Multispectral and thermal infrared data, visual scores for severity of common rust symptoms, and genotypic single nucleotide polymorphism data of three F2-derived biparental doubled-haploid maize populations

Three F2-derived biparental doubled haploid (DH) maize populations were generated for genetic mapping of resistance to common rust. Each of the three populations has the same susceptible parent, but a different resistance donor parent. Population 1 and 3 consist of 320 lines each, population 2 consists of 260 lines. The DH lines were evaluated for their susceptibility to common rust in two years and with two replications in each year. For phenotyping, a visual score (VS) for susceptibility was assigned. Additionally, unmanned aerial vehicle (UAV) derived multispectral and thermal infrared data was recorded and combined in different vegetation indices ("remote sensing", RS). The DH lines were genotyped with the DarTseq method, to obtain data on single nucleotide polymorphisms (SNPs). After quality control, 9051 markers remained. Missing values were "imputed" by the empirical mean of the marker scores of the respective locus. We used the data for comparison of genome-wide association studies and genomic prediction when based on different phenotyping methods, that is either VS or RS data. The data may be interesting for reuse for instance for benchmarking genomic prediction models, for phytopathological studies addressing common rust, or for specifications of vegetation indices.

Identification of particle distribution pattern in vertical profile via unmanned aerial vehicles observation

Below the boundary layer, the air pollutants have been confirmed to present the decreasing trend with the height in most situaitons. However, the disperiosn rate of air pollutants in the vertical profile is rarely investigated in detail, especially through in-situ measurement. With this consideration, we employed an unmanned aerial vehicle equipped with portable monitoring equipments to scrutinize the vertical distribution of PM2.5. Based on the original data, we found that PM2.5 concentration decreases gradually with altitude below the boundary layer and demonstrated an obvious linear correlation. Therefore, the vertical distribution of PM2.5 was quantified by representing the distribution of PM2.5 with the slope of PM2.5 vertical distribution. We used backward trajectories to reveal the causes of outliers (PM2.5 increasing with altitude), and found that PM2.5 in the high altitude came from the southwest. Besides, the relationship between the vertical distribution of PM2.5 and various meteorological factors was investigated using stepwise regression analysis. The results show that the four meteorological factors most strongly correlated with the slope values are: (a) the difference in relative humidity between the ground and the air; (b) the difference in temperature between the ground and the air; (c) the height of the boundary layer; and (d) the wind speed. The slope values increase with increasing the difference in relative humidity between ground and air and the difference in temperature between the ground and the air, and decrease with increasing boundary layer height and wind speed. According to the Random Forest calculations, the ground-to-air relative humidity difference is the most important at 0.718; the wind speed is the least important at 0.053; and the ground-to-air temperature difference and boundary layer height are 0.140 and 0.088, respectively.

A comprehensive review of unmanned aerial vehicle-based approaches to support photovoltaic plant diagnosis

Accurate photovoltaic (PV) diagnosis is of paramount importance for reducing investment risk and increasing the bankability of the PV technology. The application of fault diagnostic solutions and troubleshooting on operating PV power plants is vital for ensuring optimal energy harvesting, increased power generation production and optimised field operation and maintenance (O&M) activities. This study aims to give an overview of the existing approaches for PV plant diagnosis, focusing on unmanned aerial vehicle (UAV)-based approaches, that can support PV plant diagnostics using imaging techniques and data-driven analytics. This review paper initially outlines the different degradation mechanisms, failure modes and patterns that PV systems are subjected and then reports the main diagnostic techniques. Furthermore, the essential equipment and sensor's requirements for diagnosing failures in monitored PV systems using UAV-based approaches are provided. Moreover, the study summarizes the operating conditions and the various failure types that can be detected by such diagnostic approaches. Finally, it provides recommendations and insights on how to develop a fully functional UAV-based diagnostic tool, capable of detecting and classifying accurately failure modes in PV systems, while also locating the exact position of faulty modules.

Visual image design of the internet of things based on AI intelligence

Visual object detection has emerged as a critical technology for Unmanned Arial Vehicle (UAV) use due to advances in computer vision. New developments in fields like communication technology and the UAV needs to be able to act autonomously by gathering data and then making choices. These tendencies have brought us to cutting-edge levels of health care, transportation, energy, monitoring, and security for visual image detection and manufacturing endeavors. These include coordination in communication via IoT, sustainability of IoT network, and optimization challenges in path planning. Because of their limited battery life, these gadgets are limited in their range of communication. UAVs can be seen as terminal devices connected to a large network where a swarm of other UAVs is coordinating their motions, directing one another, and maintaining watch over locations outside its visual range. One of the essential components of UAV-based applications is the ability to recognize objects of interest in aerial photographs taken by UAVs. While aerial photos might be useful, object detection is challenging. As a result, capturing aerial photographs with UAVs is a unique challenge since the size of things in these images might vary greatly. The study proposal included specific information regarding the Detection of Visual Images by UAVs (DVI-UAV) using the IoT and Artificial Intelligence (AI). Included in the study of AI is the concept of DSYolov3. The DSYolov3 model was presented to deal with these problems in the UAV industry. By fusing the channel-wise feature across multiple scales using a spatial pyramid pooling approach, the proposed study creates a novel module, Multi-scale Fusion of Channel Attention (MFCAM), for scale-variant object identification tasks. The method's effectiveness and efficiency have been thoroughly tested and evaluated experimentally. The suggested method would allow us to outperform most current detectors and guarantee that the models will be useable on UAVs. There will be a 95 % success rate in terms of visual image detection, a 94 % success rate in terms of computation cost, a 97 % success rate in terms of accuracy, and a 95 % success rate in terms of effectiveness.

Internet of things enabled deep learning methods using unmanned aerial vehicles enabled integrated farm management

Smart livestock farming strives to make farming more lucrative, efficient, and ecologically beneficial by using digital technologies. Precision livestock fencing, in which each animal is followed and studied independently, is the most promising kind of smart livestock farming. The Internet of Things (IoT) allows farmers to save money and effort by keeping tabs on crops, mapping out their land, and giving them data to develop sensible management strategies for their farms. Surveillance, disaster management, firefighting, border patrol, and courier services employ Unmanned Aerial Vehicles (UAVs) that are originally created for the military. The segment focuses on UAVs in livestock and agricultural production. This is achieved via employing robots, drones, remote sensors, and computer imagery in unison with ever-improving in-Depth Learning for farming. Deep learning (DL) algorithms find many uses in the agricultural sector, from identifying plant diseases to estimating yields to detecting weeds to forecasting the weather and determining how much water is in the soil. The challenging characteristics of smart livestock farming are climate change, biodiversity loss, and continuous monitoring. Hence, in this research, the Unmanned Aerial Vehicles enabled Integrated Farm Management (UAV-IFM) has been designed to improve smart livestock farming. Safe and reliable tracking of livestock from farm to fork is made possible by this sensor, which has far-reaching implications for detecting and containing disease outbreaks and preventing the resulting financial losses and food-related health pandemics. UAV-IFM aims to improve the assessment process so that smart livestock farming may be more widely adopted and offers growth-supportive help to farmers. Conclusions gathered from this study's examination of the UAV-IFM reveal that these instruments correctly forecast and verify smart livestock farming management within the framework of the assessment procedure. The experimental analysis of UAV-IFM outperforms smart livestock farming in terms of efficiency ratio, performance, accuracy, and prediction.

