COURSE # ROO-407
INTRODUCTION TO MULTI-TARGET, MULTI-SENSOR DATA FUSION
TECHNIQUES
FOR DETECTION, IDENTIFICATION, AND TRACKING
September 15-18, 2008, in Washington, DC
An informative in-depth presentation that addresses the complexities of this multi-disciplinary topic and provides a clear picture of the technology.
This course describes the methods by which data are combined from diverse sensors to improve the probability of correctly detecting, classifying, identifying, and tracking a desired object or target. The course offers a system-level discussion of sensor characteristics that can be used to enhance data fusion. The effects of the atmosphere and countermeasures on millimeter-wave and infrared sensors are illustrated to show how sensor outputs based on different phenomenologies enhance a data fusion system.
Aspects of data and sensor fusion that are covered include a description of the JDL data fusion model, architecture options and how they influence what information is combined and where the fusion process occurs, and descriptions and examples of the algorithms used for detection, classification, identification, and state estimation and tracking of objects. The course also addresses data fusion related areas such as sensor management, state estimation, and systems performance evaluation.
Examples help demonstrate the advantages of multisensor data fusion in systems that use laser radar (imagery and range data) and other types of sensor data for object classification, and microwave or millimeter-wave sensors, IR search and track systems (angular position data), and electronic support measures (ESM) (kinematic and attribute data) for state estimation and tracking. Many of the data fusion techniques also apply when it is desired to combine information from almost any grouping of sensors as long as they can be trained to supply the required input data.
Applications and benefits:
You will benefit by enhancing your understanding of the:
- Advantages of multisensor data fusion for object discrimination.
- Multisensor data fusion principles, algorithms, and architectures.
- Taxonomies for target detection, classification, identification, and tracking algorithms.
- Practical applications.
Who should attend:
Engineers, scientists, managers, designers, and users of multisensor data fusion for target detection, classification, identification, and tracking. Those interested in selecting appropriate sensors for specific applications and applying data fusion techniques to advanced dynamic systems, such as classification of airborne targets, ground-based targets, and underwater targets. Developers and users of real-time algorithms for intelligent machine development and multiple sensor technologies for non-cooperative target recognition. This course has no prerequisites; however, a general background in electrical engineering, mathematics, or statistics is beneficial, but not required, for an understanding of the concepts presented in the course.
Course Outline:
- Defense Applications of Multisensor Systems and Data Fusion
- Tactical warfare applications of sensor and data fusion
- Military data fusion architectures and sensor applications
- Sensor Systems
- Multiple sensor phenomenology
- Benefits of multiple sensor systems
- Atmospheric and obscurant effects on IR and MMW sensors
- Influence of sensor application on choice of MMW frequency and IR wavelength band
- Data Fusion Algorithms
- Level 1, 2, 3, 4 and 5 fusion processing
- Data fusion architectures
- Taxonomy of detection, classification, and identification data fusion algorithms
- Physical models
- Feature-based inference
- Parametric (classical inference, Bayesian, Dempster-Shafer, others)
- Information-theoretic models (templates, artificial neural networks, clusters, voting, figures of merit, pattern recognition, others)
- Cognitive-based (knowledge-based, fuzzy set theory, others)
- Taxonomy of state estimation and tracking data fusion algorithms
- Search direction
- Association and correlation of data and tracks
- Data alignment
- Data and object correlation (includes data and track association)
- Position, kinematic, and attribute estimation
- Classical Inference and Decision Theory
- Confidence interval
- Sample size for a desired margin of error
- Decision theory (choosing between two hypotheses) and significance tests
- Statistical significance
- z-test for a population mean
- t-test for a population mean
- One- and two-sided tests
- Type 1 and Type 2 errors
- Power of a test
- Bayesian Inference
- Comparison of Bayesian and classical inference
- Bayesian inference fusion process with multiple sensor data
- Recursive updating of posterior probabilities
- Multispectral sensor example
- Mine detection example
- Freeway incident detection example
- Dempster-Shafer Inference
- Dempster-Shafer fusion process
- Probability mass
- Uncertainty interval
- Comparison with Bayesian inference
- Dempster's rule
- Pignistic transferable belief model and other modifications of D-S theory with examples
- Artificial Neural Networks
- Linear classifiers
- Adaptive linear combiner
- Capacity of linear classifiers
- Nonlinear classifiers
- Madaline
- Feedforward networks
- Capacity of nonlinear classifiers
- Generalization
- Learning rules
- Linear mean square algorithms
- Perceptron rule
- Back propagation algorithm
- Fuzzy Logic
- Fuzzy Logic
- Definitions and applications
- Elements of fuzzy systems
- Fuzzy sets
- Membership functions
- Production rules
- Fuzzy logic processing examples
- Inverted pendulum
- Influence of fuzzy set widths and slopes
- Fuzzy Kalman filter and scene classifier
- Voting Logic
- Definition
- Detection modes and confidence levels
- System detection and false alarm probabilities
- Relation of detection and false alarm probabilities to confidence levels
- False alarm probability selection
- Three-sensor examples
- Introduction to Multiple Sensor/Multiple Target Tracking
- What is tracking and why is it needed?
