Search

For modern radar systems, small unmanned aerial vehicles (UAVs) belong to a typical types of targets with 'low, slow, and small' characteristics. In complex combat environments, the functional requirements of radar systems are not only limited to achieving stable detection and tracking performance but also to effectively complete the recognition of small UAV targets. In this paper, a multi-dimensional feature fusion framework for small UAV target recognition utilizing a small-sized and low-cost high-resolution radar is proposed, which can fully extract and combine the geometric structure features and the micro-motion features of small UAV targets. For the performance analysis, the echo data of different small UAV targets was measured and collected with a millimeter-wave radar, and the dataset consists of high-resolution range profiles (HRRP) and micro-Doppler time–frequency spectrograms was constructed for training and testing. The effectiveness of the proposed method was demonstrated by a series of comparison experiments, and the overall accuracy of the proposed method can reach 98.5%, which demonstrates that the proposed multi-dimensional feature fusion method can achieve better recognition performance than that of classical algorithms and higher robustness than that of single features for small UAV targets. [ABSTRACT FROM AUTHOR]

Gait recognition is to recognise different individuals based on their faint differences of gait characteristics, which is different from and more challengeable than the recognition of human activities based on relatively bigger differences between different motions. Existing millimetre‐wave Multiple Input Multiple Output radar point cloud data contains time‐varying three‐dimensional spatial positions, velocity, and intensity information. How to enhance the accuracy of gait recognition by effectively utilising the available radar point cloud data has become an attractive research topic in recent years. A velocity‐depth‐time (VDT) based point cloud construction method for millimetre‐wave Multiple Input Multiple Output radar is proposed for gait recognition application, which can not only alleviate the sparsity problem of mmWave point cloud but also make the constructed point cloud to exhibit temporal structural features of micro‐motions, and therefore enable the successful application of PointNet++ to mmWave‐MIMO point cloud gait recognition. New point clouds are constructed by the proposed method using public gait recognition datasets of 10 and 20 individuals from mmWave‐MIMO radar, which are used to conduct gait recognition experiments using PointNet++. The results show that the point clouds constructed based on VDT are more conducive to the gait recognition task. Even using the classic PointNet++ model, which is not specially designed for radar point clouds, high recognition accuracy can be achieved for gait recognition tasks. The recognition accuracies are improved by 11% and 12% in this work for datasets of 10 and 20 individuals, respectively, compared with the 84% and 80% achieved by the traditional method using the same dataset and the same PointNet++ model, while the accuracies are improved by 5% and 12%, respectively, compared with the 90% and 80% achieved by the original dataset thesis method corresponding to 10‐individual and 20‐individual datasets. [ABSTRACT FROM AUTHOR]

Countermeasures for chaff jamming have drawn great attention in the field of radar target detection and tracking. Current approaches for chaff jamming recognition and suppression exhibit limitations in practical effect, generalisation ability, and hybrid jamming handling. To address the above problems, the authors first transform the traditional 1D signal processing problem into a 2D semantic segmentation task and then solve it from the perspective of the dataset construction and algorithm design. For the dataset construction, the authors use both measured and simulated data to synthesise a more realistic labelled dataset (semi‐realistic dataset), which is also with good diversity due to its adjustable chaff interference background. For the algorithm design, the authors propose a Pre‐Decluttering Dual‐Stage UNet (D2UNet) to recognise and suppress chaff jamming in two stages successively, where the former provides prior attention masks for the latter. To further improve the performance of D2UNet, the authors also design a multi‐stage loss function to achieve progressive training. Extensive experimental results demonstrate that D2UNet delivers remarkable recognition accuracy (99.305%) and suppression performance (41.326 dB peak signal‐to‐jamming ratio, 0.9952 structure similarity index measure) on the semi‐realistic dataset. Its practical effect is further verified on measured data. [ABSTRACT FROM AUTHOR]

Over the past decade, there have been great advancements in radio frequency sensor technology for human–computer interaction applications, such as gesture recognition, and human activity recognition more broadly. While there is a significant amount of study on these topics, in most cases, experimental data are acquired in controlled settings by directing participants what motion to articulate. However, especially for communicative motions, such as sign language, such directed data sets do not accurately capture natural, in situ articulations. This results in a difference in the distribution of directed American Sign Language (ASL) versus natural ASL, which severely degrades natural sign language recognition in real‐world scenarios. To overcome these challenges and acquire more representative data for training deep models, the authors develop an interactive gaming environment, ChessSIGN, which records video and radar data of participants as they play the game without any external direction. The authors investigate various ways of generating synthetic samples from directed ASL data, but show that ultimately such data does not offer much improvement over just initialising using imagery from ImageNet. In contrast, an interactive learning paradigm is proposed by the authors in which model training is shown to improve as more and more natural ASL samples are acquired and augmented via synthetic samples generated from a physics‐aware generative adversarial network. The authors show that the proposed approach enables the recognition of natural ASL in a real‐world setting, achieving an accuracy of 69% for 29 ASL signs—a 60% improvement over conventional training with directed ASL data. [ABSTRACT FROM AUTHOR]

