Radar Target Detection Research Articles

SALA-LSTM: a novel high-precision maritime radar target detection method based on deep learning

Radar detection of maritime targets plays an important role in marine environment monitoring. For civil maritime detection in the areas of inshore coastal, pulse-compression radar is universally used owing to its low cost. The complex sea clutter in the practical application will greatly affect the received radar echoes. Due to the inability to accurately describe the differences in characteristics between sea clutter and maritime targets, the detection performance of methods based on mathematical derivation is not satisfactory in actual deployment. Recently, neural-based methods have made strides in many pattern recognition tasks, such as computer vision and natural language processing. The sophisticated deep neural models can be applied to different downstream tasks due to their powerful learning ability. Inspired by this idea, we propose a maritime radar target detection method in sea clutter based on deep learning. To better model the sequence correlation of radar echoes, we propose a Self-Adaption Local Augmented Long Short-Term Memory (SALA-LSTM) structure. The proposed SALA-LSTM integrates adaptive convolution into vanilla LSTM cells, which not only maintains the inherent overall sequence modeling ability of vanilla LSTM, but also strengthens its ability to perceive the correlation on a small scale in the local scope. Based on SALA-LSTM and other neural structures, we propose a radar target detection network. A measured dataset containing different typical scenarios is utilized to evaluate the detection probability and false alarm rate. The detection performance of our proposed network is superior to that of the existing methods.

Long‐time coherent integration for radar detection of manoeuvring targets based on accurate range evolution model

AbstractLong‐time coherent integration (LTCI) is one of the most effective approaches to enhance radar detection ability of weak targets. The existing LTCI methods generally assume that the target motion satisfies polynomial models in range coordinates. However, it may be hard to provide precise description of common target motions, especially manoeuvring motions, using a polynomial with finite terms. In this study, LTCI for radar detection of weak manoeuvring targets is investigated. The range evolution rules over time are derived and employed to formulate the target signal for two common manoeuvring motions, constant acceleration (CA) and constant turn (CT) motions in Cartesian coordinates. Aiming at realising accurate energy accumulation and improving detection performance of CA and CT targets, two LTCI algorithms based on the derived range evolution model are proposed. By extracting target signal and compensating for phase fluctuation between samples in accordance with the accurate range evolution model, the coherent accumulation of target signal can be effectively accomplished, eliminating the complex range and Doppler frequency migration effects simultaneously. The use of accurate range evolution model guarantees effective energy integration regardless of target manoeuvrability and integration time as long as the target performs CA or CT motion. Moreover, more information of target kinematic characteristics such as target acceleration and turn rate, additional to range and Doppler, can be observed. Simulations are conducted to validate the effectiveness of the proposed algorithms.The cover image is based on the Research Article Long‐time coherent integration for radar detection of manoeuvring targets based on accurate range evolution model by Zeyu Xu et al., https://doi.org/10.1049/rsn2.12445.

Integrated OFDM Waveform Design for RadCom System-Based Signal-to-Clutter Noise Ratio Maximization

Integrated Radar and Communication (RadCom) Systems have become more crucial ingredients in the next generation of networks due to numerous types of characteristics, including reducing the system size, minimizing power consumption, and mitigating spectrum scarcity. In this paper, we propose an integrated Orthogonal Frequency Division Multiplexing (OFDM) waveform design strategy for RadCom system-based Signal-to-clutter Noise Ratio (SCNR) maximization. The multi-carrier OFDM waveform is exploited at the RadCom transceiver to perform the functions of the radar system and communication system concurrently. We aim to improve the radar detection performance by maximizing the SCNR and maintaining the Data Information Rate (DIR) thresholds for communication system metrics. The maximization problem is posed as a convex optimization model and solved analytically using KKT conditions to find an optimal integrated waveform design. The findings obtained via simulation verify that the proposed strategy is capable of solving the waveform design issue for RadCom systems with low complexity. In addition, the proposed strategy effectively improves radar target detection and power consumption for RadCom systems.

