Search

Any operation scenario for unmanned aerial vehicles also known as drones in real world requires resilient wireless link to guarantee capacity and performance for users, which can only be achieved by obtaining detailed knowledge about the propagation channel. Thus, this study investigates the largescale channel propagation statistics for the line of sight air–to–air (A2A) drone communications to estimate the path loss exponent (PLE). We conducted a measurement campaign at 5.8 GHz, using low cost and light weight software defined radio based channel sounder which is developed in this study and then further integrated on commercially available drones. To determine the PLE, frequency-based, time-based and time–frequency based methods are utilized. Accuracy of the proposed method is verified under ideal conditions in a well-isolated anechoic chamber before the actual measurement campaign to verify the performance in a free space path loss environment. The path loss exponent for A2A wireless drone channel is estimated with these verified methods.

The paper deals with the calibration of a non-metric digital camera Nikon EOS 6D with a 50 mm lens that could be adapted as a potential UAV sensor for the purposes of aerial inspections. The determination of the internal orientation parameters and the image errors of the non-metric digital camera involved self-calibration with Agisoft Metashape software solving the network of the images obtained from different test fields: a chessboard field, a professional laboratory field and a spatially diverse research area. The results of the control measurement for the examined object distance of 6 meters do not differ significantly. The RMSE from the control measurement for the second analyzed object distance of 15 meters was calculated on the basis of the internal orientation elements. The images from the laboratory field, the spatial test area and the chessboard field were used, and the obtained results amounted to 7.9, 9.9 and 11.5 mm, respectively. The conducted studies showed that in the case of very precise photogrammetric measurements performed by means of the Nikon EOS 6D camera equipped with a 50 mm lens, it is optimal to conduct calibration in a laboratory test field. The greatest RMSE errors were recorded for the control images with the elements of the internal camera orientation calculated on the basis of the chessboard area. The results of the experiments clearly show a relation between the accuracy of the Nikon EOS 6D camera calibrations and the percentage of the frame area filled with the test field. This explains why the weakest calibration results were obtained from the chessboard test field.

The future of mobile and internet technologies are manifesting advancements beyond the existing scope of science. The concepts of automated driving, augmented-reality, and machine-type-communication are quite sophisticated and require an elevation of the current mobile infrastructure for launching. The fifth-generation (5G) mobile technology serves as the solution, though it lacks a proximate networking infrastructure to satisfy the service guarantees. Multi-access Edge Computing (MEC) envisages such an edge computing platform. In this survey, we are revealing security vulnerabilities of key 5G-based use cases deployed in the MEC context. Probable security flows of each case are specified, while countermeasures are proposed for mitigating them.

The purpose of this article is to reduce the structural weight and drag of an unmanned aerial vehicle (UAV) or drone while increasing its endurance. To achieve a high strength to weight ratio, Finite Element Analysis is used to study the structural strength characteristics of UAV frames. A computational fluid dynamic analysis (CFD) is performed for different angles of attack and vehicle speeds to estimate the drag coefficient using the k-e turbulence model. The analysis results show that the designed UAV vehicle has excellent performance characteristics and stability at 5° AoA and 3 m/sec. This article outlines the overall design of the unmanned aerial vehicle, which was created using the CATIA V6 platform. COMSOL 5.6 software is used for structural and CFD analysis.

Geoconservation is, at its foundation, a grass-roots movement with geoheritage represented by geosites containing the most scientifically significant and valuable geodiversity elements. Problems arise in the assessment and communication of inventory due in part to inconsistent and traditionally time-consuming, ‘snapshot’ assessments that are difficult to spatially monitor. The case study of kunanyi/Mount Wellington and the encompassing IUCN Category II Wellington Park Reserve (18,250 ha) (42°53′24″ S 147°13′48″ E, Tasmania, Australia) was chosen to explore the complexities of geosite and geodiversity site assessment, detection and communication. Using digital tools, we revised a 25-year-old snapshot inventory, configuring the ESRI ‘Collector for ArcGIS’ app for in-field data collection. Putative geosite and geodiversity site attributes were assessed for scientific value, potential touristic use, and potential educational use, using the Brilha (2016) method. Additional digital tools supported spatially accurate, engaging and interactive online inventory. Our findings suggested that many of the putative geosites in the park had low or moderate scientific values, but higher additional educational or touristic use values, especially in the urban-facing park zones. Though site degradation risk was low-moderate, sites in closer proximity to City of Hobart might experience additional impacts from visitation. The Wellington Park is a significant protected area that aims to tell an important story about the evolution of the periglaciated terrain and the endemic fauna and flora that depend upon it. In this sense, the possibility that not all putative geosites have high scientific value (and instead, might be better classed as geodiversity sites) is of limited concern, because the myriad geodiversity elements and additional value rankings (including 50% being highly ‘representative’ elements) provide an opportunity for all who visit the park to observe a coherent story about Tasmania in an easily accessible location. The opportunities realised in the creation of the digital inventory and assessment process remedy many issues that currently hamper practical Geoconservation, improving cost, consistency and standardisation of the inventory assessment and the quality of geotouristic and educational products. This digital approach could assist protected area managers and geoconservationists to monitor, protect and communicate inventory over the long-term.

Flying Ad-hoc Network (FANET) is a new class of Mobile Ad-hoc Network in which the nodes move in three-dimensional (3-D) ways in the air simultaneously. These nodes are known as Unmanned Aerial Vehicles (UAVs) that are operated live remotely or by the pre-defined mechanism which involves no human personnel. Due to the high mobility of nodes and dynamic topology, link stability is a research challenge in FANET. From this viewpoint, recent research has focused on link stability with the highest threshold value by maximizing Packet Delivery Ratio and minimizing End-to-End Delay. In this paper, a hybrid scheme named Delay and Link Stability Aware (DLSA) routing scheme has been proposed with the contrast of Distributed Priority Tree-based Routing and Link Stability Estimation-based Routing FANET’s existing routing schemes. Unlike existing schemes, the proposed scheme possesses the features of collaborative data forwarding and link stability. The simulation results have shown the improved performance of the proposed DLSA routing protocol in contrast to the selected existing ones DPTR and LEPR in terms of E2ED, PDR, Network Lifetime, and Transmission Loss. The Average E2ED in milliseconds of DLSA was measured 0.457 while DPTR was 1.492 and LEPR was 1.006. Similarly, the Average PDR in %age of DLSA measured 3.106 while DPTR was 2.303 and LEPR was 0.682. The average Network Lifetime of DLSA measured 62.141 while DPTR was 23.026 and LEPR was 27.298. At finally, the Average Transmission Loss in dBm of DLSA measured 0.975 while DPTR was 1.053 and LEPR was 1.227. - Key Research and Development Program of Zhejiang Province - grant No. 2020C01076. - National Natural Science Foundation of China - grant No. 62072403.