Radar High‐Resolution Range Profile (HRRP) has great potential for target recognition because it can provide target structural information. Existing work commonly applies deep learning to extract deep features from HRRPs and achieve impressive recognition performance. However, most approaches are unable to distinguish between the target and non‐target regions in the feature extraction process and do not fully consider the impact of background noise, which is harmful to recognition, especially at low signal‐to‐noise ratios (SNR). To tackle these problems, the authors propose a radar HRRP target recognition framework termed Adaptive Soft Threshold Transformer (ASTT), which is composed of a patch embedding (PE) layer, ASTT blocks, and Discrete Wavelet Patch Merging (DWPM) layers. Given the limited semantic information of individual range cells, the PE layer integrates nearby isolated range cells into semantically explicit target structure patches. Thanks to its convolutional layer and attention mechanism, the ASTT blocks assign a weight to each patch to locate the target areas in the HRRP while capturing local features and constructing sequence correlations. Moreover, the ASTT block efficiently filters noise features in combination with a soft threshold function to further enhance the recognition performance at low SNR, where the threshold is adaptively determined. Utilising the reversibility of the discrete wavelet transform, the DWPM layer efficiently eliminates the loss of valuable information during the pooling process. Experiments based on simulated and measured datasets show that the proposed method has excellent target recognition performance, noise robustness, and small‐scale range shift robustness. [ABSTRACT FROM AUTHOR]

This paper presents exploratory work on the use of Testing with Concept Activation Vectors (TCAV) within a concept-based explanation framework to provide the explainability of millimeter-wave (MMW) radar target recognition. Given that the radar spectrum is difficult for non-domain experts to understand visually, defining concepts for radar remains a significant challenge. In response, drawing from the visual analytical experience of experts, some basic concepts based on brightness, striping, size, and shape are adopted in this paper. However, the simplicity of basic concept definitions sometimes leads to vague correlations with recognition targets and significant variability among individuals, limiting their adaptability to specific tasks. To address these issues, this study proposes a Basic Concept-Guided Deep Embedding Clustering (BCG-DEC) method that can effectively discover task-specific composite concepts. BCG-DEC methodically analyzes the deep semantic information of radar data through four distinct stages from the perspective of concept discovery, ensuring that the concepts discovered accurately conform to the task-specific property of MMW radar target recognition. The experimental results show that the proposed method not only expands the number of concepts but also effectively solves the problem of difficulty in annotating basic concepts. In the ROD2021 MMW radar explainability experiments, the concepts proved crucial for recognizing specific categories of radar targets. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers. [ABSTRACT FROM AUTHOR]

Radar systems are a topic of great interest, especially due to their extensive range of applications and ability to operate in all weather conditions. Modern radars have high requirements such as its resolution, accuracy and robustness, depending on the application. Noise Radar Technology (NRT) has the upper hand when compared to conventional radar technology in several characteristics. Its robustness to jamming, low Mutual Interference and low probability of intercept are good examples of these advantages. However, its signal processing is more complex than that associated to a conventional radar. Artificial Intelligence (AI)‐based signal processing is getting increasing attention from the research community. However, there is yet not much research on these methods for noise radar signal processing. The aim of the authors is to provide general information regarding the research performed on radar systems using AI and draw conclusions about the future of AI in noise radar. The authors introduce the use of AI‐based algorithms for NRT and provide results for its use. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ordnance Equipment Engineering is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Over the past decade, there have been great advancements in radio frequency sensor technology for human–computer interaction applications, such as gesture recognition, and human activity recognition more broadly. While there is a significant amount of study on these topics, in most cases, experimental data are acquired in controlled settings by directing participants what motion to articulate. However, especially for communicative motions, such as sign language, such directed data sets do not accurately capture natural, in situ articulations. This results in a difference in the distribution of directed American Sign Language (ASL) versus natural ASL, which severely degrades natural sign language recognition in real‐world scenarios. To overcome these challenges and acquire more representative data for training deep models, the authors develop an interactive gaming environment, ChessSIGN, which records video and radar data of participants as they play the game without any external direction. The authors investigate various ways of generating synthetic samples from directed ASL data, but show that ultimately such data does not offer much improvement over just initialising using imagery from ImageNet. In contrast, an interactive learning paradigm is proposed by the authors in which model training is shown to improve as more and more natural ASL samples are acquired and augmented via synthetic samples generated from a physics‐aware generative adversarial network. The authors show that the proposed approach enables the recognition of natural ASL in a real‐world setting, achieving an accuracy of 69% for 29 ASL signs—a 60% improvement over conventional training with directed ASL data.