HDT network: A high‐resolution range profile multi‐target detection and tracking method based on neural network

AbstractIn radar target detection and tracking tasks, the detection algorithm and data association algorithm are the primary technologies. The accuracy of detection, stability of tracking and processing speed are the key points to accomplishing effective high‐resolution range profile (HRRP) multi‐target tracking (MTT). Classic HRRP target tracking algorithms conduct the detection by extracting handcraft features and conduct tracking based on the data association algorithm. With the development of neural network methods, deep learning methods have been widely applied in target detection and tracking. An HRRP detection and tracking (HDT) network based on neural networks is proposed, which includes three steps: Firstly, the HRRP signal is processed by a convolutional neural network detector to extract the feature of the origin signal and generate the detection measurement. Secondly, a predicted measurement is generated by a Kalman filter, which estimates the current state of the target based on its previous states and the detection measurement. Finally, the ReID network calculates the cosine similarity between the tracks and measurements to associate them and a linear sum assignment operation is used to match the tracks and measurements. By using the proposed algorithm, the HDT network is capable of detecting and tracking multiple targets in complex cluttered environments with high accuracy. Experimental results on an HRRP dataset collected by a moving radar platform show the outstanding performance of the HDT network, including detection accuracy, track integrity and real‐time MTT.

Online unsupervised generative learning framework based radar jamming waveform design

AbstractThe jamming effect on radar is dominated by the design of the jamming waveform directly. Traditional jamming waveforms are generated using the template‐based method and are not environmentally resilient. Without the precise radar centre frequency support, using the direct guidance of the radar signal power spectrum density (PSD), a novel jamming waveform design method with an online unsupervised generative learning framework is proposed. The proposed framework consists of two modules: the waveform online generation module and the waveform unsupervised optimisation module. For the waveform online generation module, the well‐designed neural network (NN) is used to generate the jamming waveform. While for the waveform unsupervised iterative optimisation module, two loss functions are developed as two learning tasks to guide back‐propagation online. Given transmit power, the jamming PSD is designed adaptively to focus on the radar band and fit the radar PSD well, which improves the receiver in‐band jamming‐to‐signal ratio (JSR). It is worth noting that NN is end‐to‐end trained online without extensive prior training data. The framework can generate jamming waveforms within reasonable physical parameter ranges, and numerical experiments have shown that the designed jamming waveform performed better jamming effects on radar target detection in comparison with the traditional one.

Accurate Spatial-Frequency Response Controllable Frequency Invariant Beampattern Synthesis With Minimum Beamwidth

This communication proposes a new relaxation variable based cost function for the problem of frequency invariant (FI) beampattern synthesis. Two constraints in the spatial and frequency domains are imposed on the optimization problem. The objective of sparsifying the relaxation variable is exploited in constructing the constraint in the spatial domain, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> -spatial response variation (SRV) is introduced in the frequency domain constraint to reduce frequency variance. These constraints enable a desirable trade-off between beamwidth and FI properties while achieving accurate spatial-frequency response control. Since the resulting optimization problem is sparse and non-convex, it is then proposed to be solved by exploiting the reweighted- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">l</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> norm in this paper. The remarked feature of the new approach is the improved target detection and anti-interference performance in radar and communication systems without waveform distortion. Simulation results validate the effectiveness of the proposed method.

Multi-Scale Similarity Guidance Few-Shot Network for Ship Segmentation in SAR Images

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot learning has the ability to learn quickly from a few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder–decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN, and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-art.

Modified rank sum nonparametric CFAR to combat clutter edge

The classical rank sum (RS) nonparametric constant false alarm rate (CFAR) detector plays an important role in the theoretical study and practical application of radar target detection. In order to improve the ability of the classical RS nonparametric detector to control the false alarm rate at clutter edges, a modified rank sum (MRS) nonparametric CFAR based on the mean ratio of the samples in the leading and lagging windows is proposed. The analytical expressions of the detection probability and false alarm rate of the MRS nonparametric CFAR in homogeneous background and at clutter edges are derived, and a comparison to the performance of the classical RS nonparametric detector along with some conventional parametric CFAR schemes in homogeneous background, multiple targets situation and clutter edges is made. The numerical results show that the detection performance of the MRS nonparametric CFAR in homogeneous background and in a moderate number of interfering targets situation is close to that of the classical RS nonparametric detector, and its ability to control the rise of the false alarm rate at clutter edges is evidently improved.

