Image analysis and processing ICIAP 2022 Workshops, ICIAP International Workshops, Lecce, Italy, May 23-27, 2022, Revised selected papers . Part II / / Pier Luigi Mazzeo [and three others] editors

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (572 pages)
• Disciplina: 621.367
• Soggetto topico: Image analysis
• Persona (resp. second.): MazzeoPier Luigi
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Human Behaviour Analysis for Smart City Environment Safety - HBAxSCES -- A Framework for Forming Middle Distance Routes Based on Spatial Guidelines, Perceived Accessibility and Visual Cues in Smart City -- 1 Introduction -- 2 Orientation and Perception Along the Route When Using the Navigation Interface -- 2.1 Mental Maps and Traveler Environment in Route Network Sustainability -- 2.2 Aggregation of Information for Navigation Tasks -- 2.3 Planning, Detailing, and Optimizing a Middle-Distance Route -- 2.4 Smart Routes Application Interface -- 3 GIS Applications in the Study of Navigation Behavior -- 3.1 Materials and Methods -- 3.2 Results -- 4 Conclusion -- References -- A Survey on Few-Shot Techniques in the Context of Computer Vision Applications Based on Deep Learning -- 1 Introduction -- 2 Description of Few-Shot Learning -- 2.1 Applications of FSL -- 2.2 FSL Techniques -- 2.3 FSL Benchmarks for Computer Vision -- 3 FSL for Human Behaviour Analysis Applications -- 4 Few-Shot for Smart City Environment Safety Applications -- 5 Conclusion -- References -- Decision-Support System for Safety and Security Assessment and Management in Smart Cities -- 1 Introduction -- 2 Material and Method -- 2.1 Conceptual Model -- 2.2 System Architecture -- 3 Case Study -- 4 Conclusions and Discussion -- References -- Embedded Intelligence for Safety and Security Machine Vision Applications -- 1 Introduction -- 2 Edge Computing Machine Vision Systems in S4AllCities Project -- 3 Integration with the Distributed Edge Computing Platform (DECIoT) -- 4 Hardware Platform for Machine Vision Based on the I.MX8M PLUS -- 5 VAEC System -- 6 Conclusions -- References -- Supporting Energy Digital Twins with Cloud Data Spaces: An Architectural Proposal -- 1 Introduction. ; 2 Background and State of Art -- 2.1 Energy of Things -- 2.2 Open Initiatives in Energy Computing Field -- 3 Design of the Italian Energy Data Space -- 3.1 Logical Architecture -- 3.2 The Proposed Development Process -- 4 Conclusion -- References -- High-Level Feature Extraction for Crowd Behaviour Analysis: A Computer Vision Approach -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Pre-processing -- 3.2 Supervised Deep Learning Module -- 3.3 Unsupervised Learning for Trajectory Clustering -- 4 Experimental Results -- 5 Conclusions -- References -- Binary is the New Black (and White): Recent Advances on Binary Image Processing -- A Simple yet Effective Image Repairing Algorithm -- 1 Introduction -- 2 Background Notions -- 3 Related Work -- 4 Our Approach to Image Repairing -- 4.1 Algorithm A -- 4.2 Algorithm B -- 5 Proof of Correctness -- 5.1 Well-Composedness -- 5.2 Homotopy Equivalence -- 6 Experimental Results and Discussion -- 6.1 Results of Algorithms A and B -- 6.2 Processing The Repaired Images -- 7 Conclusion -- References -- A Novel Method for Improving the Voxel-Pattern-Based Euler Number Computing Algorithm of 3D Binary Images -- 1 Introduction -- 2 Review of Conventional Voxel-Pattern-Based Euler Number Computing Algorithm of a 3D Image -- 3 Our Proposed Method -- 4 Experimental Results -- 4.1 Execution Time Versus Image Sizes -- 4.2 Execution Time Versus Image Densities -- 5 Conclusion -- References -- Event-Based Object Detection and Tracking - A Traffic Monitoring Use Case - -- 1 Introduction -- 2 State of the Art -- 3 Object Detection and Tracking from Event Data -- 3.1 Preprocessing -- 3.2 Model-Free Detection -- 3.3 YOLO-Based Detector -- 3.4 Object Tracking -- 4 Experimental Results -- 5 Conclusions -- References -- Quest for Speed: The Epic Saga of Record-Breaking on OpenCV Connected Components Extraction. ; 1 Introduction -- 2 The First Approach -- 3 A Novel Interface -- 4 Going Faster with Blocks -- 5 Spaghetti for All -- 6 GPU Implementation -- 7 Discussion -- 8 Conclusion -- References -- An Efficient Run-Based Connected Component Labeling Algorithm for Processing Holes -- 1 Introduction and State-of-the-Art -- 2 General Overview of Our New Algorithm -- 3 Specificities of Black and White Labeling and Hole Processing -- 3.1 Black and White Labeling -- 3.2 Holes and Adjacency Tree Computation -- 3.3 Example -- 4 Benchmark and Performance Analysis -- 5 Conclusion -- References -- LSL3D: A Run-Based Connected Component Labeling Algorithm for 3D Volumes -- 1 Introduction -- 2 Classical Approaches to Connected Components Labeling and Their Evaluation -- 2.1 Main Principles of Modern CCL Algorithms -- 2.2 Benchmarking Procedure and Datasets -- 3 State-of-the-Art of 3D Algorithms -- 3.1 