Survey on Path Planning for UAVs in Healthcare Missions

This article presents a comprehensive review of the state-of-the-art applications and methodologies related to the use of unmanned aerial vehicles (UAVs) in the healthcare sector, with a particular focus on path planning. UAVs have gained remarkable attention in healthcare during the outbreak of COVID-19, and this study explores their potential as a viable option for medical transportation. The survey categorizes existing studies by mission type, challenges addressed, and performance metrics to provide a clearer picture of the path planning problems and potential directions for future research. It highlights the importance of addressing the path planning problem and the challenges that UAVs may face during their missions, including the UAV delivery range limitation, and discusses recent solutions in this field. The study concludes by encouraging researchers to conduct their studies in a realistic environment to reveal UAVs' real potential, usability, and feasibility in the healthcare domain.

An unmanned emergency blood dispatch system based on an early prediction and fast delivery strategy: Design and development study

BACKGROUND AND OBJECTIVE

For severe trauma patients, hemorrhage is the most common cause of medically preventable deaths. Early transfusion is beneficial to major hemorrhagic patients. However, the early supply of emergency blood products for major hemorrhagic patients is still a major problem in many areas. The aim of this study was to design and develop an unmanned emergency blood dispatch system for the fast delivery of blood resources and rapid emergency response to trauma events, especially those with mass hemorrhagic trauma patients and those occurred in remote areas.

METHODS

Based on the process of emergency medical services for trauma patients, we introduced unmanned aerial vehicle (UAV) and designed the main flowchart of the dispatch system, which combines an emergency transfusion prediction model and UAV-related dispatch algorithms to improve first aid efficiency and quality. The system identifies patients in need of emergency transfusion through a multidimensional prediction model. Then, by analyzing the blood center, hospitals and UAV stations nearby, the system recommends the patient's transfer destination for emergency transfusion and dispatch schemes of UAVs and trucks for a fast supply of blood products. Simulation experiments of urban and rural scenarios were conducted to evaluate the proposed system.

RESULTS

The developed emergency transfusion prediction model of the proposed system achieves a higher AUROC value of 0.8453 than a classical transfusion prediction score. In the urban experiment, by adopting the proposed system, the average wait time per patient decreased from 32 to 18 min, and the total time decreased from 42 to 29 min. Owing to the combination of the prediction and the fast delivery function, the proposed system took 4 and 11 min less wait time than the strategy with only the prediction function and the strategy with only the fast delivery function, respectively. In the rural experiment, for trauma patients requiring an emergency transfusion at 4 locations, the wait time for transfusion under the proposed system was 16.54, 17.08, 38.70 and 46.00 min less than that under the conventional strategy. The health status-related score increased by 6.9%, 0.9%, 19.1% and 36.7%, respectively.

CONCLUSIONS

Experimental results demonstrate that the proposed system works well with a faster blood supply speed for severe hemorrhagic patients and better health status. With the assistance of the system, emergency doctors at the scene of an injury are able to comprehensively analyze patients' status and the surrounding rescue conditions and then make decisions, especially when encountering mass casualties or casualties in remote areas.

Event-based formation control for multiple unmanned aerial vehicles under directed topology

This paper focuses on the problem of formation control for multiple unmanned aerial vehicles (UAV) subject to cyber attacks by a novel event-triggered communication scheme. An average method is introduced to design the triggering condition of this communication scheme, by which the amount of wrong triggering events caused by the sudden change of system states is greatly decreased, thereby saving a great deal of network bandwidth and reducing network congestion. Considering cyber attacks, a new event-based formation control strategy is developed for multi-UAV systems under directed topology by utilizing a control compensation approach. Sufficient conditions for the multi-UAV system to achieve the desired formation are acquired. Finally, a simulation example is undertaken to demonstrate the effectiveness of the theoretical results.

The q-rung fuzzy LOPCOW-VIKOR model to assess the role of unmanned aerial vehicles for precision agriculture realization in the Agri-Food 4.0 era

Smart agriculture is gaining a lot of attention recently, owing to technological advancement and promotion of sustainable habits. Unmanned aerial vehicles (UAVs) play a crucial role in smart agriculture by aiding in different phases of agriculture. The contribution of UAVs to sustainable and precision agriculture is a critical and challenging issue to be taken into account, particularly for smallholder farmers in order to save time and money, and improve their agricultural skills. Thence, this study targets to propose an integrated group decision-making framework to determine the best agricultural UAV. Previous studies on UAV evaluation, (i) could not model uncertainty effectively, (ii) weights of experts are not methodically determined; (iii) importance of experts and criteria types are not considered during criteria weight calculation, and (iv) personalized ranking of UAVs is lacking along with consideration to dual weight entities. Herein, nine critical selection criteria are identified, drawing upon the relevant literature and experts' opinions, and five extant UAVs are considered for evaluation. To circumvent the gaps, in this work, a new integrated framework is developed considering q-rung orthopair fuzzy numbers (q-ROFNs) for apt UAV selection. Specifically, methodical estimation of experts' weights is achieved by presenting the regret measure. Further, weighted logarithmic percentage change-driven objective weighting (LOPCOW) technique is formulated for criteria weight calculation, and an algorithm for personalized ranking of UAVs is presented with visekriterijumska optimizacija i kompromisno resenje (VIKOR) approach combined with Copeland strategy. The findings show that the foremost criteria in agricultural UAV selection are "camera," "power system," and "radar system," respectively. Further, it is inferred that the most promising UAV is the DJ AGRAS T30. Since the applicability of UAV in agriculture will get inevitable, the developed framework can be an effective decision support system for farmers, managers, policymakers, and other stakeholders.

