Imaging and Sensing for Unmanned Aircraft Systems: Deployment and Applications (Control, Robotics and Sensors)

Cover
Contents
About the editors
Preface
1 UAV-CPSs as a test bed for new technologies and a primer to Industry 5.0
	1.1 Introduction
	1.2 Cloud computing
	1.3 Collective UAV learning
	1.4 Human computation, crowdsourcing and call centres
	1.5 Open-source and open-access resources
	1.6 Challenges and future directions
	1.7 Conclusions
	References
2 UAS human factors and human–machine interface design
	2.1 Introduction
	2.2 UAS HMI functionalities
		2.2.1 Reconfigurable displays
		2.2.2 Sense and avoid
		2.2.3 Mission planning and management
		2.2.4 Multi-platform coordination
	2.3 GCS HMI elements
	2.4 Human factors program
		2.4.1 Requirements definition, capture and refinement
		2.4.2 Task analysis
		2.4.3 Hierarchal task analysis
		2.4.4 Cognitive task analysis
		2.4.5 Critical task analysis
		2.4.6 Operational sequence diagram
		2.4.7 Systems design and development
		2.4.8 Design evaluation
		2.4.9 Verification and validation
	2.5 Future work
	2.6 Conclusions
	References
3 Open-source software (OSS) and hardware (OSH) in UAVs
	3.1 Introduction
	3.2 Open source software
	3.3 Open source UAS
	3.4 Universal messaging protocol
	3.5 GCS software
	3.6 Processing software
	3.7 Operator information and communication
	3.8 Open source platform
	3.9 Future work
		3.9.1 OSH challenges
		3.9.2 Open data
		3.9.3 Cloud data centre
		3.9.4 Crowd-sourced data in UAV-CPSs
		3.9.5 Control of UAV swarms
	3.10 Conclusions
	References
4 Image transmission in UAV MIMO UWB-OSTBC system over Rayleigh channel using multiple description coding (MDC)
	4.1 Introduction
		4.1.1 The efficiency of the flat Rayleigh fading channel
	4.2 Multiple description coding
	4.3 Multiple input–multiple output
	4.4 Diversity
	4.5 Simulations results
	4.6 Discussion and future trends
	4.7 Conclusion
	References
5 Image database of low-altitude UAV flights with flight condition-logged for photogrammetry, remote sensing, and computer vision
	5.1 Introduction
		5.1.1 Image processing system for UAVs
	5.2 The aerial image database framework
		5.2.1 Database requirements
		5.2.2 Database design
	5.3 Image capture process
	5.4 Results
		5.4.1 Images collected
	5.5 Use of the image database
		5.5.1 Mosaics
		5.5.2 Development of CV algorithms
	5.6 Conclusion and future works
	Acknowledgements
	References
6 Communications requirements, video streaming, communications links and networked UAVs
	6.1 Introduction
	6.2 Flying Ad-hoc Networks
	6.3 The FANET protocol
	6.4 FANET: streaming and surveillance
	6.5 Discussion and future trends
		6.5.1 FNs' placement search algorithms
		6.5.2 Event detection and video quality selection algorithms
		6.5.3 Onboard video management (UAV)
		6.5.4 Video-rate adaptation for the fleet platform
		6.5.5 FNs coordination
		6.5.6 Data collection and presentation
		6.5.7 Software-Defined Networking
		6.5.8 Network Function Virtualisation
		6.5.9 Data Gathering versus Energy Harvesting
	6.6 Conclusion
	References
7 Multispectral vs hyperspectral imaging for unmanned aerial vehicles: current and prospective state of affairs
	7.1 Introduction
	7.2 UAV imaging architecture and components
		7.2.1 Future scope for UAV
	7.3 Multispectral vs. hyperspectral imaging instruments
