Multimedia sensor networks / / Huadong Ma, Liang Liu, Hong Luo

• Record Nr.: UNISA996464502303316
• Autore: Ma Huadong
• Pubbl/distr/stampa: Singapore : , : Springer, , [2021]; ©2021
• ISBN: 981-16-0107-0
• Descrizione fisica: 1 online resource (xii, 249 pages) : illustrations
• Collana: Advances in Computer Science and Technology
• Disciplina: 681.2
• Soggetti: Sensor networks; Multisensor data fusion
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references.
• Nota di contenuto: Intro -- Preface -- Contents -- 1 Introduction to Multimedia Sensor Networks -- 1.1 Basic Concepts -- 1.2 Conceptual Architecture -- 1.2.1 Sensing Layer -- 1.2.2 Transmission Layer -- 1.2.3 Processing Layer -- 1.3 Main Research Topics of Multimedia Sensor Networks -- 2 Directional Sensing Models and Coverage Control -- 2.1 Introduction -- 2.2 Directional Sensor Networks -- 2.2.1 Motivation -- 2.2.2 Coverage Problem with Directional Sensing -- 2.2.2.1 Directional Sensing Model -- 2.2.2.2 Coverage Probability with Directional Sensing Model -- 2.2.3 Coverage Enhancing with Rotatable Directional Sensing Model -- 2.2.3.1 Rotatable Directional Sensing Model -- 2.2.3.2 The Problem of Area Coverage Enhancing -- 2.2.4 Potential Field Based Coverage-Enhancing Method -- 2.2.4.1 Sensing Centroid -- 2.2.4.2 Potential Field Force -- 2.2.4.3 Control Laws -- 2.2.5 Simulation Results -- 2.2.5.1 Case Study -- 2.2.5.2 Performance Evaluation -- 2.3 Three Dimensional Directional Sensor Networks -- 2.3.1 Motivation -- 2.3.2 The 3D Directional Sensing Model -- 2.3.3 Area Coverage-Enhancing Method -- 2.3.3.1 Problem Formulation -- 2.3.3.2 Virtual Force Analysis Based Coverage-Enhancing -- 2.3.3.3 Coverage Optimization Approach -- 2.3.4 Case Study and Performance Evaluations -- 2.4 Directional K-Coverage for Target Recognition -- 2.4.1 Motivation -- 2.4.2 Collaborative Face Orientation Detection -- 2.4.3 Problem Description -- 2.4.3.1 Effective Sensing in Video ; Surveillance -- 2.4.3.2 Directional K-Coverage (DKC) Problem -- 2.4.4 Analysis of Directional K-Coverage -- 2.4.5 Experimental Results -- 2.5 L-Coverage for Target Localization -- 2.5.1 Motivation -- 2.5.2 Localization-Oriented Sensing Model -- 2.5.3 Bayesian Estimation Based L-Coverage -- 2.5.3.1 L-Coverage Concept -- 2.5.3.2 L-Coverage Illustrations.; 2.5.4 L-Coverage Probability in Randomly Deployed Camera Sensor Networks -- 2.5.5 Simulation Experiments -- 2.6 Exposure-Path Prevention for Intrusion Detection in Multimedia Sensor Networks -- 2.6.1 Motivation -- 2.6.2 System Models and Problem Formulation -- 2.6.2.1 Sensors Deploying Model -- 2.6.2.2 Continuum Percolation Model-Based Problem Formulation -- 2.6.3 Bond Percolation Model for Coverage -- 2.6.4 Critical Density for Exposure Path -- 2.6.4.1 Critical Density of Omnidirectional Sensors -- 2.6.4.2 Critical Density of Directional Sensors -- 2.6.5 Dependence Among Neighboring Edges -- 2.6.6 Simulation Evaluations -- 2.6.6.1 Omnidirectional Sensor Networks -- 2.6.6.2 Directional Sensor Networks -- References -- 3 Data Fusion Based Transmission in Multimedia Sensor Networks -- 3.1 Introduction -- 3.2 Adaptive Data Fusion for Energy Efficient Routing in Multimedia Sensor Networks -- 3.2.1 Motivation -- 3.2.2 Measurement of Image Fusion Cost -- 3.2.2.1 Measurement Model for Data Aggregation -- 3.2.2.2 Image Fusion -- 3.2.3 System Model and Problem Formulation -- 3.2.3.1 Network Model -- 3.2.3.2 Problem Formulation -- 3.2.4 Minimum Fusion Steiner Tree -- 3.2.4.1 MFST Algorithm -- 3.2.4.2 3-D Binary Tree Structure -- 3.2.5 Design and Analysis of AFST -- 3.2.5.1 Binary Fusion Steiner Tree (BFST) -- 3.2.5.2 Adaptive Fusion Steiner Tree (AFST) -- 3.2.6 Experimental Study -- 3.2.6.1 Simulation Environment -- 3.2.6.2 Impact of Correlation Coefficient -- 3.2.6.3 Impact of Unit Fusion Cost -- 3.3 Physarum Optimization: A Biology-Inspired Algorithm for the Steiner Tree Problem in Networks -- 3.3.1 Motivation -- 3.3.2 Biology-Inspired Optimization and Physarum Computing -- 3.3.3 Problem Formulation and Physarum Model -- 3.3.3.1 Steiner Tree Problem -- 3.3.3.2 Mathematical Model for Physarum -- 3.3.4 Physarum Optimization for Steiner Tree Problem.; 3.3.4.1 Initial Pressures of Vertices -- 