Abstract: Underwater acoustics has been implemented mostly in the field of sound navigation and ranging (SONAR) procedures for submarine communication, the examination of maritime assets and environment surveying, target and object recognition, and measurement and study of acoustic sources in the underwater atmosphere. With the rapid development in science and technology, the advancement in sonar systems has increased, resulting in a decrement in underwater casualties. The sonar signal processing and automatic target recognition using sonar signals or imagery is itself a challenging process. Meanwhile, highly advanced data-driven machine-learning and deep learning-based methods are being implemented for acquiring several types of information from underwater sound data. This paper reviews the recent sonar automatic target recognition, tracking, or detection works using deep learning algorithms. A thorough study of the available works is done, and the operating procedure, results, and other necessary details regarding the data acquisition process, the dataset used, and the information regarding hyper-parameters is presented in this article. This paper will be of great assistance for upcoming scholars to start their work on sonar automatic target recognition.

Abstract: In remote sensing, micro-Doppler signatures are widely used in moving target detection and automatic target recognition. However, since Doppler signatures are easily affected by the moving direction of the target, prior information of aspect angle is essential for spectral analysis. Thus, a micro-Doppler-based classifier is considered to be “angle-sensitive.” In this article, we propose an angle-insensitive classifier for the omnidirectional classification problem using the monostatic radar through a proposed new convolutional neural network. We further provide a sensible definition of “angle sensitivity,” and perform experiments on two data sets obtained through simulations and measurements. The results demonstrate that the proposed algorithm outperforms both feature-based and existing deep-learning-based counterparts, and resolve the issue of angle sensitivity in micro-Doppler-based classification.

Abstract: Under the framework of a supervised learning-based automatic target recognition (ATR) approach, recognition performance is primarily dependent on the amount of training samples. However, shortage in training samples is a consistent issue for ATR. In this article, we propose a new image to image generation method, called label-directed generative adversarial networks (LDGANs), which will provide labeled samples to be used for recognition model training. We define an entirely new loss function for the LDGAN, which utilizes the Wasserstein distance to replace the original distance measurement of the conventional generative adversarial networks (GANs), thus efficiently avoiding the collapse mode problem. The label information is also added to the loss function of the LDGAN to avoid generating a large number of unlabeled target images. More importantly, the proposed method also makes corresponding changes to the network architecture regarding the new GANs. At the same time, the detailed algorithm about the LDGAN is also introduced in this article to deal with the issue that characteristically GANs are not easy to train. Based on comparisons with other directed generation methods, the experimental results show comparative results of several types of generated images in statistical features, gradient features, classic features of synthetic aperture radar (SAR) targets and the independence from the real image. While demonstrating that the images generated by the LDGAN produced better results using the assumptions of independent and identical distribution, the experiment also explores the performance of the generated image in the ATR. A comparison of these experimental results demonstrates a better way to use the generated image for ATR. The experimental results also prove that the proposed method does have the ability to supplement information for ATR when the training sample information is insufficient.

Abstract: This authoritative resource presents a comprehensive illustration of modern Artificial Intelligence / Machine Learning (AI/ML) technology for radio frequency (RF) data exploitation. It identifies technical challenges, benefits, and directions of deep learning (DL) based object classification using radar data, including synthetic aperture radar (SAR) and high range resolution (HRR) radar. The performance of AI/ML algorithms is provided from an overview of machine learning (ML) theory that includes history, background primer, and examples. Radar data issues of collection, application, and examples for SAR/HRR data and communication signals analysis are discussed. In addition, this book presents practical considerations of deploying such techniques, including performance evaluation, energy-efficient computing, and the future unresolved issues.

Abstract: Automatic Target Recognition (ATR) for military applications is one of the core processes towards enhancing intelligencer and autonomously operating military platforms. Spurred by this and given that Synthetic Aperture Radar (SAR) presents several advantages over its counterpart data domains, this paper surveys and assesses current SAR ATR architectures that employ the most popular dataset for the SAR domain, namely the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. Based on the current methodology trends, we propose a taxonomy for the SAR ATR architectures, along with a direct comparison of the strengths and weaknesses of each method under both standard and extended operational conditions. Additionally, despite MSTAR being the standard SAR ATR benchmarking dataset we also highlight its weaknesses and suggest future research directions.

