Types Of Drones Research Articles

드론의 비행안전 및 사생활보호 등에 관한 법적 고찰

A drone is an unmanned aerial vehicle included in the ultra-light vehicle category under the Aviation Act. Recently, as the number of people who own and use drones is rapidly increasing, legal problems such as drone flight safety issues and invasion of privacy are frequently occurring. Accordingly, around 2021, the Aviation Safety Act was amended to classify drones, that is, unmanned ultra-light flying devices, into four categories according to their weight, and in all cases, the qualification conditions were mandatory so that they could fly only after obtaining a pilot’s certificate. Many users are not aware of this fact, and if they fly without a license, they will be fined at least 3 million won. Drones, which are considered a promising industry in the future, require strict regulation as they can be used for various personal crimes including unqualified flight problems. First of all, drone users must obtain a license according to the type of drone in accordance with the Aviation Safety Act, and all commercial flying devices, regardless of weight exceeding 2 kg or weight, must be reported to the Drone Management Office of the Korea Transportation Safety Authority. In addition, the enforcement rules of the Aviation Safety Act include prohibition of dropping objects, prohibition of flying that may pose a risk to human life or property in the sky over a densely populated area, prohibition of flying in a no-fly zone, prohibition of flying at night, prohibition of flying while intoxicated, etc. The prohibition of flying is stipulated as a regulated user compliance requirement. Drones usually have cameras installed to take pictures of the scenery seen from the sky, but unspecified numbers of people can be photographed, so you should use them with caution about personal information. If a scene with another person's face is uploaded to a social networking service or YouTube without consent, depending on the situation, it may be involved in a lawsuit for damages or defamation under the criminal law due to infringement of the right to portrait. To prevent this, you should try to protect the privacy of others by taking aerial shots rather than close-up shots in public places where there are people. Advances in science and technology such as information and communication technology (ICT) are also changing the means and aspects of terrorism. In particular, drones, which are widely used for low-cost general use, industrial and military use, have a very high risk of being abused for terrorism against key personnel or important national facilities, as well as invasion of privacy such as illegal filming. Drones can be used for crime or terrorism in various safety accidents at any time, so it is virtually impossible to prevent existing threats with the legal system alone. Accordingly, when a drone flying in a prohibited place or time zone or an unmanned aerial vehicle operating abnormally is discovered, it is necessary to detect and block it at an early stage. In addition, ordinary citizens who use drones for hobbies such as video shooting are urged to carefully read the contents stipulated in the law and use them safely to protect the lives and privacy of others. Police and national defense use the face recognition system on drones to search for missing persons and to recognize and intercept terrorists, a national risk factor, are expected to play a major role. As a healthy and developing drone industry is expected in the future, individuals must also follow the rules to avoid infringing on drone flight requirements and privacy of others. There are two key issues in drone legal issues: flight safety issues and invasion of privacy. In this article, we would like to consider improvement measures that can ensure the safe flight of drones, suppress the occurrence of human damage, and effectively prevent invasion of privacy.

A Modified YOLOv4 Deep Learning Network for Vision-Based UAV Recognition

The use of drones in various applications has now increased, and their popularity among the general public has increased. As a result, the possibility of their misuse and their unauthorized intrusion into important places such as airports and power plants are increasing, threatening public safety. For this reason, accurate and rapid recognition of their types is very important to prevent their misuse and the security problems caused by unauthorized access to them. Performing this operation in visible images is always associated with challenges, such as the small size of the drone, confusion with birds, the presence of hidden areas, and crowded backgrounds. In this paper, a novel and accurate technique with a change in the YOLOv4 network is presented to recognize four types of drones (multirotors, fixed-wing, helicopters, and VTOLs) and to distinguish them from birds using a set of 26,000 visible images. In this network, more precise and detailed semantic features were extracted by changing the number of convolutional layers. The performance of the basic YOLOv4 network was also evaluated on the same dataset, and the proposed model performed better than the basic network in solving the challenges. Compared to the basic YOLOv4 network, the proposed model provides better performance in solving challenges. Additionally, it can perform automated vision-based recognition with a loss of 0.58 in the training phase and 83% F1-score, 83% accuracy, 83% mean Average Precision (mAP), and 84% Intersection over Union (IoU) in the testing phase. These results represent a slight improvement of 4% in these evaluation criteria over the YOLOv4 basic model.