3.3.4.2 Main Process of Physarum Optimization -- 3.3.4.3 Convergence of Physarum Optimization -- 3.3.4.4 Algorithms of Physarum Optimization -- 3.4 A Trust-Based Framework for Fault-Tolerant Data Aggregation in Multimedia Sensor Networks -- 3.4.1 Motivation -- 3.4.2 System Model -- 3.4.2.1 Multi-Layer Trustworthy Aggregation Architecture -- 3.4.2.2 Source Model -- 3.4.2.3 Trust Model -- 3.4.3 Trust-Based Framework for Fault-Tolerant Data Aggregation -- 3.4.3.1 Self Data Trust Opinion of Sensor Node -- 3.4.3.2 Peer Node Trust Opinion -- 3.4.3.3 Trust Transfer and Peer Data Trust Opinion -- 3.4.3.4 Trust Combination and Self Data Trust Opinion of Aggregator -- 3.4.3.5 Trust-Based and Fault-Tolerant Data Aggregation Algorithm -- 3.4.4 Experimental and Simulation Studies -- 3.4.4.1 Continuous Audio Stream -- 3.4.4.2 Discrete Data -- References -- 4 In-Network Processing for Multimedia Sensor Networks -- 4.1 Introduction -- 4.2 Correlation Based Image Processing in Multimedia Sensor Networks -- 4.2.1 Motivation -- 4.2.2 Sensing Correlation -- 4.2.3 Image Processing Based on Correlation -- 4.2.3.1 Allocating the Sensing Task -- 4.2.3.2 Image Capturing -- 4.2.3.3 Image Delivering -- 4.2.3.4 Image Fusion -- 4.2.4 Experimetal Results -- 4.3 Dynamic Node Collaboration for Mobile Target Tracking in Multimedia Sensor Networks -- 4.3.1 Motivation -- 4.3.2 Related Works -- 4.3.3 System Models and Description -- 4.3.3.1 Motion Model of the Target -- 4.3.3.2 Sensing Model of Camera Sensors -- ; 4.3.3.3 Target Tracking by Sequential Monte Carlo Method -- 4.3.3.4 The Dynamic Node Collaboration Scheme -- 4.3.4 Election of the Cluster Heads -- 4.3.5 Selection of the Cluster Members -- 4.3.5.1 Utility Function -- 4.3.5.2 Cost Function -- 4.3.5.3 The Cluster Members Selection Algorithm -- 4.3.6 Simulation Results.; 4.4 Distributed Target Classification in Multimedia Sensor Networks -- 4.4.1 Motivation -- 4.4.2 Related Works -- 4.4.3 Procedure of Target Classification in Multimedia Sensor Networks -- 4.4.3.1 Target Detection -- 4.4.3.2 Feature Extraction -- 4.4.3.3 Classification -- 4.4.4 Binary Classification Tree Based Framework -- 4.4.4.1 Generation of the Binary Classification Tree -- 4.4.4.2 Division of the Binary Classification Tree -- 4.4.4.3 Selection of Multimedia Sensor Nodes -- 4.4.5 Case Study and Simulations -- 4.5 Decomposition-Fusion: A Cooperative Computing Mode for Multimedia Sensor Networks -- 4.5.1 Motivation -- 4.5.2 Typical Paradigms of Transmission-Processing for MSNs -- 4.5.3 Decomposition-Fusion Cooperative Computing Framework -- 4.5.3.1 Task Decomposition -- 4.5.3.2 Target Detection -- 4.5.3.3 Selection of Candidates -- 4.5.3.4 Selection of Cooperators -- 4.5.3.5 Interim Results Fusion -- References -- 5 Multimedia Sensor Network Supported IoT Service -- 5.1 Introduction -- 5.2 Searching in IoT -- 5.2.1 Motivation -- 5.2.2 Concept of IoT Search -- 5.2.3 Characters of Searching in IoT -- 5.2.4 Challenges of Searching in IoT -- 5.2.5 The Progressive Search Paradigm -- 5.2.5.1 Coarse-to-Fine Search Strategy -- 5.2.5.2 Near-to-Distant Search Strategy -- 5.2.5.3 Low-to-High Permission Search Strategy -- 5.2.6 Progressive IoT Search in the Multimedia Sensors Based Urban Sensing Network -- 5.3 PROVID: Progressive and Multi-modal Vehicle Re-identification for Large-Scale Urban Surveillance -- 5.3.1 Motivation -- 5.3.2 Related Work -- 5.3.3 Overview of the PROVID Framework -- 5.3.4 Vehicle Filtering by Appearance -- 5.3.4.1 Multi-level Vehicle Representation -- 5.3.4.2 The Null-Space-Based FACT Model -- 5.3.5 License Plate Verification Based on Siamese Neural Network -- 5.3.6 Spatiotemporal Relation-Based Vehicle Re-ranking -- 5.3.7 Applications.; 5.3.7.1 Application I: Suspect Vehicle Search -- 5.3.7.2 Application II: Cross-Camera Vehicle Tracking -- 5.3.8 Experiments -- 5.3.8.1 Dataset -- 5.3.8.2 Experimental Settings -- 5.3.8.3 Evaluation of Appearance-Based Vehicle Re-Id -- 5.3.8.4 Evaluation of Plate Verification -- 5.3.8.5 Evaluation of Progressive Vehicle Re-Id -- 5.3.8.6 Time Cost of the PROVID Framework -- References -- 6 Prospect of Future Research -- 6.1 Human-Like Perception -- 6.2 Intelligent Networking and Transmission -- 6.3 Intelligent Services.