Click here to download the call for tutorials.

The main purpose of the tutorial program is to provide overviews of the state of the art in the particular subfields of Information Fusion. This program should be useful to newcomers to the Information Fusion community to learn about the research achievements of the particular areas, as well as to currently active Information Fusion researchers who may be interested in widening their areas of research interest.

Tutorials will be held on Tuesday, July 5, 2016 from 08:30 to 19:00.

Tutorials do not include lunch, but include coffee/tea breaks between tutorials.

• Please select up to three tutorials, one from each time slot.
• The tutorials are assigned fixed numbers (T1 to T26) that will not be changed in the event of cancellations.
• During registration, please select the desired tutorials (by number or name).
• There will be a discount for booking two or three tutorials, see Fees and Registration page.
• You will obtain printed coupons for your tutorials while checking in for the conference. These coupons contain your name and the name of the selected tutorials and are required for participation.
• In the unlikely event that tutorials get canceled, we will offer alternatives to you. Of course, you can always opt for a refund if your chosen tutorials do not take place.

• The conference does not offer any printing services and is not responsible for study materials distributed to the attendees. This is solely the responsibility of the presenter.
• The tutorial cost for attendees is €165 - €250 per 3-hr slot, depending on time of registration and number of tutorials taken, see Fees and Registration page.
• There will be an honorarium for tutorial presenters, where the proceeds from each tutorial, less the room cost of €250, will be shared 50-50 between Fusion 2016 and the Presenter. When there is more than one presenter, the honorarium is paid to the first person named in the program.
• The number of attendees will be counted based on the registrations.
• Any tutorial with less than 5 people registered by the early-bird deadline June 1^st may be cancelled.

• Please be present in your assigned room early. The time and room for your tutorial is shown in the time table below.
• There will be a technician and a student volunteer helping you with setting up the system and providing access control.

• T1 Bayesian Multiple Target Tracking
• T2 Bayesian Networks and Trust Fusion with Subjective Logic
• T3 Multisensor-Multitarget Tracker/Fusion Engine Development and Performance Evaluation for Realistic Scenarios
• T4 An Introduction to Track-to-Track Fusion and the Distributed Kalman Filter
• T5 An Introduction to Finite-Set Statistics for Information Fusion
• T6 Information Quality in Information Fusion and Decision Making
• T7 Multitarget Tracking and Multisensor Information Fusion
• T8 Overview of High-Level Information Fusion Theory, Models, and Representations
• T9 Quantum Physics Methods for Nonlinear Filtering
• T10 Basic Concepts in Multiobject Estimation
• T11 System-of-Systems Opportunities and Issues for Information Fusion - Withdrawn by presenter
• T12 Implementations of Random-Finite-Set-Based Multi-Target Filters
• T13 Tracking and Sensor Data Fusion – Methodological Framework and Selected Applications
• T14 Multistatic Exploration – Introduction to Modern Passive Radar and Multistatic Tracking & Data Fusion - Withdrawn by presenter
• T15 Big Data Fusion and Analytics
• T16 Object Tracking, Sensor Fusion and Situational Awareness for Assisted- and Self-Driving Vehicles: Problems, Solutions and Directions
• T17 Emerging Quantum Technologies for Fusion
• T18 Maneuvering Target Tracking: Overview and Nonlinear Filtering Methods
• T19 Integration of Information to Identify Objects in Big Data - Withdrawn by presenter
• T20 Extended Object Tracking: Theory and Applications
• T21 Probabilistic Situation Assessment for Abnormal Interaction Detection
• T22 Multitarget Tracking and Sensor Calibration in Centralized and Distributed Networks - Withdrawn by presenter
• T23 Information Fusion in Resource-Limited Camera Networks
• T24 Introduction to Bayesian Filtering and Smoothing
• T25 Sensor Fusion for Intelligent Vehicles
• T26 Multisensor Data Fusion in Wireless Sensor and Actuator Networks

