High-resolution Range Profile Recognition Research Articles

Group-Fusion One-Dimensional Convolutional Neural Network for Ballistic Target High-Resolution Range Profile Recognition with Layer-Wise Auxiliary Classifiers

Ballistic missile defense systems require accurate target recognition technology. Effective feature extraction is crucial for this purpose. The deep convolutional neural network (CNN) has proven to be an effective method for recognizing high-resolution range profiles (HRRPs) of ballistic targets. It excels in perceiving local features and extracting robust features. However, the standard CNN's fully connected manner results in high computational complexity, which is unsuitable for deployment in real-time missile defense systems with stringent performance requirements. To address the issue of computational complexity in HRRP recognition based on the standard one-dimensional CNN (1DCNN), we propose a lightweight network called group-fusion 1DCNN with layer-wise auxiliary classifiers (GFAC-1DCNN). GFAC-1DCNN employs group convolution (G-Conv) instead of standard convolution to effectively reduce model complexity. Simply using G-Conv, however, may decrease model recognition accuracy due to the lack of information flow between feature maps generated by each G-Conv. To overcome this limitation, we introduce a linear fusion layer to combine the output features of G-Convs, thereby improving recognition accuracy. Additionally, besides the main classifier at the deepest layer, we construct layer-wise auxiliary classifiers for different hierarchical features. The results from all classifiers are then fused for comprehensive target recognition. Extensive experiments demonstrate that GFAC-1DCNN with such simple and effective techniques achieves higher overall testing accuracy than state-of-the-art ballistic target HRRP recognition models, while significantly reducing model complexity. It also exhibits a higher recall rate for warhead recognition compared to other methods. Based on these compelling results, we believe this work is valuable in reducing workload and enhancing missile interception rates in missile defense systems.

Dual-band polarimetric HRRP recognition via a brain-inspired multi-channel fusion feature extraction network.

Radar high-resolution range profile (HRRP) provides geometric and structural information of target, which is important for radar automatic target recognition (RATR). However, due to the limited information dimension of HRRP, achieving accurate target recognition is challenging in applications. In recent years, with the rapid development of radar components and signal processing technology, the acquisition and use of target multi-frequency and polarization scattering information has become a significant way to improve target recognition performance. Meanwhile, deep learning inspired by the human brain has shown great promise in pattern recognition applications. In this paper, a Multi-channel Fusion Feature Extraction Network (MFFE-Net) inspired by the human brain is proposed for dual-band polarimetric HRRP, aiming at addressing the challenges faced in HRRP target recognition. In the proposed network, inspired by the human brain's multi-dimensional information interaction, the similarity and difference features of dual-frequency HRRP are first extracted to realize the interactive fusion of frequency features. Then, inspired by the human brain's selective attention mechanism, the interactive weights are obtained for multi-polarization features and multi-scale representation, enabling feature aggregation and multi-scale fusion. Finally, inspired by the human brain's hierarchical learning mechanism, the layer-by-layer feature extraction and fusion with residual connections are designed to enhance the separability of features. Experiments on simulated and measured datasets verify the accurate recognition capability of MFFE-Net, and ablative studies are conducted to confirm the effectiveness of components of network for recognition.

Quadruplet depth-wise separable fusion convolution neural network for ballistic target recognition with limited samples

Radar high-resolution range profile (HRRP) plays a crucial role in ballistic target recognition due to its simplicity and fast computation. Convolutional neural networks (CNNs), a popular deep learning approach, are widely used in radar automatic target recognition (RATR) based on HRRP, thanks to their excellent feature extraction capabilities. However, current research mainly focuses on integrating branch networks like recurrent neural networks and attention mechanisms into vanilla CNNs to enhance feature extraction. Limited research exists on reducing the computational complexity of vanilla CNNs when applied to HRRP-based RATR, as well as target recognition problems with limited samples. To address these issues, this paper proposes a lightweight depth-wise separable fusion CNN (DSFCNN) for ballistic target HRRP recognition. The DSFCNN reduces the computational complexity of vanilla CNNs while improving recognition accuracy. Furthermore, we introduce the sample-level fitting and class-level distinguishability (SFCD) loss for limited-sample ballistic target HRRP recognition. The SFCD loss ensures better fitting performance of all samples, as well as higher intra-class compactness and inter-class separability, enhancing the distinguishability of embedded features in limited-sample conditions. During the training phase, the SFCD loss is equally applied to four DSFCNNs with shared structures and parameters, resulting in a model known as Quadruplet DSFCNN (QDSFCNN). However, during the testing phase, only one DSFCNN is utilized. Additionally, we propose the parameter quantity shifting-fitting performance (PQS-FP) coordinate system to elucidate the performance disparities between DSFCNN and vanilla CNNs in our experiments. PQS-FP offers inspirational insights into the relations among parameter quantity, fitting performance, and recognition performance. Extensive experimental results demonstrate the robustness and effectiveness of QDSFCNN for ballistic target recognition in various limited-sample scenarios.