Abstract Gait recognition is to recognise different individuals based on their faint differences of gait characteristics, which is different from and more challengeable than the recognition of human activities based on relatively bigger differences between different motions. Existing millimetre‐wave Multiple Input Multiple Output radar point cloud data contains time‐varying three‐dimensional spatial positions, velocity, and intensity information. How to enhance the accuracy of gait recognition by effectively utilising the available radar point cloud data has become an attractive research topic in recent years. A velocity‐depth‐time (VDT) based point cloud construction method for millimetre‐wave Multiple Input Multiple Output radar is proposed for gait recognition application, which can not only alleviate the sparsity problem of mmWave point cloud but also make the constructed point cloud to exhibit temporal structural features of micro‐motions, and therefore enable the successful application of PointNet++ to mmWave‐MIMO point cloud gait recognition. New point clouds are constructed by the proposed method using public gait recognition datasets of 10 and 20 individuals from mmWave‐MIMO radar, which are used to conduct gait recognition experiments using PointNet++. The results show that the point clouds constructed based on VDT are more conducive to the gait recognition task. Even using the classic PointNet++ model, which is not specially designed for radar point clouds, high recognition accuracy can be achieved for gait recognition tasks. The recognition accuracies are improved by 11% and 12% in this work for datasets of 10 and 20 individuals, respectively, compared with the 84% and 80% achieved by the traditional method using the same dataset and the same PointNet++ model, while the accuracies are improved by 5% and 12%, respectively, compared with the 90% and 80% achieved by the original dataset thesis method corresponding to 10‐individual and 20‐individual datasets.

Abstract Countermeasures for chaff jamming have drawn great attention in the field of radar target detection and tracking. Current approaches for chaff jamming recognition and suppression exhibit limitations in practical effect, generalisation ability, and hybrid jamming handling. To address the above problems, the authors first transform the traditional 1D signal processing problem into a 2D semantic segmentation task and then solve it from the perspective of the dataset construction and algorithm design. For the dataset construction, the authors use both measured and simulated data to synthesise a more realistic labelled dataset (semi‐realistic dataset), which is also with good diversity due to its adjustable chaff interference background. For the algorithm design, the authors propose a Pre‐Decluttering Dual‐Stage UNet (D2UNet) to recognise and suppress chaff jamming in two stages successively, where the former provides prior attention masks for the latter. To further improve the performance of D2UNet, the authors also design a multi‐stage loss function to achieve progressive training. Extensive experimental results demonstrate that D2UNet delivers remarkable recognition accuracy (99.305%) and suppression performance (41.326 dB peak signal‐to‐jamming ratio, 0.9952 structure similarity index measure) on the semi‐realistic dataset. Its practical effect is further verified on measured data.

Abstract Radar systems are a topic of great interest, especially due to their extensive range of applications and ability to operate in all weather conditions. Modern radars have high requirements such as its resolution, accuracy and robustness, depending on the application. Noise Radar Technology (NRT) has the upper hand when compared to conventional radar technology in several characteristics. Its robustness to jamming, low Mutual Interference and low probability of intercept are good examples of these advantages. However, its signal processing is more complex than that associated to a conventional radar. Artificial Intelligence (AI)‐based signal processing is getting increasing attention from the research community. However, there is yet not much research on these methods for noise radar signal processing. The aim of the authors is to provide general information regarding the research performed on radar systems using AI and draw conclusions about the future of AI in noise radar. The authors introduce the use of AI‐based algorithms for NRT and provide results for its use.

Abstract The authors deal with the problem of the design and manufacture of a high‐resolution FMCW radar for drone detection and classification. The difficulties of the problem are discrete clutter reduction and spurious phase noise mitigation. The discrete clutter is due to the reflected signals from land vehicles, birds etc., while the spurious phase noise is inherent in the radar signal due to the phase‐locked loop component and leakage between the transmitting and receiving paths. Both spurious phase noise and clutter will increase the system noise level and hence reduce the probability of detection of small targets such as drones and induce false alarms on the radar screen. In order to reduce discrete clutter, the authors propose a method to separate a drone from discrete clutter based on the design of the radar system parameters for a drone and its propeller detection, target's Doppler dispersion and moving characteristics. For spur mitigation, a method that focuses on the design of the isolation coefficient between transmitting and receiving paths to decrease the power of spurs below the minimum power requirement at the input of the analogue‐to‐digital converter is introduced. The results were applied by the authors to the development and manufacture of a radar with the given specifications for drone detection and classification. Different laboratory and field tests show that the spurs are mitigated and the drones are separated from discrete clutter with a range and accuracy better than the one recently published.

