The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems

The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems
Copyright
Contents
List of Contributors
1 Reliable Surveillance Tracking System based on Software Defined Internet of Things
	1.1 Introduction
	1.2 Surveillance Tracking System
		1.2.1 Classification of the Surveillance
			1.2.1.1 Audio surveillance
			1.2.1.2 Video surveillance
			1.2.1.3 Internet surveillance
		1.2.2 Applications
			1.2.2.1 Corporate surveillance
			1.2.2.2 Public health surveillance
			1.2.2.3 Vehicular surveillance
		1.2.3 Challenges
			1.2.3.1 Dynamic processing
			1.2.3.2 Visual processing
			1.2.3.3 Data management
			1.2.3.4 Security and privacy
	1.3 Wireless Communication Technologies
	1.4 Software Defined Networking
	1.5 Software Defined Surveillance Tracking System
		1.5.1 Traffic Engineering
		1.5.2 Proposed Traffic Engineering Framework
	1.6 Conclusion
	References
2 An Efficient Provably Secure Identity-Based Authenticated Key Agreement Scheme for Intervehicular Ad Hoc Networks
	2.1 Introduction
		2.1.1 Related Work
	2.2 Preliminaries
		2.2.1 Hardness Assumptions
		2.2.2 Desirable Security Attributes of Authenticated Key Agreement Protocols
	2.3 Security Model
		2.3.1 Participants
		2.3.2 Session
		2.3.3 Adversary
		2.3.4 Fresh Session
		2.3.5 Security Experiment
		2.3.6 Definition 1 (eCK Security of Identity-Based Authenticated Key Agreement Protocol)
	2.4 Provably Secure Identity-Based Authenticated Key Agreement Protocol for V2V Communications
		2.4.1 Setup Phase
		2.4.2 Entity Registration Phase
		2.4.3 Key Agreement Phase
	2.5 Security Analysis
		2.5.1 Event W ^ F1a
			2.5.1.1 Simulation
		2.5.2 Event W ^ F1b
		2.5.3 Event W ^ F2a
		2.5.4 Event W ^ F2b
		2.5.5 Event W ^ F2c
		2.5.6 Event W ^ F2d
	2.6 Analysis of Dang et al.’s Identity-Based Authenticated Key Agreement Protocol
		2.6.1 Key Compromise Impersonation Attack Against Dang et al.’s Protocol
		2.6.2 Flaws in the Security Proof
	2.7 Efficiency Analysis
	2.8 Conclusion
	Acknowledgment
	References
3 Dynamic Self-Aware Task Assignment Algorithm for an Internet of Things-Based Wireless Surveillance System
	3.1 Introduction
	3.2 Related Works
		3.2.1 Factors Affecting the Wireless Surveillance System
	3.3 Self-Aware Dynamic Task Assignment Algorithm
		3.3.1 Wireless Surveillance System Framework
		3.3.2 Technique for Order of Preference by Similarity to Ideal Solution
		3.3.3 Self-Aware Dynamic Task Assignment
	3.4 Simulation Analysis and Results
		3.4.1 Simulation Setup
		3.4.2 Bandwidth Analysis
		3.4.3 Energy Consumption
	3.5 Conclusion
	References
4 Smart Vehicle Monitoring and Tracking System Powered by Active Radio Frequency Identification and Internet of Things
	4.1 Related Works
	4.2 Need for Smart Vehicle Monitoring System
	4.3 Design of Smart Vehicle Monitoring System
	4.4 Evaluation of SVM-ARFIoT
	4.5 Conclusion
	References
5 An Efficient Framework for Object Tracking in Video Surveillance
	5.1 Introduction
		5.1.1 Objectives
	5.2 Related Works
	5.3 Proposed Work
	5.4 Proposed Phases
		5.4.1 Preprocessing
		5.4.2 Object Detection
		5.4.3 Feature Extraction
		5.4.4 Object Segmentation
		5.4.5 Object Tracking
	5.5 Results and Discussions
		5.5.1 Analysis Parameters
			5.5.1.1 Precision
			5.5.1.2 Recall
			5.5.1.3 F-Measure(F)
			5.5.1.4 Success and failure rate
	5.6 Conclusion
	Acknowledgment
	References
	Further Reading
6 Development of Efficient Swarm Intelligence Algorithm for Simulating Two-Dimensional Orthomosaic for Terrain Mapping Usin...