Contrastive Learning for Radar HRRP Recognition With Missing Aspects

High resolution range profile (HRRP) has attracted increasing attention in radar automatic target recognition (RATR). However, the target-aspect missing problem in non-cooperative targets recognition, which is one of the most challenging tasks in RATR, has received very few contributions recently. The proposed work is motivated by a very simple observation, i.e., as compared with HRRP signals of interesting targets, sufficient unlabeled HRRP signals are much easier to acquire. However, these signals are often neglected since there is no label information. This work focuses on the target-aspect missing problem by using a dual self-supervised contrastive learning framework. The proposed model takes advantage of massive unlabeled HRRP signals to enhance the generalization ability. Specifically, we employ self-supervised contrastive learning and online clustering module for extracting target-aspect invariant representations. Additionally, a data augmentation strategy is used as a simple yet effective module. The experimental results demonstrate that the proposed method with fewer labels enhances the recognition performance as compared to supervised and self-supervised methods in missing aspect problem.

Open-set HRRP recognition method based on joint sparse representation

Aiming at the problem of multi-view high-resolution range profile (HRRP) target recognition under open set conditions, we proposed an open set recognition method based on joint sparse representation (JSR), which solves the problem of low recognition rate of traditional methods under open set conditions. This method is applied to the background of radar single-station observation. JSR is used to solve the reconstruction error of multi-view HRRP by the over-complete dictionary, while extreme value theory (EVT) is used to model the reconstruction error tailing of matching and non-matching categories and transform the open set identification problem into a hypothesis testing problem. During recognition, we use the reconstruction error to determine the candidate class, the scores of the matching class and non-matching class are obtained according to the confidence of tail distribution, and the weighted sum of the two is used as the category criterion to finally determine the target or candidate class outside the library. This method can effectively use the relevant information between multi-view HRRPs to improve the performance of HRRP recognition under open set conditions. The algorithm is tested with HRRP data generated from MSTAR inversion, and the results show that the performance of the proposed method is better than the mainstream open set recognition method.

Open set HRRP recognition with few samples based on multi-modality prototypical networks

Learning from a few high-resolution range profiles (HRRPs) with multi-modality property caused by sensitivity of the target aspect remains a challenge in radar HRRP-based target recognition. Despite recent advances in HRRP recognition based on deep neural networks (DNNs), thanks to their powerful expressive ability, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new classes rapidly from a few HRRPs. In this work, we employ ideas from metric learning based on discriminative neural features and from recent advances that augment neural networks with FiLM layers to adapt to multi-modality input data. We first define open set learning problem on HRRP recognition task. Then, we propose a multi-modality prototypical network (MMPN) to attack the problem. Our framework learns a modality-aware network that maps a few labelled HRRPs and unlabelled HRRPs to their labels via a well defined metric space with episodic-based meta-learning strategy, obviating the need for fine-tuning to adapt to new classes. Finally, a synthetic HRRP data, called RareHRRP, is developed to evaluate that the proposed model generalize well and is efficient in computation.