		7.3.1 Multispectral imaging
			7.3.1.1 Low-resolution imaging
			7.3.1.2 High-resolution imaging
		7.3.2 Hyperspectral imaging
		7.3.3 Satellite imaging vs UAV imaging
	7.4 UAV image processing workflow
		7.4.1 Atmospheric correction
		7.4.2 Spectral influence mapping
		7.4.3 Dimensionality reduction
		7.4.4 Computational tasks
	7.5 Data processing toolkits for spatial data
	7.6 UAV open data sets for research–multispectral and hyperspectral
	7.7 Applications of MSI and HSI UAV imaging
		7.7.1 Agriculture monitoring
		7.7.2 Coastal monitoring
		7.7.3 Forestry
		7.7.4 Urban planning
		7.7.5 Defence applications
		7.7.6 Environmental monitoring
		7.7.7 Other commercial uses
	7.8 Conclusion and future scope
	References
8 Aerial imaging and reconstruction of infrastructures by UAVs
	8.1 Introduction
	8.2 Related Studies
	8.3 Visual sensors and mission planner
		8.3.1 Image projection
		8.3.2 Path planner
	8.4 3D reconstruction
		8.4.1 Stereo mapping
		8.4.2 Monocular mapping
	8.5 Data-set collection
		8.5.1 Experimental setup
		8.5.2 Data set 1
		8.5.3 Data set 2
	8.6 Experimental results
		8.6.1 Indoor scenario
		8.6.2 Outdoor Scenario 1
		8.6.3 Outdoor Scenario 2
		8.6.4 Underground scenario
	8.7 Future trends
	8.8 Conclusions
	References
9 Deep learning as an alternative to super-resolution imaging in UAV systems
	9.1 Introduction
	9.2 The super-resolution model
		9.2.1 Motion estimation
		9.2.2 Dehazing
		9.2.3 Patch selection
		9.2.4 Super-resolution
	9.3 Experiments and results
		9.3.1 Peak signal-to-noise ratio
	9.4 Critical issues in SR deployment in UAV-CPSs
		9.4.1 Big data
		9.4.2 Cloud computing services
		9.4.3 Image acquisition hardware limitations
		9.4.4 Video SR
		9.4.5 Efficient metrics and other evaluation strategies
		9.4.6 Multiple priors
		9.4.7 Regularisation
		9.4.8 Novel architectures
		9.4.9 3D SR
			9.4.9.1 Depth map super-resolution
		9.4.10 Deep learning and computational intelligence
		9.4.11 Network design
	9.5 Conclusion
	References
10 Quality of experience (QoE) and quality of service (QoS) in UAV systems
	10.1 Introduction
		10.1.1 Airborne network from a CPS perspective
	10.2 Definitions
		10.2.1 Parameters that impact QoS/QoE
		10.2.2 Impact of cloud distance on QoS/QoE
		10.2.3 QoS/QoE monitoring framework in UAV-CPSs
		10.2.4 Application-level management
		10.2.5 Network-level management
		10.2.6 Cloud distance management
		10.2.7 QoS/QoE service-level management
		10.2.8 QoS/QoE metrics in UAV-CPSs
		10.2.9 Mapping of QoS to QoE
		10.2.10 Subjective vs objective measurement
		10.2.11 Tools to measure QoS/QoE
	10.3 Applications
		10.3.1 Social networks, gaming and human–machine interfaces
		10.3.2 Data centres
		10.3.3 Electric power grid and energy systems
		10.3.4 Networking systems
		10.3.5 Surveillance
	10.4 Case studies
		10.4.1 Application scenario 1: UAV-CPSs in traffic congestion management
			10.4.1.1 QoS management at the FN
			10.4.1.2 QoS management at the UAV-CPS UCN
		10.4.2 Application scenario 2: congestion and accident avoidance using intelligent vehicle systems
	10.5 Future and open challenges
		10.5.1 Modelling and design
		10.5.2 Collaborative services
		10.5.3 Streaming
		10.5.4 Security
		10.5.5 Flying ad hoc networks
		10.5.6 User emotions
	10.6 Conclusion
	References
11 Conclusions
Index
Back Cover