micro-Doppler Features Research Articles

Classification of UAV-to-Ground Targets Based on Enhanced Micro-Doppler Features Extracted via PCA and Compressed Sensing

In order to achieve precise operations on specified targets from the unmanned aerial vehicles (UAVs), classifying ground targets correctly is especially important. Micro-Doppler effect which provides unique information of targets has been the basis for targets classification. Due to the effect of ground clutter, noise and complex signal modulation, enhancing micro-Doppler features of UAV-to-ground targets is necessary for accurate classification. This paper firstly establishes the models of UAV-to-ground targets including wheeled vehicles, tracked vehicles and pedestrians to analyze their micro-Doppler differences. Secondly, Principal Components Analysis (PCA) is utilized to remove the ground clutter. Compared with other algorithms, PCA can use a small amount of calculation to remove the ground clutter while retain nearby micro-Doppler signals. Then, micro-Doppler signals are sparsely represented based on Fourier basis. Orthogonal Matching Pursuit (OMP) is chosen to reconstruct micro-Doppler components and refine spectral lines after random projection. The three steps make up Compressed Sensing (CS) together. At last, non-linear transform of Doppler spectrum is conducted to further enhance the distinction of micro-Doppler spectral lines. Distinguishing micro-Doppler features are extracted from pre-processed micro-Doppler signals, which eventually contributes to the accurate targets classification. Comparison with other methods is also made to prove the robustness and anti-noise performance of proposed method.

Multi-frequency and multi-domain human activity recognition based on SFCW radar using deep learning

Deep learning and radar make it feasible to automatically recognize human activities in various lighting conditions, even occlusion case, which significantly promotes the application of activity recognition in the fields of security surveillance, health care, and so on. In this paper, an approach for human activity recognition (HAR) using deep learning is proposed based on stepped frequency continues wave (SFCW) radar. Specifically, SFCW radar is utilized to generate two types of characteristic representation domains, namely multiple frequencies of spectrograms in time–frequency domain and range maps in range domain. On the one hand, spectrograms and range maps provide different types of features. On the other hand, multi-frequency spectrograms furnish same type of features while with different scattering properties and frequency resolutions. Then a specific deep learning network including multiple parallel deep convolutional neural networks (DCNNs) and a sparse autoencoder is designed to extract and fuse these features associated with human activities from the multi-frequency spectrograms and rang map. In particular, each DCNN is aimed at extracting the detailed micro-Doppler features from a spectrogram, while sparse autoencoder learns prime range distribution features by compressing each range map to reduce complexity and improve robustness. Experimental results verify that the proposed deep learning scheme achieves 96.42% recognition accuracy about six types of activities by incorporating three frequencies of spectrograms and range map, and surpasses two existed methods depending on single-frequency spectrogram and combination of single-frequency spectrogram and range map.

Parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on micro-Doppler features using CNN

This paper proposes a parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on the convolutional neural network (CNN) using micro Doppler features. Firstly, the time-frequency spectrograms are acquired from the radar echo by the short-time Fourier transform. Secondly, based on the obtained spectrograms, a seven-layer CNN architecture is built to recognize the blade-number parity and classify the manoeuvre intention of the rotor target. The constructed architecture contains a leaky rectified linear unit and a dropout layer to accelerate the convergence of the architecture and avoid over-fitting. Finally, the spectrograms of the datasets are divided into three different ratios, i.e., 20%, 33% and 50%, and the cross validation is used to verify the effectiveness of the constructed CNN architecture. Simulation results show that, on the one hand, as the ratio of training data increases, the recognition accuracy of parity and manoeuvre intention is improved at the same signal-to-noise ratio (SNR); on the other hand, the proposed algorithm also has a strong robustness: the accuracy can still reach 90.72% with an SNR of −6 dB.