The authors deal with the problem of the design and manufacture of a high‐resolution FMCW radar for drone detection and classification. The difficulties of the problem are discrete clutter reduction and spurious phase noise mitigation. The discrete clutter is due to the reflected signals from land vehicles, birds etc., while the spurious phase noise is inherent in the radar signal due to the phase‐locked loop component and leakage between the transmitting and receiving paths. Both spurious phase noise and clutter will increase the system noise level and hence reduce the probability of detection of small targets such as drones and induce false alarms on the radar screen. In order to reduce discrete clutter, the authors propose a method to separate a drone from discrete clutter based on the design of the radar system parameters for a drone and its propeller detection, target's Doppler dispersion and moving characteristics. For spur mitigation, a method that focuses on the design of the isolation coefficient between transmitting and receiving paths to decrease the power of spurs below the minimum power requirement at the input of the analogue‐to‐digital converter is introduced. The results were applied by the authors to the development and manufacture of a radar with the given specifications for drone detection and classification. Different laboratory and field tests show that the spurs are mitigated and the drones are separated from discrete clutter with a range and accuracy better than the one recently published. [ABSTRACT FROM AUTHOR]

Abstract In this paper, a novel algorithm is presented for warhead recognition in the defense of ballistic missiles. The range profiles from the warheads of interest in typical illumination directions form a dataset. First, each range profile in the dataset is compared to the range profile of the target under observation, and the most similar range profile is found. Then, the observed target is considered as a warhead if the deviation of its range profile from the most similar range profile is less than or equal to a threshold. The threshold is chosen such that the detection rate is a constant. The simulation results verify the effectiveness of the proposed algorithm. Since the threshold is automatically calculated according to the detection rate, this algorithm has a larger applicability than the current methods based on range-profile matching.

Abstract Urban surveillance of slow‐moving small targets such as drones and birds in low to medium airspace using radar presents significant challenges. Detecting, locating and identifying such low observable targets in strong clutter requires both innovation in radar hardware design and optimisation of processing algorithms. To this end, the University of Birmingham (UoB) has set‐up a testbed of two L‐band staring radars to support performance benchmarking using datasets of target and clutter from realistic urban environment. This testbed is also providing the vehicle to understand how novel radar architectures can enhance radar capabilities. Some of the challenges in installing the radar at the UoB campus are highligted. Detailed benchmarking results are provided from urban monostatic and bistatic field trials that form the basis for performance comparison against future hardware modification. The solution to the challenge of interfacing the radar to the external oscillators is described and stand‐alone bench tests with the candidate oscillators are reported. The testbed provides a valuable capability to undertake detailed analysis of performance of Quantum photonic‐enabled radar and allows for its comparison with conventional oscillator technology for surveillance of low observable targets in the presence of urban clutter.

Abstract In this article, a simple, yet effective, Bayesian scheme for tracks maintenance, promotion, and deletion in drone surveillance radar is presented. It enables the simultaneous tracking of the target body and micro‐Doppler components that originate from the motion of rotors (if any) onboard an unmanned air system. This not only delivers more accurate multi‐target tracking, but also substantially improves the radar automatic target classification capability (e.g. discriminating between drone and non‐drone targets). Challenging and diverse real staring radar datasets are used here to demonstrate the efficacy and benefits of the proposed track management approach.

In this paper, a novel algorithm is presented for warhead recognition in the defense of ballistic missiles. The range profiles from the warheads of interest in typical illumination directions form a dataset. First, each range profile in the dataset is compared to the range profile of the target under observation, and the most similar range profile is found. Then, the observed target is considered as a warhead if the deviation of its range profile from the most similar range profile is less than or equal to a threshold. The threshold is chosen such that the detection rate is a constant. The simulation results verify the effectiveness of the proposed algorithm. Since the threshold is automatically calculated according to the detection rate, this algorithm has a larger applicability than the current methods based on range-profile matching. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Radar, Sonar & Navigation. It discusses the advances in AI-assisted radar sensing applications and the challenges that hinder its adoption in this field. The special issue of the journal features nine papers that address these challenges and offer innovative ideas and experimental results. The papers cover a range of topics, including health monitoring, human activity recognition, voice identification, elderly care health monitoring, track-to-track association, signal pre-processing, traffic congestion alleviation, and target recognition. The authors express their gratitude to the contributors and reviewers and believe that the research presented will inspire further exploration and innovation in this field. [Extracted from the article]

Urban surveillance of slow‐moving small targets such as drones and birds in low to medium airspace using radar presents significant challenges. Detecting, locating and identifying such low observable targets in strong clutter requires both innovation in radar hardware design and optimisation of processing algorithms. To this end, the University of Birmingham (UoB) has set‐up a testbed of two L‐band staring radars to support performance benchmarking using datasets of target and clutter from realistic urban environment. This testbed is also providing the vehicle to understand how novel radar architectures can enhance radar capabilities. Some of the challenges in installing the radar at the UoB campus are highligted. Detailed benchmarking results are provided from urban monostatic and bistatic field trials that form the basis for performance comparison against future hardware modification. The solution to the challenge of interfacing the radar to the external oscillators is described and stand‐alone bench tests with the candidate oscillators are reported. The testbed provides a valuable capability to undertake detailed analysis of performance of Quantum photonic‐enabled radar and allows for its comparison with conventional oscillator technology for surveillance of low observable targets in the presence of urban clutter. [ABSTRACT FROM AUTHOR]