A novel metaheuristics with adaptive neuro-fuzzy inference system for decision making on autonomous unmanned aerial vehicle systems

Recently, autonomous systems have received considerable attention amongst research communities and academicians. Unmanned aerial vehicles (UAVs) find useful in several applications like transportation, surveillance, disaster management, and wildlife monitoring. One of the important issues in the UAV system is energy efficiency, which can be resolved by the use of clustering approaches. In addition, high resolution remote sensing images need to be classified for effective decision making using deep learning (DL) models. Though several models are available in the literature, only few approaches have focused on the clustering and classification processes in UAV networks. In this aspect, this paper designs a novel metaheuristic with an adaptive neuro-fuzzy inference system for decision making named MANFIS-DM technique on autonomous UAV systems. The proposed MANFIS-DM technique intends to effectively organize the UAV networks into clusters and then classify the images into appropriate class labels. The proposed MANFIS-DM technique encompasses two major stages namely quantum different evolution based clustering (QDE-C) technique and ANFIS based classification technique. Primarily, the QDE-C technique involves the design of a fitness function involving three parameters namely average distance, distance to UAVs, and UAV degree. Besides, the image classification model involves a set of subprocesses namely DenseNet based feature extraction, Adadelta based hyperparameter optimization, and ANFIS based classification. The design of QDE-C algorithm with classification model for autonomous UAV systems show the novelty of the work. The experimental result analysis of the MANFIS-DM method is carried out against benchmark dataset and the results ensured the enhanced performance of the MANFIS-DM technique over the other methods with the maximum accu_y of 99.13%.

Digital Twins in Unmanned Aerial Vehicles for Rapid Medical Resource Delivery in Epidemics

The purposes are to explore the effect of Digital Twins (DTs) in Unmanned Aerial Vehicles (UAVs) on providing medical resources quickly and accurately during COVID-19 prevention and control. The feasibility of UAV DTs during COVID-19 prevention and control is analyzed. Deep Learning (DL) algorithms are introduced. A UAV DTs information forecasting model is constructed based on improved AlexNet, whose performance is analyzed through simulation experiments. As end-users and task proportion increase, the proposed model can provide smaller transmission delays, lesser energy consumption in throughput demand, shorter task completion time, and higher resource utilization rate under reduced transmission power than other state-of-art models. Regarding forecasting accuracy, the proposed model can provide smaller errors and better accuracy in Signal-to-Noise Ratio (SNR), bit quantizer, number of pilots, pilot pollution coefficient, and number of different antennas. Specifically, its forecasting accuracy reaches 95.58% and forecasting velocity stabilizes at about 35 Frames-Per-Second (FPS). Hence, the proposed model has stronger robustness, making more accurate forecasts while minimizing the data transmission errors. The research results can reference the precise input of medical resources for COVID-19 prevention and control.

Path planning optimization in unmanned aerial vehicles using meta-heuristic algorithms: a systematic review

Unmanned aerial vehicles (UAVs) have recently been increasingly popular in various areas, fields, and applications. Military, disaster management, rescue operations, public services, agriculture, and various other areas are examples. As a result, UAV path planning is concerned with determining the optimal path from the source to the destination while avoiding collisions with lowering the cost of time, energy, and other resources. This review aims to assort academic studies on the path planning optimization in UAV using meta-heuristic algorithms, summarize the results of each optimization algorithm, and extend the understanding of the current state of the path planning in UAV in the meta-heuristic optimization field. For this purpose, we implemented a broad, automated search using Boolean and snowballing searching methods to find academic works on path planning in UAVs. Studies and papers have been distinguished, and the following information was obtained and aggregated from each article: authors, publication's year, the journal name or the conference name, proposed algorithms, the aim of the study, the outcome, and the quality of each study. According to the findings, the meta-heuristic algorithm is a standard optimization method for tackling single and multi-objective problems. Besides, the findings show that meta-heuristic algorithms have a great compact on the path planning optimization in UAVs, and there is good progress in this field. However, the problem still exists mainly in complex and dynamic environments, on battlefields, in rescue missions, mobile obstacles, and with multiple UAVs.

Community acceptability of dengue fever surveillance using unmanned aerial vehicles: A cross-sectional study in Malaysia, Mexico, and Turkey

Surveillance is a critical component of any dengue prevention and control program. There is an increasing effort to use drones in mosquito control surveillance. Due to the novelty of drones, data are scarce on the impact and acceptance of their use in the communities to collect health-related data. The use of drones raises concerns about the protection of human privacy. Here, we show how willingness to be trained and acceptance of drone use in tech-savvy communities can help further discussions in mosquito surveillance. A cross-sectional study was conducted in Malaysia, Mexico, and Turkey to assess knowledge of diseases caused by Aedes mosquitoes, perceptions about drone use for data collection, and acceptance of drones for Aedes mosquito surveillance around homes. Compared with people living in Turkey, Mexicans had 14.3 (p < 0.0001) times higher odds and Malaysians had 4.0 (p = 0.7030) times the odds of being willing to download a mosquito surveillance app. Compared to urban dwellers, rural dwellers had 1.56 times the odds of being willing to be trained. There is widespread community support for drone use in mosquito surveillance and this community buy-in suggests a potential for success in mosquito surveillance using drones. A successful surveillance and community engagement system may be used to monitor a variety of mosquito spp. Future research should include qualitative interview data to add context to these findings.

The emergence of marine recreational drone fishing: Regional trends and emerging concerns

Online evidence suggests that there has been an increase in interest of using unmanned aerial vehicles or drones during land-based marine recreational fishing. In the absence of reliable monitoring programs, this study used unconventional publicly available online monitoring methodologies to estimate the growing interest, global extent, catch composition and governance of this practice. Results indicated a 357% spike in interest during 2016 primarily in New Zealand, South Africa and Australia. From an ecological perspective, many species targeted by drone fishers are vulnerable to overexploitation, while released fishes may experience heightened stress and mortality. From a social perspective, the ethics of drone fishing are being increasingly questioned by many recreational anglers and we forecast the potential for increased conflict with other beach users. In terms of governance, no resource use legislation specifically directed at recreational drone fishing was found. These findings suggest that drone fishing warrants prioritised research and management consideration.

Drone technology in municipal solid waste management and landfilling: A comprehensive review

The paper discusses the experience of using unmanned aerial vehicles (UAV) in the management of municipal solid waste landfills and dumpsites. Although the use of drones at waste disposal sites (WDS) has a more than ten-year history, the active application of these technologies has increased in the last 3-4 years. The paper analyzes scientific publications of 2010-2021 (July) and identifies the main WDS management task groups for which the solution of UAV can be used. It illustrates that most of the research is devoted to studying spatial and volumetric characteristics of landfills, which is connected with the practical needs. About a quarter of the publications focus on monitoring the emissions of landfill gas or its individual components, mainly methane. Issues of a comprehensive assessment of the technological and environmental safety of landfills and dumps are covered in the scientific literature fragmentarily and insufficiently. At the same time, the current level of technologies for collecting and processing remote sensing air data (UAV, sensors for aerial imagery, software for photogrammetric processing of aerial imagery data, geographic information systems (GIS)) makes it possible to identify and assess many environmental effects of landfills and dumps and to monitor compliance with the standards for the landfills operation, which could bring management of these facilities to a fundamentally different level. Promising areas of further research in the field of UAV application at WDS are indicated: development of processes for automatic interpretation of aerial imagery materials; product analysis of photogrammetric data processing in a GIS environment, etc.