Rotor Blades Micro-Doppler Feature Analysis and Extraction of Small Unmanned Rotorcraft

In this article, the micro-Doppler feature analysis and extraction of small unmanned rotorcraft (SUR) is considered. To be specific, the radar returns from the rotor blades are first modeled as sinusoidal frequency-modulated (SFM) signals. Then, the Gabor transform is utilized to obtain the time-frequency distribution (TFD). In order to solve the problem of limited TF analysis resolutions, high carrier frequency of radar is employed for the sake of separating different sinusoidal curves from TFD. After that, the Hough-Radon transform (HRT) is introduced to detect the sinusoidal curves from the TFD. Finally, based on the relationship between the SFM signal and the rotating blade, the micro-Doppler parameters which can reflect the threat level of the SUR to a large extend are estimated. Compared with other existing methods, the proposed method presents the relationships between the carrier frequency and the rotating blade parameters and it can be employed to extract the micro-Doppler feature of SUR with multiple rotor hubs. Simulation results demonstrate the effectiveness of the proposed micro-Doppler feature extraction method.

Enhanced Multi-Channel Feature Synthesis for Hand Gesture Recognition Based on CNN With a Channel and Spatial Attention Mechanism

Millimeter-wave (MMW) radar hand gesture recognition technology is becoming important in many electronic device control applications. Currently, most existing approaches utilize the radical and micro-Doppler features from single-channel MMW radar, which ignores the different importance of the information contained in the micro-Doppler feature background or target areas. In this paper, we propose an algorithm for hand gesture recognition jointly using multi-channel signatures. The algorithm blends the information of both micro-Doppler features and instantaneous angles (azimuth and elevation) to accomplish hand gesture recognition performed with the convolutional neural network (CNN). To have a better features fusion and make CNN focus on the most important target signal regions and suppress the unnecessary noise areas, we apply the channel and spatial attention-based feature refinement modules. We also employ gesture movement mechanism-based data augmentation for more effective training to alleviate potential overfitting. Extensive experiments demonstrate the effectiveness and superiorities of the proposed algorithm. This method achieves a correct classification rate of 96.61%, approximately 5% higher than that of the single-channel-based recognition strategy as measured based on MMW radar datasets.

Comparison of micro‐Doppler signatures registered using RBM of helicopters and WSM of vehicles

Jet engine modulation (JEM) are micro-Doppler features obtained from the radar data of aircraft, including jet aircraft and helicopters, and generally viewed as unique phenomenon suitable for identifying aerial targets. The authors demonstrate however, that JEM are not unique, and that the rotating wheel spokes on the wheels of ground vehicles produce a modulation similar to the rotating rotor blades of jet engines and helicopter rotor blades. They also develop a mathematical model to analyse the radar signal scattering mechanism of wheel spokes, and also employ a Ku-band Doppler radar system to collect radar echoes from a wheeled vehicle and a helicopter. Both the theoretical and experimental results verify the existence of rotor blade modulation (RBM) phenomena from helicopters and wheel spoke modulation (WSM) phenomena from vehicles. Both RBM and WSM are similar to JEM features. This fact indicates that JEM is a necessary but insufficient condition for the identification of aerial targets, and additional recognition features inherent in surface surveillance radar are needed to distinguish the JEM spectra arising from aerial targets and ground vehicles.

Analysis of phase noise influence on micro‐Doppler feature extraction of vibrating target

It is generally considered that increasing the carrier frequency of radar is an important way to improve the precision of micro-motion measurement. However, the increase of the radar frequency may raise the phase noise intensity of the radar transmitting signal and make the extraction more difficult, therefore it is particularly necessary to study the influence of phase noise on the extraction of micro-motion characteristics. In this study, specific studying about the effect of phase noise on the extraction of micro-Doppler (m-D) features is carried out. The effect of phase noise on the extraction performance of the m-D features is evaluated based on a parameter micro-motion signal-to-clutter ratio and an empirical formula is put forward based on the experiments. The results of simulation experiments indicate that increasing the carrier frequency cannot improve the extraction performance of micro-motion features in the case of using both time–frequency analysis method and the new developed sinusoidal frequency modulation Fourier transform (SFMFT) method. Meanwhile, increasing the frequency of target's micro-motion has an improvement effect through time–frequency method due to the increase of Doppler frequency.

