Micro-Motion Classification of Flying Bird and Rotor Drones via Data Augmentation and Modified Multi-Scale CNN

Chen, Xiaolong; Zhang, Hai; Song, Jie Guang; Guan, Jian; Li, Jiefang; He, Ziwen

doi:10.3390/rs14051107

Cited by 15 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bennett et al [26] modeled the aerodynamics of UAV m-D signatures' point amounts. Moreover, several methods and systems for classifying drones and birds of prey identification are described in [27][28][29][30][31].…”

Section: Introductionmentioning

confidence: 99%

A Micro-Motion Parameters Estimation Method for Multi-Rotor Targets without a Prior

Ren,

Liang,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Multi-rotor aircraft have the advantages of a simple structure, low cost, and flexible operation in the unmanned aerial vehicle (UAV) family, and have developed rapidly in recent years. Radar surveillance and classification of the growing number of multi-rotor aircraft has become a challenging problem due to their low-slow-small (LSS) characteristics. Estimation of the blade number is an important step in distinguishing LSS targets. However, most of the current research on micro-motion parameters estimation has focused on the analysis of rotational frequency, length, and the initial phase of blades with a prior of blade number, affecting its ability to identify LSS targets. In this article, a micro-motion parameters estimation method for multi-rotor targets without a prior is proposed. On the basis of estimating the flashing frequency of the blades, a validation function is constructed through spectral analysis to judge the number of blades, and then the rotational frequency is estimated. The blade length is calculated by estimating the maximum Doppler shift. Moreover, the variational mode decomposition (VMD)-based atomic scaling orthogonal matching pursuit (AS-OMP) method is jointly applied to estimate the blade length when suffering from the low PRF and insufficient SNR conditions. Extensive experiments on the simulated and measured data demonstrate that the proposed method outperforms robust micro-motion parameter estimation capability in low PRF and insufficient SNR conditions compared to the traditional time-frequency analysis methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A Micro-Motion Parameters Estimation Method for Multi-Rotor Targets without a Prior

Ren,

Liang,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…With the fast development of deep learning techniques [10][11][12], a new category of algorithms is applied to the radar intra-pulse signal modulation classification problem. Based on different domains of the signals worked on, they can be roughly divided into raw signal-based algorithms [13][14][15] and time-frequency transformation-based ones [16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Radar Intra–Pulse Signal Modulation Classification with Contrastive Learning

et al. 2022

View full text Add to dashboard Cite

The existing research on deep learning for radar signal intra–pulse modulation classification is mainly based on supervised leaning techniques, which performance mainly relies on a large number of labeled samples. To overcome this limitation, a self–supervised leaning framework, contrastive learning (CL), combined with the convolutional neural network (CNN) and focal loss function is proposed, called CL––CNN. A two–stage training strategy is adopted by CL–CNN. In the first stage, the model is pretrained using abundant unlabeled time–frequency images, and data augmentation is used to introduce positive–pair and negative–pair samples for self–supervised learning. In the second stage, the pretrained model is fine–tuned for classification, which only uses a small number of labeled time–frequency images. The simulation results demonstrate that CL–CNN outperforms the other deep models and traditional methods in scenarios with Gaussian noise and impulsive noise–affected signals, respectively. In addition, the proposed CL–CNN also shows good generalization ability, i.e., the model pretrained with Gaussian noise–affected samples also performs well on impulsive noise–affected samples.

show abstract

“…The micro-Doppler theory was first proposed by V. C. Chen from the US Naval Laboratory [3]; it is used to represent the Doppler effect caused by the micromotion of the various components within a target. Nowadays, micro-Doppler signatures are widely used in radar target recognition and micro-motion parameter estimation [4][5][6]. The micro-motion of the drone is generated by the propeller blade rotation, and the bird is due to the flapping of the wings.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Rotor Drone Micro-Motion Parameter Estimation Method Based on CVMD and SVD

Yang

Liang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

It is of great significance to detect drones in airspace due to the substantial increase and regrettable misuse in the consumer market. In this paper, we establish a micro-motion theoretical model of a drone and analyze the micro-Doppler signature of rotor targets and the flicker mechanisms of the multi-rotor targets. Hence, for the target recognition problem of multi-rotor drones, a multi-rotor target micro-Doppler parameter estimation method is proposed. Firstly, a signal frequency domain segmentation method is proposed based on the complex variational mode decomposition (CVMD) to separate the high-frequency part of the high-frequency flicker in the frequency domain. Secondly, for the signal after frequency domain segmentation, a flicker time domain position method based on singular value decomposition (SVD) is proposed. Finally, by integrating CVMD frequency domain segmentation and SVD time domain positioning, the reconstruction of multi-rotor target scintillation at different speeds is realized, and the micro-motion parameters of rotor blades are successfully estimated. The simulation results show that the method has high accuracy in estimating the micro-motion parameters of a multi-rotor, which makes up for the shortage of the traditional method in estimating the micro-motion parameters of the multi-rotor target.

show abstract

Micro-Motion Classification of Flying Bird and Rotor Drones via Data Augmentation and Modified Multi-Scale CNN

Cited by 15 publications

References 29 publications

A Micro-Motion Parameters Estimation Method for Multi-Rotor Targets without a Prior

A Micro-Motion Parameters Estimation Method for Multi-Rotor Targets without a Prior

Radar Intra–Pulse Signal Modulation Classification with Contrastive Learning

A Multi-Rotor Drone Micro-Motion Parameter Estimation Method Based on CVMD and SVD

Contact Info

Product

Resources

About