	6.1 Introduction
	6.2 Literature Review
		6.2.1 Efficient Three-Dimensional Placement of a Unmanned Aerial Vehicle Using Particle Swarm Optimization
		6.2.2 API Development for Cooperative Airborne-Based Sense and Avoid in Unmanned Aircraft System
		6.2.3 Multiple-Scenario Unmanned Aerial System Control: A Systems Engineering Approach and Review of Existing Control Methods
		6.2.4 Flocking Algorithm for Autonomous Flying Robots
		6.2.5 A Ground Control Station for a Multiunmanned Aerial Vehicle Surveillance System
		6.2.6 Multiunmanned Aerial Vehicle Control With the Paparazzi System
	6.3 Related Works
		6.3.1 Cooperative Unmanned Aerial Vehicle Methods
		6.3.2 Path Planning
		6.3.3 Collision Avoidance
	6.4 Proposed Architecture
		6.4.1 DroneKit-Python
			6.4.1.1 Installation
		6.4.2 DroneKit-Python Software in the Loop
			6.4.2.1 Installation
			6.4.2.2 Running software in the loop
		6.4.3 MAVLink
		6.4.4 ArduPilot
		6.4.5 Mission Planner
		6.4.6 Two-Dimensional Orthomosaics
	6.5 Simulation of the DroneKit Software in the Loop
	6.6 Collision Avoidance and Path Planning
	6.7 Applications
	6.8 Conclusion
	Further Reading
7 Trends of Sound Event Recognition in Audio Surveillance: A Recent Review and Study
	7.1 Introduction
	7.2 Nature of Sound Event Data
		7.2.1 Nature of Data
	7.3 Feature Extraction Techniques
		7.3.1 Feature Selection
		7.3.2 Feature Extraction
	7.4 Sound Event Recognition Techniques
		7.4.1 Nonprobabilistic Linear Classifier
			7.4.1.1 Support vector machines
			7.4.1.2 Hidden-Markov model
		7.4.2 Deep Learning Methodologies
			7.4.2.1 Neural networks
			7.4.2.2 Convolutional neural networks
			7.4.2.3 Recurrent neural network
	7.5 Experimentation and Performance Analysis
		7.5.1 Data Set
		7.5.2 Comparative Study on Related Work
	7.6 Future Directions and Conclusion
	References
	Further Reading
8 Object Classification of Remote Sensing Image Using Deep Convolutional Neural Network
	8.1 Introduction
	8.2 Related Works
	8.3 VGG-16 Deep Convolutional Neural Network Model
	8.4 Data Set Description
	8.5 Experimental Results and Analysis
		8.5.1 Classification of Results for Various Hyperparameters
	8.6 Conclusion
	References
9 Compressive Sensing-Aided Collision Avoidance System
	9.1 Introduction
	9.2 Theoretical Background
		9.2.1 Sparsity
		9.2.2 Compressed Sensing Problem Statement
		9.2.3 Recovery
		9.2.4 Quality Measurement
	9.3 System
		9.3.1 Signal Acquisition
		9.3.2 Image Processing
		9.3.3 Analysis
	9.4 Result
	9.5 Conclusion
	References
10 Review of Intellectual Video Surveillance Through Internet of Things
	10.1 Introduction
		10.1.1 Internet of Things Environmental Taxonomy
	10.2 Video Surveillance—Internet of Things
		10.2.1 Sensing and Monitoring
			10.2.1.1 Sensor-based motion detection
				10.2.1.1.1 Discrete sensing platform
				10.2.1.1.2 Collaborative sensing platform
				10.2.1.1.3 Wearable body sensors
			10.2.1.2 Algorithm-based motion detection
			10.2.1.3 Intelligent front-end devices
		10.2.2 Internet of Things Data Analytics
		10.2.3 Communication
			10.2.3.1 Short-range communication
			10.2.3.2 Medium-range communication
			10.2.3.3 Long-range communication
		10.2.4 Data Warehousing
			10.2.4.1 Cloud
			10.2.4.2 Fog and edge
			10.2.4.3 Hybrid technologies
		10.2.5 Application-Oriented Design
	10.3 Conclusion
	References
11 Violence Detection in Automated Video Surveillance: Recent Trends and Comparative Studies
	11.1 Introduction
	11.2 Feature Descriptors
		11.2.1 Histogram of Oriented Gradients
		11.2.2 Space–Time Interest Points
		11.2.3 Histogram of Oriented Optical Flow
		11.2.4 Violence Flow Descriptor
	11.3 Modeling Techniques
		11.3.1 Supervised Models
			11.3.1.1 Shallow models
				11.3.1.1.1 Support vector machine
			11.3.1.2 Deep models
				11.3.1.2.1 Artificial neural networks
				11.3.1.2.2 Convolutional neural networks
				11.3.1.2.3 Long short-term memory
		11.3.2 Unsupervised Models
			11.3.2.1 Shallow models
				11.3.2.1.1 Principal component analysis
			11.3.2.2 Deep models
				11.3.2.2.1 Generative adversarial network
				11.3.2.2.2 Autoencoders
					Convolutional autoencoder
					3D Autoencoder
	11.4 Experimental Study and Result Analysis
		11.4.1 Data Sets
		11.4.2 Comparative Study on Related Work
		11.4.3 Our Baseline Study
	11.5 Conclusion
	References
12 FPGA-Based Detection and Tracking System for Surveillance Camera
	12.1 Introduction
	12.2 Prior Research
	12.3 Surveillance System Tasks and Challenges
	12.4 Methodology
	12.5 Conclusion
	References
	Further Reading
Index