Abstract: Automatic target recognition (ATR) has made great progress with the development of deep learning. However, the target feature in synthetic aperture radar (SAR) image is not consistent with human vision, and the SAR training samples are always limited. These hard issues pose new challenges to the SAR ATR based on convolutional neural network (CNN). In this letter, we propose an improved CNN model to solve the limited sample issue via the feature augmentation and ensemble learning strategies. Normally, the high-level features that are more comprehensive and discriminative than the middle-level and low-level features are always employed for category discrimination. In order to make up the insufficient training features in the limited sample case, the cascaded features from optimally selected convolutional layers are concatenated to provide more comprehensive representation for the recognition. To take full advantage of these cascaded features, the ensemble learning-based classifier, namely, the AdaBoost rotation forest (RoF), is introduced to replace the original softmax layer to realize a more accurate limited sample recognition. Through the AdaBoost RoF method, not only are these features further enhanced by the rotation matrix but also a strong classifier is constructed by several weak classifiers with different adjusted weights. The experimental results on MSTAR data set show that the cascaded features and ensemble weak classifiers can fully exploit effective information in limited samples. Compared with the existing CNN method, the proposed method can improve the recognition accuracy by about 20% under the condition of ten training samples per class.

Abstract: When adding new tasks/classes in an incremental learning scenario, the previous recognition capabilities trained on the previous training data can be lost. In the real-life application of automatic target recognition (ATR), part of the previous samples may be able to be used. Most incremental learning methods have not considered how to save the previous key samples. In this article, the class boundary exemplar selection-based incremental learning (CBesIL) is proposed to save the previous recognition capabilities in the form of the class boundary exemplars. For exemplar selection, the class boundary selection method based on local geometrical and statistical information is proposed. And when adding new classes continually, a class-boundary-based data reconstruction method is introduced to update the exemplar set. Thus, when adding new classes, the previous class boundaries could be kept complete. Experimental results demonstrate that the proposed CBesIL outperforms the other state of the art on the accuracy of multiclass recognition and class-incremental recognition.

Abstract: With the development of synthetic aperture radar (SAR) system, automatic target recognition (ATR) has attracted wide attention in many decision-making tasks, in which an enhanced feature of SAR image is a powerful tool to improve the recognition accuracy. However, the presence of speckle noise and natural clutter inevitably contaminates SAR images and, thus, degrades image features. In this article, we explicitly address the speckle reduction problem for the circular SAR system, in which the motion of aircraft platform causes continuous angular variations so that different SAR images can be captured with the high interrelationship. By exploiting the underlying low-rank and continuous properties among different SAR images, a method called the $\ell _{p}$ -regularized low-rank and space-angle continuity extraction ( $\ell _{p}$ -LSCE) is proposed to suppress the noise and enhance the target feature. Taking into account the interrelationship between SAR images, we arrange the images in a 3-D tensor to investigate the space-angle continuity of the targets. Furthermore, we develop a robust $\ell _{p}$ -regularized scheme to incorporate the low-rank property of targets. Then, the joint optimization problem is solved via the framework of augmented Lagrange multiplier (ALM) with efficient computation of each ALM subproblem. The experimental results of circular SAR data sets of the moving and stationary target acquisition and recognition (MSTAR) and the VideoSAR demonstrate that the proposed method can efficiently despeckle SAR images with well-preserved target features, which is conducive to the improvement of ATR performance.