Presenter: Lawrence D. Stone and Roy L. Streit
Length: 3 hours
Brief description: This tutorial is based on the book, Bayesian Multiple Target Tracking 2nd Ed. Its purpose is to present the basic results in multiple-target tracking from a Bayesian point of view. People who register will receive a complimentary copy of the book when they attend the tutorial.
More Details

Presenter: Audun Jøsang
Length: 3 hours
Brief description: This tutorial gives attendees a first-hand insight into the theory and application of subjective logic by the author and researcher who proposed and started developing this framework in 1997. The tutorial gives an introduction to subjective logic, and how it applies to Bayesian network modelling and information fusion. ...
More Details

Presenter: T. Kirubarajan
Length: 3 hours
Brief description: While numerous tracking and fusion algorithms are available in the literature, their implementation and application on real-world problems are still challenging. Since new algorithms continue to emerge, rapidly prototyping them, developing for production and evaluating them on real-world (or realistic) problems efficiently are also essential. In addition to reviewing state-of-the-art tracking algorithms, this tutorial will focus on a number of realistic multisensor-multitarget tracking problems, simulation of large-scale tracking scenarios, rapid prototyping, development of high performance real-time tracking/fusion software, and performance evaluation on realistic scenarios. ...
More Details

Presenter: Felix Govaers
Length: 3 hours
Brief description: The increasing trend towards connected sensors (”internet of things” and ”ubiquitous computing”) derive a demand for powerful distributed estimation methodologies. In tracking applications, the ”Distributed Kalman Filter” (DKF) provides an optimal solution under certain conditions. The optimal solution in terms of the estimation accuracy is also achieved by a centralized fusion algorithm which receives either all associated measurements or so-called tracklets.... Two more recent methodologies are based on the ”accumulated state densities” (ASD) which augment the states from multiple time instants. In practical applications, tracklet fusion based on the equivalent measurement often achieves reliable results even if full communication is not available. The limitations and robustness of the tracklet fusion will be discussed. ...
More Details

Presenter: Ronald Mahler
Length: 3 hours
Brief description: Finite-set statistics is a theoretically unified mathematical machine for solving information fusion problems, based on random set theory. First systematically described in Statistical Multisource-Multitarget Information Fusion (Artech, 2007), it has attracted the interest of dozens of research groups in at least 19 nations, resulting in well over a thousand publications. Advances in Statistical Multisource-Multitarget Information Fusion (Artech, 2014) systematically described the most intriguing aspects of this research, including algorithms that outperform conventional approaches. Previous tutorials have focused on applications of random set information fusion. This is the first systematic tutorial treatment of finite-set statistics itself. ...
More Details

Presenter: Galina Rogova
Length: 3 hours
Brief description: ... The tutorial will discuss major challenges and some possible approaches addressing the problem of representing and incorporating information quality into fusion processes. In particular it will present an ontology of quality of information and identify potential methods of representing and assessing the values of quality attributes and their combination. It will also examine the relation between information quality and context, and suggest possible approaches to quality control compensating for insufficient information and model quality.
More Details

Presenter: Yaakov Bar-Shalom
Length: 3 hours
Brief description: To provide to the participants the latest state-of-the art techniques to estimate the states ofmultiple targets with multisensor information fusion. Tools for algorithm selection, design and evaluation willbe presented. These form the basis of automated decision systems foradvanced surveillanceandtargeting.The various information processing configurations for fusion are described, including the recently solvedtrack-to-track fusion from heterogeneous sensors.
More Details

Presenter: Erik Blasch
Length: 3 hours
Brief description: Over the past decade, the ISIF community has put together special sessions, panel discussions, and concept papers to capture the methodologies, directions, needs, and grand challenges of high-level information fusion (HLIF) in practical system designs. This tutorial brings together the contemporary concepts, models, and definitions to give the attendee a summary of the state-of-the-art in HLIF. Analogies from low-level information fusion (LLIF) of object tracking and identification are extended to the HLIF concepts of situation/impact assessment and process/user refinement. HLIF theories (operational, functional, formal, cognitive) are mapped to representations (semantics, ontologies, axiomatics, and agents) with contemporary issues of modeling, testbeds, evaluation, and human-machine interfaces. Discussions with examples of search and rescue, cyber analysis, and battlefield awareness are presented. ...
More Details