A 3D laser scanning system can achieve the precision of millimetre level in deformation examination of a power line tower; however, it suffers from the high cost of equipment and difficult onsite installation. The Tilt Photography with Unmanned Aerial Vehicle (TP‐UAV) is a relatively lower cost system that offers a more convenient way of 3D measurement; however, with a trade‐off of lower measurement accuracy. In order to take advantage of both technologies and improve the measurement accuracy of the TP‐UAV system, in this research, a 3D laser scanning system is applied as a calibration means for the TP‐UAV to explore the possibility of rapid measurement of the deformation in transmission facilities. A data representation model is proposed for the calibration of the parameters of the TP‐UAV system to make use of the accuracy of the 3D laser scanning, and the systematic error of the TP‐UAV system can be corrected to improve the measurement accuracy by 35%.

The metric documentation of architectural complexes requires today the use of several integrated survey methodologies. This need is an answer to the morphology of the object such as dimension, geometry, inaccessible areas and urban context. These properties inhibit the use of single surveying techniques and force the integration of Geomatics tools. In addition, the metric documentation of Cultural heritage objects not always requires uniform accuracy and resolution, therefore the integration of different surveying methodologies and techniques become the only effective solution both from a technical and economic point of view. The integration, that is today adopted as normal strategy, allows also the better understanding of the benefits which can arise to speed up the metric documentation of Cultural Heritage objects and the benefits that each of the possible surveying techniques can have thanks to the integration of the different potentialities. This study starting from an integrated survey, performed whit a combined use of Mobile Mapping System (MMS), Unmanned Aerial Vehicles (UAV) and Terrestrial Laser Scanner (TLS) and show the results of the comparisons between the possible achievable accuracies by using a correct integration between the different used technologies and the ones achievable by using the same techniques as independent tools.The case study is the architectural complex of the Ducal Palace in Gubbio (Italy), located upstream of the most important town square facing the cathedral in a very complex but realistic urban context.

Historical maps represent an important source of geographical information. The changes occurred over time can be extrapolated from them, especially if their geometric accuracies match those achievable with modern survey techniques. An 1820 map belonging to the Gregorian Cadastre provides the position of seven hermitages belonging to the monastery of Fara in Sabina (Italy). Just three of them are nowadays visible, while the others may have been covered by thick vegetation or been destroyed during the Second World War. The paper proposes the integration of geomatic techniques for the localization of the lost hermitages. To do so, Structure from Motion (SfM) algorithms were applied to UAV imagery to produce an orthophoto of the area. In addition, a GNSS survey was carried out using a professional and a low-cost receiver to correctly georeference the photogrammetric products. An accuracy assessment was then performed to evaluate the performance of the u-blox board in real applications. The accuracies obtained with the low-cost receiver indicates a possible more widespread utilization of these new devices. Subsequently, the comparison between the orthophoto and the cadastral map have been detailed. A weak correspondence between the position of the hermitages in the two maps have been observed. On the other side, the comparison led to the localization of two lost hermitages, with the other two being still undiscovered. This study has opened the door to an enhancement process of the monastery and to the rediscovery of the religious values of the hermitages.

The Isabel II dam is a monumental hydraulic structure built in the middle of the nineteenth century in Spain. In this study, unmanned aerial vehicle (UAV) photogrammetry was used as a data acquisition technique to carry out a survey of the dam’s current state and its surrounding constructions. The point cloud obtained by the photogrammetric process, together with the collected historical in-formation, served as the basis to generate an historic building information model (HBIM) that is the central core containing all the graphical, structural and archaeological information. The HBIM was validated by means of the As-Built for Autodesk Revit®-FARO® plug-in, and shows the high accuracy obtained with respect to the point cloud. The results show that with this methodology it is possible to obtain models representative of reality with an accuracy of ± 0.05 m. In addition, in order to improve the visualization, texture adjustments are made to obtain a photorealistic rendering of the model.

Dynamic soaring is an emerging flight range-extension technology that effectively reduces UAV's energy consumption by deriving wind energy from lateral gradient wind fields. Comparing with the small UAV's near the surface, the application of dynamic soaring technology in the high-altitude long-endurance flight requires the additional consideration of the influence of sustained side wind, the influence of the sideslip angle cannot be ignored. This puts higher requirements on the flight dynamics model. In this paper, the dynamic model for the high-altitude dynamic soaring based on the six-degree-of-freedom equation is modeled to replace the traditional mass point model; the energy change principle of the high-altitude dynamic gliding is derived; the effect of the high-altitude wind field on the dynamic soaring UAV is analyzed; and the way to get optimal wind field energy acquisition and energy saving efficiency are analyzed. The results show that the dynamics model based on the six-degree-of-freedom equation can more realistically reflect at high altitude; the application of dynamic soaring can effectively improve the range of the high-altitude UAV; the wind direction at high-altitude wind field has a significant effect on the dynamic soaring efficiency.

The agricultural sector is experiencing a new revolution, giving birth to the so‐called Agriculture 4.0 paradigm. It brings digital technologies in the field to support the farmers' work, enhancing the productivity of farms. In this chapter, attention is focused on the role that both Internet of things ( IoT ) and Unmanned Aerial Vehicle ( UAVs ) can play in this regard, whether used in a joint manner or not. We analyze the work being done both in recent research projects and in the literature on those topics, taking into account the role of long‐range wireless communications to enable such scenarios, and the potential of 5G and the upcoming multi‐access edge computing ( MEC ) technology, especially in rural areas, where lack of connectivity still hampers the process of digital transformation.

This study focuses on detecting vehicle crossings (events) with ground-based interferometric radar (GBR) time series data recorded at bridges in the course of critical infrastructure monitoring. To address the challenging event detection and time series classification task, we rely on a deep learning (DL) architecture. The GBR-displacement data originates from real-world measurements at two German bridges under normal traffic conditions. As preprocessing, we only apply a low-pass filter. We develop and evaluate a one-dimensional convolutional neural network (CNN) to achieve a solely data-driven event detection. As a baseline machine learning approach, we use a Random Forest (RF) with a selected feature-based input. Both models’ performance is evaluated on two datasets by focusing on identifying events and pure bridge oscillations. Generally, the event classification results are promising, and the CNN outperforms the RF with an overall accuracy of 94.7% on the test subset. By relying on an entirely unknown second dataset, we focus on the models’ performances regarding the distinction between events and decays. On this dataset, the CNN meets this challenge successfully, while the feature-based RF classifies the majority of non-event decays as events. To sum up, the presented results reveal the potential of a data-driven DL approach concerning the detection of bridge crossing events in GBR-based displacement time series data. Based on such an event detection, a prospective assessment of bridge conditions seems feasible as an extension to previous structural health monitoring approaches.

