detection and tracking with a mobile camera using a statistical framework

En esta tesis se aborda la detección y el seguimiento automático de vehículos mediante técnicas de visión artificial con una cámara monocular embarcada. Este problema ha suscitado un gran interés por parte de la industria automovilística y de la comunidad científica ya que supone el primer paso en aras de la ayuda a la conducción, la prevención de accidentes y, en última instancia, la conducción automática. A pesar de que se le ha dedicado mucho esfuerzo en los últimos años, de momento no se ha encontrado ninguna solución completamente satisfactoria y por lo tanto continúa siendo un tema de investigación abierto. Los principales problemas que plantean la detección y seguimiento mediante visión artificial son la gran variabilidad entre vehículos, un fondo que cambia dinámicamente debido al movimiento de la cámara, y la necesidad de operar en tiempo real. En este contexto, esta tesis propone un marco unificado para la detección y seguimiento de vehículos que afronta los problemas descritos mediante un enfoque estadístico. El marco se compone de tres grandes bloques, i.e., generación de hipótesis, verificación de hipótesis, y seguimiento de vehículos, que se llevan a cabo de manera secuencial. No obstante, se potencia el intercambio de información entre los diferentes bloques con objeto de obtener el máximo grado posible de adaptación a cambios en el entorno y de reducir el coste computacional. Para abordar la primera tarea de generación de hipótesis, se proponen dos métodos complementarios basados respectivamente en el análisis de la apariencia y la geometría de la escena. Para ello resulta especialmente interesante el uso de un dominio transformado en el que se elimina la perspectiva de la imagen original, puesto que este dominio permite una búsqueda rápida dentro de la imagen y por tanto una generación eficiente de hipótesis de localización de los vehículos. Los candidatos finales se obtienen por medio de un marco colaborativo entre el dominio original y el dominio transformado. Para la verificación de hipótesis se adopta un método de aprendizaje supervisado. Así, se evalúan algunos de los métodos de extracción de características más populares y se proponen nuevos descriptores con arreglo al conocimiento de la apariencia de los vehículos. Para evaluar la efectividad en la tarea de clasificación de estos descriptores, y dado que no existen bases de datos públicas que se adapten al problema descrito, se ha generado una nueva base de datos sobre la que se han realizado pruebas masivas. Finalmente, se presenta una metodología para la fusión de los diferentes clasificadores y se plantea una discusión sobre las combinaciones que ofrecen los mejores resultados. El núcleo del marco propuesto está constituido por un método Bayesiano de seguimiento basado en filtros de partículas. Se plantean contribuciones en los tres elementos fundamentales de estos filtros: el algoritmo de inferencia, el modelo dinámico y el modelo de observación. En concreto, se propone el uso de un método de muestreo basado en MCMC que evita el elevado coste computacional de los filtros de partículas tradicionales y por consiguiente permite que el modelado conjunto de múltiples vehículos sea computacionalmente viable. Por otra parte, el dominio transformado mencionado anteriormente permite la definición de un modelo dinámico de velocidad constante ya que se preserva el movimiento suave de los vehículos en autopistas. Por último, se propone un modelo de observación que integra diferentes características. En particular, además de la apariencia de los vehículos, el modelo tiene en cuenta también toda la información recibida de los bloques de procesamiento previos. El método propuesto se ejecuta en tiempo real en un ordenador de propósito general y da unos resultados sobresalientes en comparación con los métodos tradicionales. ABSTRACT This thesis addresses on-road vehicle detection and tracking with a monocular vision system. This problem has attracted the attention of the automotive industry and the research community as it is the first step for driver assistance and collision avoidance systems and for eventual autonomous driving. Although many effort has been devoted to address it in recent years, no satisfactory solution has yet been devised and thus it is an active research issue. The main challenges for vision-based vehicle detection and tracking are the high variability among vehicles, the dynamically changing background due to camera motion and the real-time processing requirement. In this thesis, a unified approach using statistical methods is presented for vehicle detection and tracking that tackles these issues. The approach is divided into three primary tasks, i.e., vehicle hypothesis generation, hypothesis verification, and vehicle tracking, which are performed sequentially. Nevertheless, the exchange of information between processing blocks is fostered so that the maximum degree of adaptation to changes in the environment can be achieved and the computational cost is alleviated. Two complementary strategies are proposed to address the first task, i.e., hypothesis generation, based respectively on appearance and geometry analysis. To this end, the use of a rectified domain in which the perspective is removed from the original image is especially interesting, as it allows for fast image scanning and coarse hypothesis generation. The final vehicle candidates are produced using a collaborative framework between the original and the rectified domains. A supervised classification strategy is adopted for the verification of the hypothesized vehicle locations. In particular, state-of-the-art methods for feature extraction are evaluated and new descriptors are proposed by exploiting the knowledge on vehicle appearance. Due to the lack of appropriate public databases, a new database is generated and the classification performance of the descriptors is extensively tested on it. Finally, a methodology for the fusion of the different classifiers is presented and the best combinations are discussed. The core of the proposed approach is a Bayesian tracking framework using particle filters. Contributions are made on its three key elements: the inference algorithm, the dynamic model and the observation model. In particular, the use of a Markov chain Monte Carlo method is proposed for sampling, which circumvents the exponential complexity increase of traditional particle filters thus making joint multiple vehicle tracking affordable. On the other hand, the aforementioned rectified domain allows for the definition of a constant-velocity dynamic model since it preserves the smooth motion of vehicles in highways. Finally, a multiple-cue observation model is proposed that not only accounts for vehicle appearance but also integrates the available information from the analysis in the previous blocks. The proposed approach is proven to run near real-time in a general purpose PC and to deliver outstanding results compared to traditional methods.

