Linked e-resources
Details
Table of Contents
Intro; Preface; Contents; 1 Semantic Gap in Image and Video Analysis: An Introduction; 1.1 Introduction; 1.2 Chapters Included in the Book; 1.3 Conclusion; References; 2 Low-Level Feature Detectors and Descriptors for Smart Image and Video Analysis: A Comparative Study; 2.1 Introduction; 2.2 Low-Level Feature Detectors and Descriptors; 2.2.1 SIFT, SURF, ORB, and A-KAZE Extractors; 2.2.2 PHOG, WGCH, and Haralick Extractors; 2.3 Low-Level Feature Comparison and Discussion; 2.3.1 Behavior and Robustness; 2.3.2 Matching Process; 2.4 Conclusions; References
3 Scale-Insensitive MSER Features: A Promising Tool for Meaningful Segmentation of Images3.1 Introduction; 3.2 Summary of MSER and SIMSER Features; 3.2.1 MSER Features; 3.2.2 SIMSER Features; 3.2.3 Segmentation Using MSER Blobs; 3.3 SIMSER-Based Image Segmentation; 3.3.1 Image Smoothing in SIMSER Detection; 3.3.2 SIMSER Detection in Color Images; 3.4 Concluding Remarks; References; 4 Active Partitions in Localization of Semantically Important Image Structures; 4.1 Introduction; 4.2 Background; 4.2.1 Active Contours; 4.2.2 Knowledge; 4.3 Active Partitions; 4.3.1 Representation
4.3.2 Partition4.3.3 Evolution; 4.4 Example; 4.4.1 Global Analysis; 4.4.2 Local Analysis; 4.5 Summary; References; 5 Model-Based 3D Object Recognition in RGB-D Images; 5.1 Introduction; 5.2 Knowledge Representation Hierarchy; 5.2.1 Related Work; 5.2.2 Proposed RGB-D Data Hierarchy; 5.3 3D Object Modelling; 5.3.1 Geometric Primitives; 5.3.2 Complex Objects; 5.4 System Framework; 5.4.1 Solution Principles; 5.4.2 Knowledge-Based Framework; 5.4.3 Semantic Net; 5.4.4 Bayesian Net; 5.4.5 The Basic Control; 5.5 System Implementation; 5.5.1 Model Structure; 5.5.2 Object Instances
5.6 Testing Scenarios5.6.1 Data Acquisition; 5.6.2 Data Preprocessing and Extension; 5.6.3 Segmentation; 5.6.4 Hypothesis Generation; 5.6.5 Hypothesis Update and Verification; 5.6.6 Method Vulnerabilities; 5.7 Conclusions; References; 6 Ontology-Based Structured Video Annotation for Content-Based Video Retrieval via Spatiotemporal Reasoning; 6.1 The Limitations of Video Metadata and Feature Descriptors; 6.1.1 Core Video Metadata Standards; 6.1.2 Feature Extraction for Concept Mapping; 6.1.3 Machine Learning in Video Content Analysis; 6.1.4 The Semantic Gap
6.2 Semantic Enrichment of Audiovisual Contents6.2.1 Video Semantics; 6.2.2 Spatiotemporal Video Annotation Using Formal Knowledge Representation; 6.2.3 Vocabularies and Ontologies; 6.2.4 Semantic Enrichment of Videos with Linked Data; 6.2.5 Spatiotemporal Annotation in Action; 6.3 Ontology-Based Video Scene Interpretation; 6.3.1 Video Event Recognition via Reasoning Over Temporal DL Axioms; 6.3.2 Video Event Recognition Using SWRL Rules; 6.3.3 Handling the Uncertainty of Concept Depiction with Fuzzy Axioms
3 Scale-Insensitive MSER Features: A Promising Tool for Meaningful Segmentation of Images3.1 Introduction; 3.2 Summary of MSER and SIMSER Features; 3.2.1 MSER Features; 3.2.2 SIMSER Features; 3.2.3 Segmentation Using MSER Blobs; 3.3 SIMSER-Based Image Segmentation; 3.3.1 Image Smoothing in SIMSER Detection; 3.3.2 SIMSER Detection in Color Images; 3.4 Concluding Remarks; References; 4 Active Partitions in Localization of Semantically Important Image Structures; 4.1 Introduction; 4.2 Background; 4.2.1 Active Contours; 4.2.2 Knowledge; 4.3 Active Partitions; 4.3.1 Representation
4.3.2 Partition4.3.3 Evolution; 4.4 Example; 4.4.1 Global Analysis; 4.4.2 Local Analysis; 4.5 Summary; References; 5 Model-Based 3D Object Recognition in RGB-D Images; 5.1 Introduction; 5.2 Knowledge Representation Hierarchy; 5.2.1 Related Work; 5.2.2 Proposed RGB-D Data Hierarchy; 5.3 3D Object Modelling; 5.3.1 Geometric Primitives; 5.3.2 Complex Objects; 5.4 System Framework; 5.4.1 Solution Principles; 5.4.2 Knowledge-Based Framework; 5.4.3 Semantic Net; 5.4.4 Bayesian Net; 5.4.5 The Basic Control; 5.5 System Implementation; 5.5.1 Model Structure; 5.5.2 Object Instances
5.6 Testing Scenarios5.6.1 Data Acquisition; 5.6.2 Data Preprocessing and Extension; 5.6.3 Segmentation; 5.6.4 Hypothesis Generation; 5.6.5 Hypothesis Update and Verification; 5.6.6 Method Vulnerabilities; 5.7 Conclusions; References; 6 Ontology-Based Structured Video Annotation for Content-Based Video Retrieval via Spatiotemporal Reasoning; 6.1 The Limitations of Video Metadata and Feature Descriptors; 6.1.1 Core Video Metadata Standards; 6.1.2 Feature Extraction for Concept Mapping; 6.1.3 Machine Learning in Video Content Analysis; 6.1.4 The Semantic Gap
6.2 Semantic Enrichment of Audiovisual Contents6.2.1 Video Semantics; 6.2.2 Spatiotemporal Video Annotation Using Formal Knowledge Representation; 6.2.3 Vocabularies and Ontologies; 6.2.4 Semantic Enrichment of Videos with Linked Data; 6.2.5 Spatiotemporal Annotation in Action; 6.3 Ontology-Based Video Scene Interpretation; 6.3.1 Video Event Recognition via Reasoning Over Temporal DL Axioms; 6.3.2 Video Event Recognition Using SWRL Rules; 6.3.3 Handling the Uncertainty of Concept Depiction with Fuzzy Axioms