Abstract: A zero-shot learning (ZSL) method of automatic target recognition (ATR) in synthetic aperture radar (SAR) image is proposed to address the scenario, where no SAR sample of a particular target is available for training. To learn features of the unseen target, physics-based electromagnetic (EM) simulated images of the target under different azimuth angles are used as the training data instead. The challenge lies in the fact that the simulated image has a distinct but nonessential texture that the real images do not have and, thus, can easily result in an overfitted discriminator network. To overcome this problem, all images are first preprocessed with a nonessential factor suppression step and then fed into a pretrained convolutional neural network for feature extraction. Finally, the feature vector is fed into a trainable fully-connected network for classification. The low-dimensional embedding of feature vectors suggests that the nonessential factor suppression can align the simulated samples with true samples effectively. We propose the max-tolerability principle and averaged margin index for ZSL, which is a useful indicator for selecting optimal classifier. We validated our method on ten-type target recognition task on MSTAR data sets and achieved 91.93% accuracy on nine known targets and 79.08% accuracy on zero-shot target.

Abstract: This paper deals with the problem of loaded/unloaded drones classification. Precisely, exploiting the different micro-Doppler signatures exhibited by a drone with both any load and payloads of different weights, a novel signature extraction procedure is developed for automatic recognition purposes. The developed algorithms is based on a novel adaptation of the spectral kurtosis technique to the problem at hand, specifically the analysis of narrowband and wideband spectrograms of the radar echoes reflected by the drones. In addition, the principal component analysis is used to reduce the feature vector size. The experiments conducted on measured bistatic radar data prove the effectiveness of the proposed method in separating the quoted classes of objects.

Abstract: With the recent advances of deep learning, automatic target recognition (ATR) of synthetic aperture radar (SAR) has achieved superior performance. By not being limited to the target category, the SAR ATR system could benefit from the simultaneous extraction of multifarious target attributes. In this paper, we propose a new multi-task learning approach for SAR ATR, which could obtain the accurate category and precise shape of the targets simultaneously. By introducing deep learning theory into multi-task learning, we first propose a novel multi-task deep learning framework with two main structures: encoder and decoder. The encoder is constructed to extract sufficient image features in different scales for the decoder, while the decoder is a tasks-specific structure which employs these extracted features adaptively and optimally to meet the different feature demands of the recognition and segmentation. Therefore, the proposed framework has the ability to achieve superior recognition and segmentation performance. Based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, experimental results show the superiority of the proposed framework in terms of recognition and segmentation.

Abstract: Inverse synthetic aperture radar (ISAR) is capable of producing 2-D and 3-D images of non-cooperative targets Compared with 2-D ISAR images, 3-D ISAR reconstructions can provide not only range and cross-range information, but also the information about the third dimension of the target, which is of great significance for automatic target recognition (ATR) and even more specifically to the case of non-cooperative target recognition The alignment between the point-like 3-D ISAR reconstructions of targets and the targets’ models, such as computer aided design (CAD) models, becomes one of the essential issues in ATR that uses 3-D ISAR reconstructions In this article, we propose an approach to address the alignment problem The alignment problem can be decomposed into two steps, a coarse alignment and an accurate alignment The coarse alignment can be accomplished by means of the principal component analysis (PCA), whereas the accurate alignment can be achieved by iterative closest point algorithm In this article, the 180° ambiguity issue in PCA is discussed, and a corresponding robust solution is proposed Moreover, the k-d tree is utilized to accelerate the searching for the pairs of correspondences, both in coarse and accurate alignment steps In order to simulate real radar scenarios, target self-occlusion is also taken into consideration The experimental results based on target's scattering point model simulation as well as the electromagnetic simulation in different radar scenarios verify the validity of the proposed method

Abstract: In recent years, seabed inspection has become one of the most sought-after tasks for Autonomous Underwater Vehicles (AUVs) in various applications. Forward-Looking Sonars (FLS) are commonly favored over optical cameras, which are not-negligibly affected by environmental conditions, to carry out inspection and exploration tasks. Indeed, sonars are not influenced by illumination conditions and can provide high-range data at the cost of lower-resolution images compared to optical sensors. However, due to the lack of features, sonar images are often hard to interpret by using conventional image processing techniques, leading to the necessity of human operators analyzing thousands of images acquired during the AUV mission to identify the potential targets of interest. This paper reports the development of an Automatic Target Recognition (ATR) methodology to identify and localize potential targets in FLS imagery, which could help human operators in this challenging, demanding task. The Mask R-CNN (Region-based Convolutional Neural Network), which constitutes the core of the proposed solution, has been trained with a dataset acquired in May 2019 at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale - CSSN) basin, in La Spezia (Italy). The ATR strategy was then successfully validated online in the same site in October 2019, where the targets were replaced and relocated on the seabed.