Polarimetric HRRP recognition based on feature‐guided Transformer model

Polarimetric high-resolution range profile (HRRP) holds great potential for radar automatic target recognition (RATR) owing to its capability of providing both polarimetric and spatial scattering information. In recent years, deep learning (DL) has obtained state-of-the-art results in many classification tasks and has drawn great attention in the RATR field. However, as one of the most challenging tasks in RATR, small training sample case will restrict the application of DL because its superior performance generally depends on a large number of training samples. A feature-guided deep model based on Transformer framework is proposed for polarimetric HRRP recognition with limited training samples. In the proposed model, artificial features are introduced to the attention module to guide the model focus on the range cells of HRRP with more target scattering information so as to reduce the dependence of the model on the number of training samples. Several different approaches are also studied to measure the similarity between artificial features and HRRP data to further improve the learning capacity of the model. Experimental results demonstrate that the proposed feature-guided Transformer model modifying by Cosine similarity measure is able to achieve a better performance for polarimetric HRRP recognition with limited training samples.

Application of the fruit fly optimization algorithm to an optimized neural network model in radar target recognition

With the development of computer technology, there are more and more algorithms and models for data processing and analysis, which brings a new direction to radar target recognition. This study mainly analyzed the recognition of high resolution range profile (HRRP) in radar target recognition and applied the generalized regression neural network (GRNN) model for HRRP recognition. In order to improve the performance of HRRP, the fruit fly optimization algorithm (FOA) algorithm was improved to optimize the parameters of the GRNN model. Simulation experiments were carried out on three types of aircraft. The improved FOA-GRNN (IFOA-GRNN) model was compared with the radial basis function (RBF) and GRNN models. The results showed that the IFOA-GRNN model had a better convergence accuracy, the highest average recognition rate (96.4 %), the shortest average calculation time (275 s), and a good recognition rate under noise interference. The experimental results show that the IFOA-GRNN model has a good performance in radar target recognition and can be further promoted and applied in practice.

Polarimetric HRRP Recognition Based on ConvLSTM With Self-Attention

Polarimetric high resolution range profile (HRRP) holds great potential for radar automatic target recognition (RATR) owing to its capability of providing both polarimetric and spatial scattering information. Conventional polarimetric HRRP recognition methods generally extract a set of features and put them into a well-trained classifier, which heavily rely on expertise. On the contrary, deep learning can automatically learn deep features of the training data and has obtained state-of-the-art results in many classification tasks. In this article, a novel deep model based on convolutional long short-term memory (ConvLSTM) network and self-attention mechanism is proposed for polarimetric HRRP recognition. In the proposed model, ConvLSTM employs the convolutional operator and recurrent LSTM structure to capture and aggregate target polarimetric and spatial scattering information from different dimensions simultaneously. Self-attention mechanism is introduced before ConvLSTM to make the model focus on the discriminative range cells and help improve the learning capacity of ConvLSTM. Experiment results on the simulated and measured datasets demonstrate the effectiveness of the proposed model for multi-class targets recognition. The results of two expanded experiments also show that this model performs well in noise and small training sample cases, showcasing good potentials in practical applications.

A staked discriminative auto-encoder based on center loss for radar target HRRP recognition

In the radar automatic target recognition filed, extracting representative features from the radar high resolution range profile (HRRP) is the key issues, which determines the accuracy and reliability of radar target recognition. In this paper, we propose a novel stacked discriminative auto-encoder(S-disAE), the center loss is integrated into auto-encoder, it can force the learned feature with large distance close to their class feature representation center, so as to reduce the intra-class variations while keeping the features of different classes separable. In pre-training stage of our discriminative auto-encoder(disAE), we combine the mean square error loss and center loss to learn the main factors of input raw data and minimize the intra-class variations of the feature, in fine-tuning stage, we also combine the softmax cross entropy loss and center loss to improve the classification accuracy. We conduct several experiments on the simulated HRRP data, the results demonstrate that the proposed algorithm can extract discriminant features and improve the HRRP recognition accuracy.