Purpose of Review A lot of research into decentralised, state-based conflict detection and resolution, or detect and avoid algorithms has been executed. This paper explains the essential properties of state-based conflict detection and reviews the work in the context of applications for not only manned but also unmanned aerial vehicles, where this might be applied relatively soon. Recent Findings Lately, based on several reviews of a variety of published algorithms, a selection has been implemented and simulated in extremely high traffic densities for comparison. Summary The modified voltage potential has been surprisingly efficient, even compared with more complex algorithms or adaptations, as is apparent from looking at macroscopic metrics like domino effect, efficiency and safety. This indicates that to this date, it is so far the most suitable algorithm for the detect and avoid role for unmanned aerial vehicles in urban airspaces, or other areas where a high density is expected.

Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.

The possibility of equipping UAVs with lightweight GNSS receivers in order to estimate the camera position within a photogrammetric block allows for a reduction of the number of Ground Control Points (GCP), saving time during the field work and decreasing operational costs. Additionally, this makes it possible to build photogrammetric models even in morphologically complex areas or in emergency situations. This work is proposing a non-intrusive and low-cost procedure to retrieve the coordinates of the camera projection centre with decimetric accuracy. The method was designed and tested with the quadcopter DJI Matrice 210 V2 drone equipped with a DJI ZENMUSE X5S camera and an Emlid reach M, a low-cost, single-frequency (L1) GNSS receiver. GNSS observations are post-processed in PPK in order to obtain the UAV trajectory. Synchronization between the camera and the GNSS receiver is achieved by looking at the camera triggering timestamps in flight telemetry data, without requiring an electronic connection between camera and the GNSS that may be troublesome with commercial UAVs. Two surveys were carried out, respectively to calibrate and validate the procedure. The validation test evidenced the possibility of obtaining the coordinates of the camera projection centres with decimetric accuracy. The centre of projections can then be employed for GNSS-assisted aerial triangulation as input of the bundle block adjustment. Provided that at least one GCP is used, it is possible to reach centimetric accuracy on the ground.

The safety assessment process tailored to Remotely Piloted Aircraft Systems (RPAS) applications has been discussed briefly. The modified Hazard Reference System for STANAG 4703 Category UAV including Non Safety Effect (NSE) severity category has been proposed. The Functional Hazard Analysis (FHA) for small Unmanned Aerial Vehicle (UAV) Structural Health Monitoring (SHM) system has been conducted.

A fundamental step of UAV photogrammetric processes is to collect Ground Control Points (GCPs) by means of geodetic-quality GNSS receivers or total stations, thus obtaining an absolutely oriented model with a centimetric accuracy. This procedure is usually time-consuming, expensive and potentially dangerous for operators who sometimes need to reach inaccessible areas. UAVs equipped with low-cost GNSS/IMU sensors can provide information about position and attitude of the images. This telemetry information is not enough for a photogrammetric restitution with a centimetric accuracy, but it can be usefully exploited when a lower accuracy is required. The algorithm proposed in this paper aims at improving the quality of this information, in order to introduce it into a direct-photogrammetric process, without collecting GCPs. In particular, the estimation of an optimal trajectory is obtained by combining the camera positions derived from UAV telemetry and from the relative orientation of the acquired images, by means of a least squares adjustment. Then, the resulting trajectory is used as a direct observation of the camera positions into a commercial software, thus replacing the information of GCPs. The algorithm has been tested on different datasets, comparing the classical photogrammetric solution (with GCPs) with the proposed one. These case-studies showed that using the improved trajectory as input to the commercial software (without GCPs) the reconstruction of the three-dimensional model can be improved with respect to the solution computed by using the UAV raw telemetry only.

Currently in Transylvania there are over 600 castles, considered monuments belonging to the world or national heritage. Some of them have disappeared, some are in an advanced degradation, the vast majority being in different stages of degradation, but recoverable, through very expensive investments. The first condition for them to start a program of recovery and put them again in the tourist and cultural circuit is to know exactly the state in which they are, to evaluate the costs. The development of geomatics technologies now allows for the high fidelity assessment of this aspect. These included Global Navigation Satellite System (GNSS) - Total Stations + Levels precision, terrestrial and aerial photogrammetry, laser scanners with fixed stations, for each presenting technical data and products analyzed sequentially and corroborated-complementary. The purpose of the entire action was to establish a Workflow as dedicated as possible to the requests of the specialists involved in such projects, architects, builders, restorers, historians, cultural people, etc. The paper can highlight a model of good practices in this field, the researches continuing, by consulting the beneficiaries of products from the range offered through these activities.

This paper presents a human-robot interaction (HRI) study of a dedicated Mission Specialist interface for performing telemanipulation tasks using a small unoccupied aerial vehicle (UAV). Current literature suggests that the successful completion of aerial manipulation tasks in real-world environments requires human input due to challenges in autonomous perception and control. Visual information of the remote environment in a telemanipulation interface can significantly affect performance under direct control; however, the effects of interface visualizations on task performance have not been studied for UAV telemanipulation. This work evaluated the effects of interface viewpoint on aerial manipulation task performance. The interfaces evaluated in this study included video streams from cameras located onboard the UAV, including: (i) a manipulator egocentric view, (ii) a manipulator exocentric view, and (iii) a combination of egocentric and exocentric views. A total of 36 participants completed three different manipulation tasks using all three interface conditions. The observations and results showed that both the exocentric and mixed view configurations contributed to improved task performance over an egocentric-only interface. Further, this study resulted in data regarding view use, view effectiveness, and task type that can be used for further developing interfacing for aerial manipulators that change and adapt to the environment and task.

UAS with inflatable wings (UASWIW) is relatively a novel and complex arena and more to that is its certification process, which is more complex as well as challenging. This paper broadly presents a three-tier architecture to identify the potential hazards associated with UASWIW and proposes the necessary certifications required according to 14CFR. For the sake of simplicity, only a few aerodynamic potential hazards are taken into account and evaluated accordingly. The proposed analytic approach completely satisfies the rules and guidelines controlled by the Federal Aviation Administration (FAA) and would prove a milestone for future researchers who wish to pursue in the same arena.