Estimation of dump and landfill waste volumes using unmanned aerial systems

The paper discusses how the choice of software and hardware components used in unmanned aerial systems (UAS) affects the accuracy of estimating volume on landfills and dumpsites, and the amount of ground work needed to create a high-altitude justification of reference geodetic network. A non-specialized low-cost unmanned aerial vehicle (UAV) and a specialized UAV of a geodetic class were compared in scenarios with different numbers of ground control points. In addition, the use of desktop and cloud software for photogrammetric data-processing was assessed. Both specialized geodetic and non-specialized low-cost UAVs made it possible to obtain fairly accurate estimates of waste volume. The differences in the UAV results compared to data obtained by ground surveys were about 1.0%, even with a minimum number of ground control points (GCP). With complete abandonment of GCP and processing aerial data in cloud services, these differences increased to 5.0%. Low-cost UAV and cloud services can be used for operational monitoring of waste volume changes at landfills and dumpsites. A geodesic-class UAV allows researchers to build a more accurate digital terrain model of the landfill surface, but it does not give any advantages in waste volume estimation.

Conditional trust: Community perceptions of drone use in malaria control in Zanzibar

BACKGROUND

The potential of drones to support public health interventions, such as malaria vector control, is beginning to be realised. Although permissions from civil aviation authorities are often needed for drone operations, the communities over which they fly tend to be ignored: How do affected communities perceive drones? Is drone deployment accepted by communities? How should communities be engaged?

METHODS

An initiative in Zanzibar, United Republic of Tanzania is using drones to map malarial mosqutio breeding sites for targeting larval source management interventions. A community engagement framework was developed, based on participatory research, across three communities where drones will be deployed, to map local perceptions of drone use. Costs associated with this exercise were collated.

RESULTS

A total of 778 participants took part in the study spanning a range of community and stakeholder groups. Overall there was a high level of acceptance and trust in drone use for public health research purposes. Despite this level of trust for drone operations this support was conditional: There was a strong desire for pre-deployment information across all stakeholder groups and regular updates of this information to be given about drone activities, as well as consent from community level governance. The cost of the perception study and resulting engagement strategy was US$24,411.

CONCLUSIONS

Mapping and responding to community perceptions should be a pre-requisite for drone activity in all public health applications and requires funding. The findings made in this study were used to design a community engagement plan providing a simple but effective means of building and maintaining trust and acceptability. We recommend this an essential investment.

Honeybee-based biohybrid system for landmine detection

Legacy landmines in post-conflict areas are a non-discriminatory lethal hazard and can still be triggered decades after the conflict has ended. Efforts to detect these explosive devices are expensive, time-consuming, and dangerous to humans and animals involved. While methods such as metal detectors and sniffer dogs have successfully been used in humanitarian demining, more tools are required for both site surveying and accurate mine detection. Honeybees have emerged in recent years as efficient bioaccumulation and biomonitoring animals. The system reported here uses two complementary landmine detection methods: passive sampling and active search. Passive sampling aims to confirm the presence of explosive materials in a mine-suspected area by the analysis of explosive material brought back to the colony on honeybee bodies returning from foraging trips. Analysis is performed by light-emitting chemical sensors detecting explosives thermally desorbed from a preconcentrator strip. The active search is intended to be able to pinpoint the place where individual landmines are most likely to be present. Used together, both methods are anticipated to be useful in an end-to-end process for area surveying, suspected hazardous area reduction, and post-clearing internal and external quality control in humanitarian demining.

Effective and Safe Trajectory Planning for an Autonomous UAV Using a Decomposition-Coordination Method

In this paper, we present a Decomposition Coordination (DC) method applied to solve the problem of safe trajectory planning for autonomous Unmanned Aerial Vehicle (UAV) in a dynamic environment. The purpose of this study is to make the UAV more reactive in the environment and ensure the safety and optimality of the computed trajectory. In this implementation, we begin by selecting a dynamic model of a fixed-arms quadrotor UAV. Then, we define our multi-objective optimization problem, which we convert afterward into a scalar optimization problem (SOP). The SOP is subdivided after that into smaller sub-problems, which will be treated in parallel and in a reasonable time. The DC principle employed in our method allows us to treat non-linearity at the local level. The coordination between the two levels is achieved after that through the Lagrange multipliers. Making use of the DC method, we can compute the optimal trajectory from the UAV’s current position to a final target practically in real-time. In this approach, we suppose that the environment is totally supervised by a Ground Control Unit (GCU). To ensure the safety of the trajectory, we consider a wireless communication network over which the UAV may communicate with the GCU and get the necessary information about environmental changes, allowing for successful collision avoidance during the flight until the intended goal is safely attained. The analysis of the DC algorithm’s stability and convergence, as well as the simulation results, are provided to demonstrate the advantages of our method and validate its potential.

Artificial intelligence-enabled Internet of Things-based system for COVID-19 screening using aerial thermal imaging

Internet of Things (IoT) has recently brought an influential research and analysis platform in a broad diversity of academic and industrial disciplines, particularly in healthcare. The IoT revolution is reshaping current healthcare practices by consolidating technological, economic, and social views. Since December 2019, the spreading of COVID-19 across the world has impacted the world's economy. IoT technology integrated with Artificial Intelligence (AI) can help to address COVID-19. UAVs equipped with IoT devices can collect raw data that demands computing and analysis to make intelligent decision without human intervention. To mitigate the effect of COVID-19, in this paper, we propose an IoT-UAV-based scheme to collect raw data using onboard thermal sensors. The thermal image captured from the thermal camera is used to determine the potential people in the image (of the massive crowd in a city), which may have COVID-19, based on the temperature recorded. An efficient hybrid approach for a face recognition system is proposed to detect the people in the image having high body temperature from infrared images captured in a real-time scenario. Also, a face mask detection scheme is introduced, which detects whether a person has a mask on the face or not. The schemes' performance evaluation is done using various machine learning and deep learning classifiers. We use the edge computing infrastructure (onboard sensors and actuators) for data processing to reduce the response time for real-time analytics and prediction. The proposed scheme has an average accuracy of  99.5% using various performance evaluation metrics indicating its practical applicability in real-time scenarios.

Maturity Levels of Public Safety Applications using Unmanned Aerial Systems: a Review

Unmanned Aerial Systems (UAS) are becoming increasingly popular in the public safety sector. While some applications have so far only been envisioned, others are regularly performed in real-life scenarios. Many more fall in between and are actively investigated by research and commercial communities alike. This study reviews the maturity levels, or “market-readiness”, of public safety applications for UAS. As individual assessments of all applications suggested in the literature are infeasible due to their sheer number, we propose a novel set of application categories: Remote Sensing, Mapping, Monitoring, Human-drone Interaction, Flying Ad-hoc Networks, Transportation, and Counter UAV Systems. Each category’s maturity is assessed through a literature review of contained applications, using the metric of Application Readiness Levels (ARLs). Relevant aspects such as the environmental complexity and available mission time of addressed scenarios are taken into account. Following the analysis, we infer that improvements in autonomy and software reliability are the most promising research areas for increasing the usefulness and acceptance of UAS in the public safety domain.