In this article, a simple, yet effective, Bayesian scheme for tracks maintenance, promotion, and deletion in drone surveillance radar is presented. It enables the simultaneous tracking of the target body and micro‐Doppler components that originate from the motion of rotors (if any) onboard an unmanned air system. This not only delivers more accurate multi‐target tracking, but also substantially improves the radar automatic target classification capability (e.g. discriminating between drone and non‐drone targets). Challenging and diverse real staring radar datasets are used here to demonstrate the efficacy and benefits of the proposed track management approach. [ABSTRACT FROM AUTHOR]

Abstract Pooling operations, essential for neural networks, reduce feature map dimensions while preserving key features and enhancing spatial invariance. Traditional pooling methods often miss the feature maps' alternating currentcomponents. This study introduces a novel global pooling technique utilizing spectral self‐attention, leveraging the discrete cosine transform for spectral analysis and a self‐attention mechanism for assessing frequency component significance. This approach allows for efficient feature synthesis through weighted averaging, significantly boosting TOP‐1 accuracy with minimal parameter increase, outperforming existing models.

Tomographic synthetic aperture radar (TomoSAR) possesses 3D imaging capability, making it significant for building reconstruction using TomoSAR data. The reconstruction algorithm is closely related to building point cloud detection, while traditional detection methods suffer from low automation and reliance on manual configuration. This study proposes a building point cloud reconstruction method based on deep learning semantic segmentation. Initially, deep learning method is employed for end‐to‐end building point cloud segmentation, followed by point cloud reconstruction based on the segmentation results. The proposed method is simple and efficient, elevating the level of automation in point cloud processing. Experimental validation on real TomoSAR data confirms that the proposed method achieves automated and refined reconstruction of building point clouds. [ABSTRACT FROM AUTHOR]

Pooling operations, essential for neural networks, reduce feature map dimensions while preserving key features and enhancing spatial invariance. Traditional pooling methods often miss the feature maps' alternating currentcomponents. This study introduces a novel global pooling technique utilizing spectral self‐attention, leveraging the discrete cosine transform for spectral analysis and a self‐attention mechanism for assessing frequency component significance. This approach allows for efficient feature synthesis through weighted averaging, significantly boosting TOP‐1 accuracy with minimal parameter increase, outperforming existing models. [ABSTRACT FROM AUTHOR]

Abstract Interrupted sampling repeater jamming can produce numerous active false targets with high fidelity, which is a significant challenge for coherent pulse radar. This poses a threat to the effectiveness of anti‐jamming technology, such as time‐frequency analysis and frequency agility for conventional constant pulse repetition interval (PRI) radar, which will render the radar inoperable to detect and track the actual target. A random PRI and intra‐pulse frequency agile radar waveform with low interception properties is proposed, which can effectively restrict the acquisition of radar waveform parameters by the jammer, destroy the coherence of jamming signals, and capture the range‐dimensional centroid feature of the echo. Accordingly, a jamming identification method based on the scale constrained Gaussian mixture model and an entity radar target energe recovery algorithm based on the neighbourhood weighted maximum entropy are proposed for target detection. Theoretical analysis and simulation experiments demonstrate the effectiveness of the proposal.

Abstract The authors investigate the feasibility of forming a composite Gaussian waveform in the high‐frequency region for jetfighter class targets with a high potential to combat the noise effect and the late‐time signature onset ambiguity when estimating the target resonance signature. The excitation waveform comprises a composite of modulated carriers with fractional bandwidth and amplitude adapted to lower specular content while enhancing the radar target resonance content in the radar return, subsequently increasing the likelihood of extracting the resonance parameters more accurately. The validation of improvement in the resonance signature requires finding the error between the excitation frequencies and the extractable resonant frequencies in the return echo and, second, the similarity or resemblance between the original echo waveform and the reconstructed waveform by the estimated resonance set. The results presented the robustness rate in instantaneous, average, and overall fashion. In conclusion, a fractional bandwidth between 0.3 and 0.4 would significantly improve the signature overall robustness with a circular then slant scattering polarisation set outperforming the horizontal and vertical directions. Also, excluding the signal's high and low energy portions further enhance the accuracy of the estimated resonance mode set.

For modern radar systems, small unmanned aerial vehicles (UAVs) belong to a typical types of targets with ‘low, slow, and small’ characteristics. In complex combat environments, the functional requirements of radar systems are not only limited to achieving stable detection and tracking performance but also to effectively complete the recognition of small UAV targets. In this paper, a multi-dimensional feature fusion framework for small UAV target recognition utilizing a small-sized and low-cost high-resolution radar is proposed, which can fully extract and combine the geometric structure features and the micro-motion features of small UAV targets. For the performance analysis, the echo data of different small UAV targets was measured and collected with a millimeter-wave radar, and the dataset consists of high-resolution range profiles (HRRP) and micro-Doppler time–frequency spectrograms was constructed for training and testing. The effectiveness of the proposed method was demonstrated by a series of comparison experiments, and the overall accuracy of the proposed method can reach 98.5%, which demonstrates that the proposed multi-dimensional feature fusion method can achieve better recognition performance than that of classical algorithms and higher robustness than that of single features for small UAV targets.

