Understand multi-sensor fusion--the most sophisticated way to deliver accurate real-world data to computer systems. Applications include aviation, medicine, military, manufacturing, and transportation. The Sensor Fusion Toolkit on disk contains C programs discussed in the book and supports each section.
"synopsis" may belong to another edition of this title.
A large number of important applications depend on computers interfacing with the real world. These applications include military, medical, manufacturing, transportation, safety, and environmental planning systems. Many have been difficult to realize because of problems involved with inputting data from sensors directly into automated systems. Sensor fusion has emerged as the method of choice for resolving these problems. This book is written as an introduction to this field. It also contains detailed information needed for designing practical applications. The book is appropriate for use as an upper division undergraduate or graduate level textbook. It should also be of interest to researchers in most scientific and engineering fields, since they require the processing and interpretation of sensor data. These fields include electrical/computer engineering, computer science, mathematics, mechanical engineering, and the signal processing community.
The text is self-contained and assumes only that the reader knows a higher-level programming language that uses pointers. All other material is explained in the text. Recurring themes are multidimensional data structures, reasoning with uncertainty, system dependability and the use of meta-heuristics. All these topics are covered in depth, and relevant applications are given. In our experience, these topics are most easily understood when combined with practical applications. Since these topics are of broad interest, the information contained in this book could easily be integrated into courses whose central focus range from artificial intelligence to mechanical engineering.
Accompanying the text is a set of functioning C programs that implement the applications discussed. The software includes implementations of machine learning meta-heuristics that have established themselves in engineering: neural networks, simulated annealing, genetic algorithms, and tabu search. It also contains an example Kalman filter that illustrates the use of modern control theory. Our Distributed Dynamic Sensor Fusion algorithm from Chapter 14 is also included. This algorithm is more computationally efficient than the Kalman filter and can be used for a wider class of problems.
Part 1 provides a general overview of sensor fusion, and defines most of the terminology used in the text. Part 2 provides the mathematics and computer science background required for the rest of the book. For most researchers, the most interesting part of the book will be Part 3. In Part 3, the results of six years of sensor fusion research for the Office of Naval Research are presented. Much of this work has been published in refereed journals, and these papers have been edited for content and style. These chapters include novel approaches to fusion-related problems such as image registration, distributed agreement, and sensor selection, as well as efficient algorithms for fusing sensor data. The final section, Part 4, concludes the book by reviewing the state of the art and discussing a number of innovative implementations.
Increasingly, applications require computers to interface with the real world and draw data directly from it. These applications range from defense to medicine, manufacturing to environmental health. They all depend on inputs that are noisy, incomplete, and of limited accuracy.
This book introduces multi-sensor fusion, which has emerged as the method of choice for implementing robust systems that can handle imperfect inputs. It represents the first broad, practical text on the subject - covering all the technologies and methods associated with multi-sensor fusion, including:
The book reflects six years of sensor fusion research for the Office of Naval Research, introducing novel solutions to challenges such as image registration, distributed agreement, and sensor selection.
Multi-Sensor Fusion focuses extensively on applications, including neural networks, genetic algorithms, tabu search and simulated annealing. It comes with a set of functioning C programs on disk to implement these applications. This Sensor Fusion Toolkit includes both a standard Kalman filter and the authors' enhanced Distributed Dynamic Sensor Fusion algorithm, which is easier to use and solves more problems.
This is the essential tutorial and reference for any professional or advanced student developing systems that utilize sensor input, including computer scientists, electrical, mechanical and chemical engineers.
"About this title" may belong to another edition of this title.
Book Description Prentice Hall PTR, 1997. Hardcover. Book Condition: New. Bookseller Inventory # P110139016538