Unmanned Aerial Vehicle (UAV): A Comprehensive Survey

Chaurasia, Rohit; Mohindru, Vandana

doi:10.1002/9781119769170.ch1

Cited by 40 publications

(28 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the use of drones has become increasingly popular, and they have been applied to various scientific and commercial purposes in different fields of photogrammetry, surveying, agriculture, natural disaster management, and so on [27]. There are different types of drones, each used for a specific purpose; and, in terms of design technology, application, and physical characteristics, they can be divided into four types: multirotor, helicopter, VTOL, and fixed-wing [28][29][30][31].…”

Section: State Of the Art Workmentioning

confidence: 99%

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

Javan

Samadzadegan

Gholamshahi

et al. 2022

Drones

View full text Add to dashboard Cite

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.

show abstract

Section: State Of the Art Workmentioning

confidence: 99%

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

Javan

Samadzadegan

Gholamshahi

et al. 2022

Drones

View full text Add to dashboard Cite

show abstract

“…To reach an optimum communication link with different environment characteristics, the least squares tuning algorithm is considered where tuning is necessary to adjust the Hata-Davidson propagation model's parameters to the measured data. Mathematical equations for the least squares tuning algorithm are presented as per Equations ( 6) to (8).…”

Section: Mathematical Calculationmentioning

confidence: 99%

“…where the tuning algorithm is exemplified by the concept of minimizing the sum of the squares of the differences E between the measured data Y i and the predicted data PLHD i ; n denotes the total number of used data. In the Hata-Davidson propagation model, we used two main tuning terms, as per Equations ( 7) and (8). These two terms reportedly affect propagation models, which are related to distance (d), and frequency (f).…”

Section: Mathematical Calculationmentioning

confidence: 99%

“…Many applications could benefit from integration with UAVs, such as telecommunications, remote sensing, the monitoring of disaster-relief activities, high-resolution imaging, atmospheric studies, smart cities, smart agriculture, smart service delivery, wearable devices, traffic monitoring, border monitoring, news gathering, localization, and navigation. Hence, drones can provide seamless communication systems, as well as a variety of sensing applications and connections to grid networks, to support the idea of hyper-connected world in more efficient and timely manner [8,9]. This integration is vital, especially in the current digital era, when it is anticipated that over 50 billion devices will be connected to the internet by 2030, which in turn could generate real-time data that would open doors towards hyper-connected societies, and thus more global smart connectivity.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modifying Hata-Davidson Propagation Model for Remote Sensing in Complex Environments Using a Multifactional Drone

Almalki

Soufiene

2022

Sensors

View full text Add to dashboard Cite

The coupling of drones and IoT is a major topics in academia and industry since it significantly contributes towards making human life safer and smarter. Using drones is seen as a robust approach for mobile remote sensing operations, such as search-and-rescue missions, due to their speed and efficiency, which could seriously affect victims’ chances of survival. This paper aims to modify the Hata-Davidson empirical propagation model based on RF drone measurement to conduct searches for missing persons in complex environments with rugged areas after manmade or natural disasters. A drone was coupled with a thermal FLIR lepton camera, a microcontroller, GPS, and weather station sensors. The proposed modified model utilized the least squares tuning algorithm to fit the data measured from the drone communication system. This enhanced the RF connectivity between the drone and the local authority, as well as leading to increased coverage footprint and, thus, the performance of wider search-and-rescue operations in a timely fashion using strip search patterns. The development of the proposed model considered both software simulation and hardware implementations. Since empirical propagation models are the most adjustable models, this study concludes with a comparison between the modified Hata-Davidson algorithm against other well-known modified empirical models for validation using root mean square error (RMSE). The experimental results show that the modified Hata-Davidson model outperforms the other empirical models, which in turn helps to identify missing persons and their locations using thermal imaging and a GPS sensor.

show abstract