Pioneering Remotely Piloted Aerial Systems (Drone) Delivery of a Remotely Telementored Ultrasound Capability for Self Diagnosis and Assessment of Vulnerable Populations-the Sky Is the Limit

Remotely Piloted Aerial Systems (RPAS) are poised to revolutionize healthcare in out-of-hospital settings, either from necessity or practicality, especially for remote locations. RPAS have been successfully used for surveillance, search and rescue, delivery, and equipping drones with telemedical capabilities being considered. However, we know of no previous consideration of RPAS-delivered tele-ultrasound capabilities. Of all imaging technologies, ultrasound is the most portable and capable of providing real-time point-of-care information regarding anatomy, physiology, and procedural guidance. Moreover, remotely guided ultrasound including self-performed has been a backbone of medical care on the International Space Station since construction. The TeleMentored Ultrasound Supported Medical Interventions Group of the University of Calgary partnered with the Southern Alberta Institute of Technology to demonstrate RPAS delivery of a smartphone-supported tele-ultrasound system by the SwissDrones SDO50 RPAS. Upon receipt of the sanitized probe, a completely ultrasound-naïve volunteer was guided by a remote expert located 100 km away using online video conferencing (Zoom), to conduct a self-performed lung ultrasound examination. It proved feasible for the volunteer to examine their anterior chest, sides, and lower back bilaterally, correlating with standard recommended examinations in trauma/critical care, including the critical locations of a detailed COVID-19 lung diagnosis/surveillance examination. We contend that drone-delivered telemedicine including a tele-ultrasound capability could be leveraged to enhance point-of-care diagnostic accuracy in catastrophic emergencies, and allow diagnostic capabilities to be delivered to vulnerable populations in remote locations for whom transport is impractical or undesirable, speeding response times, or obviating the risk of disease transmission depending on the circumstances.

Estimate the Unknown Environment with Biosonar Echoes-A Simulation Study

Unmanned aerial vehicles (UAVs) have shown great potential in various applications such as surveillance, search and rescue. To perform safe and efficient navigation, it is vitally important for a UAV to evaluate the environment accurately and promptly. In this work, we present a simulation study for the estimation of foliage distribution as a UAV equipped with biosonar navigates through a forest. Based on a simulated forest environment, foliage echoes are generated by using a bat-inspired bisonar simulator. These biosonar echoes are then used to estimate the spatial distribution of both sparsely and densely distributed tree leaves. While a simple batch processing method is able to estimate sparsely distributed leaf locations well, a wavelet scattering technique coupled with a support vector machine (SVM) classifier is shown to be effective to estimate densely distributed leaves. Our approach is validated by using multiple setups of leaf distributions in the simulated forest environment. Ninety-seven percent accuracy is obtained while estimating thickly distributed foliage.

Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms

Crop classification in early phenological stages has been a difficult task due to spectrum similarity of different crops. For this purpose, low altitude platforms such as drones have great potential to provide high resolution optical imagery where Machine Learning (ML) applied to classify different types of crops. In this research work, crop classification is performed at different phenological stages using optical images which are obtained from drone. For this purpose, gray level co-occurrence matrix (GLCM) based features are extracted from underlying gray scale images collected by the drone. To classify the different types of crops, different ML algorithms including Random Forest (RF), Naive Bayes (NB), Neural Network (NN) and Support Vector Machine (SVM) are applied. The results showed that the ML algorithms performed much better on GLCM features as compared to gray scale images with a margin of 13.65% in overall accuracy.

Enabling a large-scale assessment of litter along Saudi Arabian red sea shores by combining drones and machine learning

Beach litter assessments rely on time inefficient and high human cost protocols, mining the attainment of global beach litter estimates. Here we show the application of an emerging technique, the use of drones for acquisition of high-resolution beach images coupled with machine learning for their automatic processing, aimed at achieving the first national-scale beach litter survey completed by only one operator. The aerial survey had a time efficiency of 570 ± 40 m² min^-1 and the machine learning reached a mean (±SE) detection sensitivity of 59 ± 3% with high resolution images. The resulting mean (±SE) litter density on Saudi Arabian shores of the Red Sea is of 0.12 ± 0.02 litter items m^-2, distributed independently of the population density in the area around the sampling station. Instead, accumulation of litter depended on the exposure of the beach to the prevailing wind and litter composition differed between islands and the main shore, where recreational activities are the major source of anthropogenic debris.

Automatic external defibrillator provided by unmanned aerial vehicle (drone) in Greater Paris: A real world-based simulation

AIM

To reduce the delay in defibrillation of out-of-hospital cardiac arrest (OHCA) patients, recent publications have shown that drones equipped with an automatic external defibrillator (AED) appear to be effective in sparsely populated areas. To study the effectiveness of AED-drones in high-density urban areas, we developed an algorithm based on emergency dispatch parameters for the rate and detection speed of cardiac arrests and technical and meteorological parameters.

METHODS

We ran a numerical simulation to compare the actual time required by the Basic Life Support team (BLSt) for OHCA patients in Greater Paris in 2017 to the time required by an AED-drone. Endpoints were the proportion of patients with "AED-drone first" and the defibrillation time gained. We built an open-source website (https://airborne-aed.org/) to allow modelling by modifying one or more parameters and to help other teams model their own OHCA data.

RESULTS

Of 3014 OHCA patients, 72.2 ± 0.7% were in the "no drone flight" group, 25.8 ± 0.2% in the "AED-drone first" group, and 2.1 ± 0.2% in the "BLSt-drone first" group. When a drone flight was authorized, it arrived an average 190 s before BLSt in 93% of cases. The possibility of flying the drone during the aeronautical night improved the results of the "AED-drone first" group the most (+60%).

CONCLUSIONS

In our very high-density urban model, at most 26% of OHCA patients received an AED from an AED-drone before BLSt. The flexible parameters of our website model allows evaluation of the impact of each choice and concrete implementation of the AED-drone.

Monitoring oyster culture rafts and seagrass meadows in Nagatsura-ura Lagoon, Sanriku Coast, Japan before and after the 2011 tsunami by remote sensing: their recoveries implying the sustainable development of coastal waters

Background

Coastal ecosystems are blue infrastructures that support coastal resources and also aquaculture. Seagrass meadows, one of coastal ecosystems, provide substrates for epiphytic diatoms, which are food resources for cultured filter feeder organisms. Highly intensive coastal aquaculture degrades coastal environments to decrease seagrass meadows. Therefore, efficient aquaculture management and conservation of seagrass meadows are necessary for the sustainable development of coastal waters. In ria-type bays, non-feeding aquaculture of filter feeders such as oysters, scallops, and ascidians are actively practiced along the Sanriku Coast, Japan. Before the 2011 Great East Japan Earthquake, the over-deployment of oyster culture facilities polluted the bottom environment and formed an hypoxic bottom water layer due to the organic excrements from cultured oysters. The tsunami in 2011 devastated the aquaculture facilities and seagrass meadows along the Sanriku Coast. We mapped the oyster culture rafts and seagrass meadows in Nagatsura-ura Lagoon, Sanriku Coast before and after the tsunami and monitored those and environments after the tsunami by field surveys.