Template free Micro Doppler Signature Classification for Wheeled and Tracked Vehicles

The micro-Doppler signature is a time-varying frequency modulation imparted on radar echo caused by target’s micro-motion. To save the trouble of constructing template in the target classification, this paper investigates the micro-Doppler signature of wheeled and tracked vehicles and proposes a template-free classification method. Firstly, the echo signature is established and the micro-Doppler difference of these two kinds of targets is analysed. Secondly, some new micro-Doppler features are defined according to their difference. The new defined features are micro-Doppler bandwidth, micro-Doppler expansion rate and micro-Doppler peak number. According to the characteristic of the micro-Doppler in the time-frequency domain, we proposed to realise the feature extraction by Hough transformation. Lastly, template-free subjection functions are proposed to define the relationship between the features and the vehicles. By fuzzy comprehensive evaluation, the final classification result is obtained by combining the subjection probabilities together. Experimental results based on the simulated data and measured data are presented, which prove that the algorithm has good performance.

Micro‐Doppler feature extraction method for vibration targets based on the segmental intrinsic chirp component decomposition

Based on the three-antenna interferometric radar system, a novel micro-Doppler feature extraction method for vibration targets is proposed in this study. First, the theory of interferometric processing of echo signal for vibration targets is introduced and explained. Second, short-time Fourier transform is conducted with the time–frequency diagram of echo signal obtained. Then, the signals received by three-antenna model are decomposed based on the segmental intrinsic chirp component decomposition. Finally, the 2D trajectory of vibration target is reconstructed and its micro-Doppler features are effectively extracted via the interferometric phase. Besides, the micro-Doppler parameters can also be estimated with the method. Two simulation experiments are conducted to validate the proposed method.

Three‐dimensional reconstruction of space rotating target based on narrow‐band radar networks

The micro-motion of space target is an important signature for classification and recognition, which has received great attention. Based on the micro-Doppler signals from narrow-band radar networks, this study proposes a three-dimensional reconstruction method of space rotating target. First, the rotational plane projection model and the three-dimensional structure construction model are built based on the micro-Doppler analysis of rotating targets. Then, the rotational axis of the target is accurately estimated by exploiting the relationship of micro-Doppler features of sub-radars in the radar networks. Finally, under the constraint of the physical shape of a cone target, the target with arbitrary number scatters can be reconstructed by setting a cost function. Experiments verify the validity and accuracy of the proposed method.

Application of S-Transform Random Consistency in Inverse Synthetic Aperture Imaging Laser Radar Imaging

Under the same principle, laser radar could be more sensitive to the micro-Doppler (m-D) effect due to its wave length, as the characteristic of multi-resolution, S transform could reduce the influence of the micro-Doppler component and enhance the imaging effect. This paper presents a method for micro-Doppler feature extraction in Inverse Synthetic Aperture Imaging Laser Radar (ISAIL) imaging. It is accessible and comprehensive, applying Random Sample Consensus (RANSAC) for the separation and reconstruction of micro-Doppler and rigid body signals. Experiments show that the method can effectively remove the micro-Doppler information and obtain a clear target distance-instantaneous Doppler image.

A Method of Ultrasonic Finger Gesture Recognition Based on the Micro-Doppler Effect

With the popularity of small-screen smart mobile devices, gestures as a new type of human–computer interaction are highly demanded. Furthermore, finger gestures are more familiar to people in controlling devices. In this paper, a new method for recognizing finger gestures is proposed. Ultrasound was actively emitted to measure the micro-Doppler effect caused by finger motions and was obtained at high resolution. By micro-Doppler processing, micro-Doppler feature maps of finger gestures were generated. Since the feature map has a similar structure to the single channel color image, a recognition model based on a convolutional neural network was constructed for classification. The optimized recognition model achieved an average accuracy of 96.51% in the experiment.

A robust detection method for micro-Doppler feature of rotating blades under low SNR

Rotation of rotor blades is typically micro-motion and would induce micro-Doppler modulation. However, accurate detection will become extremely difficult when the echo signal is corrupted by strong noise. This paper proposes a method to realize extraction of micro-Doppler feature from the rotating rotor blade echo signals with low signal-to-noise ratio (SNR). The proposed method is characterized by applying low-rank decomposition for saliency detection of spectrogram. MATLAB simulation results verify that the proposed method is effective in saliency detection of the spectrogram from rotor blade echo signals and is robust in estimating the maximum micro-Doppler shift under low SNR.