Pixel-Based Algorithms -- 3.2 Block-Based Algorithms -- 3.3 Segment-Based Algorithms -- 4 LSL3D and Efficient Unification Strategies for 3D Volumes -- 4.1 Extension of the Segment-Based Unification for 3D Volumes -- 4.2 A Finite-State Machine-Based Unification -- 4.3 Computational Reuse of Merged Lines -- 5 Architecture-Specific Optimizations of Run-Length Encoding on 3D Images -- 6 Conclusion and Future Work -- References -- Artificial Intelligence for Preterm Infants' HealthCare - AI-Care -- Deep-Learning Architectures for Placenta Vessel Segmentation in TTTS Fetoscopic Images -- 1 Introduction -- 2 Materials and Methods -- 2.1 Backbones -- 2.2 Decoder Architectures -- 3 Experimental Protocol -- 4 Results -- 5 Discussion and Conclusions -- References -- An Advanced Tool for Semi-automatic Annotation for Early Screening of Neurodevelopmental Disorders -- 1 Introduction -- 2 Related Work -- 2.1 Marker-Less AI Tools for Children's Motion Analysis. ; 2.2 Existing Tools for Face Childrens' Analysis -- 3 The Proposed Annotation Tool -- 3.1 The Graphical User Interface -- 3.2 Deep Learning Components -- 4 The Dataset -- 5 Experimental Results -- 6 Conclusions -- References -- Some Ethical Remarks on Deep Learning-Based Movements Monitoring for Preterm Infants: Green AI or Red AI? -- 1 Introduction -- 2 State of the Art: Green AI and Red AI -- 3 Methods -- 3.1 Considered Deep Learning Architectures -- 3.2 The BabyPose Dataset -- 3.3 Evaluation Metrics -- 4 Results and Discussion -- 5 Conclusion -- References -- Towards a Complete Analysis of People: From Face and Body to Clothes - T-CAP -- Effect of Gender, Pose and Camera Distance on Human Body Dimensions Estimation -- 1 Introduction -- 2 The Problem of Human Body Dimensions Estimation -- 3 Related Work -- 4 Material and Methods -- 4.1 Dataset -- 4.2 Neural Anthropometer -- 5 Results and Discussion -- 5.1 Effect of Gender -- 5.2 Effect of Pose -- 5.3 Effect of Camera Distance -- 5.4 Quantitative Comparison to Related Work -- 6 Conclusions and Future Work -- 6.1 Future Work -- References -- StyleTrendGAN: A Deep Learning Generative Framework for Fashion Bag Generation -- 1 Introduction -- 2 State-of-the-Art -- 3 Materials and Methods -- 3.1 Deep Generative Models -- 3.2 MADAME Dataset -- 3.3 Performance Metrics -- 4 Results and Discussion -- 5 Conclusions and Future Works -- References -- Gender Recognition from 3D Shape Parameters -- 1 Introduction -- 2 Related Work -- 3 Datasets -- 4 Approach -- 4.1 Model Selection -- 5 Results -- 5.1 Comparison with Previous Body Shape-Based Methods -- 5.2 Comparison with Image-Based Methods -- 6 Conclusions -- References -- Recognition of Complex Gestures for Real-Time Emoji Assignment -- 1 Introduction and Motivations -- 2 Proposed Method -- 2.1 Methods for Recognizing Facial Expressions. ; 2.2 Methods for Recognizing Hand Gestures -- 3 Real-Time Emoji Assignment -- 4 Experimental Results -- 5 Conclusion -- References -- Generating High-Resolution 3D Faces Using VQ-VAE-2 with PixelSNAIL Networks -- 1 Introduction -- 2 Related Works -- 2.1 3D to 2D Representations -- 2.2 3D Face Generation with GANs -- 2.3 3D Face Generation with Autoencoders -- 3 Method -- 3.1 VQ-VAE-2 with PixelSNAIL -- 3.2 Metrics for Quantitative Evaluation -- 4 Experiments -- 4.1 Quantitative Evaluation -- 5 Discussion and Conclusion -- References -- Artificial Intelligence for Digital Humanities - AI4DH -- The Morra Game: Developing an Automatic Gesture Recognition System to Interface Human and Artificial Players -- 1 Introduction -- 2 Methods -- 2.1 Apparatus -- 2.2 Procedure -- 3 Results -- 4 Discussion -- References -- Integration of Point Clouds from 360° Videos and Deep Learning Techniques for Rapid Documentation and Classification in Historical City Centers -- 1 Introduction -- 2 Background -- 3 Method -- 3.1 Generation of Point Clouds from 360° Videos -- 3.2 Deep Learning-Based Point Cloud Classification -- 4 Case Study -- 4.1 Dataset - Bassano Dataset -- 4.2 Acquisition and Post-processing -- 4.3 Classification -- 5 Conclusion -- References -- Towards the Creation of AI-powered Queries Using Transfer Learning on NLP Model - The THESPIAN-NER Experience -- 1 Introduction -- 1.1 The Digital Infrastructure of INFN-CHNet -- 2 The NER Model -- 2.1 The Training Dataset: Archaeological Documents and Scientific Reports Annotated with INCEpTION -- 2.2 Training and Evaluation of the Model -- 3 The Web Service: AI-powered Queries -- 4 Conclusions and Outlook -- References -- Detecting Fake News in MANET Messaging Using an Ensemble Based Computational Social System -- 1 Introduction -- 2 Literature Review -- 2.1 Vehicular Ad Hoc Networks. ; 2.2 Computational Social Systems.
• Titolo autorizzato: Image Analysis and Processing
• ISBN: 3-031-13324-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910586584103321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture notes in computer science ; ; 13374.