Abstract:Unmanned aerial vehicles (UAVs) are massively seeping into a wide range of human activities. Along with other remotely controlled or automatic devices, they have entered many aspects of human activities and industry. While the majority of researchers have been working on the construction, deployment and non-military use of UAVs, the protection against UAVs remained on the edge of their interest. Nowadays, the situation is rapidly changing. The risk of misuse of UAVs by criminals, guerrillas or terrorists has c… Show more
“…Firstly, the world coordinates of the drone which is found in the image are converted to camera coordinates by using quaternions and a rotation matrix. The rotations are described as a yaw-pitch-roll sequence, and the rotation matrix can be obtained by using the Euler angles which are available in the simulator as shown in Equation (1).…”
Section: Drone Image Dataset and Auto-labellingmentioning
confidence: 99%
“…Counter-drone systems are an emerging need to detect and eliminate malicious drones or any kind of UAV that threaten public security or individual privacy. Technologies for the detection, localisation and identification of small UAVs include infrared sensors, laser devices, optical surveillance aids and devices, acoustic devices, Light Detection and Ranging (LiDAR) sensors, equipment operating with image recognition technology, devices capable of detecting and localising UAV remote control signals and human air observers (1) . After a target drone is detected, elimination methods such as laser guns, water cannons, birds trained to catch drones and jamming can be applied.…”
The number of unmanned aerial vehicles (UAVs, also known as drones) has increased dramatically in the airspace worldwide for tasks such as surveillance, reconnaissance, shipping and delivery. However, a small number of them, acting maliciously, can raise many security risks. Recent Artificial Intelligence (AI) capabilities for object detection can be very useful for the identification and classification of drones flying in the airspace and, in particular, are a good solution against malicious drones. A number of counter-drone solutions are being developed, but the cost of drone detection ground systems can also be very high, depending on the number of sensors deployed and powerful fusion algorithms. We propose a low-cost counter-drone solution composed uniquely by a guard-drone that should be able to detect, locate and eliminate any malicious drone. In this paper, a state-of-the-art object detection algorithm is used to train the system to detect drones. Three existing object detection models are improved by transfer learning and tested for real-time drone detection. Training is done with a new dataset of drone images, constructed automatically from a very realistic flight simulator. While flying, the guard-drone captures random images of the area, while at the same time, a malicious drone is flying too. The drone images are auto-labelled using the location and attitude information available in the simulator for both drones. The world coordinates for the malicious drone position must then be projected into image pixel coordinates. The training and test results show a minimum accuracy improvement of 22% with respect to state-of-the-art object detection models, representing promising results that enable a step towards the construction of a fully autonomous counter-drone system.
“…Firstly, the world coordinates of the drone which is found in the image are converted to camera coordinates by using quaternions and a rotation matrix. The rotations are described as a yaw-pitch-roll sequence, and the rotation matrix can be obtained by using the Euler angles which are available in the simulator as shown in Equation (1).…”
Section: Drone Image Dataset and Auto-labellingmentioning
confidence: 99%
“…Counter-drone systems are an emerging need to detect and eliminate malicious drones or any kind of UAV that threaten public security or individual privacy. Technologies for the detection, localisation and identification of small UAVs include infrared sensors, laser devices, optical surveillance aids and devices, acoustic devices, Light Detection and Ranging (LiDAR) sensors, equipment operating with image recognition technology, devices capable of detecting and localising UAV remote control signals and human air observers (1) . After a target drone is detected, elimination methods such as laser guns, water cannons, birds trained to catch drones and jamming can be applied.…”
The number of unmanned aerial vehicles (UAVs, also known as drones) has increased dramatically in the airspace worldwide for tasks such as surveillance, reconnaissance, shipping and delivery. However, a small number of them, acting maliciously, can raise many security risks. Recent Artificial Intelligence (AI) capabilities for object detection can be very useful for the identification and classification of drones flying in the airspace and, in particular, are a good solution against malicious drones. A number of counter-drone solutions are being developed, but the cost of drone detection ground systems can also be very high, depending on the number of sensors deployed and powerful fusion algorithms. We propose a low-cost counter-drone solution composed uniquely by a guard-drone that should be able to detect, locate and eliminate any malicious drone. In this paper, a state-of-the-art object detection algorithm is used to train the system to detect drones. Three existing object detection models are improved by transfer learning and tested for real-time drone detection. Training is done with a new dataset of drone images, constructed automatically from a very realistic flight simulator. While flying, the guard-drone captures random images of the area, while at the same time, a malicious drone is flying too. The drone images are auto-labelled using the location and attitude information available in the simulator for both drones. The world coordinates for the malicious drone position must then be projected into image pixel coordinates. The training and test results show a minimum accuracy improvement of 22% with respect to state-of-the-art object detection models, representing promising results that enable a step towards the construction of a fully autonomous counter-drone system.
“…Another indisputable advantage of this device is its low price in combination with normal commercial availability [6]. Figure 5 shows an object with a marked critical defence point (red circle), access roads (3, 5), high-rise areas (1,2,4), and a low building (6), which poses the greatest risk due to the possibility of direct visibility to defended point It is advisable to place the sensors so that they cover most of the area and selected places outside the area from which the UAS control could be performed. The Alfa AWUS036AC device, which is connected to a certain small computer, e.g.…”
Section: The Proposed Concept Applied In the Urban Areamentioning
confidence: 99%
“…A very dynamic development of Unmanned Aerial Systems (UASs) is becoming highly visible as they are used in all areas of human activities [2].…”
This paper describes methods of eliminating Unmanned Aerial Vehicles (UAV) nondestructively, using Electronic Warfare Methods. The aim is to introduce certain methods of UAV detection and elimination in a complex environment and terrain, e.g., in an urban and battlefield environment, that will result in finding the control device position and the UAV itself. Neural networks, cyber penetration elements, and wireless network scanning programs are all used to address this issue. The output of this article is a new concept of a comprehensive solution, which can be implemented into the existing complex system of electronic defence against UAVs, e.g., within the allied base. Conclusions will be also used to further improve the above-mentioned topics at the authors' workplace, within the frame of long-term projects and specifically as a part of solutions applicable to the force protection of combat support units, namely field artillery, which is described here in detail.
“…The producers of commercial drones compete for potential customers, and they are constantly innovating and improving their products. These innovations continuously improve flight parameters such as flying range, speed, load capacity, and autonomous activity algorithms or artificial intelligence capable of transporting the drone through a number of obstacles [1]. Like any technology, drones can be misused.…”
The fight against unmanned vehicles is nothing new; however, especially with the arrival of new technologies that are easily accessible for the wider population, new problems are arising. The deployment of small unmanned aerial vehicles (UAVs) by paramilitary organizations during conflicts around the world has become a reality, non-lethal “paparazzi” actions have become a common practice, and it is only a matter of time until the population faces lethal attacks. The basic prerequisite for direct defense against attacking UAVs is their detection. The authors of this paper analysed the possibility of detecting flying aircraft in several different electro-magnetic spectrum bands. Firstly, methods based on calculations and simulations were chosen, and experiments in laboratories and measurements of the exterior were subsequently performed. As a result, values of the radar cross section (RCS), the noise level, the surface temperature, and optical as well as acoustic traces of tested devices were quantified. The outputs obtained from calculated, simulated, and experimentally detected values were found via UAV detection distances using specific sensors working in corresponding parts of the frequency spectrum.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.