Description
This is the sequel to the 2007 Artech House bestselling title, Statistical MultisourceMultitarget Information Fusion. That earlier book was a comprehensive resource for an indepth understanding of finiteset statistics (FISST), a unified, systematic, and Bayesian approach to information fusion. The cardinalized probability hypothesis density (CPHD) filter, which was first systematically described in the earlier book, has since become a standard multitarget detection and tracking technique, especially in research and development. Since 2007, FISST has inspired a considerable amount of research, conducted in more than a dozen nations, and reported in nearly a thousand publications. This sequel addresses the most intriguing practical and theoretical advances in FISST, for the first time aggregating and systematizing them into a coherent, integrated, and deepdive picture. Special emphasis is given to computationally fast exact closedform implementation approaches. The book also includes the first complete and systematic description of RFSbased sensor/platform management and situation assessment.
Table Of Contents
Introduction to the Book  Overview of FiniteSet Statistics. Recent Advances in FiniteSet Statistics. Organization of the Book.; I. Elements of FiniteSet Statistics; Random Finite Sets Introduction. SingleSensor, SingleTarget Statistics. Random Finite Sets (RFSs). Multiobject Statistics in a Nutshell. ; Multiobject Calculus Introduction. Basic Concepts. Set Integrals. Multiobject Differential Calculus. Key Formulas of Multiobject Calculus.; Multiobject Statistics Introduction. Basic Multiobject Statistical Descriptors. Important Multiobject Processes. Basic Derived RFSs.; Multiobject Modeling and Filtering Introduction. The MultisensorMultitarget Bayes Filter. Multitarget Bayes Optimality. RFS Multitarget Motion Models. RFS Multitarget Measurement Models. Multitarget Markov Densities. MultisensorMultitarget Likelihood Functions. The Multitarget Bayes Filter in p.g.fl. Form. The Factored Multitarget Bayes Filter. Approximate Multitarget Filters.; Multiobject Metrology Introduction. Multiobject Miss Distance. Multiobject Information Functionals.; II. RFS Filters: Standard Measurement Model; Introduction to Part II  Summary of Major Lessons Learned. Standard Multitarget Measurement Model. An Approximate Standard Likelihood Function. Standard Multitarget Motion Model. Standard Motion Model with Target Spawning. Organization of Part II. ; Classical PHD and CPHD Filters Introduction. A General PHD Filter. ArbitraryClutter PHD Filter. Classical PHD Filter. Classical Cardinalized PHD (CPHD) Filter. Zero False Alarms (ZFA) CPHD Filter. PHD Filter for StateDependent Poisson Clutter. ; Implementing Classical PHD/CPHD Filters Introduction. Spooky Action at a Distanceù. Merging and Splitting for PHD Filters. Merging and Splitting for CPHD Filters. Gaussian Mixture (GM) Implementation. Sequential Monte Carlo (SMC) Implementation.; Multisensor PHD and CPHD Filters Introduction. The MultisensorMultitarget Bayes Filter. The General Multisensor PHD Filter. The Multisensor Classical PHD Filter. IteratedCorrector Multisensor PHD/CPHD Filters. Parallel Combination Multisensor PHD and CPHD Filters. An Erroneous Averaged Multisensor PHD Filter. Performance Comparisons. ; JumpMarkov PHD/CPHD Filters Introduction. JumpMarkov Filters: A Review. Multitarget JumpMarkov Systems. JumpMarkov PHD Filter. JumpMarkov CPHD Filter. Variable State Space JumpMarkov CPHD Filters. Implementing JumpMarkov PHD/CPHD Filters. Implemented JumpMarkov PHD/CPHD Filters.; Joint Tracking and SensorBias Estimation Introduction. Modeling Sensor Biases. Optimal Joint Tracking and Registration. The BURTPHD Filter. SingleFilter BURTPHD Filters. Implemented BURTPHD Filters.; MultiBernoulli Filters Introduction. The Bernoulli Filter. The Multisensor Bernoulli Filter. The CBMeMBer Filter. JumpMarkov CBMeMBer Filter. ; RFS Multitarget Smoothers Introduction. SingleTarget ForwardBackward Smoother. General Multitarget ForwardBackward Smoother. Bernoulli ForwardBackward Smoother. PHD ForwardBackward Smoother. ZTACPHD Smoother.; Exact ClosedForm Multitarget Filter Introduction. Labeled RFSs. Examples of Labeled RFSs. Modeling for the VoVo Filter. Closure