It had been predicted that by 2020, nearly 26 billion devices would be connected to the Internet, with a big percentage being vehicles. The Internet of Vehicles (IoVa) is a concept that refers to the connection and cooperation of smart vehicles and devices in a network through the generation, transmission, and processing of data that aims at improving traffic congestion, travel time, and comfort, all the while reducing pollution and accidents. However, this transmission of sensitive data (e.g., location) needs to occur with defined security properties to safeguard vehicles and their drivers since attackers could use this data. Blockchain is a fairly recent technology that guarantees trust between nodes through cryptography mechanisms and consensus protocols in distributed, untrustful environments, like IoV networks. Much research has been done in implementing the former in the latter to impressive results, as Blockchain can cover and offer solutions to many IoV problems. However, these implementations have to deal with the challenge of IoV node’s resource constraints since they do not suffice for the computational and energy requirements of traditional Blockchain systems, which is one of the biggest limitations of Blockchain implementations in IoV. Finally, these two technologies can be used to build the foundations for smart cities, enabling new application models and better results for end-users.

Open-pit mines generally have operational problems such as puddling and inappropriate water flow over haul roads, particularly if located in areas with high rainfall indices. These situations increase truck cycle times, promote rapid deterioration of haul-road wearing-course material, reduce productivity due to downtime and increase road maintenance. In addition, operational costs are raised as the frequency of truck maintenance and tire failures also increase. The use of a high-resolution three-dimensional elevation model, created based on Unmanned Aerial Vehicle (UAV) photogrammetry, has been shown to be an effective technique to detect anomalies in a fast and precise way. With the proposed approach, it is possible to diagnose haul-road conditions after rainfall or to anticipate the potential occurrence of such anomalies before they become a greater problem. This diagnosis can then be used to prioritize maintenance activities in open-pit mines. To describe the methodology, a case study is presented demonstrating and validating the results obtained. Las minas a cielo abierto generalmente tienen problemas operativos, como empozamiento y flujo de agua no apropiados en los caminos de acarreo, principalmente en minas ubicadas en áreas con altos índices de lluvia. Estas situaciones aumentan los tiempos de ciclo de los camiones, promueven el rápido deterioro de las carreteras de transporte ocasionando la reducción de productividad debido al aumento del tiempo de inactividad y de la frecuencia del mantenimiento de las carreteras. Además de eso, los costos operativos se incrementan una vez que aumenta la frecuencia del mantenimiento de los camiones y desgaste de los neumáticos. El uso de un modelo de elevación tridimensional de alta resolución, creado a partir fotogrametría de datos de vehículos aéreos no tripulados (UAV), ha demostrado ser una técnica eficaz para detectar anomalías de forma rápida y precisa. Con el enfoque propuesto, es posible diagnosticar las condiciones de los caminos de acarreo después de la lluvia, o anticipar el potencial de ocurrencia de tales anomalías antes de que se conviertan en un problema mayor. Este diagnóstico se puede utilizar para priorizar las actividades de mantenimiento en minas a cielo abierto. Para describir la metodología, se presenta un estudio de caso que demuestra y valida los resultados obtenidos.

The present fuel cell technology is under considerations as a potential power source for Unmanned Aerial Vehicles. Fuel cells are an electrochemical power plant that takes hydrogen and oxygen as inputs and produces electricity, water and heat as outputs. Most of the global hydrogen production is from non-renewable fossil fuels. Therefore, this paper investigates how to save hydrogen fuel consumption and operate at high efficiency in the fuel cell/battery hybrid system to power a small Aircraft. We achieved that by working on the power management of the fuel cell/battery hybrid propulsion system for small UAV by using the fuzzy logic controller and charging up the batteries. The hybrid propulsion system consists of a 1.2kW PEM fuel cell, three 12V batteries, DC/DC converters, and an electric engine. The fuzzy logic controls the batteries' output powers through the bidirectional DC/DC converter. It will help maintain the fuel cell operates at an optimal point with high efficiency as the main power supply for different flight phases to achieve the desired power.

Focusing on the aerodynamic characteristics of the blended wing body (BWB) aircraft with boundary layer ingestion(BLI) distributed propulsion system; the influences of propulsion system parameters under the condition of cruise and takeoff are studied. Firstly, based on the momentum source method (MSM), the NASA ducted propeller model is simulated, which verifies the reliability of the numerical method in this paper. Then, by using the method of structural grid and S-A turbulence model to solve the Reynolds averaged Navier-Stokes (RANS) equation, the aerodynamic characteristics of the BLI UAV model with D80 ducted fan in cruise state are numerically calculated. It is proved that the advantage of the BLI distributed propulsion system is superior in increasing lift. And the aerodynamic characteristics of the BLI UAV with different propulsion system parameters are compared. At last, the aerodynamic effect of ducted fan thrust on the BLI UAV is carried out. The results show that, due to the suction function of the BLI distributed propulsion system, the air flow velocity near the BWB fuselage is effectively accelerated, and the flow along the spanwise is restrained, which improves the lift coefficient about 16% and lift-to-drag ratio about 10%. Under the condition of equal thrust, the D80 ducted fan brings larger load of the propeller, which makes the static pressure at the inlet and outlet smaller. Compared with D150 ducted fan, the lift-to-drag ratio is increased by 15%. When aircraft takes off, increasing the thrust of the ducted fan can reduce the possibility of flow separation on the upper surface of the fuselage, which is conducive to the safety.

We investigated the outage performance of non-orthogonal multiple access (NOMA) in satellite-terrestrial systems which contain hardware impairments. An unmanned aerial vehicle (UAV) was implemented to forward signals from a satellite to users on the ground. A two-user model was applied to achieve spectral efficiency. In practical, real-life scenarios, the UAV and ground users encounter issues with imperfect hardware. We examined the performance gap between two users experiencing practical problems such as hardware impairment and imperfect successive interference cancellation (SIC). To implement a practical scenario, Shadow-Rician fading was adopted in the satellite links, and Rician fading was employed in the terrestrial links for ground users. In the main results, we derived the closed-form expression of the outage probability, and to evaluate the system performance of two NOMA users, we obtained the approximate expressions for high signal-to-noise ratios (SNR). Finally, we produced Monte-Carlo simulations to verify the analytical expressions and demonstrate the effect of the main system parameters, such as the number of transmit antennas on the satellite, transmit SNR, and level of hardware impairment on the system performance metric. Web of Science 9 117937 117925

In this work, the results of Ultra-Wideband air-to-ground measurements carried out in a real-world factory environment are presented and discussed. With intelligent industrial deployments in mind, we envision a scenario where the Unmanned Aerial Vehicle can be used as a supplementary tool for factory operation, optimization and control. Measurements address narrow band and wide band characterization of the wireless radio channel, and can be used for link budget calculation, interference studies and time dispersion assessment in real factories, without the usual limitation for both radio terminals to be close to ground. The measurements are performed at different locations and different heights over the 3.1-5.3 GHz band. Some fundamental propagation parameters values are determined vs. distance, height and propagation conditions. The measurements are complemented with, and compared to, conventional ground-to-ground measurements with the same setup. The conducted measurement campaign gives an insight for realizing wireless applications in smart connected factories, including UAV-assisted applications.