Methods

We conducted field surveys and monitored the environmental parameters in Nagatsura-ura Lagoon every month since 2014. We used high-resolution satellite remote sensing images to map oyster culture rafts and seagrass meadows at irregular time intervals from 2006 to 2019 in order to assess their distribution. In 2019, we also used an unmanned aerial vehicle to analyze the spatial variability of the position and the number of ropes suspending oyster clumps beneath the rafts.

Results

In 2013, the number and distribution of the oyster culture rafts had been completely restored to the pre-tsunami conditions. The mean area of culture raft increased after the tsunami, and ropes suspending oyster clumps attached to a raft in wider space. Experienced local fishermen also developed a method to attach less ropes to a raft, which was applied to half of the oyster culture rafts to improve oyster growth. The area of seagrass meadows has been expanding since 2013. Although the lagoon had experienced frequent oyster mass mortality events in summer before the tsunami, these events have not occurred since 2011. The 2011 earthquake and tsunami deepened the sill depth and widened the entrance to enhance water exchange and improve water quality in the lagoon. These changes brought the expansion of seagrass meadows and reduction of mass mortality events to allow sustainable oyster culture in the lagoon. Mapping and monitoring of seagrass meadows and aquaculture facilities via satellite remote sensing can provide clear visualization of their temporal changes. This can in turn facilitate effective aquaculture management and conservation of coastal ecosystems, which are crucial for the sustainable development of coastal waters.

Automatic detection and quantification of floating marine macro-litter in aerial images: Introducing a novel deep learning approach connected to a web application in R

The threats posed by floating marine macro-litter (FMML) of anthropogenic origin to the marine fauna, and marine ecosystems in general, are universally recognized. Dedicated monitoring programmes and mitigation measures are in place to address this issue worldwide, with the increasing support of new technologies and the automation of analytical processes. In the current study, we developed algorithms capable of detecting and quantifying FMML in aerial images, and a web-oriented application that allows users to identify FMML within images of the sea surface. The proposed algorithm is based on a deep learning approach that uses convolutional neural networks (CNNs) capable of learning from unstructured or unlabelled data. The CNN-based deep learning model was trained and tested using 3723 aerial images (50% containing FMML, 50% without FMML) taken by drones and aircraft over the waters of the NW Mediterranean Sea. The accuracies of image classification (performed using all the images for training and testing the model) and cross-validation (performed using 90% of images for training and 10% for testing) were 0.85 and 0.81, respectively. The Shiny package of R was then used to develop a user-friendly application to identify and quantify FMML within the aerial images. The implementation of this, and similar algorithms, allows streamlining substantially the detection and quantification of FMML, providing support to the monitoring and assessment of this environmental threat. However, the automated monitoring of FMML in the open sea still represents a technological challenge, and further research is needed to improve the accuracy of current algorithms.

The disruptive potential of drones

Drones are increasingly being used in marketing. Yet, despite rapidly growing adoption and incredible versatility, drones hardly feature in marketing research. This oversight is striking as their unique characteristics and the plethora of applications have major consequences for marketing. In particular, we outline how drones have implications for theory and practice in relation to business models, consumers, and society and public policy. We highlight these far-reaching consequences and provide a rich future research trajectory aimed to further theory development on the emerging phenomenon of drones.

Floating marine macro-litter in the North Western Mediterranean Sea: Results from a combined monitoring approach

The aim of the present study was twofold: (i) to validate the drone methodology for floating marine macro-litter (FMML) monitoring, by comparing the results obtained through concurrent drone surveys and visual observations from vessels, and (ii) to assess FMML densities along the North Western Mediterranean Sea using the validated drone surveys. The comparison between monitoring techniques was performed based on 18 concurrent drone/vessel transects. Similar densities of FMML were detected through the two methods (16 items km^-2 from the drone method vs 19 items km^-2 from the vessel-based visual method). The assessment of FMML densities was done using 40 additional drone transects performed over the waters off the Catalan coast. The densities of FMML observed ranged 0-200 items km^-2. These results provide a validation of the use of drones to monitor FMML and contribute to increasing the knowledge about the density of FMML in the North Western Mediterranean Sea.

Image dataset acquired from an unmanned aerial vehicle over an experimental site within El Soldado estuary in Guaymas, Sonora, México

It is well known that remote sensing is a series of procedures which detects physical characteristics of the earth surface by remotely-measuring its reflected and emitted radiation using cameras or sensors. Lately, the increasing use of unmanned aerial vehicles (UAVs) as remote sensing platforms and the development of small-size sensors have resulted in the expansion of continuous monitoring of earth surface at smaller spatial scales. For this reason, the integration of UAV- and consumer-grade cameras can be useful to acquire surface characteristics at plot or footprint scale. This dataset contains 314 aerial images covering an area of aproximately 18,800 m² within the footprint of an Eddy covariance and meterorological station. The monitoring site was deployed at “El Soldado” estuary (27°57′14.4″ N and 110°58′19.2″ W) located in the southern coast of the Mexican State of Sonora. UAV flight path was programmed to flight in autonomous mode with an altitude of 30 m, a velocity of 5 m/s and a frontal and side overlap of 85 and 75% respectively. This dataset was created to support mapping surveys for surface classification and site description. This dataset is aimed to support researchers, stakeholders and general public interested in coastal areas, natural resources management and ecosystem conservation. Finally, this dataset could be also used for those interested in digital photogrammetry and 3D reconstruction as benchmark example to develop high resolution orthomosaics.

Remote sensing of coastal algal blooms using unmanned aerial vehicles (UAVs)

The explosive growth of phytoplankton under favorable conditions in subtropical coastal waters can lead to water discolouration and massive fish kills. Traditional water quality monitoring relies on manual field sampling and laboratory analysis of chlorophyll-a (Chl-a) concentration, which is resources intensive and time consuming. The cloudy weather of Hong Kong also precludes using satellite images for algal blooms monitoring. This study for the first time demonstrates the use of an Unmanned Aerial Vehicle (UAVs) to quantitatively map surface water Chl-a distribution in coastal waters from a low altitude. An estimation model for Chl-a concentration from visible images taken by a digital camera on a UAV has been developed and validated against one-year field data. The cost-effective and robust technology is able to map the spatial and temporal variations of Chl-a concentration during an algal bloom. The proposed method offers a useful complement to traditional field monitoring for fisheries management.