Abstract: Deep learning has been successfully utilized in synthetic aperture radar (SAR) automatic target recognition tasks and obtained state-of-the-art results. However, current deep learning algorithms do not perform well when SAR images are occluded, noisy, or with a great depression angle variance. This article proposes a novel method, SAR capsule network, to achieve the accurate and robust classification of SAR images without significantly increasing network complexity. Specifically, we develop a convolutional neural network extension based on Hinton's capsule network to capture spatial relationships specialized in classification between different entities in a SAR image. The SAR capsules are learned by a vector-based full connection operation instead of the traditional routing process, which not only alleviates the computational burden but also improves recognition accuracy. For occlusion, additive noise, and multiplicative noise tests, SAR capsule network shows superior robustness compared with typical convolution neural networks. When missing training data in a certain aspect angle range or existing a large depression angle variance between training data and test data, the proposed network achieves better performance than the existing works and reveals some competitive advantages in several test scenarios.

Abstract: Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), most algorithms of which have employed and relied on sufficient training samples to receive a strong discriminative classification model, has remained a challenging task in recent years, among which the challenge of SAR data acquisition and further insight into the intuitive features of SAR images are the main concerns. In this paper, a deep transferred multi-level feature fusion attention network with dual optimized loss, called a multi-level feature attention Synthetic Aperture Radar network (MFFA-SARNET), is proposed to settle the problem of small samples in SAR ATR tasks. Firstly, a multi-level feature attention (MFFA) network is established to learn more discriminative features from SAR images with a fusion method, followed by alleviating the impact of background features on images with the following attention module that focuses more on the target features. Secondly, a novel dual optimized loss is incorporated to further optimize the classification network, which enhances the robust and discriminative learning power of features. Thirdly, transfer learning is utilized to validate the variances and small-sample classification tasks. Extensive experiments conducted on a public database with three different configurations consistently demonstrate the effectiveness of our proposed network, and the significant improvements yielded to surpass those of the state-of-the-art methods under small-sample conditions.

Abstract: A critical need in the development of any automatic target recognition system is the ability to accurately predict and quantify the detection and classification performance under various operational and environmental conditions. In this paper, we propose new methods capable of predicting and estimating the performance of a multichannel detection system using multiple synthetic aperture sonar. Performance prediction and estimation is accomplished by analyzing the multichannel coherence statistics and characterizing the background conditions within the image. The ability of the method to provide an assessment of image complexity for various background conditions is studied. The saddlepoint approximation is employed to approximate the empirical null distribution of the test statistics for threshold selection and to achieve a prescribed false alarm rate. Test results on two real and one synthetic sonar imagery data sets with different target and background conditions are provided, which indicate the capability of the proposed methods in describing the distribution of the likelihood ratio and predicting the detector's performance in low to medium clutter environments.

Abstract: Synthetic aperture radar (SAR) has always received wide attention for its developing performance in military and civil applications. SAR automatic target recognition (ATR) is an important research field of the SAR application with the growing number and resolution of the SAR images. SAR images will be greatly influenced by the imaging azimuth, which could also be utilized to extract the correlation features between the adjacent azimuths. In this paper, we proposed a multi-view convolutional neural network and long short term memory (CNN-LSTM) network to extract and fuse the feature extracted from different adjacent azimuths. It adopts the structure of convolutional neural network to extract the optimal feature from the SAR images. Then, the structure of multiple layers of the long short term memory is adopted to fuse the optimal features of adjacent azimuths. Finally, a softmax is employed as the classifier to get the recognition results. Experimental results based on the MSTAR data set have shown the effectiveness and accuracy of the proposed method.