Unmanned aerial vehicle (UAV) has been increasingly used in a wide range of commercial and civilian applications. As an advanced cyber-physical system, UAVs are exposed to a wide range of cyberattacks. This paper first surveys existing literature for different cyberattacks. Then, we classify these attacks based on their attack entry points, which can be radio channels, messages or on-board systems. There are six classes of UAV cyberattacks, namely channel jamming, message interception, message deletion, message injection, message spoofing and on-board system attack. In the existing literature, there is no survey focusing on UAV cyberattack countermeasures. To close this gap, we survey existing countermeasures for the six attack classes. A comprehensive review of countermeasures is important because countermeasure may not be exclusive to an attack. Knowing a wide range of existing countermeasures can prepare us against existing and new cyberattacks. We classify countermeasure into three classes, namely prevention, detection and mitigation. Prevention countermeasures stop a cyberattack from starting. When prevention countermeasures fail, detection countermeasures alert UAV operator of an attack. After detecting an attack, mitigation countermeasures limits the damage. Following the survey, we further discuss the open challenges in developing countermeasures and propose some potential future research works.

The widespread use of Unmanned Aerial Vehicles (UAV) has made the security and computing resource application efficiency of UAV a hot topic in the security field of the Internet of Things. In this paper, an optimized lightweight identity security authentication protocol, Optimized Identity Authentication Protocol (ODIAP) is proposed for Internet of Drones (IoD) networks. The protocol is targeted to the security risks faced by IoD networks, and proposes the security authentication mechanism consisting of 3 phases and 7 authentication processes, which enables the protocol has both forward and backward security, and can resist mainstream network attacks. Meanwhile, this paper fully considers the computational load and proposes the identity information generation and verification method based on the Chinese residual theorem, which reduces the computational load of resource-constrained nodes and shifts the complex computational process to server nodes with abundant computational resources. Moreover, after security protocol analysis and tool verification based on the automated security verification tool Proverif, the protocol in this paper has complete security. At the same time, the performance analysis and comparison with other mainstream protocols shows that this protocol effectively optimizes the use of computing resources without compromising security.

The term Internet of Things (IoT) has emerged in recent decades because this network revolutionizes almost every aspect of our daily life, including products such as smartphones and intelligent vehicles, and crucial tasks such as precision agriculture and environmental monitoring. Myriads of communication technologies have been developed to fulfill the two main features of the IoT: long-range transmissions and low power consumption. Long-range (LoRa) has become one of the vital parts of IoT communication. In this study, the real-time deployments of an unmanned aerial vehicle (UAV)-based LoRa communication network are systematically reviewed, with a focus on the communication setup and its reported performance. Importantly, the UAV-based LoRa communication network has a low bit rate connectivity to ensure the high reliability of connections, especially in applications that require long transmission ranges. This study provides recommendations for researchers on what research perspectives need to be explored when implementing UAVs for IoT-based LoRa communication. This study also describes publication trends related to UAV-based LoRa communication networks. A supplementary Excel file that contains the reported publications on UAV-based LoRa communication networks is included to show this publication trend.

Drones are of different shapes, sizes, characteristics, and configurations. It can be classified for the purpose of its deployment, either in the civilian or military domain. The earliest usage of drones was totally for military purposes, but manufacturers promptly tested it for civilian fields like border surveillance, disaster relief, pipeline inspection, and rescue. Drone manufacturing, equipment installation, power supply, multi-rotor system, and embedded sensors are not the pressing issues for researchers of drone technologies. What is required is to utilize a drone for a complex operation and ensure secured data broadcasting among drones with the ground control station via a self-organized, resourceless, and infrastructureless network (Flying Ad Hoc Networks (FANETs)). These operations are no less important in areas like an emergency, search and rescue operations, border surveillance, and physical phenomenon sensing for the end-user. However, it is not without some challenges for the researchers keeping in view the threats these operations are exposed to concerning security issues and challenges. To overcome these challenges, the researchers have to strive towards a secured drone operation by developing a robust and lightweight key agreement protocol for IoD deployment civilian drones. Consequently, the researchers in this study have attempted to design a key agreement scheme for the IoD deployment of civilian drones. The security of the proposed key agreement scheme has been verified by ProVerif2.02 and Real-Or-Random (ROR) model, while its performance scenario has been tackled by considering storage, computation, and communication overheads analysis. In comparing the proposed framework with prior protocols, it has been demonstrated that the scheme is quite efficient and may be recommended for operations in a given IoD environment.

This paper presents drone classification at millimeter-wave (mmWave) radars using the deep learning (DL) technique. The adoption mmWave technology in radar systems enables better resolution and aid in detecting smaller drones. Using radar cross-section (RCS) signature enables us to detect malicious drones and suitable action can be taken by respective authorities. Existing drone classification converts the RCS signature into images and then performs drone classification using a convolution neural network (CNN). Converting every signature into an image induces additional computation overhead; further CNN model is trained considering fixed learning rate. Thus, when using CNN-based drone classification under a highly dynamic environment exhibit poor classification accuracy. This paper present an improved long short-term memory (LSTM) by introducing a weight optimization model that can reduce computation overhead by not allowing the gradient to not flow through hidden states of the LSTM model. Further, present adaptive learning rate optimizing (ALRO) model for training the LSTM model. Experiment outcome shows LSTM-ALRO achieves much better drone detection accuracies of 99.88% when compared with the existing CNN-based drone classification model.