of Multitarget Bayes Filter. Implementation of the VoVo Filter: Sketch Performance Results. ; III. RFS Filters for Unknown Backgrounds; Introduction to Part III Introduction. Overview of the Approach. Models for Unknown Backgrounds. Organization of Part III; RFS Filters for Unknown pD Introduction. The pDCPHD Filter. BetaGaussian Mixture (BGM). Approximation. BGM Implementation of the pDPHD Filter. BGM Implementation of the pDCPHD Filter. The pDCBMeMBer Filter. Implementations of pDAgnostic RFS Filters.; RFS Filters for Unknown Clutter Introduction. A General Model for Unknown Bernoulli Clutter. CPHD Filter for General Bernoulli Clutter. The ŒªCPHD Filter. The Œ?CPHD Filter. Multisensor Œ?CPHD Filters. The Œ?CBMeMBer Filter. Implemented ClutterAgnostic RFS Filters. ClutterAgnostic Pseudofilters. CPHD/PHD Filters with PoissonMixture Clutter. Related Work.; IV. RFS Filters for Nonstandard Measurement Models; RFS Filters for Superpositional Sensors Introduction. Exact Superpositional CPHD Filter. Hauschildt 's Approximation. ThouinNannuruCoates (TNC) Approximation.; RFS Filters for Pixelized Images Introduction. The IO Multitarget Measurement Model. IO Motion Model. IOCPHD Filter. IOMeMBer Filter. Implementations of IOMeMBer Filters.; RFS Filters for ClusterType Targets Introduction. ExtendedTarget Measurement Models. ExtendedTarget Bernoulli Filters. ExtendedTarget PHD/CPHD Filters. ExtendedTarget CPHD Filter: APB Model. ClusterTarget Measurement Model. ClusterTarget PHD and CPHD Filters. Measurement Models for Level1 Group Targets. PHD/CPHD Filters for Level1 Group Targets. Measurement Models for General Group Targets. PHD/CPHD Filters for Level‚Ñì Group Targets. A Model for Unresolved Targets. Motion Model for Unresolved Targets. The UnresolvedTarget PHD Filter. Approximate UnresolvedTarget PHD Filter. Approximate UnresolvedTarget CPHD Filter. ; RFS Filters for Ambiguous Measurements Introduction. Random Set Models of Ambiguous Measurements. Generalized Likelihood Functions (GLFs). Unification of ExpertSystem Theories. GLFs for Imperfectly Characterized Targets. GLFs for Unknown Target Types. GLFs for Information with Unknown Correlations. GLFs for Unreliable Information Sources. Using GLFs in Multitarget Filters. GLFs in RFS Multitarget Filters. Using GLFs with Conventional Multitarget Filters. ; V. Sensor, Platform, and Weapons Management; Introduction to Part V  Basic Issues in Sensor Management. Information Theory and Intuition: An Example. Summary of RFS Sensor Control. Organization of Part V.; SingleTarget Sensor Management Introduction. Example: MissileTracking Cameras. SingleSensor, SingleTarget Control: Modeling. SingleSensor, SingleTarget Control: SingleStep. SingleSensor, SingleTarget Control: Objective Functions. SingleSensor, SingleTarget Control: Hedging. SingleSensor, SingleTarget Control: Optimization. Special Case 1: Ideal Sensor Dynamics. Simple Example: LinearGaussian Case. Special Case 2: Simplified Nonideal Dynamics. ; Multitarget Sensor Management Introduction. Multitarget Control: Target and Sensor State Spaces. Multitarget Control: Control Spaces. Multitarget Control: Measurement Spaces. Multitarget Control: Motion Models. Multitarget Control: Measurement Models. Multitarget Control: Summary of Notation. Multitarget Control: Single Step. Multitarget Control: Objective Functions. MultisensorMultitarget Control: Hedging. MultisensorMultitarget Control: Optimization. Sensor Management with Ideal Sensor Dynamics. Simplified Nonideal Multisensor Dynamics. Target Prioritization. ; Approximate Sensor Management Introduction. Sensor Management with Bernoulli Filters. Sensor Management with PHD Filters. Sensor Management with CPHD Filters. Sensor Management with CBMeMBer Filters. RFS Sensor Management Implementations. ; Appendix A Glossary of Notation and Terminology. References. About the Author. Index. ;
Author

Ronald P.S. Mahler
Ronald P.S. Mahler is a senior staff research scientist at Lockheed Martin Advanced Technology Laboratories in Eagan, MN. He earned his Ph.D. in mathematics from Brandeis University, Waltham, MA. He is recipient of the 2005 IEEE AESS Harry Rowe Mimno Award, the 2007 IEEE AESS M. Barry Carlton Award, and the 2007 JDLDFG Joseph Mignogna Data Fusion Award.