Drone Detection Using Convolutional Neural Networks with Acoustic STFT Features

Seo, Yoojeong; Jang, Beomhui; Im, Sungbin

doi:10.1109/avss.2018.8639425

Cited by 48 publications

(23 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The support vector machine (SVM) was then used to classify the UAVs. Seo et al [18] used a STFT method to transform the UAV sound signal into a spectrogram and used CNN to perform a classification task. Thai et al [27] used camera to capture the flight video of the UAVs, and employed optical flow to localize and track the flight trajectory of the UAV, through Harris detection and CNN, and finally applied k-nearest neighbor (KNN) for UAV classification.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

BisSiam: Bispectrum Siamese Network Based Contrastive Learning for UAV Anomaly Detection

Li¹,

Zhou²,

Cai³

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

In recent years, a surging number of unmanned aerial vehicles (UAVs) are pervasively utilized in many areas. However, the increasing number of UAVs may cause privacy and security issues such as voyeurism and espionage. It is critical for individuals or organizations to manage their behaviors and proactively prevent the misbehaved invasion of unauthorized UAVs through effective anomaly detection. The UAV anomaly detection framework needs to cope with complex signals in the noisy-prone environments and to function with very limited labeled samples. This paper proposes BISSIAM, a novel framework that is capable of identifying UAV presence, types and operation modes. BISSIAM converts UAVs signals to bispectrum as the input and exploits a siamese network based contrastive learning model to learn the vector encoding. A sampling mechanism is proposed for optimizing the sample size involved in the model training whilst ensuring the model accuracy without compromising the training efficiency. Finally, we present a similarity-based fingerprint matching mechanism for detecting unseen UAVs without the need of retraining the whole model. Experiment results show that our approach outperforms other baselines and can reach 92.85% accuracy of UAV type detection in unsupervised learning scenarios. 91.4% accuracy can be achieved when BISSIAM is used for detecting the UAV type of the out-of-sample UAVs.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Complex signal sources in noise-prone environments. Existing work typically collects and extracts UAV signals through analyzing physical signals, such as acoustic [17], [18], radar [19], [20], radio-frequency (RF) signal [21], [22], [23], [24],…”

Section: Introductionmentioning

confidence: 99%

BisSiam: Bispectrum Siamese Network Based Contrastive Learning for UAV Anomaly Detection

Li¹,

Zhou²,

Cai³

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…Seo et al proposed to use the normalized STFT to create 2D images from drones' acoustic signals [41]. The sound signal was first divided to 20-ms segments with 50% overlapping.…”

Section: Ml-based Drone Classification By Acoustic Datamentioning

confidence: 99%

Machine Learning-Based Drone Detection and Classification: State-of-the-Art in Research

2019

View full text Add to dashboard Cite

This paper presents a comprehensive review of current literature on drone detection and classification using machine learning with different modalities. This research area has emerged in the last few years due to the rapid development of commercial and recreational drones and the associated risk to airspace safety. Addressed technologies encompass radar, visual, acoustic, and radio-frequency sensing systems. The general finding of this study demonstrates that machine learning-based classification of drones seems to be promising with many successful individual contributions. However, most of the performed research is experimental and the outcomes from different papers can hardly be compared. A general requirement-driven specification for the problem of drone detection and classification is still missing as well as reference datasets which would help in evaluating different solutions.

show abstract

“…The major de iciency of the model is observed at (13,3), where 14 out of 200 test data which belongs to class 3 is predicted as class 13. These two controllers belong to the same company and both their time-series plots and spectrograms show high virtual resemblance.…”

Section: Model With a Merged Training Setmentioning

confidence: 99%

RF-based low-SNR classification of UAVs using convolutional neural networks

Ozturk¹,

Erden²,

Güvenç³

2021

ITU-J FET

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs), or drones, which can be considered as a coverage extender for Internet of Everything (IoE), have drawn high attention recently. The proliferation of drones will raise privacy and security concerns in public. This paper investigates the problem of classification of drones from Radio Frequency (RF) fingerprints at the low Signal-to-Noise Ratio (SNR) regime. We use Convolutional Neural Networks (CNNs) trained with both RF time-series images and the spectrograms of 15 different off-the-shelf drone controller RF signals. When using time-series signal images, the CNN extracts features from the signal transient and envelope. As the SNR decreases, this approach fails dramatically because the information in the transient is lost in the noise, and the envelope is distorted heavily. In contrast to time-series representation of the RF signals, with spectrograms, it is possible to focus only on the desired frequency interval, i.e., 2.4 GHz ISM band, and filter out any other signal component outside of this band. These advantages provide a notable performance improvement over the time-series signals-based methods. To further increase the classification accuracy of the spectrogram-based CNN, we denoise the spectrogram images by truncating them to a limited spectral density interval. Creating a single model using spectrogram images of noisy signals and tuning the CNN model parameters, we achieve a classification accuracy varying from 92% to 100% for an SNR range from -10 dB to 30 dB, which significantly outperforms the existing approaches to our best knowledge.

show abstract

Drone Detection Using Convolutional Neural Networks with Acoustic STFT Features

Cited by 48 publications

References 8 publications

BisSiam: Bispectrum Siamese Network Based Contrastive Learning for UAV Anomaly Detection

BisSiam: Bispectrum Siamese Network Based Contrastive Learning for UAV Anomaly Detection

Machine Learning-Based Drone Detection and Classification: State-of-the-Art in Research

RF-based low-SNR classification of UAVs using convolutional neural networks

Contact Info

Product

Resources

About