Due to the tremendous advancement in interactive multimedia systems and technologies, security has become a major aspect. Advanced technology can be utilized for hacking autonomous systems like Unmanned Aerial vehicles (UAVs) in different ways such as spoofing and jamming. It can be spoofed by the injection of fake signals into the sensors. For the protection of the UAVs from the Global Positioning System (GPS) signal spoofing attack, we propose a new methodology by incorporating a machine learning (ML) algorithm such as Support Vector Machine (SVM). A detailed analysis of several learning algorithms is also carried out to choose the suitable learning algorithm for the proposed work. Once the suitable ML algorithm is selected, we perform K-fold analyses to develop other learning models by choosing different values of K-folds thus we called them K-learning models. The purpose of developing K-learning models is to apply voting techniques to the developed K-learning models. Moreover, the signal features used in the proposed work are jitter, jitter (absolute), jitter (local), jitter (RAP), jitter (ppq5), shimmer, shimmer (local), shimmer (dB), shimmer (apq3), shimmer (apq5) and frequency modulation. Based on these features of the signal, we train our proposed model for the detection of counterfeit GPS signals. To gauge the performance of the proposed model, we perform different experimentation analyses such as accuracy, precision, recall, and F1-score. The results and analysis show the effectiveness of the proposed work over existing techniques.

Fertilizer misapplications have induced widespread environmental deteriorations, climatic catastrophes, and economic losses; meanwhile, the Precision Agriculture (PA) endorsements have been influential in alleviating these issues. This study intended to tackle the fertilizer consumption inefficiencies by utilizing non-destructive remote sensing technologies, soil macronutrient distribution analysis, and a deep learning model. Specifically, an Unmanned Air Vehicle (UAV) was used in a cornfield to capture the plant's reflectance information for retrieving the Normalized Difference Vegetation Index (NDVI) during the vegetative and reproductive growth stages. Consequently, the field's soil samples were examined for their Nitrogen, Phosphorus, Potassium, and Carbon (NPKC) macronutrient constituencies. Finally, a Convolutional Neural Network-Regression model was developed to predict infield NPKC spatiotemporal variations in soil using the NDVI measurements. The deep learning model effectively determined the surpluses or shortages of the NPKC macronutrients within the cornfield throughout the growth stages. The model performed vigorously with R2 values of 0.93, 0.92, 0.98, and 0.83 in predicting N, P, K, and C levels in soil, respectively.

Deep learning provides a powerful new approach to many computer vision tasks. Height prediction from aerial images is one of those tasks which benefited greatly from the deployment of deep learning, thus replacing traditional multi-view geometry techniques. This manuscript proposes a two-stage approach to solve this task, where the first stage is a multi-task neural network whose main branch is used to predict the height map resulting from a single RGB aerial input image, while being augmented with semantic and geometric information from two additional branches. The second stage is a refinement step, where a denoising autoencoder is used to correct some errors in the first stage prediction results, producing a more accurate height map. Experiments on two publicly available datasets show that the proposed method is able to outperform state-of-the-art computer vision based and deep learning-based height prediction methods. Code is publicly available at: https://github.com/melhousni/DSMNet.

In this article, we aim to explore the potential of using onboard cameras and pre-stored geo-referenced imagery for Unmanned Aerial Vehicle (UAV) localization. Such a vision-based localization enhancing system is of vital importance, particularly in situations where the integrity of the global positioning system (GPS) is in question (i.e., in the occurrence of GPS outages, jamming, etc.). To this end, we propose a complete trainable pipeline to localize an aerial image in a pre-stored orthomosaic map in the context of UAV localization. The proposed deep architecture extracts the features from the aerial imagery and localizes it in a pre-ordained, larger, and geotagged image. The idea is to train a deep learning model to find neighborhood consensus patterns that encapsulate the local patterns in the neighborhood of the established dense feature correspondences by introducing semi-local constraints. We qualitatively and quantitatively evaluate the performance of our approach on real UAV imagery. The training and testing data is acquired via multiple flights over different regions. The source code along with the entire dataset, including the annotations of the collected images has been made public.11https://github.com/m-hamza-mughal/Aerial-Template-Matching. Up-to our knowledge, such a dataset is novel and first of its kind which consists of 2052 high-resolution aerial images acquired at different times over three different areas in Pakistan spanning a total area of around 2 km2.

Drones will be a significant part of future mobile communication networks, serving as mobile users or acting as mobile base stations at sky. Although they will provide several solutions related to mobile communication networks and other non-communication services, drones also possess numerous challenges, especially when it comes to their handover management. Unlike terrestrial networks, drones are mobile devices that move in a three-dimension (3D) environment, which further complicates mobility issues. Therefore, this paper provides an overview on the handover management for connected drones in the future mobile networks. The study summarizes how current research efforts approach the issues that characterize drones, with special focus on the handover process. This work also provides a general concept of drone integration in heterogeneous networks and discusses specific solutions for addressing possible problems. This survey further offers a brief discussion and guidance for upcoming research directions related to connected drones in future heterogeneous networks.

Various studies have been done in recent years on unmanned solar-powered aircraft for non-stop flight at a specified location or area. However, if a solar-powered unmanned aerial vehicle (UAV) can achieve a non-stop flight around the world, it may lead to the possibility of a pseudolite (i.e., pseudo-satellite) operation. These solar UAVs capable of operating as a satellite enable sustainable aviation that provides cheaper communication accessibility. Recently, we have developed a mathematical model for solar UAVs that was followed by the fabrication of a solar UAV model. Both the mathematical design model and the prototype model have been published. Thus, this work aims to determine the actual flight performance characteristics of the fabricated solar UAV. In this work, the bench and flight tests of the prototype solar and non-solar UAV model were compared in terms of aerodynamic characteristics and performance. These characteristics are determined using the flight test data and then compared with simulation data using a mathematical design model published earlier. Both accelerated and un-accelerated methods have been applied to predict the polar drag curve, and a distinct band of data obtained for both UAV prototypes. The predicted zero-lift drag coefficients were similar to the theoretical prediction in these UAVs.

In the UAV (often called drones) industry a zero defects culture is required. However, process improvement through the DMAIC lean methodology has not been widely studied in this industry. This paper examines how to solve the increasing quality problems of a small drones’ assembly company. A circular DMAIC methodology was used as an adaptation of the DMAIC methodology. Principal results obtained demonstrate a reduction of the lead time and an increment in the leanness degree level from 23% to 60%. Multifunctional worker rate increased from 75% to 83% and motion waste was reduced almost in a 50%. Line balancing and Simulation were applied.