One-dimension hierarchical local receptive fields based extreme learning machine for radar target HRRP recognition

Radar automatic target recognition (RATR) aims at extracting meaningful target features from the electromagnetic echo signal and utilizing the features to automatically recognize the target types. The high-resolution range profile (HRRP) plays an important role in RATR field, HRRP is the amplitude of the echo summation for target scattering centers in each range cell of wideband radar. Using deep neural networks for HRRP radar target recognition encounters the problem of storage overhead and slow convergence rate, to resolve those issues, we propose a one-dimension local receptive fields based extreme learning auto-encoder (1D ELM-LRF-AE) network for HRRP local structures and meaningful representations learning. ELM-LRF-AE consists of an input layer, a random convolution layer, a pooling layer, several local connected layers and an output layer, it reconstructs the input with a greedy strategy that the input feature vectors are divided into several subgroups and the i-th pooling feature vector is used to reconstruct the i-th grouping input feature vector. Then we use the learned pooling feature vectors to replace the random pooling feature vectors as the learned representations. We also stack several 1D ELM-LRF-AEs to build 1D hierarchical local receptive fields based extreme learning machine (1D H-ELM-LRF) for high level HRRP abstract representations learning and recognition. Experimental results on simulated HRRP data set demonstrate the superior high recognition performance and high computational efficiency of our algorithm.

Robust sequential high‐resolution range profile recognition based on the infinite conditional restricted Boltzmann machine

Feature extraction for radar high-resolution range profiles (HRRPs) is an essential procedure for robust target recognition based on radar HRRPs. It is almost always better to utilise multiple HRRPs from the target than a single HRRP. The commonly used recognition techniques are not robust enough to extract features from HRRP sequences, especially when there is not enough training data. In this study, the authors present a compact model named the infinite conditional restricted Boltzmann machine (iCRBM) for jointly feature learning and recognition of radar HRRPs. The model is developed from the conditional restricted Boltzmann machine, which is a powerful model for representing high-dimensional and multi-modal conditional distributions. Unlike ordinary RBMs, iCRBM can automatically select the model complexity according to the data, which especially suits for the case of large data dimensionality and small training dataset. A multi-scale structure is also proposed for learning multiple scales of temporal/spatial dependencies. Two types of radar HRRP recognition experiments were conducted to validate the efficiency and robustness of iCRBM: the multi-view HRRP recognition and the small aperture HRRP recognition. The results indicate that, the proposed model can be more adaptive at learning the feature of HRRPs than other common methods. The multi-scale structure is helpful for better recovering missing HRRP samples from non-consecutive sequences.

HRRP Target Recognition With Deep Transfer Learning

Recently, radar high-resolution range profile (HRRP) recognition based on convolutional neural networks (CNNs) has received considerable attention due to its robustness to translation and amplitude changes. Most of the existing methods require that sufficient labeled data with complete aspect angles be used as training data, which is a difficult task in practice. In addition, HRRP signals have a high sensitivity to the aspect angle. Therefore, the representative and discriminative powers of the features extracted from typical CNN models are reduced due to incomplete aspect angles in the training data, which significantly limit the recognition performance. This paper first considers the problem of HRRP recognition with incomplete aspect angle training data and addresses the problem by a deep transfer learning framework. Specifically, the two proposed methods enhance the recognition performance by exploring the discriminative power and the intraclass consistency with auxiliary data, which have HRRP signals with complete aspect angles. This paper generates a simulated HRRP dataset from public data to validate the proposed work. The comparisons of the recognition results demonstrate that the proposed framework outperforms the latest CNN-based models.

VGM-RNN: HRRP Sequence Extrapolation and Recognition Based on a Novel Optimized RNN

High-Resolution Range Profile (HRRP) sequence has attracted academic attentions in the field of radar automatic target recognition (RATR) owing to its abundant spatial-temporal correlation between adjacent samples. However, it is difficult in the working state of radar to obtain complete HRRP sequence samples due to various internal and external factors such as ground clutter and systematic error, which poses an enormous challenge to radar target recognition. Therefore, it is crucial to repair the missing HRRPs based on the adjacent samples in the previous frames. In this paper, we discuss the extrapolate method of incomplete samples and propose an improved neural network algorithm named as Vanishing Gradient Mitigation Recurrent Neural Network (VGM-RNN). The lost samples in the sequence can be extrapolated by VGM-RNN, and the problem of vanishing gradient which is possessed in classical RNN can be effectively mitigated. The proposed method in this paper can be divided into two parts, as sample extrapolation and sequence recognition, in which sample extrapolation is the core method. Experimental results on Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our proposed model exhibits higher accuracy and efficiency, as well as excellent anti-noise performance, compared with traditional methods. It is suggested that our proposed model can be effectively applied to radar system.