- Where does MS/MTT fit in the Data Fusion framework?
- Mathematical preliminaries
- Basic Elements of a Tracking System
- Coordinate systems
- Data correlation and gating
- Maneuver detection and prediction
- Gain computation and track update
- Track initiation
- Signal processing requirements (assumptions)
- Least-Squares Estimation and the Kalman Filter
- Single-Target Tracking
- Track initiation
- Tracking in a cluttered environment
- Heuristic approaches
- Track bifurcation
- The probabilistic data association filter (PDAF)
- Maneuvers and the multiple model approach
- Multiple-Target Tracking
- Tracking in a cluttered environment
- The assignment problem
- Joint probabilistic data association filter (JPDAF)
- Multiple hypothesis tracker (MHT)
- Maneuvers
- MHT and the multiple model approach
- Multiple Radar Tracking
- Architectures
- Centralized or distributed?
- Tracks or measurements?
- Sensor registration and alignment
- Track fusion
- Multiple Dissimilar Sensor Data Fusion
- Active and passive sensors
- Functional requirements
- Passive data fusion: EO/IR, ESM sensors
- ID sensors and data: ESM, JEM, HRR, IFF/SIF
- Sensor Management in Data Fusion Systems
- Sensor management functions
- Establishing target priorities
- Sensor tasking
- Evaluation of tracking systems
- Covariance analyses
- Correlation probabilities
- Markov chains
- Simulation and Monte Carlo techniques
Text: Sensor and Data Fusion: A Tool for Information Assessment and Decision Making, Lawrence A. Klein (SPIE, PM 138, 2007).
About the Instructors
Lawrence A. Klein is a consultant specializing in the development of multiple sensor concepts for tactical and reconnaissance military applications, millimeter-wave and infrared sensors for homeland defense, and sensors and data fusion concepts for intelligent transportation systems. While at Hughes Aircraft, he developed missile deployment strategies and sensors used in missile guidance. As a systems manager at Aerojet ElectroSystems, he was responsible for the conceptual design and execution of programs that integrated active and passive millimeter-wave and infrared multispectral sensors in satellites and smart "fire-and-forget" weapons. He was the program manager of three Manufacturing Methods and Techniques projects that lowered the cost of millimeter-wave integrated circuits. At Honeywell, he developed passive millimeter-wave midcourse missile guidance systems and millimeter-wave sensors for mine applications. Other books written by Dr. Klein include Millimeter-Wave and Infrared Multisensor Design and Signal Processing (Artech House, 1997), which describes multisensor applications, design, and performance; and Sensor Technologies and Data Requirements for ITS (Artech House, 2001), which discusses sensor applications to traffic and transportation management systems. Dr. Klein received his Ph.D. in Electrical Engineering from New York University in 1973 and is a past reviewer for the IEEE Transactions on Antennas and Propagation, Geoscience and Remote Sensing, and Transactions on Aerospace and Electronic Systems.
Martin Dana is a Senior Scientist at Raytheon Systems Company (formerly Hughes Aircraft Company) in El Segundo, California. He has more than 25 years of experience in the analysis and design of multisensor tracking and identification systems for air defense and air traffic control. His specific areas of interest include track acquisition in cluttered
environments and multiple sensor registration and alignment. He has installed and verified the operation of multiple radar air defense systems in Europe, the Middle East, Japan, and Korea. Dr. Dana received a Ph.D. in mathematics from Washington State University in 1972. He has published papers on data fusion in various NATO AGARD publications and the proceedings of the US Combat ID and Data Fusion Symposia. His early work in registration for multiple sensor tracking may be found in Chapter 5 of Bar-Shalom's book, Multitarget-Multisensor Tracking, published by Artech House in 1990. Dr. Dana is a reviewer for the IEEE Transactions on Aerospace and Electronic Systems.
Details:
Course: ROO-407 Duration: 4 Days FEE: $1,699 CEUs: 2.88
Please direct any additional inquiries regarding our courses to Zygmond Turski, Program Director, by e-mail, FAX: (240) 371-4488 or TELEPHONE: (301) 871-9608.
Call toll free 1-800-683-7267 from anywhere in the Continental U.S. or CANADA.
Last modified April 6, 2008.