Roads are means of transportation that play an important role in supporting people's lives such as economic, social, educational and cultural activities. In its service, the age of road is often not as planned because it has damage to the surface layer. Maintenance, repair and rehabilitation efforts are needed. However, before that steps are needed to identify each type and level of damage that occurs so that recommendations can be proposed for improvement. Road distresses identification is still done manually by surveyors who fill out forms and sketches of road distress. On the other hand, UAV ( U nmaned A erial V ehicle) which have many advantage s, such as : save time, money, labor and able to produce a geographical database for transportation issue. In this research data acquisition use automatic mode along road corridor. Aerial photo data is processed and analyzed by using SfM (structure from M otion) software to produce DSM ( D igital S urface M odel) and orthophoto. DSM is used to determine the depth profile of road distress. While the orthophoto results are then used in the process of visual interpretation to identify road distress . This research using quadcopter platform using digital camera with flight altitude less than 20 metres to obtain precise DSM and orthophoto . The results obtained by several types of road distress can be identified by using UAVs in the form of alligator cracking, potholes, edge cracking, shoving and depression. This type of road distress classification was obtained based on visual interpretation obtained an accuracy rate of 96.36 %.

As the world is digitizing fast, the increase in Big and Small Data offers opportunities to enrich official statistics for reporting on Sustainable Development Goals (SDG). However, survey data coming from an increased number of organizations (Small Data) and Big Data offer challenges in terms of data heterogeneity. This paper describes a methodology for combining various data sources to create a more comprehensive dataset on SDG 6.1.1. (proportion of population using safely managed drinking water services). We enabled digital volunteers to trace buildings on satellite imagery and used the traces on OpenStreetMap to facilitate visual detection of water points on Unmanned Aerial Vehicle (UAV) imagery and estimate the number of people served per water point. Combining data on water points identified on our UAV imagery with data on water points from field surveys improves the overall quality in terms of removal of inconsistencies and enrichment of attribute information. Satellite imagery enables scaling more easily than UAV imagery but is too costly to acquire at sufficiently high resolution. For small areas, our workflow is cost-effective in creating an up-to-date and consistent water point dataset by combining UAV imagery, Volunteered Geographic Information, and field survey data.

UAVs in recent times have achieved an increased rate of development, and hence, can cover a large spectrum of missions. Based on the dimensions, we can find UAVs from large dimensions used to operate at the global level through mini UAVs used inside buildings. The large UAVs are operated almost like a manned aircraft. For this reason, it uses the airport infrastructure and a runway for take-off and landing. The mini UAVs can be launched by hand. Between these two extremes, there is a category of UAVs used at the tactical level, which cannot be launched by hand and is not possible to build a runaway. These UAVs are launched using RATO (rocket-assisted take-off) or catapults. To improve the launch system, this should have a few moving parts to reduce maintenance costs and be powered by electric energy to be easily integrated into the automatic control loop. This paper presents a new design of a launch catapult based on electromagnetic energy for tactical UAVs. This technology is under development to launch projectiles with high velocity; however, it has theoretically proved the possibility to equally launch UAVs. The second part presents the theoretical approach necessary to find the expression of force under certain approximation for electromagnetic launch system design.

Caves have been used by humans and animals for several thousand years until present but, at these time scales, their structures can rapidly change due to erosion and concretion processes. For this reason, the availability of precise 3D models improves the data quality and quantity allowing the reconstruction of their ancient appearance, structure and origin. However, caves are usually characterised by lack of light, high percentage of relative humidity, narrow spaces and complex morphology. Thus, quite often the traditional topographic instruments cannot be employed. In the La Sassa cave (Sonnino, Italy) a huge deposit ranging from Pleistocene to the Second World War has been found and stratigraphic evidence suggested that the shape of the cave and its entrance might have been different. In this paper, the fusion of the internal and external 3D photogrammetric models of the La Sassa, made to support the archaeological excavations, is presented, A Nikon camera with a fisheye lens and a smartphone camera have been used to survey the internal part of the cave, while an aerial drone has been employed for the external area. The two models have been georeferenced and scaled using GCPs acquired by a double frequency GNSS (GPS and GLONASS) receiver. A low-resolution DTM derived from a previous aerial laser scanning survey and the 3D models have been elaborated in CloudCompare environment to highlight the complete morphology of the cave and its surroundings.

The increasing frequency of emergencies urges the need for a detailed and thorough knowledge of the landscape. The first hours after a disaster are not only chaotic and problematic, but also decisive to successfully save lives and reduce damage to the building stock. One of the most important factors in any emergency response is to get an adequate awareness of the real situation, what is only possible after a thorough analysis of all the available information obtained through the Italian protocol Topography Applied to Rescue. To this purpose geomatic tools are perfectly suited to create, manage and dynamically enrich an organized archive of data to have a quick and functional access to information useful for several types of analysis, helping to develop solutions to manage the emergency and improving the success of rescue operations. Moreover, during an emergency like an earthquake, the conventional inspection to assess the damage status of buildings requires special tools and a lot of time. Therefore, given the large number of buildings requiring safety measures and rehabilitation, efficient use of limited resources such as time and equipment, as well as the safety of the involved personnel are important aspects. The applications shown in the paper are intended to underline how the above-mentioned objective, in particular the rehabilitation interventions of the built heritage, can be achieved through the use of data acquired from UAV platform integrated with geographic data stored in GIS platforms.

The management of riverine areas is fundamental due to their great environmental importance. The fast changes that occur in these areas due to river mechanics and human pressure makes it necessary to obtain data with high temporal and spatial resolution. This study proposes a workflow to map riverine species using Unmanned Aerial Vehicle (UAV) imagery. Based on RGB point clouds, our work derived simple geometric and spectral metrics to classify an area of the public hydraulic domain of the river Palancia (Spain) in five different classes: Tamarix gallica L. (French tamarisk), Pinus halepensis Miller (Aleppo pine), Arundo donax L. (giant reed), other riverine species and ground. A total of six Machine Learning (ML) methods were evaluated: Decision Trees, Extra Trees, Multilayer Perceptron, K-Nearest Neighbors, Random Forest and Ridge. The method chosen to carry out the classification was Random Forest, which obtained a mean score cross-validation close to 0.8. Subsequently, an object-based reclassification was done to improve this result, obtaining an overall accuracy of 83.6%, and individually a producer’s accuracy of 73.8% for giant reed, 87.7% for Aleppo pine, 82.8% for French tamarisk, 93.5% for ground and 80.1% for other riverine species. Results were promising, proving the feasibility of using this cost-effective method for periodic monitoring of riverine species. In addition, the proposed workflow is easily transferable to other tasks beyond riverine species classification (e.g., green areas detection, land cover classification) opening new opportunities in the use of UAVs equipped with consumer cameras for environmental applications.

