Maggio / Cavallaro Video Tracking

Theory and Practice
1. Auflage 2011
ISBN: 978-1-119-95686-0
Verlag: John Wiley & Sons
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 292 Seiten, E-Book

Video Tracking provides a comprehensive treatment of thefundamental aspects of algorithm and application development forthe task of estimating, over time, the position of objects ofinterest seen through cameras. Starting from the general problemdefinition and a review of existing and emerging video trackingapplications, the book discusses popular methods, such as thosebased on correlation and gradient-descent. Using practicalexamples, the reader is introduced to the advantages andlimitations of deterministic approaches, and is then guided towardmore advanced video tracking solutions, such as those based on theBayes' recursive framework and on Random Finite Sets.
Key features:
* Discusses the design choices and implementation issues requiredto turn the underlying mathematical models into a real-worldeffective tracking systems.
* Provides block diagrams and simil-code implementation of thealgorithms.
* Reviews methods to evaluate the performance of video trackers- this is identified as a major problem by end-users.
The book aims to help researchers and practitioners developtechniques and solutions based on the potential of video trackingapplications. The design methodologies discussed throughout thebook provide guidelines for developers in the industry working onvision-based applications. The book may also serve as a referencefor engineering and computer science graduate students involved invision, robotics, human-computer interaction, smart environmentsand virtual reality programmes

Autoren/Hrsg.

Maggio, Emilio

Cavallaro, Andrea

Inhaltsverzeichnis

Foreword.
About the authors.
Preface.
Acknowledgments.
Notations.
Acronyms.
1 What is video tracking?
1.1 Introduction.
1.2 The design of a video tracker.
1.3 Problem formulation.
1.4 Interactive versus automated tracking.
1.5 Summary.
2 Applications.
2.1 Introduction.
2.2 Media production and augmented reality.
2.3 Medical applications and biological research.
2.4 Surveillance and business intelligence.
2.5 Robotics and unmanned vehicles.
2.6 Tele-collaboration and interactive gaming.
2.7 Art installations and performances.
2.8 Summary.
References.
3 Feature extraction.
3.1 Introduction.
3.2 From light to useful information.
3.3 Low-level features.
3.4 Mid-level features.
3.5 High-level features.
3.6 Summary.
References.
4 Target representation.
4.1 Introduction.
4.2 Shape representation.
4.3 Appearance representation.
4.4 Summary.
References
5 Localisation.
5.1 Introduction.
5.2 Single-hypothesis methods.
5.3 Multi-hypothesis methods.
5.4 Summary.
References.
6 Fusion.
6.1 Introduction.
6.2 Fusion strategies.
6.3 Feature fusion in a Particle Filter.
6.4 Summary.
References.
7 Multi-target management.
7.1 Introduction.
7.2 Measurement validation.
7.3 Data association.
7.4 Random Finite Sets for tracking.
7.5 Probabilistic Hypothesis Density filter.
7.6 The Particle PHD filter.
7.7 Summary.
References.
8 Context modeling.
8.1 Introduction.
8.2 Tracking with context modelling.
8.3 Birth and clutter intensity estimation.
8.4 Summary.
References.
9 Performance evaluation.
9.1 Introduction.
9.2 Analytical vs. empirical methods.
9.3 Ground truth.
9.4 Evaluation scores.
9.5 Comparing trackers.
9.6 Evaluation protocols.
9.7 Datasets.
9.8 Summary.
References.
Epilogue.
Further reading.
Appendix A: Comparative results.
A.1 Single versus structural histogram.
A.1.1 Experimental setup.
A.1.2 Discussion.
A.2 Localisation algorithms.
A.2.1 Experimental setup.
A.2.2 Discussion.
A.3 Multi-feature fusion.
A.3.1 Experimental setup.
A.3.2 Reliability scores.
A.3.3 Adaptive versus non-adaptive tracker.
A.3.4 Computational complexity.
A.4 PHD filter.
A.4.1 Experimental setup.
A.4.2 Discussion.
A.4.3 Failure modalities.
A.4.4 Computational cost.
A.5 Context modelling.
A.5.1 Experimental setup.
A.5.2 Discussion.
References.
Index.

Über Autor(innen)

Dr Emilio Maggio, Vicon, UK
Dr Maggio is Computer Vision Scientist at Vicon, the motioncapture worldwide market leader. From 2004 - 2008 he was aPh.D. student at the Department of Electronic Engineering, QueenMary, University of London. In 2005 and again in 2007 he wasawarded the best student paper prize at ICASSP. Dr Maggio has actedas a reviewer for the IEEE Transactions on Circuits and Systems forVideo Technology, the International Journal of Image andGraphics and ACM Multimedia.
Dr Andrea Cavallaro, School of Electronic Engineering andComputer Science, Queen Mary, University of London, UK
Dr Cavallaro is Reader in Multimedia Signal Processing at QueenMary, University of London. He is the author of more than 70papers, including 5 book chapters. He is an elected member of theIEEE Signal Processing Society, Multimedia Signal ProcessingCommittee. He has been a member of the organizing/ technicalcommittee for several international conferences such as TechnicalChair of EUSIPCO 08 and General Chair of the IEEE InternationalConference on Advanced Video and Signal based Surveillance (AVSS2007), with General Chair positions being held for forthcoming 2009conferences such as BMVC 09. He has been guest editor of severalspecial issues, including 'Multi-sensor object detection andtracking', Signal, Image and Video Processing (Springer). DrCavallaro was awarded the Royal Academy of Engineering teachingprize in 2007.