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers.

This paper presents exploratory work on the use of Testing with Concept Activation Vectors (TCAV) within a concept-based explanation framework to provide the explainability of millimeter-wave (MMW) radar target recognition. Given that the radar spectrum is difficult for non-domain experts to understand visually, defining concepts for radar remains a significant challenge. In response, drawing from the visual analytical experience of experts, some basic concepts based on brightness, striping, size, and shape are adopted in this paper. However, the simplicity of basic concept definitions sometimes leads to vague correlations with recognition targets and significant variability among individuals, limiting their adaptability to specific tasks. To address these issues, this study proposes a Basic Concept-Guided Deep Embedding Clustering (BCG-DEC) method that can effectively discover task-specific composite concepts. BCG-DEC methodically analyzes the deep semantic information of radar data through four distinct stages from the perspective of concept discovery, ensuring that the concepts discovered accurately conform to the task-specific property of MMW radar target recognition. The experimental results show that the proposed method not only expands the number of concepts but also effectively solves the problem of difficulty in annotating basic concepts. In the ROD2021 MMW radar explainability experiments, the concepts proved crucial for recognizing specific categories of radar targets.

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the interference caused by multipath ghosts, this paper presents a multipath target discrimination method based on separated Gaussian similarity matrices. The proposed method utilizes separated Gaussian similarity functions based on the Maximum Likelihood principle to quantify the similarity from distance and angle perspectives. Meanwhile, dimensionality reduction is applied to maximize the distinction between multipath ghosts and actual targets. This method can effectively discriminate the multipath relationships and attributes of detected targets and has higher recognition accuracy than other geometry‐based methods. The effectiveness and superiority of the proposed method were validated through Monte‐Carlo and practical experiments. [ABSTRACT FROM AUTHOR]

Interrupted sampling repeater jamming can produce numerous active false targets with high fidelity, which is a significant challenge for coherent pulse radar. This poses a threat to the effectiveness of anti‐jamming technology, such as time‐frequency analysis and frequency agility for conventional constant pulse repetition interval (PRI) radar, which will render the radar inoperable to detect and track the actual target. A random PRI and intra‐pulse frequency agile radar waveform with low interception properties is proposed, which can effectively restrict the acquisition of radar waveform parameters by the jammer, destroy the coherence of jamming signals, and capture the range‐dimensional centroid feature of the echo. Accordingly, a jamming identification method based on the scale constrained Gaussian mixture model and an entity radar target energe recovery algorithm based on the neighbourhood weighted maximum entropy are proposed for target detection. Theoretical analysis and simulation experiments demonstrate the effectiveness of the proposal. [ABSTRACT FROM AUTHOR]

The authors investigate the feasibility of forming a composite Gaussian waveform in the high‐frequency region for jetfighter class targets with a high potential to combat the noise effect and the late‐time signature onset ambiguity when estimating the target resonance signature. The excitation waveform comprises a composite of modulated carriers with fractional bandwidth and amplitude adapted to lower specular content while enhancing the radar target resonance content in the radar return, subsequently increasing the likelihood of extracting the resonance parameters more accurately. The validation of improvement in the resonance signature requires finding the error between the excitation frequencies and the extractable resonant frequencies in the return echo and, second, the similarity or resemblance between the original echo waveform and the reconstructed waveform by the estimated resonance set. The results presented the robustness rate in instantaneous, average, and overall fashion. In conclusion, a fractional bandwidth between 0.3 and 0.4 would significantly improve the signature overall robustness with a circular then slant scattering polarisation set outperforming the horizontal and vertical directions. Also, excluding the signal's high and low energy portions further enhance the accuracy of the estimated resonance mode set. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the continuous development of target recognition technology, people pay more and more attention to the cost of sample generation, tag addition and network training. Active learning can choose as few samples as possible to achieve a better recognition effect. In this paper, a small number of the simulation generated radar cross-section time series are selected as the training data, combined with the least confidence and edge sampling, a sample selection method based on few-shot learning is proposed. The effectiveness of the method is verified by the target type recognition test in multi time radar cross-section time series. Using the algorithm in this paper, 10 kinds of trajectory data are selected from all 19 kinds of trajectory data, and the training model is tested, which can achieve similar results with 19 kinds of trajectory data training model. Compared with the random selection method, the accuracy is improved by 4–10% in different time lengths. [ABSTRACT FROM AUTHOR]

