Fundamentals of Object Tracking

by Subhash Challa , Mark R. Morelande , Darko Mušicki , Robin J. Evans

• ISBN13: 9780521876285
• ISBN10: 0521876281
• Format: Hardcover
• Copyright: 2011-11-28
• Publisher: Cambridge University Press

Summary

Kalman filter, particle filter, IMM, PDA, ITS, random sets... The number of useful object-tracking methods is exploding. But how are they related? How do they help track everything from aircraft, missiles and extra-terrestrial objects to people and lymphocyte cells? How can they be adapted to novel applications? Fundamentals of Object Tracking tells you how. Starting with the generic object-tracking problem, it outlines the generic Bayesian solution. It then shows systematically how to formulate the major tracking problems - maneuvering, multiobject, clutter, out-of-sequence sensors - within this Bayesian framework and how to derive the standard tracking solutions. This structured approach makes very complex object-tracking algorithms accessible to the growing number of users working on real-world tracking problems and supports them in designing their own tracking filters under their unique application constraints. The book concludes with a chapter on issues critical to successful implementation of tracking algorithms, such as track initialization and merging.

Author Biography

Subhash Challa is a Professor and Senior Principal Researcher at the NICTA, Victoria Research Laboratory at the University of Melbourne. He is also the co-founder and CEO of SenSen Networks Pty Ltd, a leading video business intelligence solutions company. Mark R. Morelande is a Senior Research Fellow in the Melbourne Systems Laboratory at the University of Melbourne. Darko Muicki is a Professor in the Department of Electronic Systems Engineering at Hanyang University in Ansan, Republic of Korea.

Table of Contents

Preface	p. ix
Introduction to object tracking	p. 1
Overview of object tracking problems	p. 2
Bayesian reasoning with application to object tracking	p. 7
Recursive Bayesian solution for object tracking	p. 16
Summary	p. 21
Filtering theory and non-maneuvering object tracking	p. 22
The optimal Bayesian filter	p. 22
The Kalman filter	p. 25
The extended Kalman filter	p. 31
The unscented Kalman filter	p. 36
The point mass filter	p. 43
The particle filter	p. 46
Performance bounds	p. 53
Illustrative example	p. 57
Summary	p. 60
Modeling for maneuvering object tracking	p. 62
The optimal Bayesian filter	p. 66
Generalized pseudo-Bayesian filters	p. 72
Interacting multiple model filter	p. 84
Particle filters for maneuvering object tracking	p. 91
Performance bounds	p. 97
Illustrative example	p. 99
Summary	p. 102
Single-object tracking in clutter	p. 103
The optimal Bayesian filter	p. 104
The nearest neighbor filter	p. 107
The probabilistic data association filter	p. 111
Maneuvering object tracking in clutter	p. 119
Particle filter for tracking in clutter	p. 122
Performance bounds	p. 126
Illustrative examples	p. 131
Summary	p. 132
Single- and multiple-object tracking in clutter: object-existence-based approach	p. 133
Introduction	p. 133
Problem statement/models	p. 138
Track state	p. 142
Optimal Bayes' recursion	p. 147
Optimal track update cycle	p. 171
Track component control	p. 184
Object-existence-based single-object tracking	p. 191
Object-existence-based multi-object tracking	p. 205
Summary	p. 221
Multiple-object tracking in clutter: random-set-based approach	p. 223
The optimal Bayesian multi-object tracking filter	p. 225
The probabilistic hypothesis density approximations	p. 227
Approximate filters	p. 237
Object-existence-based tracking filters	p. 244
Performance bounds	p. 260
Illustrative example	p. 262
Summary	p. 264
Bayesian smoothing algorithms for object tracking	p. 265
Introduction to smoothing	p. 265
Optimal Bayesian smoothing	p. 266
Augmented state Kalman smoothing	p. 268
Smoothing for maneuvering object tracking	p. 271
Smoothing for object tracking in clutter	p. 275
Smoothing with object existence uncertainty	p. 278
Illustrative example	p. 283
Summary	p. 288
Object tracking with time-delayed, out-of-sequence measurements	p. 289
Optimal Bayesian solution to the OOSM problem	p. 289
Single- and multi-lag OOSM algorithms	p. 293
Augmented state Kalman filter for multiple-lag OOSM	p. 294
Augmented state PDA filter for multiple-lag OOSM in clutter	p. 297
Simulation results	p. 302
Summary	p. 311
Practical object tracking	p. 312
Introduction	p. 312
Linear multi-target tracking	p. 313
Clutter measurement density estimation	p. 317
Track initialization	p. 322
Track merging	p. 329
Illustrative examples	p. 332
Summary	p. 343
Mathematical and statistical preliminaries	p. 344
Finite set statistics (FISST)	p. 354
Pseudo-functions in object tracking	p. 358
References	p. 351
Index	p. 370
Table of Contents provided by Ingram. All Rights Reserved.