Classification of UAV-to-Ground Vehicles Based on Micro-Doppler Signatures Using Singular Value Decomposition and Deep Convolutional Neural Networks

Attack from the unmanned aerial vehicles (UAVs) has been the main means of high-precision strike. Therefore, classifying ground vehicles from the UAV with high accuracy is of great significance. In order to avoid the complex feature extracting process and realize the classification of UAV-to-ground vehicles in different situations, this paper proposed a method based on micro-Doppler signatures using singular value decomposition (SVD) and deep convolutional neural networks (DCNNs). First, models of UAV-to-ground vehicles are built to analyze the micro-Doppler components and Doppler signals in five different cases are given. Second, time-frequency spectrums of Doppler signals with low signal-to-noise ratios are improved after removing noise using SVD. Third, transfer-learning of pre-trained DCNNs is achieved using measured data and classification under various conditions is realized using the new-trained network. When there is no noise, the overall classification accuracy of two types of Doppler signals, three types of Doppler signals, four types of Doppler signals and five types of Doppler signals has reached 100%, 97%, 97%, and 96%, respectively. Comparison with current methods which need to extract micro-Doppler features by time-frequency techniques are also made. Outstanding performance proves the superiority and robustness of the proposed method.

Classification of UAV-to-ground vehicles based on micro-Doppler signatures using singular value decomposition and reconstruction

Classification of ground vehicles from the unmanned aerial vehicles (UAVs) is the basis for local precision strikes. In this paper, a method based on micro-Doppler effect which provides unique information of targets is proposed for ground vehicles classification. Firstly, models describing the air-to-ground relationship between ground vehicles and the UAV are built to derive mathematical expressions of radar echo signals. Secondly, Singular Value Decomposition (SVD) is utilized to analyze micro-Doppler components of the ground wheeled vehicle and the ground tracked vehicle respectively. Thirdly, according to classify requirements, specific signal components are restored by Singular Value Reconstruction (SVR). Seven micro-Doppler features are extracted from reconstructed signals. At last, these features are sent to Support Vector Machine (SVM) classifier. Compared with current related methods such as Empirical Mode Decomposition (EMD) and multi-level wavelet decomposition (MWD), experimental results in different cases illustrate the effectiveness of this method. Discrimination performance under various signal-to-noise ratios (SNRs) also proves the robustness of proposed method.

Radar micro-Doppler signatures of drones and birds at K-band and W-band

Due to the substantial increase in the number of affordable drones in the consumer market and their regrettable misuse, there is a need for efficient technology to detect drones in airspace. This paper presents the characteristic radar micro-Doppler properties of drones and birds. Drones and birds both induce micro-Doppler signatures due to their propeller blade rotation and wingbeats, respectively. These distinctive signatures can then be used to differentiate a drone from a bird, along with studying them separately. Here, experimental measurements of micro-Doppler signatures of different types of drones and birds are presented and discussed. The data have been collected using two radars operating at different frequencies; K-band (24 GHz) and W-band (94 GHz). Three different models of drones and four species of birds of varying sizes have been used for data collection. The results clearly demonstrate that a phase coherent radar system can retrieve highly reliable and distinctive micro-Doppler signatures of these flying targets, both at K-band and W-band. Comparison of the signatures obtained at the two frequencies indicates that the micro-Doppler return from the W-band radar has higher SNR. However, micro-Doppler features in the K-band radar returns also reveal the micro-motion characteristics of drones and birds very effectively.

Micro-Doppler Feature Extraction of Inverse Synthetic Aperture Imaging Laser Radar Using Singular-Spectrum Analysis.

Different from microwave radar, laser radar could be more sensitive to the micro-Doppler (m-D) effect due to its wave length. This limits the application of conventional methods, such as time–frequency based approach, since the processing needs a receiver with much higher sampling frequency than microwave radar. In this paper, a micro-Doppler feature extraction algorithm is proposed for the inverse synthetic aperture imaging laser radar (ISAIL). Singular-spectrum analysis (SSA) is employed for separation and reconstruction of the micro-Doppler and rigid body signal. Clear ISAIL image is obtained by minimum entropy criteria after echo signal decomposition. After theoretical derivation, the computation efficiency and ability of the proposed method is proved by the results of simulation and real data of An-26.