Comparison of spectrogram, persistence spectrum and percentile spectrum based image representation performances in drone detection and classification using novel HMFFNet: Hybrid Model with Feature Fusion Network

Drone detection and classification are gaining great importance in military and civilian applications because of their availability and widespread usages. This study presents a new framework, named as Hybrid Model with Feature Fusion Network (HMFFNet), for drone detection and classification using Radio Frequency (RF) signals. It is composed of three stages. In the first stage, 1D RF signals are segmented to specific sizes and each segment is transformed into 2D signals in terms of spectrogram, persistence spectrum and percentile spectrum images to be employed in the well-known deep learning architectures through transfer learning approach. In the second stage, VGG19, one of these architectures, is utilized for feature extraction using the transformed images. Then the features are fused in various combinations to improve their discriminative property. Finally, these features are processed by a Support Vector Machine (SVM) classifier in the last stage of the proposed framework. To evaluate the performance of the HMFFNet, numerous experiments were conducted on the publicly available DroneRF dataset. The experimental results showed that the performance of the novel percentile spectrum based features are better compared to the widely-used and good-performing spectrogram based features in drone detection and classification. Also, fusion of features from three drone representing images further improve the performance of the proposed frameworks. For the quantitative evaluation, experiments yield to the accuracy rates of 100%, 99.55%, and 97.75% for 2-Class drone existence, 4-Class drone type detection and 10-Class drone mode detection, respectively, showing higher results than that of other state-of-the-art studies.

Position Controller for a Flapping-Wing Drone Using UWB

This paper proposes an integral approach for accurate ultra-wideband indoor position control of flapping-wing micro-air vehicles. Three aspects are considered to achieve a reliable and accurate position controller. The first aspect is a velocity/attitude flapping-wing model for drag compensation. The model is compared with real flight data and shown to be applicable for more than one type of flapping-wing drone. The second improvement regards a voltage-dependent thrust control. Lastly, a characterisation of ground effects in flapping-wing flight is obtained from hovering experiments. The proposed controller improves position control by a factor [Formula: see text], reaching a mean absolute error of 10[Formula: see text]cm for the position in [Formula: see text] and [Formula: see text], and 4.9[Formula: see text]cm for the position in [Formula: see text].

A decision support model for selecting unmanned aerial vehicle for medical supplies: context of COVID-19 pandemic

PurposeIn recent times, due to rapid urbanization and the expansion of the E-commerce industry, drone delivery has become a point of interest for many researchers and industry practitioners. Several factors are directly or indirectly responsible for adopting drone delivery, such as customer expectations, delivery urgency and flexibility to name a few. As the traditional mode of delivery has some potential drawbacks to deliver medical supplies in both rural and urban settings, unmanned aerial vehicles can be considered as an alternative to overcome the difficulties. For this reason, drones are incorporated in the healthcare supply chain to transport lifesaving essential medicine or blood within a very short time. However, since there are numerous types of drones with varying characteristics such as flight distance, payload-carrying capacity, battery power, etc., selecting an optimal drone for a particular scenario becomes a major challenge for the decision-makers. To fill this void, a decision support model has been developed to select an optimal drone for two specific scenarios related to medical supplies delivery.Design/methodology/approachThe authors proposed a methodology that incorporates graph theory and matrix approach (GTMA) to select an optimal drone for two specific scenarios related to medical supplies delivery at (1) urban areas and (2) rural/remote areas based on a set of criteria and sub-criteria critical for successful drone implementation.FindingsThe findings of this study indicate that drones equipped with payload handling capacity and package handling flexibility get more preference in urban region scenarios. In contrast, drones with longer flight distances are prioritized most often for disaster case scenarios where the road communication system is either destroyed or inaccessible.Research limitations/implicationsThe methodology formulated in this paper has implications in both academic and industrial settings. This study addresses critical gaps in the existing literature by formulating a mathematical model to find the most suitable drone for a specific scenario based on its criteria and sub-criteria rather than considering a fleet of drones is always at one's disposal.Practical implicationsThis research will serve as a guideline for the practitioners to select the optimal drone in different scenarios related to medical supplies delivery.Social implicationsThe proposed methodology incorporates GTMA to assist decision-makers in order to appropriately choose a particular drone based on its characteristics crucial for that scenario.Originality/valueThis research will serve as a guideline for the practitioners to select the optimal drone in different scenarios related to medical supplies delivery.

