Background subtraction is a widely used concept for detection of moving objects in videos. In the last two decades there has been a lot of development in designing algorithms for background subtraction, as well as wide use of these algorithms in various important applications, such as visual surveillance, sports video analysis, motion capture, etc. Various statistical approaches have been proposed to model scene backgrounds. The concept of background subtraction also has been extended to detect objects from videos captured from moving cameras. This book reviews the concept and practice of background subtraction. We discuss several traditional statistical background subtraction models, including the widely used parametric Gaussian mixture models and non-parametric models. We also discuss the issue of shadow suppression, which is essential for human motion analysis applications. This book discusses approaches and tradeoffs for background maintenance. This book also reviews many of the recent developments in background subtraction paradigm. Recent advances in developing algorithms for background subtraction from moving cameras are described, including motion-compensation-based approaches and motion-segmentation-based approaches
1. Object detection and segmentation in videos -- 1.1 Characterization of video data -- 1.2 What is foreground and what is background? -- 1.3 The space of solutions -- 1.3.1 Foreground detection vs. background subtraction -- 1.3.2 Video segmentation and motion segmentation -- 1.4 Background subtraction concept --
2. Background subtraction from a stationary camera -- 2.1 Introduction -- 2.2 Challenges in scene modeling -- 2.3 Probabilistic background modeling -- 2.4 Parametric background models -- 2.4.1 A single Gaussian background modeL -- 2.4.2 A mixture Gaussian background model -- 2.5 Non-parametric background models -- 2.5.1 Kernel density estimation (KDE) -- 2.5.2 KDE background models -- 2.5.3 KDE-background practice and other non-parametric models -- 2.6 Other background models -- 2.6.1 Predictive-filtering background models -- 2.6.2 Hidden Markov model background subtraction -- 2.6.3 Subspace methods for background subtraction -- 2.6.4 Neural network models -- 2.7 Features for background modeling -- 2.8 Shadow suppression -- 2.8.1 Color spaces and achromatic shadows -- 2.8.2 Algorithmic approaches for shadow detection -- 2.9 Tradeoffs in background maintenance --
3. Background subtraction from a moving camera -- 3.1 Difficulties in the moving-camera case -- 3.2 Motion-compensation-based background-subtraction techniques -- 3.3 Motion segmentation -- 3.4 Layered-motion segmentation -- 3.5 Motion-segmentation-based background-subtraction approaches -- 3.5.1 Orthographic camera, factorization-based background models -- 3.5.2 Dense Bayesian appearance modeling -- 3.5.3 Moving away from the affine assumption, manifold-based background models --
Bibliography -- Author's biography
Background subtraction : theory and practice
2015
1 Online-Ressource (xvi, 67 Seiten)
Illustrationen
Campusweiter Zugriff (Universität Hannover) - Vervielfältigungen (z.B. Kopien, Downloads) sind nur von einzelnen Kapiteln oder Seiten und nur zum eigenen wissenschaftlichen Gebrauch erlaubt. Keine Weitergabe an Dritte. Kein systematisches Downloaden durch Robots.
Includes bibliographical references (pages 55-66)
Book
Electronic Resource
English
DDC: | 621.367 |
Fast Lighting Independent Background Subtraction
British Library Online Contents | 2000
|Background Subtraction Using Markov Thresholds
IEEE | 2005
|Comparative study of background subtraction algorithms
British Library Online Contents | 2010
|Statistical Background Subtraction for a Mobile Observer
British Library Conference Proceedings | 2003
|Statistical background subtraction for a mobile observer
IEEE | 2003
|