Development of test scenarios and bicyclist surrogate for the evaluation of bicyclist automatic emergency braking systems

Purpose To support the standardized evaluation of bicyclist automatic emergency braking (AEB) systems, test scenarios, test procedures and test system hardware and software tools have been investigated and developed by the Transportation Active Safety Institute (TASI) at Indiana University-Purdue University Indianapolis. This paper aims to focus on the development of test scenarios and bicyclist surrogate for evaluating vehicle–bicyclist AEB systems. Design/methodology/approach The harmonized general estimates system (GES)/FARS 2010-2011 crash data and TASI 110-car naturalistic driving data (NDD) are used to determine the crash geometries and environmental factors of crash scenarios including lighting conditions, vehicle speeds, bicyclist speeds, etc. A surrogate bicyclist including a bicycle rider and a bicycle surrogate is designed to match the visual and radar characteristics of bicyclists in the USA. A bicycle target is designed with both leg pedaling and wheel rotation to produce proper micro-Doppler features and generate realistic motion for camera-based AEB systems. Findings Based on the analysis of the harmonized GES/FARS crash data, five crash scenarios are recommended for performance testing of bicyclist AEB systems. Combined with TASI 110-car naturalistic driving data, the crash environmental factors including lighting conditions, obscuring objects, vehicle speed and bicyclist speed are determined. The surrogate bicyclist was designed to represent the visual and radar characteristics of the real bicyclists in the USA. The height of the bicycle rider mannequin is 173 cm, representing the weighted height of 50th percentile US male and female adults. The size and shape of the surrogate bicycle were determined as 26-inch wheel and mountain/road bicycle frame, respectively. Both leg pedaling motion and wheel rotation are suggested to produce proper micro-Doppler features and support the camera-based AEB systems. Originality/value The results have demonstrated that the developed scenarios, test procedures and bicyclist surrogate will provide effective objective methods and necessary hardware and software tools for the evaluation and validation of bicyclist AEB systems. This is crucial for the development of advanced driver assistance systems.

Effect of sparsity‐aware time–frequency analysis on dynamic hand gesture classification with radar micro‐Doppler signatures

Dynamic hand gesture recognition is of great importance in human-computer interaction. In this study, the authors investigate the effect of sparsity-driven time-frequency analysis on hand gesture classification. The time-frequency spectrogram is first obtained by sparsity-driven time-frequency analysis. Then three empirical micro-Doppler features are extracted from the time-frequency spectrogram and a support vector machine is used to classify six kinds of dynamic hand gestures. The experimental results on measured data demonstrate that, compared to traditional time-frequency analysis techniques, sparsity-driven time-frequency analysis provides improved accuracy and robustness in dynamic hand gesture classification.

Short-Time State-Space Method for Micro-Doppler Identification of Walking Subject Using UWB Impulse Doppler Radar

In this paper, ultra-wideband (UWB) Doppler radar signatures from walking human subjects are processed with the state-space method (SSM) to analyze compressed radar echoes for the first time. A new mathematical model is proposed to detect the human walking strides using UWB radar, while micro-Doppler ( $\mu $ -D) features are extracted for gait analysis using short-time SSM (STSSM). To distinguish $\mu $ -D signatures of different subjects’ body parts, the SSM used for the characterization of radar target signatures and sensor fusion is applied on a sliding short-time window to enhance the resolution of feature extraction from data collected on a dismount. This method of the application of SSM to sliding short-time data is validated with a full-wave electromagnetic (EM) simulation of a walking subject using the Boulic model that represents the human kinematics. An EM scattering model is then utilized to compare the performance of a short-time Fourier transform with STSSM. Experimental results show that STSSM can be successfully applied to identify multiple $\mu $ -D trajectories in real experimental data, thus demonstrating the capability to positively identify human motions (right foot, left foot, and torso) even in a low signal-to-noise ratio environment.