Presenter: Bhashyam Balaji and Fred Daum
Length: 3 hours
Brief description: Relationships between nonlinear filtering and quantum physics has been studied in the past. In this tutorial, more modern connections between the two fields are drawn, particularly based on methods drawn from Feynman path integrals, quantum field theory and renormalization group.
More Details

Presenter: Daniel Clark, Emmanuel D. Delande, and Jérémie Houssineau
Length: 3 hours
Brief description: ... This tutorial will highlight some basic mathematical concepts in multiobject estimation to enable researchers to better understand and contribute to innovations in this field. The goal of the presenters is to inspire participants to develop a broader mathematical perspective and explore the literature in spatial statistics and point processes to aid their research in sensor fusion. The presenters will highlight where new concepts to multiobject estimation in sensor fusion, such as regional variance for estimating population uncertainty, can be facilitated when considering a measuretheoretic point process perspective.
More Details

Presenter: Alan Steinberg
Length: 3 hours
Brief description: Current concepts and methods in System-of-Systems Engineering (SoSE) will be presented, together with the role of information fusion. ... Methods for maximizing the effectiveness of cooperative sensing and cooperative engagement tactics will be discussed. ... Advanced multi-sensor, highly integrated weapons platforms provide enormous new capabilities. ... Data integrity and consistency are critical in integrating and using systems-of-systems. Attendees will learn current techniques for aligning data in space and time and in confidence. ... There will be discussion of SoS Engineering methodology for developing SoS architectural and management solutions to meet requirements of technical performance, cost, flexibility and extensibility. Developmental and operational testing and evaluation of systems-of-systems involves special challenges, not the least of which are multiple interacting control-loops in such systems.
More Details

Presenter: Ba-Ngu Vo and Ba-Tuong Vo
Length: 3 hours
Brief description: The Finite Set Statistics framework for multi-sensor multi-target tracking has attached considerable interest in recent years. It provides a unified perspective of multi-target tracking in a very intuitive manner by drawing direct parallels with the simpler problem of single-target tracking. This framework has lead to the development of multi-target filters such as the Probability Hypothesis Density (PHD), Cardinalized PHD (CPHD), Multi-Bernoulli filters and recently, the Generalized Labeled Multi-Bernoulli filter. In this tutorial, we show how these filters are implemented and illustrate via Matlab how these filters work. ...
More Details

Presenter: Wolfgang Koch
Length: 3 hours
Brief description: The tutorial covers the material of the recently published book of the presenter with the same title (Springer 2014, Mathematical Engineering Series, ISBN 978-3-642-39270-2) and thus provides an guided introduction to deeper reading. Starting point is the well known JDL model of sensor data and information fusion that provides general orientation within the world of fusion methodologies and its various applications, covering a dynamically evolving field of ever increasing relevance. Using the JDL model as a guiding principle, the tutorial introduces into advanced fusion technologies based on practical examples taken from real world applications.
More Details

Presenter: Wolfgang Koch
Length: 3 hours
Brief description: Advanced distributed signal and data fusion for passive radar systems, where DVB TV or GSM mobile phone base stations are used as sources for illuminating targets, for example, is a topic of increasing interest. Even in remote regions of the world, transmitters of electromagnetic radiation become a potential radar transmitter stations enabling covert surveillance for air, sea, and ground scenarios. Analogous considerations are valid for sub-sea surveillance. Illustrated by examples and experimental results, principles of passive radar as well as advanced multistatic tracking and de-ghosting techniques will be discussed.
More Details