Airborne Radar Staggered PRF Coherent Processing Method for Down-Looking Target Detection

Airborne radar plays a crucial role in detecting aerial targets, but its detection capability can be significantly affected by strong ground clutter when operating in down-looking mode. The range-Doppler (RD) results of ground clutter in airborne radar may overlap the range-Doppler results of the targets, causing target occlusion and rendering them undetectable. In addition to target detection, accurate extraction of target parameters is also of great importance. Due to the high-speed movement of the airborne platform, targets may exhibit range-Doppler ambiguity, necessitating the use of appropriate methods to resolve the range-Doppler ambiguity. Aiming at the problem of target occlusion by clutter with range-Doppler two-dimensional ambiguity during airborne radar down-looking target detection, this paper conducts a study on the detection of airborne radar down-looking targets based on orthogonal signals combined with pulse repetition frequency (PRF) staggered transmission. An optimization method is employed to design multiple sets of PRF values, aiming to reduce the radar blind zone. The range-Doppler two-dimensional ambiguity of targets is resolved using multiple sets of PRF, and coherent processing is performed on the corresponding echoes using the transmission intervals, maximizing the utilization of radar transmission energy. This approach enhances the signal-to-noise ratio (SNR) and improves the detection performance and parameter estimation accuracy, particularly for low SNR targets. The superiority of the proposed approach is demonstrated through simulation experiments.

Vehicle Target Detection Method for Wide-Area SAR Images Based on Coarse-Grained Judgment and Fine-Grained Detection

The detection of vehicle targets in wide-area Synthetic Aperture Radar (SAR) images is crucial for real-time reconnaissance tasks and the widespread application of remote sensing technology in military and civilian fields. However, existing detection methods often face difficulties in handling large-scale images and achieving high accuracy. In this study, we address the challenges of detecting vehicle targets in wide-area SAR images and propose a novel method that combines coarse-grained judgment with fine-grained detection to overcome these challenges. Our proposed vehicle detection model is based on YOLOv5, featuring a CAM attention module, CAM-FPN network, and decoupled detection head, and it is strengthened with background-assisted supervision and coarse-grained judgment. These various techniques not only improve the accuracy of the detection algorithms, but also enhance SAR image processing speed. We evaluate the performance of our model using the Wide-area SAR Vehicle Detection (WSVD) dataset. The results demonstrate that the proposed method achieves a high level of accuracy in identifying vehicle targets in wide-area SAR images. Our method effectively addresses the challenges of detecting vehicle targets in wide-area SAR images, and has the potential to significantly enhance real-time reconnaissance tasks and promote the widespread application of remote sensing technology in various fields.

An improved dynamic programming tracking-before-detection algorithm based on LSTM network value function

The detection and tracking of small and weak maneuvering radar targets in complex electromagnetic environments is still a difficult problem to effectively solve. To address this problem, this paper proposes a dynamic programming tracking-before-detection method based on long short-term memory (LSTM) network value function(VL-DP-TBD). With the help of the estimated posterior probability provided by the designed LSTM network, the calculation of the posterior value function of the traditional DP-TBD algorithm can be more accurate, and the detection and tracking effect achieved for maneuvering small and weak targets is improved. Utilizing the LSTM network to model the posterior probability estimation of the target motion state, the posterior probability moving features of the maneuvering target can be learned from the noisy input data. By incorporating these posterior probability estimation values into the traditional DP-TBD algorithm, the accuracy and robustness of the calculation of the posterior value function can be enhanced, so that the improved architecture is capable of effectively recursively accumulating the movement trend of the target. Simulation results show that the improved architecture is able to effectively reduce the aggregation effect of a posterior value function and improve the detection and tracking ability for non-cooperative nonlinear maneuvering dim small target. Abbreviations LSTM: Long short-term memory; DP-TBD: Dynamic programming-based tracking before detection; DBT: Detection before tracking; TBD: Tracking before detection; HT-TBD: Tracking-before-detection algorithm based on the Hough transform; PF-TBD: Tracking-before-detection algorithm based on particle filtering; RFS-TBD: Tracking-before-detection algorithm based on random finite sets; SNR: Signal-to-noise ratio; DP: Dynamic programming; EVT: Extreme value theory; EVT: Generalized extreme value theory; GLRT: Generalized likelihood ratio detection; KT: Keystone transformation; PGA: Phase gradient autofocusing; CFAR: Constant false-alarm rate; J-CA-CFAR: Joint intensity-spatial CFAR; MF: Merit function; CP-DP-TBD: Candidate plot-based DP-TBD; CIT: Coherent integration time; RNN: Recurrent neural network; CS: Current statistical; Pd: Detection probability; Pt: Tracking probability.

