Track-before-detect using expectation maximisation : the histogram probabilistic multi-hypothesis tracker: theory and applications /

Track-before-detect using expectation maximisation : the histogram probabilistic multi-hypothesis tracker: theory and applications /

Saved in:
Bibliographic Details
Author / Creator:Davey, Samuel J., author.
Imprint:Singapore : Springer, 2018.
Description:1 online resource (xxi, 352 pages) : illustrations (some color)
Language:English
Series:Signals and communication technology, 1860-4862
Signals and communication technology,
Subject:
Gaussian measures.
Gaussian measures.
Format: E-Resource Book
URL for this record:http://pi.lib.uchicago.edu/1001/cat/bib/11543425
Hidden Bibliographic Details
Other authors / contributors:Gaetjens, Han X., author.
ISBN:9789811075933
981107593X
9789811075926
9811075921
Digital file characteristics:text file PDF
Notes:Includes bibliographical references and index.
Online resource; title from PDF title page (SpringerLink, viewed February 13, 2018).
Summary:This book offers a detailed description of the histogram probabilistic multi-hypothesis tracker (H-PMHT), providing an accessible and intuitive introduction to the mathematical mechanics of H-PMHT as well as a definitive reference source for the existing literature on the method. Beginning with basic concepts, the authors then move on to address extensions of the method to a broad class of tracking problems. The latter chapters present applications using recorded data from experimental radar, sonar and video sensor systems. The book is supplemented with software that both furthers readers' understanding and acts as a toolkit for those who wish to apply the methods to their own problems.
Other form:Printed edition: 9789811075926
Standard no.:10.1007/978-981-10-7593-3
Table of Contents:
  • Intro; Foreword; Reference; Acknowledgements; Contents; About the Authors; Parlance; 1 Introduction; 1.1 Historical Development of H-PMHT; 1.2 Preliminaries; 1.3 Expectation
  • Maximisation; 1.4 Notation; 1.5 Canonical Multi-target Scenario; 1.6 Measures of Performance; 1.6.1 Cardinality Measures; 1.6.2 Association Measures; 1.6.3 Accuracy Measures; 1.6.4 Track to Truth Association; 1.7 Monograph Synopsis; References; 2 Idealised Track-Before-Detect; 2.1 Single Target Comparison; 2.2 Summary; References; 3 Point Measurement Probabilistic Multi-hypothesis Tracking; 3.1 Gaussian Mixture Models.
  • 3.2 Dynamic Mixture Model3.2.1 Expectation Step; 3.2.2 Linear Gaussian Maximisation Step; 3.3 Non-Gaussian Mixtures; 3.4 Incorporating Clutter; 3.5 Examples of PMHT Point Measurement Tracking; 3.5.1 Two Targets; 3.5.2 Numerous Targets; 3.6 Problems with PMHT; 3.6.1 Model Order Estimation; 3.6.2 Adaptivity; 3.6.3 Optimism; 3.7 Summary; References; 4 Histogram Probabilistic Multi-hypothesis Tracking; 4.1 Histogram Data Association; 4.1.1 Expectation Step; 4.1.2 Maximisation Step; 4.2 Unobserved Pixels; 4.3 Image Quantising; 4.3.1 Quantisation in the Limit; 4.3.2 Resampled Target Prior.
  • 4.4 Associated Images4.5 Algorithm Summary for Gaussian Appearance; 4.6 Simulated Example; 4.7 Summary; References; 5 Implementation Considerations; 5.1 Alternative Resampled Prior; 5.2 Integrals; 5.3 Vectorised Two-Dimensional Case; 5.4 Single-Target Chip Processing; 5.5 Covariance Estimates; 5.5.1 Observed Information; 5.5.2 Joint Probabilistic Data Association; 5.6 Track Management; 5.6.1 Track Quality Score; 5.6.2 Hierarchical Track Update; 5.6.3 Track Decisions; 5.6.4 Image Vetting; 5.6.5 New Candidate Formation; 5.6.6 Integrated Track Management; 5.7 Summary; References.
  • 6 Poisson Scattering Field6.1 Hysteresis; 6.2 Poisson and Multinomial Equivalence; 6.3 Dynamic Non-homogeneous Poisson Mixture Model; 6.3.1 Point Measurement Data; 6.3.2 Image Measurement Data; 6.4 Examples; 6.4.1 Measurement Rate Estimation; 6.4.2 Average Power Estimation; 6.4.3 Track Initiation; 6.5 Clutter Mapping; 6.6 Target Life Cycle; 6.7 Summary; References; 7 Known Non-Gaussian Target Appearance; 7.1 Grid-Based Maximisation for Non-Gaussian Appearance; 7.2 Particle-Based Maximisation for Non-Gaussian Appearance; 7.3 Cell-Varying Point Spread Function.
  • 7.4 Gaussian Mixture Appearance Approximation7.5 Simulated Examples; 7.5.1 Linear Gaussian Appearance; 7.5.2 Linear Non-Gaussian Appearance; 7.5.3 Crossing Non-Gaussian Scenario; 7.5.4 Diverging Target Scenario; 7.6 Summary; References; 8 Adaptive Appearance Models; 8.1 Deterministic Gaussian Appearance; 8.2 Stochastic Gaussian Appearance; 8.3 General Framework for Appearance Estimation; 8.4 Gaussian Mixture Appearance; 8.5 Bounding Box; 8.6 Dirichlet Appearance; 8.7 Appearance Library; 8.8 Correlated Kinematics and Appearance; 8.9 Simulated Examples; 8.9.1 Gaussian Targets.

Similar Items