Drone Detection and Defense Systems: Survey and a Software-Defined Radio-Based Solution

Chiper, Florin-Lucian; Marțian, Alexandru; Vlădeanu, Călin; Marghescu, Ion; Crăciunescu, Răzvan; Fratu, Octavian

doi:10.3390/s22041453

Cited by 58 publications

(36 citation statements)

References 114 publications

(97 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, now we have more friendly interfaces exploiting natural interactions and enhanced by improved self-stabilization drone mechanisms. Many recent works deal with drone communication protocols (Hassija et al, 2021), with drone detection in military and security-related contexts (Chiper et al, 2022), or with specific drone applications, either military or civil (e.g., Roldán-Gómez et al, 2021), or for entertainment (Kim et al, 2018).…”

Section: Related Work On Traditional and Natural Interaction-based Dr...mentioning

confidence: 99%

A Natural Human-Drone Embodied Interface: Empirical Comparison With a Traditional Interface

Vincenzo¹,

Palini²,

Marsico

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Despite the importance of usability in human-machine interaction (HMI), most commonly used devices are not usable by all potential users. In particular, users with low or null technological experience, or with special needs, require carefully designed systems and easy-to-use interfaces supporting recognition over recall. To this purpose, Natural User Interfaces (NUIs) represent an effective strategy as the user's learning is facilitated by features of the interface that mimic the human “natural” sensorimotor embodied interactions with the environment. This paper compares the usability of a new NUI (based on an eye-tracker and hand gesture recognition) with a traditional interface (keyboard) for the distal control of a simulated drone flying in a virtual environment. The whole interface relies on “dAIsy”, a new software allowing the flexible use of different input devices and the control of different robotic platforms. The 59 users involved in the study were required to complete two tasks with each interface, while their performance was recorded: (a) exploration: detecting trees embedded in an urban environment; (b) accuracy: guiding the drone as accurately and fast as possible along a predefined track. Then they were administered questionnaires regarding the user's background, the perceived embodiment of the device, and the perceived quality of the virtual experience while either using the NUI or the traditional interface. The results appear controversial and call for further investigation: (a) contrary to our hypothesis, the specific NUI used led to lower performance than the traditional interface; (b) however, the NUI was evaluated as more natural and embodied. The final part of the paper discusses the possible causes underlying these results that suggest possible future improvements of the NUI.

show abstract

Section: Related Work On Traditional and Natural Interaction-based Dr...mentioning

confidence: 99%

A Natural Human-Drone Embodied Interface: Empirical Comparison With a Traditional Interface

Vincenzo¹,

Palini²,

Marsico

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…Compared to the detection solutions relying on acoustic and visual sensing, both active and passive RF drone detection methods ensure higher robustness, achieving good results regardless of the environmental conditions [ 10 ]. The passive approaches, exploiting the physical layer protocols used by drones, analyze the RF spectrum to identify the uplink or downlink transmissions that occur between drones and their controller based on the well-known features of these links [ 21 , 22 , 23 , 24 ]. The major drawback of passive RF methods is their limitation in detecting the UAVs that function in fully autonomous mode.…”

Section: Introductionmentioning

confidence: 99%

UWB Sensing for UAV and Human Comparative Movement Characterization

Digulescu

Despina-Stoian

Popescu

et al. 2023

Sensors

View full text Add to dashboard Cite

Nowadays, unmanned aerial vehicles/drones are involved in a continuously growing number of security incidents. Therefore, the research interest in drone versus human movement detection and characterization is justified by the fact that such devices represent a potential threat for indoor/office intrusion, while normally, a human presence is allowed after passing several security points. Our paper comparatively characterizes the movement of a drone and a human in an indoor environment. The movement map was obtained using advanced signal processing methods such as wavelet transform and the phase diagram concept, and applied to the signal acquired from UWB sensors.

show abstract

“…It can identify three models (Parrot Bebop, Parrot AR, DJI Phantom), and for the Parrot model, it is able to identify the flight mode of the drone. The DronEnd system [ 10 ] is used to jam the RF of the drones. Yang et al [ 11 ] are able to detect drones with close to 100% accuracy at distances up to 2.4 km.…”

Section: Introductionmentioning

confidence: 99%

Drone Model Classification Using Convolutional Neural Network Trained on Synthetic Data

2022

View full text Add to dashboard Cite

We present a convolutional neural network (CNN) that identifies drone models in real-life videos. The neural network is trained on synthetic images and tested on a real-life dataset of drone videos. To create the training and validation datasets, we show a method of generating synthetic drone images. Domain randomization is used to vary the simulation parameters such as model textures, background images, and orientation. Three common drone models are classified: DJI Phantom, DJI Mavic, and DJI Inspire. To test the performance of the neural network model, Anti-UAV, a real-life dataset of flying drones is used. The proposed method reduces the time-cost associated with manually labelling drones, and we prove that it is transferable to real-life videos. The CNN achieves an overall accuracy of 92.4%, a precision of 88.8%, a recall of 88.6%, and an f1 score of 88.7% when tested on the real-life dataset.

show abstract

Drone Detection and Defense Systems: Survey and a Software-Defined Radio-Based Solution

Cited by 58 publications

References 114 publications

A Natural Human-Drone Embodied Interface: Empirical Comparison With a Traditional Interface

A Natural Human-Drone Embodied Interface: Empirical Comparison With a Traditional Interface

UWB Sensing for UAV and Human Comparative Movement Characterization

Drone Model Classification Using Convolutional Neural Network Trained on Synthetic Data

Contact Info

Product

Resources

About