Backscattering enhancement of a chessboard metasurface based on the orbital angular momentum detection approach

In recent years, metasurfaces have been widely employed in stealth technology, which brings great challenges for radar target detection. In order to address this issue, a novel detection approach for metasurface-stealth-target (MST) based on orbital angular momentum (OAM) vortex wave is proposed in this paper. Compared to a conventional plane wave detection system, the transmitting wave of the proposed approach is OAM-modulated, of which the wavefront is helical along the beam axis. Thus, the differentiated exciting source is introduced to different parts of MST. According to the established scattering model and full-wave simulation, the echo of MST has a strong correlation with OAM order l, which exhibits quite different scattering characteristics from the plane wave illumination. A chessboard metasurface (CM) is taken as an example to be irradiated by an OAM vortex wave of l=±2. The backscattering is significantly boosted compared to plane-wave detection, which is against the stealth ability of CM. This phenomenon is also verified by experiments. The results reveal that OAM detection is a promising approach for MST detection..

MT-FANet: A Morphology and Topology-Based Feature Alignment Network for SAR Ship Rotation Detection

In recent years, ship target detection in synthetic aperture radar (SAR) images has significantly progressed due to the rapid development of deep learning (DL). However, since only the spatial feature information of ship targets is utilized, the current DL-based SAR ship detection approaches cannot achieve a satisfactory performance, especially in the case of multiscale, rotations, or complex backgrounds. To address these issues, in this paper, a novel deep-learning network for SAR ship rotation detection, called a morphology and topology-based feature alignment network, is proposed which can better exploit the morphological features and inherent topological structure information. This network consists of the following three main steps: First, deformable convolution is introduced to improve the representational ability for irregularly shaped ship targets, and subsequently, a morphology and topology feature pyramid network is developed to extract inherent topological structure information. Second, based on the aforementioned features, a rotation alignment feature head is devised for fine-grained processing as well as aligning and distinguishing the features; to enable regression prediction of rotated bounding boxes; and to adopt a parameter-sharing mechanism to improve detection efficiency. Therefore, utilizing morphological and inherent topological structural information enables a superior detection performance to be achieved. Finally, we evaluate the effectiveness of the proposed method using the rotated ship detection dataset in SAR images (RSDD-SAR). Our method outperforms other DL-based algorithms with fewer parameters. The overall average precision is 90.84% and recall is 92.21%. In inshore and offshore scenarios, our method performs well for the detection of multi-scale and rotation-varying ship targets, with its average precision reaching 66.87% and 95.72%, respectively.

Bayesian Detectors for Wideband Radar Target With Range Walking in Compound Gaussian Clutter

In this paper, the problem of the wideband radar target detection with the range walking in compound Gaussian clutter without the secondary data is addressed. The wideband radar target return with the range walking is represented as a canonical linear model in the multi-rank subspace, and the clutter is modeled as a two-dimensional random process with separable complex inverse Wishart distributed random covariance matrices in the pulse and range-frequency domains. The generalized likelihood ratio test (GLRT), the Wald test and the Rao test based on the above target and clutter models are designed under the Bayesian framework. The Laplace approximation is adopted to compute the second-kind confluent hypergeometric function of matrix argument (SKCHFMA) in the proposed detectors. Finally, the performance of the detectors is validated by the simulations.

Deep learning-based lightweight radar target detection method

For target detection tasks in complicated backgrounds, a deep learning-based radar target detection method is suggested to address the problems of a high false alarm rate and the difficulties of achieving high-performance detection by conventional methods. Considering the issues of large parameter count and memory occupation of the deep learning-based target detection models, a lightweight target detection method based on improved YOLOv4-tiny is proposed. The technique applies depthwise separable convolution (DSC) and bottleneck architecture (BA) to the YOLOv4-tiny network. Moreover, it introduces the convolutional block attention module (CBAM) in the improved feature fusion network. It allows the network to be lightweight while ensuring detection accuracy. We choose a certain number of pulses from the pulse-compressed radar data for clutter suppression and Doppler processing to obtain range–Doppler (R–D) images. Experiments are run on the R–D two-dimensional echo images, and the results demonstrate that the proposed method can quickly and accurately detect dim radar targets against complicated backgrounds. Compared with other algorithms, our approach is more balanced regarding detection accuracy, model size, and detection speed.

An improved dynamic programming tracking-before-detection algorithm based on LSTM network

The detection and tracking of small and weak maneuvering radar targets in complex electromagnetic environments is still a difficult problem to effectively solve. To address this problem, this paper proposes a dynamic programming tracking-before-detection method based on a long short-term memory (LSTM) network (LSTM-DP-TBD). With the predicted target motion state provided by the LSTM network, the state transition range of the traditional DP-TBD algorithm can be updated in real time, and the detection and tracking effect achieved for maneuvering small and weak targets is also improved. Utilizing the LSTM network to model the moving state of the target, the moving features of the maneuvering target can be learned from the noisy input data. By incorporating these features into the traditional DP-TBD algorithm, the state transition set can be adjusted in time with the changes in the moving state of the target so that the new algorithm is capable of effectively recursively accumulating the movement trend of the maneuvering small and weak target. Simulation results show that the new algorithm is able to effectively accomplish the task of detecting and tracking maneuvering small and weak targets, and it achieves improved detection and tracking probabilities.

