COURSE # ROO-408
INTRODUCTION TO MULTI-TARGET, MULTI-SENSOR DATA FUSION
FOR DETECTION, IDENTIFICATION, AND TRACKING
... an informative, in-depth presentation addressing the complexities of this multi-disciplinary field and its expanding role in a modern digital battlespace ...
Numerous DOD initiatives to increase the effectiveness of the Warfighter (FCS, WIN-T), National Maritime Domain Awareness (MDA), and Level 1 and 2 fusion for the E-3 AWACS SENTRY aircraft, to name a few, bring to the forefront technologies supporting ISTAR (Intelligence, Surveillance, Target Acquisition, Reconnaissance) and sensor and data fusion. Concurrent, rapid advances in sensor technologies covering wide frequency spectra ranging from extremely low frequencies to microwave, millimeter-wave (MMW), sub-MMW, infrared (IR) and visible, provide massive amounts of data, some more valuable than others. Sensor characteristics, processes and algorithms used to determine and select the most valuable data from each sensor, and techniques to fuse these data in real time and in a manner that supplies meaningful and timely information for the Warfighter, are the subjects of this class.
The course presents sensor and data fusion methods that improve the probability of correct target detection, classification, identification, and state estimation. These techniques combine information from collocated or dispersed sensors that utilize either similar or different technologies to generate target signatures or imagery. The effects of the atmosphere and countermeasures on millimeter-wave and infrared sensors are presented to illustrate how the use of different phenomenology-based sensors enhances a data fusion system.
Following the introduction of the JDL data fusion model, several methods for describing sensor and data fusion architectures are presented. Data fusion algorithm taxonomies and a general description of the algorithms and methods used for detection, classification, identification, and state estimation and tracking are discussed next. This is followed by consideration of situation and threat assessment. Subsequent sections of this course more fully develop the classical inference, Bayesian, Dempster-Shafer, voting logic, artificial neural network, and fuzzy logic data fusion algorithms. Radar tracking system design considerations, multiple sensor registration, track initiation in clutter, Kalman filtering, interacting multiple models, and data fusion maturity as it affects real-time tracking complete the topics treated in the course.
Specific examples are offered to demonstrate the advantages of multi-sensor data fusion in systems that use microwave and millimeter-wave detection and tracking radars, laser radars (imagery and range data), and forward-looking IR sensors (imagery data). 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 supply the input data required by the fusion algorithm.
Applications and benefits:
You will benefit by enhancing your understanding of the:
- Application of modern sensors to sensor and data fusion.
- Advantages of multi-sensor data fusion for object discrimination and state estimation.
- Multi-sensor data fusion principles, algorithms, and architectures that enable the assessment of new and existing systems.
- Taxonomies for target detection, classification, and identification.
- Skills needed to develop and apply data fusion algorithms in more complex situations.
- Practical applications.
Who should attend:
Many ongoing DoD efforts that focus on discerning better intelligence in real time employ a wide array of advanced sensors and elaborate data fusion techniques. This course presents underlying concepts, technology and selected applications, rendering it invaluable to system architects, engineers, scientists, managers, designers, military operations personnel, and other users of multi-sensor data fusion for target detection, classification, identification, and tracking. This course is also beneficial to those who select appropriate sensors for specific applications and missions; to those who apply data fusion techniques to advanced dynamic systems, such as classification of airborne targets, ground-based targets, and underwater targets; and to developers and users of real-time algorithms for intelligent machine development and multiple sensor technologies for non-cooperative target recognition. There are no specific prerequisites for this course, however, a general background in electrical engineering, mathematics, or statistics is recommended for a better understanding of the concepts presented.
- Defense Applications of Multisensor Systems and Data Fusion
- Need for smart sensors
- Defining detection, classification, and identification
- Sensor Systems
- Multiple sensor phenomenology
- Military data fusion architectures
- 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
- Sensor and Data Fusion: What is it?
- Levels 0, 1, 2, 3, 4 and 5 fusion processing
- Duality of data fusion and resource management
- 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 expert systems, fuzzy set theory, others)
- Taxonomy of State Estimation and Tracking Data Fusion Algorithms
- Search directions
- Correlation and association of data and tracks:
- Data alignment
- Data and track association (prediction gates, correlation metrics, data and track-to-track association)
- Position, kinematic, and attribute estimation
- Fusion Levels 2, 3, 4, and 5
- Situation assessment (Level 2)
- Threat assessment (Level 3)
- Refinement of the data fusion process (Level 4)
- Human-computer interaction issues (Level 5)
- 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
- Conditional probabilities
- Bayes' rule with illustrative examples
- 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 Evidential Reasoning
- Dempster-Shafer fusion process
- Probability mass
- Uncertainty interval
- Dempster's rule
- Comparison with Bayesian inference
- Probability mass function origination examples
- Using known characteristics of data gathered by the sensors
- Using confusion matrices
- Modifications of D-S theory with examples
- Pignistic transferable belief, plausibility transform, plausible and paradoxical reasoning, and other modifications of the original theory
- Artificial Neural Networks
- Linear classifiers
- Adaptive linear combiner
- Capacity of linear classifiers
- Nonlinear classifiers
- Feedforward networks
- Capacity of nonlinear classifiers
- Learning rules
- Linear mean square algorithms
- Perceptron rule
- Back propagation algorithm
- Fuzzy Logic
- Fuzzy logic definitions and applications
- Data correlation and gating
- Elements of fuzzy systems
- Fuzzy sets
- Membership functions
- Production rules
- Fuzzy logic processing and examples
- Inverted pendulum
- Influence of fuzzy set widths and slopes
- Fuzzy Kalman filter and scene classifier
- Fuzzy neural network examples
- Voting Logic
- 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
- Radar Tracking System Design Considerations
- Measurements versus tracks
- Characteristics of tracking radars
- Measures of quality for tracking
- Tracker design issues
- State space and coordinate conversion
- Multiple Sensor Registration
- A requirement for multisensor tracking
- Specific functional requirements
- Error sources
- Impact of bias errors on tracking
- Bias error budget
- Track Initiation in Clutter
- What is the initiation problem?
- The Sequential Probability Ratio Test (SPRT)
- Definition of the decision criteria
- Example application of the SPRT
- Properties of the SPRT
- Practical recommendations for track initiation
- Introduction to Kalman Filtering
- What is it and what does it do?
- The Kalman filter equations
- The filtering process
- Filter initialization
- Error covariance and Kalman filter recursive equations
- The Kalman gain: Keeping it large enough
- Models for the process noise covariance matrix Q
- Interacting Multiple Models (IMM)
- What is it and what does it do?
- The IMM process
- The components of a model
- Multiple-Sensor Tracking Architectures and Data Fusion Maturity
- Data Fusion/Track Management Options
- Data fusion maturity
Sensor and Data Fusion: A Tool for Information Assessment and Decision Making, Second Edition, Lawrence A. Klein (SPIE, PM222, 2012).
About the Instructor
Dr. 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 sensor 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 detection. In addition to this course?s textbook, Dr. Klein wrote 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.
Course: ROO-408 Duration: 3 Days FEE: $1,499 CEUs: 2.16
Please direct any additional inquiries regarding our courses to Zygmond Turski, Program Director, by e-mail, FAX: (240) 371-4488 or TELEPHONE: (202) 241-6326.
Call toll free 1-800-683-7267 from anywhere in the Continental U.S. or CANADA.
Last modified April 13, 2016.