A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering.

High-resolution range profile (HRRP) has attracted intensive attention from radar community because it is easy to acquire and analyze. However, most of the conventional algorithms require the prior information of targets, and they cannot process a large number of samples in real time. In this paper, a novel HRRP recognition method is proposed to classify unlabeled samples automatically where the number of categories is unknown. Firstly, with the preprocessing of HRRPs, we adopt principal component analysis (PCA) for dimensionality reduction of data. Afterwards, t-distributed stochastic neighbor embedding (t-SNE) with Barnes–Hut approximation is conducted for the visualization of high-dimensional data. It proves to reduce the dimensionality, which has significantly improved the computation speed. Finally, it is exhibited that the recognition performance with density-based clustering is superior to conventional algorithms under the condition of large azimuth angle ranges and low signal-to-noise ratio (SNR).

Polarimetric radar target recognition framework based on LSTM

Polarimetric information is of great importance for radar target recognition. Conventional polarimetric features are hand-designed based on scattering mechanism. In this study, a novel polarimetric target recognition framework based on long–short-term memory (LSTM) network is proposed. The different polarimetric channels are regarded as the sequential inputs in LSTM, and the features are extracted automatically. Experimental results on dual-polarised high-resolution range profile recognition demonstrate that the features learnt by LSTM are more discriminating than conventional features. The recognition performance of the proposed method outperforms the state-of-the-art methods as well.

Deep forest for radar HRRP recognition

High-resolution range profile (HRRP) has received intensive attention in the radar automatic target recognition filed. Here, deep forest is applied to the recognition of HRRP. The deep forest is a deep learning method, which is a cascade of ensemble learners. In each layer, there are various ensemble learners. The input of each layer is the combination of the previous layer output and the original input data. The number of cascade levels can be adaptively determined such that the model complexity can be automatically set. Experiments based on measured data show that deep forest is feasible and achieves highly competitive performance for HRRP recognition.

Radar HRRP recognition based on CNN

In this study, ground target recognition based on one-dimensional convolutional neural network (CNN) is studied by exploiting the targets’ high-resolution range profiles (HRRPs). Contrary to conventional methods which need feature extraction artificially, CNN can automatically discover features for classification. The authors propose a multi-channel CNN architecture that can be applied on diverse forms of HRRP such as amplitude, complex, spectrum etc. Experimental results demonstrate the superiorities of the proposed method over conventional methods based on handcrafted features and single-channel CNN in terms of recognition accuracy. Visualisation of the ‘deep features’ shows higher separability than handcrafted features, thus providing an insight into its effectiveness in exploiting the intrinsic structures.

Open set HRRP recognition based on convolutional neural network

Most existing algorithms in high-resolution range profile recognition focus on the closed set cases, where the test sample is from a known class. However, a sample could be drawn from unknown classes in realistic scenario, which is named as open set recognition. Here, open set HRRP recognition is achieved by incorporating extreme value theory into convolutional neural network. The softmax layer is replaced by a so-called openmax layer which estimates probabilities of the test sample belonging to known and unknown classes. Experimental results demonstrate that the proposed method outperforms the state-of-art algorithms such as NN, 1-vs-set machine, and W-SVM in terms of correct rejection rate.

HRRP-based target recognition with deep contractive neural network

One of the radar high resolution range profile (HRRP) target recognition issues is the existence of noise interference, especially for the ground target. The recognition performance of traditional shallow methods degrades as suffering from the limited capability of extracting robust and discriminative features. In this paper, a novel deep neural network called stacked denoising and contractive auto-encoder (SDCAE) is designed for millimeter wave radar HRRP recognition. To enhance the capability of learning robust structure and correlations from corrupted HRRP data, a denoising contractive auto-encoder is designed by combining the advantages of denoising auto-encoder and contractive auto-encoder. As an extension of deep auto-encoders, SDCAE inherits the advantage of enhancing the robustness of features via reducing external noise, retaining local invariance to obtain more discriminative representations of training samples. Experimental results demonstrate the superior performance of the proposed method over traditional methods, especially in noise interference condition and with few training samples.