Micro-Motion Classification of Flying Bird and Rotor Drones via Data Augmentation and Modified Multi-Scale CNN

Aiming at the difficult problem of the classification between flying bird and rotary-wing drone by radar, a micro-motion feature classification method is proposed in this paper. Using K-band frequency modulated continuous wave (FMCW) radar, data acquisition of five types of rotor drones (SJRC S70 W, DJI Mavic Air 2, DJI Inspire 2, hexacopter, and single-propeller fixed-wing drone) and flying birds is carried out under indoor and outdoor scenes. Then, the feature extraction and parameterization of the corresponding micro-Doppler (m-D) signal are performed using time-frequency (T-F) analysis. In order to increase the number of effective datasets and enhance m-D features, the data augmentation method is designed by setting the amplitude scope displayed in T-F graph and adopting feature fusion of the range-time (modulation periods) graph and T-F graph. A multi-scale convolutional neural network (CNN) is employed and modified, which can extract both the global and local information of the target’s m-D features and reduce the parameter calculation burden. Validation with the measured dataset of different targets using FMCW radar shows that the average correct classification accuracy of drones and flying birds for short and long range experiments of the proposed algorithm is 9.4% and 4.6% higher than the Alexnet- and VGG16-based CNN methods, respectively.

Intelligent mobile detection of cracks in concrete utilising an unmanned aerial vehicle

Cracks in constructions may result in negative consequences in terms of expenditure and safety. This in turn highlights the importance of finding ways to detect these cracks easily and effectively. Hence, technological advances play significant role in enabling effective and innovative ideas, such as the use of autonomous drones and artificial intelligence solutions. In this research, we utilise a type of drone called an unmanned aerial vehicle, equipped with a high-speed camera that can capture images of cracks in buildings, and pass the information to the system. We utilised a dataset that has images collected from different Middle East Technical University (METU) campus buildings with various concrete surfaces (with and without cracks). The crack detection approach uses statistical measures and a support vector machine that prevents overfitting, attains a good rate of accuracy, tackles problems in real-time, and can train a model when a small dataset exists. The combination of an unmanned aerial vehicle, artificial intelligence, and digital image processing gives excellent results. Performance metrics reported for seven rounds of experiments showed rates of accuracy in detection ranging from 83.3–100% (with 100% achieved in two rounds). This demonstrates the effectiveness of our proposed detection system in detecting cracks in constructions.

QoS-Aware Multilayer UAV Deployment to Provide VoWiFi Service over 5G Networks

Drones equipped with wireless network cards can provide communication services in open areas. This paper proposes a hierarchical two-layered network architecture with two types of drones according to their communication equipment: Access and Distribution. While access drones provide WiFi access to ground users, distribution drones act as WiFi-to-5G relay forwarding packets into the 5G Core Network. In this context, we formulate a novel optimization problem for the 3-D initial placement of drones to provide Voice over WiFi (VoWiFi) service to ground users. Our optimization problem finds the minimum number of drones (and their type and location) to be deployed constrained to coverage and minimum voice speech quality. We have used a well-known metaheuristic algorithm (Particle Swarm Optimization) to solve our problem, examining the results obtained for different terrain sizes (from 25 m × 25 m to 100 m × 100 m ) and ground users (from 10 to 100 ). In the most demanding case, we were able to provide VoWiFi service with four distribution drones and five access drones. Our results show that the overall number of UAVs deployed grows with the terrain size (i.e., with users’ sparsity) and the number of ground users.