Dataset for recognition of snail trails and hot spot failures in monocrystalline Si solar panels

This article presents a dataset for thermal characterization of photovoltaic systems to identify snail trails and hot spot failures. This dataset has 277 thermographic aerial images that were acquired by a Zenmuse XT IR camera (7–13 μm wavelength) from a DJI Matrice 100 ¹drone (quadcopter). Additionally, our dataset includes the next environmental measurements: temperature, wind speed, and irradiance. The experimental set up consisted in a photovoltaic array of 4 serial monocrystalline Si panels (string) and an electronic equipment emulating a real load. The conditions for images acquisition were stablished in a flight protocol in which we defined altitude, attitude, and weather conditions.

Use of drones in clinical microbiology and infectious diseases: current status, challenges and barriers

BACKGROUND

Drones or unmanned aerial vehicles are autonomous or remotely controlled multipurpose aerial vehicles driven by aerodynamic forces and capable of carrying a payload. Whereas initially used exclusively for military purposes, the use of drones has gradually spread into other areas. Given their great flexibility and favourable costs, the use of drones has also been piloted in various healthcare settings.

OBJECTIVES

We briefly summarize current knowledge regarding the use of drones in healthcare, focusing on infectious diseases and/or microbiology when applicable.

SOURCES

Information was sought through PubMed and extracted from peer-reviewed literature published between January 2010 and August 2019 and from reliable online news sources. The search terms 'drones', 'unmanned aerial vehicles', 'microbiology' and 'medicine' were used.

CONTENT

Peer-reviewed literature on the use of drones in healthcare has steadily increased in recent years. Drones have been successfully evaluated in various pilot programmes and are already implemented in some settings for transporting samples and delivering blood, vaccines, medicines, organs, life-saving medical supplies and equipment. In addition, a promising proof-of-concept 'lab-on-a-drone' was recently presented, as well as several pilot studies showing the benefits of drone use in surveillance and epidemiology of infectious diseases.

IMPLICATIONS

The potential for drone use in clinical microbiology, infectious diseases and epidemiology is vast. Drones may help to increase access to healthcare for individuals that might otherwise not benefit from appropriate care due to remoteness and lack of infrastructure or funds. However, factors such as national airspace legislation and legal medical issues, differences in topography and climates, cost-effectiveness, and community attitudes and acceptance in different cultures and societies currently impede the widespread use of drones. Significant cost savings compared with ground transportation, speed and convenience of delivery, and the booming drone sector will probably drive drone implementation in various areas of medicine in the next 5 years.

Environmental assessment and historic erosion calculation of abandoned mine tailings from a semi-arid zone of northwestern Mexico: insights from geochemistry and unmanned aerial vehicles

Mining is known as one of the primary economic activities where exploitation of minerals and other materials have become essential for human development. However, this activity may represent a risk to the environment, starting from deforestation and ending with production of residues that might contain potentially toxic elements. Tailing deposits from historical mining are an example of waste that may represent an environmental concern when abandoned and exposed to environmental conditions. The town of Nacozari de Garcia, in northwestern Mexico, has three abandoned mine tailings (locally known as tailings I, II, and III) located around the urban area that represent important sources of dust and pollution. Images obtained using unmanned aerial vehicles (UAV) in conjunction with geochemical data are used to assess historic erosion calculation and pollution considering contamination and hazard indexes in tailings II and III. Digital elevation models of abandoned tailings were obtained using photogrammetry with UAV. A total of 37 surficial samples were collected from mine tailings to determine elemental concentrations (As, Cu, Pb, W, Zn) using portable X-ray fluorescence. Higher concentrations were found on samples from mine tailing II. Average concentrations followed the decreasing order of Cu > Zn > W > Pb > As for tailing II, whereas decreasing order of Cu > Zn > W > As > Pb was found for tailing III. Contamination Index (CI) values obtained from tailings II and III represent a low potential of pollution, whereas efflorescent crusts from these tailings represent a high potential of polluting soils and sediments by dust generation. Hazard Average Quotient (HAQ) values on both tailings suggest a very high potential of contamination if fluids infiltrate tailings and interact with surficial water and/or groundwater. Obtained surfaces of mine tailings II and III are 146,216 and 216,689 m², respectively, which represent around 11% of the urbanized area. A loss mass of 321,675 tons was determined for mine tailing II, whereas 634,062 tons for tailing III, accounting for 0.96 million tons of total eroded mass. Since abandonment, calculated erosion rates of 493 t ha^-1 year^-1 (tailing II) and 232 t ha^-1 year^-1 (tailing III) are in agreement with those determined in other mining areas. CI and HAQ indexes provide good estimates of pollution associated with abandoned mine tailings from Nacozari de García. Historic erosion determined in these tailings is an environmental concern since eroded material and polluted water have been incorporated into the Moctezuma River, which feeds several villages, whose major activities include agriculture and livestock raising.

The running kinematics of free-roaming giraffes, measured using a low cost unmanned aerial vehicle (UAV)

The study of animal locomotion can be logistically challenging, especially in the case of large or unhandleable animals in uncontrolled environments. Here we demonstrate the utility of a low cost unmanned aerial vehicle (UAV) in measuring two-dimensional running kinematics from free-roaming giraffes (Giraffa camelopardalis giraffa) in the Free State Province, South Africa. We collected 120 Hz video of running giraffes, and calibrated each video frame using metatarsal length as a constant object of scale. We tested a number of methods to measure metatarsal length. The method with the least variation used close range photography and a trigonometric equation to spatially calibrate the still image, and derive metatarsal length. In the absence of this option, a spatially calibrated surface model of the study terrain was used to estimate topographical dimensions in video footage of interest. Data for the terrain models were collected using the same equipment, during the same study period. We subsequently validated the accuracy of the UAV method by comparing similar speed measurements of a human subject running on a treadmill, with treadmill speed. At 8 m focal distance we observed an error of 8% between the two measures of speed. This error was greater at a shorter focal distance, and when the subject was not in the central field of view. We recommend that future users maximise the camera focal distance, and keep the subject in the central field of view. The studied giraffes used a grounded rotary gallop with a speed range of 3.4–6.9 ms⁻¹ (never cantering, trotting or pacing), and lower duty factors when compared with other cursorial quadrupeds. As this pattern might result in adverse increases in peak vertical limb forces with speed, it was notable to find that contralateral limbs became more in-phase with speed. Considering the latter pattern and the modest maximal speed of giraffes, we speculate that tissue safety factors are maintained within tolerable bounds this way. Furthermore, the angular kinematics of the neck were frequently isolated from the pitching of the body during running; this may be a result of the large mass of the head and neck. Further field experiments and biomechanical models are needed to robustly test these speculations.

