Dynamic Vision for Perception
and Control of Motion
by Ernst D. Dickmanns
Reviewed by: Antonio-Jose Sanchez-Salmeron ,
Universidad Politécnica de Valencia
Click above to go to the publisher’s web page where there is a description of the book and links to the Table of Contents and sample pages. You can also purchase the book in print or electronic versions.
Book Reviews Published in
the IAPR Newsletter
by Polanski and Kimmel
Introduction to clustering large and high-dimensional data
The Text Mining Handbook
by Feldman and Sanger
Information Theory, Inference,
and Learning Algorithms
“Foundations and Trends in Computer Graphics and Vision”
Curless, Van Gool, and Szeliski., Editors
Applied Combinatorics on Words
by M. Lothaire
Human Identification Based on Gait
by Nixon, Tan and Chellappar
Mathematics of Digital Images
by Stuart Hogan
Advances in Image and Video Segmentation
Graph-Theoretic Techniques for Web Content Mining
by Schenker, Bunke, Last and Kandel
Handbook of Mathematical Models in Computer Vision
by Paragios, Chen, and Faugeras (Editors)
The Geometry of Information Retrieval
by van Rijsbergen
Biometric Inverse Problems
by Yanushkevich, Stoica, Shmerko and Popel
Correlation Pattern Recognition
by Kumar, Mahalanobis, and Juday
Pattern Recognition 3rd Edition
by Theodoridis and Koutroumbas
Dictionary of Computer Vision and
by R.B. Fisher, et. Al
Kernel Methods for Pattern Analysis
by Shawe-Taylor and Cristianini
Machine Vision Books
CVonline: an overview
The Guide to Biometrics by Bolle, et al
Pattern Recognition Books
Jul. ‘04 [pdf]
Dynamic Vision for Perception and Control of Motion by Professor Ernst D. Dickmanns is a long summary (474 pages) about the author and his colleagues’ experience (from 1985 until 2005) on autonomous road-following vehicles.
This book formulates a general approach to dynamic vision for researchers and also for newcomers interested in visual perception. Dynamic vision systems have a broad basis. It is hard for newcomers to handle all the ingredients necessary in this field. This book presents both the theoretical and practical ingredients required in a general approach.
Hybrid architectures, applied on mobile robots, combine low-level reactive behaviours with higher level deliberation and reasoning. This book defines a hybrid approach applied to autonomous road-following vehicles based on real time machine vision. Active subjects with capabilities for perception and control of behaviours are at the core of this approach. Hybrid architectures are usually modelled as having three layers; one deliberative, one reactive and one middle layer. This book is mainly focused on the reactive and middle layers.
The aim of this book is described by the following, as taken from the book:
The sense of vision for autonomous systems is considered an animation process driven by the analysis of image sequences. Starting from bottom-up feature extraction, tapping knowledge bases in which generic knowledge about ‘the world’ is available leads to the ‘mental’ construction of an internal spatiotemporal (4-D) representation of a framework that is intended to duplicate the essential aspects of the world sensed.
This internal (re-)construction is then projected into images with the parameters that the perception and hypothesis generation system have come up with. A model of perspective projection underlies this ‘imagination’ process. With the initial internal model of the world installed, a large part of future visual perception relies on feedback of prediction errors for adapting model parameters so that discrepancies between prediction and image analysis are reduced, at best to zero. Especially in this case, but also for small prediction-errors the process observed is supposed to be understood.
The knowledge elements contain the temporal aspects using differential equation constraints for temporal evolution. For example, manoeuvres are characterized by specific control time histories leading to finite state transitions. This manoeuvre knowledge allows decoupling behaviour decision from control implementation without losing the advantages at both ends. Minimal delay time and direct feedback control based on special sensor data are essential for good control actuation. On the other hand, knowledge about larger entities in space and time (like manoeuvres) are essential for good decision-making taking into account environmental conditions.
These vision and control topics, applied to autonomous road-following vehicles, are discussed in depth in this text, accompanied by mathematical equations and figures. The text is divided into 15 chapters. It starts with four chapters giving a general introduction to dynamic vision and providing the basic knowledge representation schemes underlying the 4-D approach developed. The following two chapters, chapters 5 and 6, cover procedural knowledge enabling real-time visual interpretation and scene understanding. Chapters 7 to 14 encompass system integration for recognition of roads, lanes and other vehicles. Chapter 15 gives some conclusions and an outlook on chances for future developments. And finally, three appendices provide more details on ‘Contribution to Ontology for Ground Vehicles’, ‘Lateral dynamics’ and ‘Recursive Least-squares Line fit’.