Visual Analysis of Behaviour (eBook)

From Pixels to Semantics

Shaogang Gong, Tao Xiang (Autoren)

eBook Download: PDF

2011
XIX, 356 Seiten
Springer London (Verlag)
978-0-85729-670-2 (ISBN)

Infos

This book presents a comprehensive treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. Topics: covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and 'man-in-the-loop' active learning; examines multi-camera behaviour correlation, person re-identification, and 'connecting-the-dots' for abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, 'bag-of-words' representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines.

---

This book presents a comprehensive treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. Topics: covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and "e;man-in-the-loop"e; active learning; examines multi-camera behaviour correlation, person re-identification, and "e;connecting-the-dots"e; for abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, "e;bag-of-words"e; representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines.

Inhalt

Part I: IntroductionAbout BehaviourBehaviour in ContextTowards Modelling BehaviourPart II: Single-Object BehaviourUnderstanding Facial ExpressionModelling GestureAction RecognitionPart III: Group BehaviourSupervised Learning of Group ActivityUnsupervised Behaviour ProfilingHierarchical Behaviour DiscoveryLearning Behavioural ContextModelling Rare and Subtle BehavioursMan in the LoopPart IV: Distributed BehaviourMulti-Camera Behaviour CorrelationPerson Re-IdentificationConnecting the DotsEpilogue

Produkt-Details

• Erscheint lt. Verlag: 26.5.2011
• Zusatzinfo: XIX, 356 p.
• Verlagsort: London
• Sprache: englisch
• Themenwelt: Informatik ► Grafik / Design ► Digitale Bildverarbeitung
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Sozialwissenschaften ► Politik / Verwaltung
• Schlagworte: activity recognition • Bayesian networks • biometrics • Facial Expression Modelling • Gait Recognition • Multimodal data fusion • Statistical Learning • Visual Behaviour Modelling • Visual Behaviour Representation • Visual Surveillance
• ISBN-10: 0-85729-670-1 / 0857296701
• ISBN-13: 978-0-85729-670-2 / 9780857296702