Presenter: Subrata Das
Length: 3 hours
Brief description: Big data has tremendous potential to transform businesses but poses significant challenge in searching, processing, and extracting actionable intelligence. In this tutorial, I will present some techniques for fusion and analytics to process big centralized warehouse data, inherently distributed data, and data residing on the cloud. The fusion and analytics techniques to be discussed will handle both structured transactional and sensor data as well as unstructured textual data such as human intelligence, emails, blogs, surveys, etc. As a background, this tutorial is intended to provide an account of both the cutting-edge and the most commonly used approaches to high-level data fusion and predictive and text analytics. The demos to be presented are in the areas of distributed search and situation assessment, information extraction and classification, and sentiment analyses. ...
More Details

Presenter: T. Kirubarajan
Length: 3 hours
Brief description: ... In this tutorial, we aim to discuss a number of problems related to assisted- and self-driving vehicles, potential solutions and directions for research & development. The issues discussed in this tutorial will span multitarget tracking, multisensor fusion and situational awareness within the context of smart cars. We will also present some of the algorithms that are available in the open literature as well as those we have developed recently. In addition, we will also discuss related computational issues and sensor technologies. Finally, we will present some results on real data.
More Details

Presenter: Bhashyam Balaji
Length: 3 hours
Brief description: ... Although the fundamentals of quantum physics have been well-known since the 1920s, in the last few decades several novel consequences of the laws of quantum physics (particularly, in the areas of atomic, molecular and optical physics and quantum computer science and information theory) have been discovered. ... In particular, in the areas of sensing, quantum physics sets the bounds on the sensitivity of sensing... that is orders of magnitude below the sensitivity of current sensors. In the area of computing, it has been observed that a quantum computer allows some computations to be carried out that are unfeasible using current or future classical computing technology. In the area of communication, quantum physics enables provable secure communication and at much higher data rates than those allowed by classical Shannon limit. Many of these advances could have major near-term and long-term consequences in the areas of sensing, secure communication, big data analysis, and machine learning, and hence sensor and information fusion.
More Details

Presenter: X. Rong Li and Vesselin P. Jilkov
Length: 3+3 hours
Brief description: The principal challenges for tracking a maneuverable target are nonlinearity in both target motion and measurement models as well as the uncertainty in the pattern of target motion. This tutorial presents theoretical and algorithmic means available to meet these challenges. The overview part elucidates a well organized panorama of maneuvering target tracking. The other part presents an in-depth coverage of recent advances in nonlinear filtering for maneuvering target tracking, including some of the instructors’ results and insights as well as better known methods. The tutorial highlights the underlying ideas and pros and cons of approaches and techniques as well as inter-relationships among them. It is an outgrowth of the instructors’ ongoing comprehensive survey and several short courses of the same subject as well as a graduate course on target tracking taught at the Electrical Engineering Department of the University of New Orleans.
More Details

Presenter: Grace S. Shieh
Length: 3 hours
Brief description: Big data has tremendous potential to transform businesses and research but raises significant challenges in pre-processing and extracting useful information and information integration to identify objects of interest. In this tutorial, I will present some statistical methods/machine learning for fusion and analysis of big data in cancer research, e.g., DNA sequencing data, gene expression data (RNA-seq) from The Cancer Genome Atlas (TCGA), protein expression and clinical features of cancer patients. This tutorial aims to cover both useful statistical/data mining methods and the cutting-edge directions. ...
More Details

Presenter: Karl Granström, Stephan Reuter, and Marcus Baum
Length: 3 hours
Brief description: Autonomous driver safety functions are standard in many modern cars, and semi-automated systems (e.g., traffic jam assist) are becoming more and more common. Construction of a driverless vehicle requires solutions to many different problems, among them multiple object tracking. This tutorial will introduce the audience to extended object tracking, i.e., object tracking using modern high resolution sensors that give multiple detections per object. State of the art theory will be introduced, and relevant real world applications will be shown where different object types—e.g., pedestrians, bicyclists, cars—are tracked using different sensors such as lidar, radar, and camera.
More Details