Detection and Recognition of Drones Based on a Deep Convolutional Neural Network Using Visible Imagery

Drones are becoming increasingly popular not only for recreational purposes but also in a variety of applications in engineering, disaster management, logistics, securing airports, and others. In addition to their useful applications, an alarming concern regarding physical infrastructure security, safety, and surveillance at airports has arisen due to the potential of their use in malicious activities. In recent years, there have been many reports of the unauthorized use of various types of drones at airports and the disruption of airline operations. To address this problem, this study proposes a novel deep learning-based method for the efficient detection and recognition of two types of drones and birds. Evaluation of the proposed approach with the prepared image dataset demonstrates better efficiency compared to existing detection systems in the literature. Furthermore, drones are often confused with birds because of their physical and behavioral similarity. The proposed method is not only able to detect the presence or absence of drones in an area but also to recognize and distinguish between two types of drones, as well as distinguish them from birds. The dataset used in this work to train the network consists of 10,000 visible images containing two types of drones as multirotors, helicopters, and also birds. The proposed deep learning method can directly detect and recognize two types of drones and distinguish them from birds with an accuracy of 83%, mAP of 84%, and IoU of 81%. The values of average recall, average accuracy, and average F1-score were also reported as 84%, 83%, and 83%, respectively, in three classes.

Toolkit Carrying Drone For Maintenance Of High Altitude Transmission Lines

Research and analysis on drones is increasing rapidly nowadays in various fields of application. One of the major problem which arises in the drone application is its ability of lifting heavy loads when attached to it that requires proper design and selection of the required type of drone for its ability to carry out various missions including lifting a heavy load. One of the important type of drone that is widely used is hexacopter drone. This paper shows the design of hexacopter drone that lifts the toolkit which has to be delivered for maintenance of transmission lines at high altitude. It is designed with the help of calculation and analysis of the criteria and constraints by the aid of software. The calculations shows the ability of hexacopter drone of lifting a toolkit and delivering it to the location at higher altitude.

Monitoring of plastic debris in the lower Citarum River using Unmanned Aerial Vehicles (UAVs)

Plastic pollution has become a problem in recent years. Various methods are used to reduce and prevent plastic pollution. Many methods have been used to estimate the abundance and transportation of plastics in waters, especially rivers. This paper presents the use of an Unmanned Aerial Vehicle (UAV) to observe plastic waste in river flow. Monitoring plastic debris was conducted at the downstream part of the Citarum river in the Muara Gembong sub-district, Bekasi Regency, West Java Province, on March 6, 8, and 10, 2021. The type of drone used was the DJI Phantom 3 Pro. Data analysis uses the CVAT program developed by Intel to label images. The results show differences between visual counting and UAV, visual counting has a higher value than UAV, but VC might suffer from an observer bias. The counting bias is dependent on the current and the ability of the eye. On the other hand, the results of aerial surveys during the calculation process can be reinterpreted manually or automatically and corrected again. Monitoring plastic debris using UAVs can be an alternative to observing the plastic transportation process in rivers, especially in areas that are difficult to access.

DroneSense: The Identification, Segmentation, and Orientation Detection of Drones via Neural Networks

The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles. Here, we present a CNN using a decision tree and ensemble structure to fully characterise drones in flight. Our system determines the drone type, orientation (in terms of pitch, roll, and yaw), and performs segmentation to classify different body parts (engines, body, and camera). We also provide a computer model for the rapid generation of large quantities of accurately labelled photo-realistic training data and demonstrate that this data is of sufficient fidelity to allow the system to accurately characterise real drones in flight. Our network will provide a valuable tool in the image processing chain where it may build upon existing drone detection technologies to provide complete drone characterisation over wide areas.

Multi-Frequency Radar Micro-Doppler Based Classification of Micro-Drone Payload Weight

The use of drones for recreational, commercial and military purposes has seen a rapid increase in recent years. The ability of counter-drone detection systems to sense whether a drone is carrying a payload is of strategic importance as this can help determine the potential threat level posed by a detected drone. This paper presents the use of micro-Doppler signatures collected using radar systems operating at three different frequency bands for the classification of carried payload of two different micro-drones performing two different motions. Use of a KNN classifier with six features extracted from micro-Doppler signatures enabled mean payload classification accuracies of 80.95, 72.50 and 86.05%, for data collected at S-band, C-band and W-band, respectively, when the drone type and motion type are unknown. The impact on classification performance of different amounts of situational information is also evaluated in this paper.

