Detection, Tracking and Classification of Aircraft and Drones in Digital Towers Using Machine Learning on Motion Patterns

Thai, Van-Phat; Zhong, Wen‐De; Pham, Thinh Hung; Alam, Sameer; Dương, Vũ

doi:10.1109/icnsurv.2019.8735240

Cited by 33 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. As a departure from the optical-based approaches, Rozantsev et al [28] stacked the motion windows of UAVs on several consecutive frames and combined them with a regression motion stabilization algorithm to achieve UAV track in low light or almost invisible conditions.…”

Section: Related Workmentioning

confidence: 99%

“…• T. Li, Z. Hong, Q. Cai, L.Yu, Z. Wen [25], [26]), or through camera-based target tracking from video streaming [27], [28] or statistically monitoring network traffic data [29], [30]. Acoustic-based approaches are typically sensitive to environmental noises whilst the visual quality of camera is subject to the surrounding conditions such as building blockage, ambient lighting, etc.…”

Section: Introductionmentioning

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%

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

“…In work [12] the authors trained a K-Nearest Neighbour (KNN) classifier to differentiate between drones and aircrafts. They used x, y coordinates extracted from videos of installations at an airport.…”

Section: Related Workmentioning

confidence: 99%

Radar Discrimination of Small Airborne Targets Through Kinematic Features and Machine Learning

Doumard

Riesco

Petrunin

et al. 2022

2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC)

View full text Add to dashboard Cite

This work studies binary classification problem for small airborne targets (drones vs other) by means of their trajectory analysis. For this purpose a set of the kinematic features extracted from drone trajectories using radar detections with a classification scheme that utilises Random Forests is proposed. The development is based on experimental data acquired from the Holographic radar from Aveillant Ltd. An approach for real-time classification is proposed, where an adaptive sliding window procedure is employed to make predictions over time from trajectories. Several models utilising different kinematic features (angle, slope, velocity, and their combination) are studied. The best model achieves an accuracy of more than 95%. In addition, fundamental issues with imbalanced datasets in the context of this topic are raised and illustrated using the collected data.

show abstract

“…Acoustic sensors do not require line-of-sight (LOS); however, they suffer from short range, as drones could operate very quietly [12,28], and data gathered using microphone systems are prone to wind and environmental clutter. On the other hand, a LOS vision under daylight is essential for techniques that utilize camera images [14,29]. Using thermal or laser-based cameras to overcome this issue increases the cost signi icantly.…”

Section: Literature Review and Contribu-tionsmentioning

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

Detection, Tracking and Classification of Aircraft and Drones in Digital Towers Using Machine Learning on Motion Patterns

Cited by 33 publications

References 11 publications

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

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

Radar Discrimination of Small Airborne Targets Through Kinematic Features and Machine Learning

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

Contact Info

Product

Resources

About