Distributed Drone Base Station Positioning for Emergency Cellular Networks Using Reinforcement Learning

Due to the unpredictability of natural disasters, whenever a catastrophe happens, it is vital that not only emergency rescue teams are prepared, but also that there is a functional communication network infrastructure. Hence, in order to prevent additional losses of human lives, it is crucial that network operators are able to deploy an emergency infrastructure as fast as possible. In this sense, the deployment of an intelligent, mobile, and adaptable network, through the usage of drones-unmanned aerial vehicles-is being considered as one possible alternative for emergency situations. In this paper, an intelligent solution based on reinforcement learning is proposed in order to find the best position of multiple drone small cells (DSCs) in an emergency scenario. The proposed solution's main goal is to maximize the amount of users covered by the system, while drones are limited by both backhaul and radio access network constraints. Results show that the proposed Q-learning solution largely outperforms all other approaches with respect to all metrics considered. Hence, intelligent DSCs are considered a good alternative in order to enable the rapid and efficient deployment of an emergency communication network.

Delivery of Automated External Defibrillators (AED) by Drones: Implications for Emergency Cardiac Care

Purpose of Review

Out-of-hospital cardiac arrest (OHCA) remains a significant health problem in the USA and only 8.6% of victims survive with good neurological function, despite advances in emergency cardiac care. The likelihood of OHCA survival decreases by 10% for every minute without resuscitation.

Recent Findings

Automatic external defibrillators (AEDs) have the potential to save lives yet public access defibrillators are underutilized (< 2% of the time) because they are difficult to locate and rarely available in homes or residential areas, where the majority (70%) of OHCA occur. Even when AEDs are within close proximity (within 100 m), they are not used 40% of the time.

Unmanned aerial vehicles: potential tools for use in zoonosis control

Unmanned aerial vehicles (UAVs) have become useful tools to extend human abilities and capacities. Currently UAVs are being used for the surveillance of environmental factors related to the transmission of infectious diseases. They have also been used for delivering therapeutic drugs and life-saving supplies to patients or isolated persons in extreme conditions. There have been very few applications of UAVs for disease surveillance, control and prevention to date. However, we foresee many uses for these machines in the fight against zoonotic disease. The control of zoonoses has been a big challenge as these diseases are naturally maintained in animal populations. Among 868 reported zoonoses, echinococcosis (hydatid disease) is one of the most severe public health problems and listed as one of 17 neglected tropical diseases targeted for control by the World Health Organization. Infected dogs (domestic or stray) play the most important role as definitive hosts in maintaining the transmission of echinococcosis. However, the actual contribution of wild canines to transmission has received little attention as yet, but should certainly not be ignored. This paper summarizes the history of development and application of UAVs, with an emphasis on their potential use for zoonosis control. As an example, we outline a pilot trial of echinococcosis control in the Qinghai-Tibet Plateau region, in which UAVs were used to deliver baits with praziquantel for wildlife deworming. The data suggested that this is a cost-effective and efficient approach to the control of zoonotic diseases transmitted among wild animal populations.

Unmanned aerial vehicles (drones) to prevent drowning

BACKGROUND

Drowning literature have highlighted the submersion time as the most powerful predictor in assessing the prognosis. Reducing the time taken to provide a flotation device and prevent submersion appears of paramount importance. Unmanned aerial vehicles (UAVs) can provide the location of the swimmer and a flotation device.

OBJECTIVE

The objective of this simulation study was to evaluate the efficiency of a UAV in providing a flotation device in different sea conditions, and to compare the times taken by rescue operations with and without a UAV (standard vs UAV intervention). Several comparisons were made using professional lifeguards acting as simulated victims. A specifically-shaped UAV was used to allow us to drop an inflatable life buoy into the water.

RESULTS

During the summer of 2017, 28 tests were performed. UAV use was associated with a reduction of time it took to provide a flotation device to the simulated victim compared with standard rescue operations (p < 0.001 for all measurements) and the time was reduced even further in moderate (81 ± 39 vs 179 ± 78 s; p < 0.001) and rough sea conditions (99 ± 34 vs 198 ± 130 s; p < 0.001). The times taken for UAV to locate the simulated victim, identify them and drop the life buoy were not altered by the weather conditions.

CONCLUSION

UAV can deliver a flotation device to a swimmer safely and quickly. The addition of a UAV in rescue operations could improve the quality and speed of first aid while keeping lifeguards away from dangerous sea conditions.

Unmanned aerial vehicles for the assessment and monitoring of environmental contamination: An example from coal ash spills

Unmanned aerial vehicles (UAVs) offer new opportunities to monitor pollution and provide valuable information to support remediation. Their low-cost, ease of use, and rapid deployment capability make them ideal for environmental emergency response. Here we present a UAV-based study of the third largest coal ash spill in the United States. Coal ash from coal combustion is a toxic industrial waste material present worldwide. Typically stored in settling ponds in close proximity to waterways, coal ash poses significant risk to the environment and drinking water supplies from both chronic contamination of surface and ground water and catastrophic pond failure. We sought to provide an independent estimate of the volume of coal ash and contaminated water lost during the rupture of the primary coal ash pond at the Dan River Steam Station in Eden, NC, USA and to demonstrate the feasibility of using UAVs to rapidly respond to and measure the volume of spills from ponds or containers that are open to the air. Using structure-from-motion (SfM) imagery analysis techniques, we reconstructed the 3D structure of the pond bottom after the spill, used historical imagery to estimate the pre-spill waterline, and calculated the volume of material lost. We estimated a loss of 66,245 ± 5678 m³ of ash and contaminated water. The technique used here allows rapid response to environmental emergencies and quantification of their impacts at low cost, and these capabilities will make UAVs a central tool in environmental planning, monitoring, and disaster response.

Automatic identification of agricultural terraces through object-oriented analysis of very high resolution DSMs and multispectral imagery obtained from an unmanned aerial vehicle

Agricultural terraces are features that provide a number of ecosystem services. As a result, their maintenance is supported by measures established by the European Common Agricultural Policy (CAP). In the framework of CAP implementation and monitoring, there is a current and future need for the development of robust, repeatable and cost-effective methodologies for the automatic identification and monitoring of these features at farm scale. This is a complex task, particularly when terraces are associated to complex vegetation cover patterns, as happens with permanent crops (e.g. olive trees). In this study we present a novel methodology for automatic and cost-efficient identification of terraces using only imagery from commercial off-the-shelf (COTS) cameras on board unmanned aerial vehicles (UAVs). Using state-of-the-art computer vision techniques, we generated orthoimagery and digital surface models (DSMs) at 11 cm spatial resolution with low user intervention. In a second stage, these data were used to identify terraces using a multi-scale object-oriented classification method. Results show the potential of this method even in highly complex agricultural areas, both regarding DSM reconstruction and image classification. The UAV-derived DSM had a root mean square error (RMSE) lower than 0.5 m when the height of the terraces was assessed against field GPS data. The subsequent automated terrace classification yielded an overall accuracy of 90% based exclusively on spectral and elevation data derived from the UAV imagery.