Custom cover image
Computer Analysis of Human Behavior / edited by Albert Ali Salah, Theo Gevers
Contributor(s): Resource type: Ressourcentyp: Buch (Online)Book (Online)Language: English Series: SpringerLink BücherPublisher: London : Springer-Verlag London Limited, 2011Description: Online-Ressource (XV, 409p. 117 illus., 86 illus. in color, digital)ISBN:- 9780857299949
- 005.437
- 4.019
- 006.4 23
- QA76.9.U83 QA76.9.H85
- QA76.9.H85
- QA76.9.U83
Contents:
Summary: This book provides a broad survey of advanced pattern recognition techniques for human behavior analysis. Clearly structured, the book begins with concise coverage of the major concepts, before introducing the most frequently used techniques and algorithms in detail, and then discussing examples of real applications. Features: contains contributions from an international selection of experts in the field; presents a thorough introduction to the fundamental topics of human behavior analysis; investigates methods for activity recognition, including gait and posture analysis, hand gesture analysis, and semantics of human behavior in image sequences; provides an accessible psychological treatise on social signals for the analysis of social behaviors; discusses voice and speech analysis, combined audiovisual cues, and social interactions and group dynamics; examines applications in different research fields; each chapter concludes with review questions, a summary of the topics covered, and a glossary.PPN: PPN: 1651053596Package identifier: Produktsigel: ZDB-2-SCS
Computer Analysis of Human Behavior; Preface; Overview and Goals; Target Audience; Organization of the Book; Contents; Contributors; Acronyms; Part I: Tools of the Trade; Chapter 1: Bayesian Methods for the Analysis of Human Behaviour; 1.1 Bayesian Methods; 1.2 A Note on Bayesian Networks; 1.3 Approximating the Marginal Distribution; 1.3.1 Sampling; 1.3.2 Variational Approximations; 1.4 Non-parametric Methods; 1.4.1 The Dirichlet Process; 1.4.2 The Gaussian Process
1.4.2.1 Gaussian Process as Bayesian Linear Regression; 1.4.2.2 Kernel Functions; 1.4.2.3 Classifcation; 1.5 Human Behaviour Modelling; 1.6 Summary; 1.7 Questions; 1.8 Glossary; References; Chapter 2: Introduction to Sequence Analysis for Human Behavior Understanding; 2.1 Introduction; 2.2 Graphical Models; 2.2.1 Graph Theory; 2.2.2 Conditional Independence; 2.3 Bayesian Networks; 2.3.1 Factorization; 2.3.2 The d-Separation Criterion; 2.3.3 Hidden Markov Models; 2.4 Conditional Random Fields
2.4.1 Factorization and Conditional Independence; 2.4.2 Linear Chain Conditional Random Fields; 2.5 Training and Inference; 2.5.1 Message Passing; 2.5.1.1 Inference; 2.5.1.2 Training; 2.6 Summary; 2.7 Questions; 2.8 Glossary; References; Chapter 3: Detecting and Tracking Action Content; 3.1 Introduction; 3.2 Representations; 3.2.1 Spatial Representations; 3.2.2 Spatio-Temporal Representations; 3.3 Descriptors; 3.3.1 Non-appearance Based Descriptors; 3.3.2 Appearance Based Descriptors; 3.4 Finding Action Content
3.4.1 Point Detection; 3.4.2 Body Parts Detection; 3.4.3 Detection of Silhouette; 3.5 Tracking; 3.5.1 Tracking by Association; 3.5.2 Flow Estimation; 3.5.3 Kernel Tracking; 3.6 Summary; 3.7 Questions; 3.8 Glossary; References; Chapter 4: Computational Visual Attention; 4.1 What Is Attention? And Do We Need Attentive Machines?; 4.2 Human Visual Attention; 4.2.1 The Human Visual System; 4.2.1.1 Eye, Retina, and Ganglion Cells; 4.2.1.2 From the Optic Chiasm to V1
4.2.1.3 Beyond V1: the Extrastriate Cortex and the Visual Pathways; 4.2.1.4 Neurobiological Correlates of Visual Attention; 4.2.2 Psychological Concepts of Attention; 4.2.3 Important Psychological Attention Models; 4.3 Computational Attention Systems; 4.3.1 General Structure; 4.3.2 Bottom-up Saliency; 4.3.2.1 Intensity Channel; 4.3.2.2 Color Channel; 4.3.2.3 Orientation Channel; 4.3.2.4 Motion Channel; 4.3.2.5 The Uniqueness Weight; 4.3.2.6 Normalization; 4.3.2.7 The Conspicuity Maps; 4.3.2.8 The Saliency Map and Focus Selection
4.3.3 Visual Search with Top-down Cues
No physical items for this record