Improving the Flight Endurance of a Separate-Lift-and-Thrust Hybrid through Gaussian Process Optimization

A separate-lift-and-thrust hybrid is a modified fixed-wing drone which includes quadcopter rotors. This results in the combined capability of forwarding flight as well as vertical take-off and landing (VTOL), making it a low-cost method that can deliver substantial gains in utility. Though this is a strong point compared to other types of VTOL drones, the hybrid design may incur a significant trade-off because added weight and drag can severely reduce the drone's flight endurance. This study attempts to mitigate the impact by improving the configuration of the selection and positioning parameters. Since drag estimations are costly, a Gaussian process optimization method was performed, as it is economical with respect to the required number of iterations. A set of arbitrarily selected components was prepared for use with the optimization method, recording the relevant performance data and constructing the CAD models of the components for use in simulations. The optimization method was able to increase the estimated flight endurance to 27.99 minutes, a significant improvement compared to a set of random configurations, which only yielded 9.54 minutes at best. The respectable result was obtained even though difficulties were experienced regarding the infeasible regions that arise from the many constraints. Future implementation of this optimization approach can be further improved. It may be worthwhile to utilize a low-fidelity model from the base fixed-wing drone simulations, in contrast with using an initial zero mean for the prior of the Gaussian process.

Drones in Insect Pest Management

One of the major components in precision agriculture is crop health monitoring, which includes irrigation, fertilization, pesticide sprays, and timely harvest of the crop. Further, the progressive change in growth and development is critical in crop monitoring and taking suitable decisions to maintain health status. In order to accomplish the task, drones are highly useful for on site detection of problems so as to undertake corrective measures instantly. Although it is expensive to build algorithms and establish relationships between ground truth and spectral signatures, it is a user-friendly technique once the basics studies are done. As labor availability and technical manpower are extremely limited, particularly in India, drones are gaining popularity in the context of smart farming. Insect pests are known to cause catastrophe and drastic reduction in food grain production across the globe. The losses that have been predicted by FAO is over 37% due to pests and diseases. Recently, crops cultivated in India have been threatened by invasive pests like fall army worm (Spodoptera frugiperda) in corn and Rugose spiraling whitefly in coconut (Aleurodicus rugiperculatous Martin); these pests caused extensive damage during the years 2018 and 2019. The plant protection measures are to be taken on a community basis so as to ensure effective management of pests. In India, more than 80% of farmlands are in the category of small and marginal (<1 ha), so it is very difficult to manage the invasive pests. If one field is sprayed, the pests simply shift their feeding to the neighboring fields. To address this, drones become essential. Drones are unmanned aerial vehicles exploited in a wide array of disciplines such as defense, monitoring systems, and disaster management but are only beginning to be utilized in agricultural sciences. There are three major types of drones, namely fixed wing, multi-rotor, and hybrid type, and the usage depends on specific applications. The other types depend on degree of automation, size, weight, and power source. The set operational parameters such as flight speed, height, and endurance need to be optimized to use drones appropriately in agriculture and allied sectors. In addition, parameters related to drone-based spraying such as droplet size, spread, density, uniformity, deposition, and penetrability should also be factored in when implementing drone-based mitigation strategies. Despite the fact that drone technology is highly relevant and appropriate for pest management, the adoption of the technology is restricted. Regulatory guidelines have been set across the globe to perform site-specific farm management with higher precision at a very high resolution. Overall, drones can be employed in almost all agricultural field operations and are considered excellent tools for rapid, reliable, and non-destructive detection of field problems. This review provides panoramic views of drone technology and its application in the management of pests in a digital agriculture era.

Drone technology for identification of healing forest spot at Kampung Cisamaya Mount Ciremai National Park

Reconnecting people to nature through healing activities in the forest ecosystem is important. Various studies have shown that forest ecosystems dominated by tree vegetation have positive impacts on physical and psychological health. Not all locations in the forest ecosystem are suitable for healing forests (HF), but their suitability should be identified. Land slope, vegetation density, and easiness access to the site are some physical parameters of the land which are indicators for the development of HF site. Identification of suitable HF spots can be identified using drone technology and GIS. The research objective was the use of drones equipment in identifying potential sites for HF activities. The research site was Kampung Cisamaya in Mount Ciremai National Park. The type of drone used was the Phantom 4 Pro Obsidian equipped with a 20-megapixel RGB camera. The stages of research activities were data acquisition, processing, and analyzing from drone spatial data. Vegetation density was determined through GRVI (Green-Red Vegetation Index), while drone data analyzed the slope classification by DTM (Digital Terrain Model). The accessibility to the location was analyzed through data from the spatial map of the Kuningan Regency. The results found that the use of drones was effective in evaluating the suitability spots for HF activities. From this study can be concluded that the Cisamaya area was suitable for the development of HF activities due to physical parameters of flat to gentle slopes (0-15%), having dense vegetation, as well as the easiness access by people.