Presenter: Carlo Regazzoni and Lucio Marcenaro
Length: 3 hours
Brief description: The tutorial aims at providing an overview of new insights in extending Dynamic Bayesian Networks techniques for representing, modeling and automatically interpreting and managing complex interaction situations occurring in cognitive environments starting from observations provided by multidimensional signals collected through a distributed network of embedded systems. A uniform representation is discussed that can also be used to support decisions concerning interactions between operators and the status of the observed environment. Solutions, which are based on an extension of traditional Bayesian filters for object assessment, are the basis background of discussion from which techniques in this tutorial. ...
More Details

Presenter: Murat Uney, Simon Julier, and Daniel Clark
Length: 3 hours
Brief description: … This tutorial will present methods for fusion and registration in networks of sensors. In the first part, the focus will be on integrating information output by local filtering at the sensor nodes. Both optimal and suboptimal algorithms will be presented and discussed. The second part will cover registration/calibration of sensors. First, a centralised setting will be considered in which the sensor measurements are available at a centre. It will be shown how the registration process can exploit the Probability Hypothesis Density (PHD) filtering principles for handling the uncertainties in the multitarget model. The second topic will be a distributed setting in which several sensor nodes exchange filtered distributions as opposed to measurements. A recent solution will be introduced which feature local processing at the sensor nodes and message passing operations for selfcalibration.
More Details

Presenter: Andrea Cavallaro and Juan C. SanMiguel
Length: 3 hours
Brief description: … This tutorial will introduce key features of modern visual sensor networks while exploring the issues commonly found in such networks, which have recently become central in several applications. For smart-camera networks to enable these emerging applications they need to adapt to unforeseen conditions and varying tasks under constrained resources. The tutorial will offer theoretical explanations followed by examples using the WiseMNet++ simulator.
More Details

Presenter: Simo Särkkä
Length: 3 hours
Brief description: ... The tutorial introduces the current state-of-the-art of non-linear (single-target) optimal filtering and smoothing methods in a unified Bayesian framework. The attendees learn what non-linear Kalman filters and particle filters are, how they are related, and their relative advantages and disadvantages. They also discover how Bayesian parameter estimation methods can be combined with the filtering and smoothing algorithms. ... Example applications from navigation, remote surveillance, and time series analysis.
More Details

Presenter: Bharanidhar Duraisamy, Ting Yuan, Tilo Schwarz, and Martin Fritzsche
Length: 3 hours
Brief description: This tutorial is focussed towards the stringent requirements, foundations, development and testing of sensor fusion algorithms meant for advanced driver assistance functions and driverless applications in automotive vehicle systems. ... The interesting part of the tutorial is covered on the different challenging and important practical aspects such as fusion with incomplete information, data association, etc. related to fusion and target tracking in automotive setting. Fusion and management of the different extended target representations of heterogeneous nature obtained from sensors with different resolution is presented with examples. More than one kind of intelligent vehicular sensor fusion framework dealing with tracked objects i.e. track level fusion and raw sensor measurements i.e. measurement level fusion, with results obtained using several real world data sets that contains various static and dynamic targets would be presented in this tutorial.
More Details

Presenter: Claudio Miceli de Farias
Length: 3 hours
Brief description: This tutorial focuses on presenting Multisensor Data Fusion Techniques for Wireless Sensor and Actuator networks. Advances in microelectromechanical systems technologies and wireless communications have enabled the construction of devices, called sensors, endowed with processing and communication capabilities, used to monitor physical quantities in an environment. ... Recent years have witnessed the emergence of the Shared/ Virtual Sensor and Actuator Networks, which instead of assuming an application-specific design, allow the sensing and communication infrastructure to be shared among multiple applications. ... However, wireless sensors and actuators commonly rely on batteries as their energy sources, whose replacement is undesirable or unfeasible. Therefore, in order to reduce the amount of data to be transmitted in the wireless channel, thus saving energy, Multisensor Data Fusion Methods (MDF) can be employed.
More Details