The radar echoes of birds and drones target have high similarity, which make it difficult to distinguish them. Therefore, the spatio-temporal characteristics of target tracks formed by drones, birds and dynamic precipitation clutter are studied, and the differences in motion mechanisms and behavior patterns between drones and birds are analyzed. A motion feature extraction method based on target tracks is proposed and target feature vectors are constructed. Based on the measured track data of the target provided by the detection bird radar system, a training and test sample set is established. The supervised learning method combined with the random forest model is used to distinguish the target tracks of drones, birds and precipitation clutter. The experimental results show that the correct recognition rate of drone targets over a wide area can reach over 85%, and the classifier model has high calculation efficiency, strong sample adaptability, and good universality and practical value. [ABSTRACT FROM AUTHOR]

Abstract Hand gesture recognition based on micro‐Doppler (MD) radar has garnered considerable attention from researchers as a potential method for human–computer interaction (HCI). However, two significant challenges, that is, obvious differences in MD map size and lots of redundant information contained in the MD maps, are encountered. Here, a multi‐scale graph‐based hand gesture recognition framework is proposed. First, a MD graph representation method is developed, which is adapted to arbitrary‐sized frames and enables to map the key features in a sparse manner. Then, the multi‐scale information from MD graph is fully extracted for hand gesture recognition. Experimental results show that the proposed framework achieves a state‐of‐the‐art accuracy of 96.73% on the four‐class radar hand gesture dataset, while reducing up to 99% of the redundant information in the MD maps. This framework requires only a little amount of memory storage with good hand gesture recognition capability, demonstrating its high potential in the HCI field.

Abstract This paper presents a radar‐based algorithm for autonomous estimation of drone intention. The algorithm is based on radar's kinematic measurements, providing fast and robust intention estimation for multiple targets. The core idea of the proposed algorithm is to build intention‐specific features for each intention in advance and use them in actual drone surveillance situations. To effectively depict the trajectory characteristics of various intentions, the trajectory frequency is computed on multiple phase planes through Monte Carlo Simulations. Finally, a naive Bayes classifier is applied to integrate the trajectory likelihood in different phases and ultimately compute the intention likelihood of all intentions concerned. Numerical simulations for the three candidate intentions of image acquisition, smuggling, and kamikaze attack demonstrated the performance of the presented method. The simulation results show that one can estimate the true intention of a specific drone by comparing the value of each intention likelihood.

Hand gesture recognition based on micro‐Doppler (MD) radar has garnered considerable attention from researchers as a potential method for human–computer interaction (HCI). However, two significant challenges, that is, obvious differences in MD map size and lots of redundant information contained in the MD maps, are encountered. Here, a multi‐scale graph‐based hand gesture recognition framework is proposed. First, a MD graph representation method is developed, which is adapted to arbitrary‐sized frames and enables to map the key features in a sparse manner. Then, the multi‐scale information from MD graph is fully extracted for hand gesture recognition. Experimental results show that the proposed framework achieves a state‐of‐the‐art accuracy of 96.73% on the four‐class radar hand gesture dataset, while reducing up to 99% of the redundant information in the MD maps. This framework requires only a little amount of memory storage with good hand gesture recognition capability, demonstrating its high potential in the HCI field. [ABSTRACT FROM AUTHOR]

Abstract This work introduces an attention mechanism that can be integrated into any standard convolution neural network to improve model sensitivity and prediction accuracy with minimal computational overhead. The attention mechanism is introduced in a lightweight network – Alexnet and its classification performance for human micro‐Doppler signatures is evaluated. The Alexnet model trained with an attention module can implicitly highlight the salient regions in the radar signatures while suppressing the irrelevant background regions and consistently improving network predictions. Network visualizations are provided through class activation mapping, providing better insights into how the predictions are made. The visualizations demonstrate how the attention mechanism focusses on the region of interest in the radar signatures.

Abstract To address the interference caused by multipath ghosts, this paper presents a multipath target discrimination method based on separated Gaussian similarity matrices. The proposed method utilizes separated Gaussian similarity functions based on the Maximum Likelihood principle to quantify the similarity from distance and angle perspectives. Meanwhile, dimensionality reduction is applied to maximize the distinction between multipath ghosts and actual targets. This method can effectively discriminate the multipath relationships and attributes of detected targets and has higher recognition accuracy than other geometry‐based methods. The effectiveness and superiority of the proposed method were validated through Monte‐Carlo and practical experiments.