Design of entertainment drone with rotating LED display technology

The drone light show is a popular form of performance. This paper designs a new type of entertainment drone with rotating LED display technology. This drone is equipped with a rotating LED display, a single drone can display a complete picture, and has a good display effect. The application of the new entertainment drone can reduce the cost and technical difficulty of the drone light show, and expand the applicable scenarios of the drone light show.

CNN-SSDI: Convolution neural network inspired surveillance system for UAVs detection and identification

In recent years, the availability of commercial unmanned air vehicles (UAVs) has increased enormously because of device miniaturization and low cost. However, the abuse of UAVs needs to be investigated to prevent serious security threats for civilians. Therefore, this paper presents a convolutional neural network-based surveillance system for drone detection and its type identification, namely CNN-SSDI. The network architecture is cleverly designed based on deep convolution layers to successfully learn all intrinsic feature maps of radio-frequency signals that are collected from three different types of drones. Further, a detailed comparative analysis of various kernel impairments of the convolution layer structure was investigated under various performance metrics evaluation and higher accuracy in drone surveillance systems. According to the empirical results, CNN-SSDI can detect a UAV with 99.8% accuracy and recognize drone types with an accuracy of 94.5%, which outperforms other existing drone detection and identification techniques.

Analysis and classification of drone sounds from digital media

AbstractThe use of the quadcopter‐type drone is now at a mature and practical stage, and many major manufacturers are expanding their range of applications. Because of the high maneuverability and practicality of this flying object, how we ensure it is used for benign purposes in urban life has become a major issue. Most such drones are small enough to avoid many current airborne detection methods and cheap enough to be disposable. We were able to gather enough amount of multimedia sources including drone‐related sources using open online platforms, such as YouTube and other similar services. For a subset of commercial quadcopter drones, we collected sound sample data consisting of recordings and YouTube videos and built a trained simple nonlinear neural network filter to classify them. We used Mel‐frequency cepstral coefficients to reduce the amount of data as the input signal and created two‐dimensional spectrogram images to minimize the loss of temporal information in the sample, as suggested by previous research. Most of the acoustic signal energy in the drone sound existed in specific frequency bands and residual signal patterns were spread up to around 15 kHz. We designed and tested several recurrent and convolutional neural network models and one of the simple neural network models based on the LeNet architecture could classify over 10 different types of drones from acoustic data with over 97% accuracy including an additional path for the detection of general acoustic drone patterns.

Single and multiple drones detection and identification using RF based deep learning algorithm

Unmanned aerial systems, especially drones have gone through remarkable improvement and expansion in recent years. Drones have been widely utilized in many applications and scenarios, due to their low price and ease of use. However, in some applications drones can pose a malicious threat. To diminish risks to public security and personal privacy, it is necessary to deploy an effective and affordable anti-drone system in sensitive areas to detect, localize, identify, and defend against intruding malicious drones. This research article presents a new publicly available radio frequency drone dataset and investigates detection and identification methodologies to detect single or multiple drones and identify a single detected drone's type. Moreover, special attention in this paper has been underlined to examine the possibility of using deep learning algorithms, particularly fully connected deep neural networks as an anti-drone solution within two different radio frequency bands. We proposed a supervised deep learning algorithm with fully-connected deep neural network models that use raw drone signals rather than features. Regarding the research results, the proposed algorithm shows a lot of potentials. The probability of detecting a single drone is 99.8%, and the probability of type identification is 96.1%. Moreover, the results of multiple drones detection demonstrate an average accuracy of 97.3%. There have not been such comprehensive publications, to this time, in the open literature that have presented and enlightened the problem of multiple drones detection in the radio frequency domain.