Anisotropy-based robust performance analysis of finite horizon linear discrete time varying systems

We consider a problem of robust performance analysis of linear discrete time varying systems on a bounded time interval. The system is represented in the state-space form. It is driven by a random input disturbance with imprecisely known probability distribution; this distributional uncertainty is described in terms of entropy. The worst-case performance of the system is quantified by its a-anisotropic norm. Computing the anisotropic norm is reduced to solving a set of difference Riccati and Lyapunov equations and a special form equation.

Performance analysis of polymer optical fibre based Fabry-Perot sensor formed by two uniform Bragg gratings

The stress sensitivity of polymer optical fibre (POF) based Fabry-Perot sensors formed by two uniform Bragg gratings with finite dimensions is investigated. POF has received high interest in recent years due to its different material properties compared to its silica counterpart. Biocompatibility, a higher failure strain and the highly elastic nature of POF are some of the main advantages. The much lower Young’s modulus of polymer materials compared to silica offers enhanced stress sensitivity to POF based sensors which renders them great candidates for acoustic wave receivers and any kind of force detection. The main drawback in POF technology is perhaps the high fibre loss. In a lossless fibre the sensitivity of an interferometer is proportional to its cavity length. However, the presence of the attenuation along the optical path can significantly reduce the finesse of the Fabry-Perot interferometer and it can negatively affect its sensitivity at some point. The reflectivity of the two gratings used to form the interferometer can be also reduced as the fibre loss increases. In this work, a numerical model is developed to study the performance of POF based Fabry-Perot sensors formed by two uniform Bragg gratings with finite dimensions. Various optical and physical properties are considered such as grating physical length, grating effective length which indicates the point where the light is effectively reflected, refractive index modulation of the grating, cavity length of the interferometer, attenuation and operating wavelength. Using this model, we are able to identify the regimes in which the PMMA based sensor offer enhanced stress sensitivity compared to silica based one.