Abstract: Inverse synthetic aperture radar (ISAR) images of dynamic targets have been used for automatic target recognition purposes. Limited experimental data of ISAR images of automotive targets are currently available to the radar community. In this paper, we propose an electromagnetic simulation model for generating ISAR images of dynamic automotive targets for a short-range automotive radar. Further, we provide an open-source database of approximately 750 ISAR images for each of five common automotive targets - two cars, truck, bicycle, and auto-rickshaw. Our results show that ISAR images provide useful insights regarding the dimensions of the vehicles, the number of wheels and the orientation of the vehicle along its trajectory with respect to the radar.

Abstract: Automatic Target Recognition (ATR) algorithms classify a given Synthetic Aperture Radar (SAR) image into one of the known target classes using a set of training images. Recently, learning methods have shown to achieve state-of-the-art classification accuracy if abundant training data is available sampled uniformly over the classes and their poses. In this paper, we consider the problem of improving the generalization performance of learning methods in SAR-ATR when training data is limited. We propose a data augmentation approach using sparse signal models that capitalizes on commonly observed phenomenology of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we exploit the sparsity of the scattering centers in the spatial domain as well as the limited persistence of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting. Using this fitted model, we synthesize new images at poses not available in training set to augment the training data used by CNN. We validate the performance of the proposed model based data augmentation strategy on subsampled versions of the MSTAR dataset. The experimental results show that for the training data starved region, the proposed method provides a significant gain in the generalization performance of the resulting ATR algorithm.

Abstract: Synthetic aperture radar (SAR) automatic target recognition (ATR) based on convolutional neural network (CNN) is a research hotspot in recent years. However, CNN is data-driven, and severe overfitt...

Abstract: The low resolution of infrared (IR) images makes feature extraction for classification of a challenging work. Learning-based methods, therefore, are preferred to be used on such raw imagery. In this article, in order to avoid difficulties in feature extraction, a novel multitask extension of the widely used sparse-representation-classification (SRC) method is proposed in both single and multiview set-ups. That is, the test sample could be a single IR image or images from different views. In both single-view and multiview scenarios, we try to employ collaborative spike and slab priors. This is because the traditional sparsity-inducing measures such as the $l_{0}$ -row pseudonorm makes it hard to capture the sparse structure of the coefficient matrix when expanded in terms of a training dictionary, and the priors are proved to be able to capture fairly general sparse structures. Furthermore, a joint prior and sparse coefficient estimation method (JPCEM) is proposed for the first time in this article in order to alleviate the need to handpick prior parameters required before classification. Multiple experiments are conducted on a synthetic Comanche Forward Looking IR (FLIR) Automatic Target Recognition (ATR) database collected by Army Research Lab and a challenging mid-wave IR (MWIR) image ATR database made available by the U.S. Army Night Vision and Electronic Sensors Directorate. The final results substantiate the merits of the proposed JPCEM through comparisons with other state-of-the-art methods, including both the ones based on SRC and the ones constructed using deep learning frameworks.

Abstract: Image fusion expands the space-time scope of the detection target by making full use of the information complementarity between images, which is useful for automatic target recognition. An adaptive fractional multi-scale edge-preserving decomposition based on the weighted least square framework is proposed to fuse infrared (IR) and visible (VIS) images. It decomposes images into the base layer and the detail layer. The saliency map is obtained based on adaptive fractional saliency detection of the IR image. This map is beneficial to fuse the base layer and highlights the saliency information significantly. Then, the detail layer is fused by classical choose-max. The experiments indicate that the proposed method outperforms state-of-the-art fusion methods in extracting the target and preserving background information of the IR and VIS images.

Abstract: Ship target interpretation in SAR images has become an important topic in research in recent years. With the improvement of SAR image resolution, the performance of traditional automatic target recognition (ATR) method decreases gradually. The emergence of deep network provides a new solution for SAR image ship interpretation. Ship target interpretation in SAR images based on deep learning is divided into detection and classification, but they haven't been integrated yet. Based on the process flow of traditional ATR system, an integration method of ship target detection and recognition based on deep network is proposed in this paper. And at the end of the network, the squeeze-and-excitation (SE) module is added to the classification subnetwork. The effectiveness of the proposed integration method is verified by experiments, and the classification accuracy of the ship increased by 3.7% after adding SE module.