This paper presents a radar‐based algorithm for autonomous estimation of drone intention. The algorithm is based on radar's kinematic measurements, providing fast and robust intention estimation for multiple targets. The core idea of the proposed algorithm is to build intention‐specific features for each intention in advance and use them in actual drone surveillance situations. To effectively depict the trajectory characteristics of various intentions, the trajectory frequency is computed on multiple phase planes through Monte Carlo Simulations. Finally, a naive Bayes classifier is applied to integrate the trajectory likelihood in different phases and ultimately compute the intention likelihood of all intentions concerned. Numerical simulations for the three candidate intentions of image acquisition, smuggling, and kamikaze attack demonstrated the performance of the presented method. The simulation results show that one can estimate the true intention of a specific drone by comparing the value of each intention likelihood. [ABSTRACT FROM AUTHOR]

The accuracy of radar emitter signal sorting nowadays deteriorates due to the high flexibility and complexity of modern radar pulse streams and the density of crowded electromagnetic environment. In modern radar signal sorting based on pulse repetition interval, conventional methods usually fail to achieve acceptable accuracy and lack stable performance for two main reasons: (1) Conventional methods require a large number of pulses in the stream, which is not practical in many applications. (2) These methods are sensitive to pulse loss and random noise pulses. These two reasons are the main problem that is addressed in this paper. Our proposed model is a machine learning architecture called Unified Residual Recurrent Neural Network (URRNN). In this architecture, residual neural network and recurrent neural network are combined and modified to alleviate the forementioned shortcomings of traditional approaches and enhance the model performance in both classification and deinterleaving tasks. This aim is achieved due to the fact that URRNN extracts both spatial and temporal features, which means more information about processed stream that is exploited to enhance model performance. Three different architectural combinations of URRNN, which show high accuracy and reasonable processing time, are built and trained. The structural and functional description are provided for each architecture. Simulation demonstrates high accuracy and reliable performance of the proposed methods in different circumstances. The results are compared with the results obtained by other conventional machine learning techniques. [ABSTRACT FROM AUTHOR]

The existing automatic target recognition (ATR) methods for synthetic aperture radar (SAR) images mainly utilize the real-valued magnitude information while often ignoring the phase information. However, the phase information also provides important details, which can be utilized to improve the ATR performance. To address this issue, a fully complex-valued light-weight network (CVLWNet) is proposed based on complex-valued operations, such as complex-valued convolution and complex-valued batch normalization. Besides, to achieve reduced parameters and enhanced robustness of the designed network, many complex-valued blocks of operations are built, including the CMish activation function, the complex-valued residual link block (CVReLBlock), the lightweight complex-valued cross stage partial block (LC-CSPBlock). In the designed CVLWNet, the input, output, and weight parameters are all complex-valued, which makes it possible to sufficiently exploit the complex-valued characteristics of SAR data. Comparative experiments are conducted with the moving and stationary target acquisition and recognition dataset. Compared with the state-of-the-art real-valued and complex-valued models under both standard and extended operating conditions, the performance of proposed method is verified.

This work introduces an attention mechanism that can be integrated into any standard convolution neural network to improve model sensitivity and prediction accuracy with minimal computational overhead. The attention mechanism is introduced in a lightweight network – Alexnet and its classification performance for human micro‐Doppler signatures is evaluated. The Alexnet model trained with an attention module can implicitly highlight the salient regions in the radar signatures while suppressing the irrelevant background regions and consistently improving network predictions. Network visualizations are provided through class activation mapping, providing better insights into how the predictions are made. The visualizations demonstrate how the attention mechanism focusses on the region of interest in the radar signatures. [ABSTRACT FROM AUTHOR]

Abstract Continuous Human Activity Recognition (HAR) in arbitrary directions is investigated in this paper using a network of five spatially distributed pulsed Ultra‐Wideband radars. While activities performed continuously and in unconstrained trajectories provide a more realistic and natural scenario for HAR, the network of radar sensors is proposed to address the issue of unfavourable or occluded perspectives when using only a single sensor. Different techniques to combine the relevant information from the multiple radars in the network are investigated, focussing on signal level fusion directly applied on Range‐Time maps, and the selection of radar nodes based on location and velocity of the target derived from multilateration processing and tracking. Recurrent Neural Networks with and without bidirectionality are used to classify the activities based on the micro‐Doppler (μD) spectrograms obtained for sensor fusion techniques. To assess classification performances, novel evaluation metrics accounting for the continuous nature of the sequence of activities and inherent imbalances in the dataset are proposed and compared with existing metrics. It is shown that the conventional accuracy metric may not capture all the important aspects for continuous HAR, and the proposed metrics can be considered for a more comprehensive evaluation.

Radar enables a convenient, contactless way for gait analysis in daily scenarios, such as in‐home health monitoring. However, the overlapping of human limb components could occur in both range and velocity dimensions of the radar echo, which makes it difficult to distinguish the limbs. In this study, a trajectory tracking and recombination method based on range‐Doppler‐time data is proposed for gait feature estimation under insufficient radar resolution. In the trajectory tracking step, the scattering amplitude is included for Kalman filtering, and the weighted joint nearest neighbour algorithm is proposed for data association. Then, the trajectories are recombined to construct the limb tracks based on the relative range‐Doppler angles. Finally, the limb tracks are used to estimate the spatial‐temporal and kinematic gait features. In our simulation, the trajectory tracking accuracies range from 98.2% to 99.6%. The gait feature estimation accuracies for simulation and measurement are no less than 91.9% and 93.8% respectively. [ABSTRACT FROM AUTHOR]