Composite Backscatter Characteristics of Conductive/Dielectric Ships and Sea Surfaces with Breaking Waves under High Sea Conditions.

When a radar detects marine targets, the radar echo is influenced by the shape, size and dielectric properties of the targets, as well as the sea surface under different sea conditions and the coupling scattering between them. This paper presents a composite backscattering model of the sea surface and conductive and dielectric ships under different sea conditions. The ship scattering is calculated using the equivalent edge electromagnetic current (EEC) theory. The scattering of the sea surface with wedge-like breaking waves is calculated using the capillary wave phase perturbation method combined with the multi-path scattering method. The coupling scattering between ship and sea surface is obtained using the modified four-path model. The results reveal that the backscattering RCS of the dielectric target is significantly reduced compared with the conducting target. Furthermore, the composite backscattering of the sea surface and ship increases significantly in both HH and VV polarizations when considering the effect of breaking waves under high sea conditions at low grazing angles in the upwind direction, especially for HH polarization. This research offers valuable insights into optimizing radar detection of marine targets in varying sea conditions.

BM3D denoising-based multi-target detection method for complex background radar images

Abstract For the complex background of traditional radar image target detection methods is affected by multiple interferers, which leads to a low recognition rate of multi-target classification and a high false alarm rate. In this paper, the current hot research BM3D denoising method is introduced into radar image target detection. Firstly, the detection process of the BM3D algorithm is constructed, and the image pixels are reasonably clustered by denoising so that the image blocks in homogeneous regions have a high matching degree and those in non-homogeneous regions have a low matching degree. Secondly, the clustering recognition feature is used to limit the search range of similar blocks to homogeneous regions, to improve the denoising efficiency of the algorithm. Finally, the simulation results of this paper show that compared with previous algorithms, the BM3D detection method has significantly improved in both the subjective visual effect map and objective numerical indexes. For example, the image denoising quality is improved by about 0.716dB on average and up to 1.031dB, the image denoising time is shortened by about 19.962s on average, and the algorithm runs 1.211 times faster than the original algorithm. It is proved that the algorithm can improve denoising efficiency and reduce computational complexity while enhancing detailed information.

A prior knowledge-driven reference signal extraction network towards measured data in DRM-based passive radar

We propose a novel intelligent reference signal extraction system for DRM-based passive radar. By fully using prior knowledge of the received signal, a pilot conditional reference signal extraction network (PCRSENet) is designed to replace both conventional channel estimation and signal equalization. The PCRSENet estimates the channel state information (CSI) implicitly and outputs reference signals directly. Meanwhile, what makes it challenging to utilize deep learning in reference signal extraction of passive radar is not only the limited measured data but also the truth transmission signals and CSI being unknown. So, the least square (LS) estimator-aided training sets generation method is employed, which obtains the CSI from measured data by LS estimator as prior knowledge and then simulates DRM signals as accurate labels of training sets. We evaluate the proposed method on measured data, and the experimental results show that the proposed method works effectively for target detection in DRM-based passive radar with different working parameters when the training and test sets are in the same transmission mode.

Multi-fold high-order cumulants based CFAR detector for radar weak target detection

As an important detection means, radar is widely used in target monitoring field. However, due to the small radar cross section (RCS) of stealthy or small target and the complex detection environment, the target echo signal is usually submerged in the environmental clutter. Then the target detection based on Pulse-Doppler radar shows the characteristics of weak signal detection. In this paper, the multi-fold high-order cumulant (HOC) on the radar range-Doppler (R-D) map is proposed to elevate the detection performance of the weak target signal, which can effectively eliminate the noise. Then the processed signal is sent to the CFAR detector to estimate the targets' range and velocity. Although HOC has been used in radar signal detection, the detection algorithm was mainly done on the processed signal after one-fold HOC. We propose a construction method of multi-fold HOC using a set of delay vectors to further eliminate residual noise after one-fold HOC processing. Our proposed multi-fold HOC can be seen as a data preprocessing method, which can also be applied to other detection algorithm to further improve its detection performance. Simulation results show that the proposed multi-fold HOC based CFAR algorithm can greatly reduce SNR required for signal detection, and has an advantage in radar weak signal detection.