Application of machine learning for drone classification using radars

Hudson, Sinclair; Balaji, Bhashyam

doi:10.1117/12.2588694

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach taken in the paper is as follows, which is similar to prior work, such as [23]). The time domain signal is first converted to a frequency domain signal via an STFT.…”

Section: Detection and Classificationmentioning

confidence: 99%

Hybrid Quantum Neural Network Advantage for Radar-Based Drone Detection and Classification in Low Signal-to-Noise Ratio

Malarvanan

2024

Preprint

View full text Add to dashboard Cite

In this paper, we investigate the performance of a Hybrid Quantum Neural Network (HQNN) and a comparable classical Convolution Neural Network (CNN) for detection and classification problem using a radar. Specifically, we take a fairly complex radar time-series model derived from electromagnetic theory, namely the Martin-Mulgrew model, that is used to simulate radar returns of objects with rotating blades, such as drones. We find that when that signal-to-noise ratio (SNR) is high, CNN outperforms the HQNN for detection and classification. However, in the low SNR regime (which is of greatest interest in practice) the performance of HQNN is found to be superior to that of the CNN of a similar architecture.

show abstract

“…The approach taken in the paper is as follows, which is similar to prior work, such as [23]). The time domain signal is first converted to a frequency domain signal via an STFT.…”

Section: Detection and Classificationmentioning

confidence: 99%

Hybrid Quantum Neural Network Advantage for Radar-Based Drone Detection and Classification in Low Signal-to-Noise Ratio

Malarvanan

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors of [14 -15] tracked and classified drones using radar sensors. Work was done to show off how STFT spectrograms may be fed into a Convolutional Neural Network (CNN) to categorise drones [16]. The authors of [17] participated in a study that not only discusses the design choices made in contemporary deep (CNN) object detectors, but also offers a thorough analysis of the problems that the computer vision community is currently grappling with, as well as some complementary and innovative approaches to solving them.…”

Section: Related Workmentioning

confidence: 99%

A Reliable Algorithm with Increased Accuracy for Drone Detection

2022

View full text Add to dashboard Cite

Everybody, regardless of their intentions, may access drones thanks to increased technologies and privatisation. The disruption of aviation order, terrorist assaults, invasions of personal privacy, and the transit of hazardous materials are thus most at risk. The threat placed should be de-escalated right away. One of the most efficient ways to cope with it is drone detection and localisation. The YOLO algorithm, one of several deep learning algorithms, applies a single neural network to the entire image, splits it into parts, and forecasts bounding boxes and probabilities for each zone. The projected probabilities are used to weight these bounding boxes. Because of its speed, FPS (Frames Per Second), and memory usage, the new version YOLOv5 is popular. Using a Kaggle drone dataset, a trained model is created. The YOLOv5 technique is then used, and the model weights are obtained. Graphs are used for trained weight interpretation. These weights are employed in the drone detection process. Images and videos are used in this proposed work to detect drones. The aim of the proposed work is to improve the YOLOv5 algorithm's ability to detect drones with greater precision.

show abstract

“…The rotation of propeller blades on a drone is sufficient to generate these signatures. The use of radars for studying micro-Doppler signatures has been shown effective [11] and has been used in conjunction with machine learning for many UAV classification problems [12][13][14][15][16][17][18][19]. As such, radars are the chosen technology for this paper.…”

Section: Introductionmentioning

confidence: 99%

“…They also proposed a new multifrequency analysis of the HERM lines, which enables the approximation of the propeller rates [23]. In this paper, we leverage the work of Hudson et al, who demonstrated the potential of passing STFT spectrograms into a Convolutional Neural Network (CNN) to classify drones [13].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for Classification of Drones Using Radars

Raval

Hunter

Hudson

et al. 2021

Drones

View full text Add to dashboard Cite

The ability to classify drones using radar signals is a problem of great interest. In this paper, we apply convolutional neural networks (CNNs) to the Short-Time Fourier Transform (STFT) spectrograms of the simulated radar signals reflected from the drones. The drones vary in many ways that impact the STFT spectrograms, including blade length and blade rotation rates. Some of these physical parameters are captured in the Martin and Mulgrew model which was used to produce the datasets. We examine the data under X-band and W-band radar simulation scenarios and show that a CNN approach leads to an F1 score of 0.816±0.011 when trained on data with a signal-to-noise ratio (SNR) of 10 dB. The neural network which was trained on data from an X-band radar with 2 kHz pulse repetition frequency was shown to perform better than the CNN trained on the aforementioned W-band radar. It remained robust to the drone blade pitch and its performance varied directly in a linear fashion with the SNR.

show abstract

Application of machine learning for drone classification using radars

Cited by 6 publications

References 0 publications

Hybrid Quantum Neural Network Advantage for Radar-Based Drone Detection and Classification in Low Signal-to-Noise Ratio

Hybrid Quantum Neural Network Advantage for Radar-Based Drone Detection and Classification in Low Signal-to-Noise Ratio

A Reliable Algorithm with Increased Accuracy for Drone Detection

Convolutional Neural Networks for Classification of Drones Using Radars

Contact Info

Product

Resources

About