Performance Analysis of IP based WSNs in real time systems

Wireless sensor networks (WSNs) are the key enablers of the internet of things (IoT) paradigm. Traditionally, sensor network research has been to be unlike the internet, motivated by power and device constraints. The IETF 6LoWPAN draft standard changes this, defining how IPv6 packets can be efficiently transmitted over IEEE 802.15.4 radio links. Due to this 6LoWPAN technology, low power, low cost micro- controllers can be connected to the internet forming what is known as the wireless embedded internet. Another IETF recommendation, CoAP allows these devices to communicate interactively over the internet. The integration of such tiny, ubiquitous electronic devices to the internet enables interesting real-time applications. This thesis work attempts to evaluate the performance of a stack consisting of CoAP and 6LoWPAN over the IEEE 802.15.4 radio link using the Contiki OS and Cooja simulator, along with the CoAP framework Californium (Cf). Ultimately, the implementation of this stack on real hardware is carried out using a raspberry pi as a border router with T-mote sky sensors as slip radios and CoAP servers relaying temperature and humidity data. The reliability of the stack was also demonstrated during scalability analysis conducted on the physical deployment. The interoperability is ensured by connecting the WSN to the global internet using different hardware platforms supported by Contiki and without the use of specialized gateways commonly found in non IP based networks. This work therefore developed and demonstrated a heterogeneous wireless sensor network stack, which is IP based and conducted performance analysis of the stack, both in terms of simulations and real hardware.

Performance Analysis of 5G based Positioning in Railway Applications

Rail transportation has significant importance in the future world. This importance is tightly bounded to accessible, sustainable, efficient and safe railway systems. Precise positioning in railway applications is essential for increasing railway traffic, train-track control, collision avoidance, train management and autonomous train driving. Hence, precise train positioning is a safety-critical application. Nowadays, positioning in railway applications highly depends on a cellular-based system called GSM-R, a railway-specific version of Global System for Mobile Communications (GSM). However, GSM-R is a relatively outdated technology and does not provide enough capacity and precision demanded by future railway networks. One option for positioning is mounting Global Navigation Satellite System (GNSS) receivers on trains as a low-cost solution. Nevertheless, GNSS can not provide continuous service due to signal interruption by harsh environments, tunnels etc. Another option is exploiting cellular-based positioning methods. The most recent cellular technology, 5G, provides high network capacity, low latency, high accuracy and high availability suitable for train positioning. In this thesis, an approach to 5G-based positioning for railway systems is discussed and simulated. Observed Time Difference of Arrival (OTDOA) method and 5G Positioning Reference Signal (PRS) are used. Simulations run using MATLAB, based on existing code developed for 5G positioning by extending it for Non Line of Sight (NLOS) link detection and base station exclusion algorithms. Performance analysis for different configurations is completed. Results show that efficient NLOS detection improves positioning accuracy and implementing a base station exclusion algorithm helps for further increase.

A performance analysis of mesh models for cloud-based workflows

Nell'ambito della loro trasformazione digitale, molte organizzazioni stanno adottando nuove tecnologie per supportare lo sviluppo, l'implementazione e la gestione delle proprie architetture basate su microservizi negli ambienti cloud e tra i fornitori di cloud. In questo scenario, le service ed event mesh stanno emergendo come livelli infrastrutturali dinamici e configurabili che facilitano interazioni complesse e la gestione di applicazioni basate su microservizi e servizi cloud. L’obiettivo di questo lavoro è quello di analizzare soluzioni mesh open-source (istio, Linkerd, Apache EventMesh) dal punto di vista delle prestazioni, quando usate per gestire la comunicazione tra applicazioni a workflow basate su microservizi all’interno dell’ambiente cloud. A questo scopo è stato realizzato un sistema per eseguire il dislocamento di ognuno dei componenti all’interno di un cluster singolo e in un ambiente multi-cluster. La raccolta delle metriche e la loro sintesi è stata realizzata con un sistema personalizzato, compatibile con il formato dei dati di Prometheus. I test ci hanno permesso di valutare le prestazioni di ogni componente insieme alla sua efficacia. In generale, mentre si è potuta accertare la maturità delle implementazioni di service mesh testate, la soluzione di event mesh da noi usata è apparsa come una tecnologia ancora non matura, a causa di numerosi problemi di funzionamento.