Made available in DSpace on 2020-12-12T02:09:44Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-09-01 This work proposes the Drone Reconfigurable Architecture (DRA), which is a modular architecture for UAVs with electrical, mechanical, and computational specifications. The theoretical aspects of the architecture are introduced through a case study with practical implementations aiming to design a multi-rotor UAV, which also includes the manufacturing steps of a functional prototype. Our proposal can be used in a scenario where the capacity of physical reconfiguration of a UAV would confer an enormous advantage to these aircraft in terms of applicability. This happens in the case where each task typically requires a robot with a particular physical architecture (number and position of propellers, autonomy, thrust, sensors, and communication). Results of a set of tests with an aircraft assembly are presented to verify the versatility of the proposed architecture, demonstrating the better performance of these aircraft when compared with conventional UAVs. The proposed methodology allows applications in a variety of scenarios like cargo transportation, support, agriculture, publicity, pest control, surveillance, inspection, and entertainment, between others. In these scenarios, although a software with some generic components could easily control drones to perform all of them, it is unthinkable to consider that a single drone with a particular physical structure would be able to be adapted to all of the tasks necessary (as path following, localization, and mapping). Institute of Science and Technology of Sorocaba (ICTS) São Paulo State University (Unesp) Automation and Integrated Systems Group (GASI) Laboratory of Robotics and Cognitive Systems (LaRoCS) Institute of Computing (IC) University of Campinas (Unicamp) Institute of Science and Technology of Sorocaba (ICTS) São Paulo State University (Unesp) Automation and Integrated Systems Group (GASI)

Unmanned Aerial Vehicles (UAVs) have been getting more and more popular in both civil and military arena. Similar to manned aircraft, their propulsion systems or engines emit harmful gases such as nitrogen oxides. Since UAVs have different mission profiles and operational parameters than manned aircraft, it is worthy to investigate their NOx emissions. Therefore, in this study, NOx emissions of a turbofan powered UAV for complete flight cycle was calculated and optimized within a range of altitude and speed parameters. NOx emissions were calculated based on ICAO ground test data and corrected to any speed and altitude during flight legs using both Boeing Fuel Flow Method 2 and DLR Fuel Flow Method. Total NOx emissions were calculated for complete flight cycles for different altitude and speed parameters. Numerical results were presented graphically and additionally optimization studies were conducted. Optimization studies include determination and comparison of speed and altitude for minimum NOx emissions by the two fuel flow methods and maximum loiter time achievable by UAV.

This work addresses the issue of ocean monitoring and clean-up of polluted zones, as well as the notion of trajectory planning and fault tolerance for semi-autonomous unmanned vehicles. A hybrid approach for unmanned aerial vehicles (UAVs) is introduced to monitor the ocean region and cooperate with swarm of unmanned surface vehicles (USVs) to clean dirty zones. The paper proposes two solutions that apply to trajectory planning from the base of life to the dirty zone for swarm USVs. The first solution is performed by a modified Genetic Algorithm (GA), and the second uses a modified Ant Algorithm (AA). The proposed solutions were both implemented in the simulation with different scenarios for the dirty zone. This approach detects and reduces the pollution level in ocean zones while taking into account the problem of fault tolerance related to unmanned cleaning vehicles.

Made available in DSpace on 2020-12-12T01:21:44Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-01-01 Crop protection on major crops is now required to follow the principles of integrated pest management so the timing and accuracy of any application of a pesticide or biopesticide has to be more precise to minimize adverse effects on non-target species. The development of UAVs (unmanned aerial vehicles) provides a means of providing a more targeted application of the correct dose, especially by using formulations that are more persistent, thus minimizing loss of spray in areas subject to rain. Avoiding use of too high a dosage allows greater survival of natural enemies and reduces the selection pressure for pests becoming resistant to specific modes of action. The downward flow of air from a UAV should also provide better distribution and impaction of droplets within a crop canopy, reduce soil impaction caused by taking heavy loads of spray applied with 200 l ha–1 of water, and allow treatments when fields are too wet to access with ground equipment. In Asia, many smallholder farmers are using a drone in preference to using a knapsack sprayer. According to Matthews, it has been shown that ULV spraying can be effective, but it needs a narrow droplet spectrum with the droplets remaining stable and not shrinking to become too small. Formulation research can reduce the volatility of the spray, hence the success of oil-based sprays. However, instead of petroleum-based oils, there is a chance to develop vegetable oil carriers with micro-sized particle suspensions to deliver low toxicity pesticides in droplets that can be deposited within the crop and not drift beyond the crop boundary. Oil deposits will be less prone to loss after rain so less should be lost in neighbouring ditches and water courses, especially as rainfall patterns are forecast to change. More studies are needed to evaluate the swath for deposition, buffer zones, formulation, nozzle selection, to guide future specific legislation for UAV applications. AgroEfetiva Sao Paulo State University UNESP Sao Paulo State University UNESP

BACKGROUND The fruit fly Drosophila suzukii, or spotted wing drosophila (SWD), is a serious pest worldwide, attacking many soft‐skinned fruits. An efficient monitoring system that identifies and counts SWD in crops and their surroundings is therefore essential for integrated pest management (IPM) strategies. Existing methods, such as catching flies in liquid bait traps and counting them manually, are costly, time‐consuming and labour‐intensive. To overcome these limitations, we studied insect trap monitoring using image‐based object detection with deep learning. RESULTS Based on an image database with 4753 annotated SWD flies, we trained a ResNet‐18‐based deep convolutional neural network to detect and count SWD, including sex prediction and discrimination. The results show that SWD can be detected with an area under the precision recall curve (AUC) of 0.506 (female) and 0.603 (male) in digital images taken from a static position. For images collected using an unmanned aerial vehicle (UAV), the algorithm detected SWD individuals with an AUC of 0.086 (female) and 0.284 (male). The lower AUC for the aerial imagery was due to lower image quality caused by stabilisation manoeuvres of the UAV during image collection. CONCLUSION Our results indicate that it is possible to monitor SWD using deep learning and object detection. Moreover, the results demonstrate the potential of UAVs to monitor insect traps, which could be valuable in the development of autonomous insect monitoring systems and IPM. © 2020 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry., We studied the use of deep learning for unmanned aerial vehicle (UAV)‐based detection of Drosophila suzukii in sticky traps. Our results show that there is potential for UAVs to perform this task.