Abstract: In recent years, convolutional neural network (CNN) has been increasingly considered as a promising technology for military and homeland security applications. The fusion of CNN and Support vector machine (SVM), a popular traditional machine learning approach, has received intensive attention in the field of synthetic aperture radar (SAR) automatic target recognition (ATR). This paper, firstly, discusses the effects of some preprocessing and image enhancement methods on the performance of SAR ATR, starting with the pre-trained AlexNet in a transfer-learning based approach. Secondly, the architecture of AlexNet is modified to form a new model suitable for SAR ATR. Finally, we propose a hybrid model associated with the success of the learning feature of our CNN model and the ability of SVM to process high-dimensional dataset effectively. To evaluate the proposed method, experiments are performed on the Moving and Stationary Target Acquisition and Recognition (MSTAR) public database. The comparative results demonstrate that these preprocessing and enhancement methods prior to the deep-learning process are not necessary since the feature representation ability of AlexNet is already powerful. Furthermore, experimental results on the benchmark MSTAR dataset illustrate the effectiveness of the proposed new model. On classification of ten-class targets, the commonly used translation augmentation for training data has been performed. By combining the CNN and SVM, the classification accuracy percentages can be slightly improved for our proposed new model.

Abstract: This paper is devoted to the study of an automatic target recognition method to classify Inverse Synthetic Aperture Radar (ISAR) images of moving targets. 2-D ISAR imagery generation allows to obtain a pertinent representation of the moving target reflectivity distribution employing radar imaging system. The proposed target recognition technique is based on a combined the polar representation with shape matrix description applied on ISAR image. These descriptors (features) are used to achieve the recognition task method using Neural Network and Support Vector Machine. Several simulations are provided to validate the performances of the proposed method for the automatic aircraft target recognition.

Abstract: The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.

Abstract: The deep convolutional neural networks (CNNs) have achieved the state of art performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, these networks often provide sub-optimal recognition results in the case of imbalanced SAR data distribution. In this paper, a synthetic minority class data method for improving imbalanced SAR target recognition using the generative adversarial network (GAN) is proposed. The minority class SAR data is first over-sampled by optimized data augmentation policies from automatic search method, which enlarge the training set for GAN. The progressive growing of GANs (PGGAN) is then trained on these data and generates high quality and diverse minority class SAR data to alleviate imbalanced data distribution. Experimental results on the designed imbalanced distributed Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset indicate that our method can effectively improve the recognition accuracy of minority class by approximately 11.68%.

Abstract: Single Image Super Resolution (SISR) is the process of mapping a low-resolution image to a high-resolution image. This inherently has applications in remote sensing as a way to increase the spatial resolution in satellite imagery. This suggests a possible improvement to automated target recognition in image classification and object detection. We explore the effect that different training sets have on SISR with the network, Super Resolution Generative Adversarial Network (SRGAN). We train 5 SRGANs on different land-use classes (e.g. agriculture, cities, ports) and test them on the same unseen dataset. We attempt to find the qualitative and quantitative differences in SISR, binary classification, and object detection performance. We find that curated training sets that contain objects in the test ontology perform better on both computer vision tasks while having a complex distribution of images allows object detection models to perform better. However, Super Resolution (SR) might not be beneficial to certain problems and will see a diminishing amount of returns for datasets that are closer to being solved.

Abstract: The deep learning has some new vitality to the synthetic aperture radar (SAR) automatic target recognition (ATR). By introducing different constraints, deep belief network (DBN) has become apply to SAR target recognition recent years, but the existing DBN algorithms have some questions including the high training epochs, low recognition rate and complex structure. Therefore, an algorithm based on guided reconstruction and weighted norm-constrained DBN is proposed. Firstly, in order to reduce the dimension of the image output feature, increase the speed of preprocessing, generate a one-dimensional image vector and normalized, a SAR target classification algorithm with two-scale fusion character based on guided filter reconstruction algorithm is introduced. Then, the sparse feature extraction of SAR image is carried out by weighted norm-constrained DBN. By the regularization constraint of the probability distribution, the algorithm can minimize the joint probability distribution of visual layer and hidden layer by samples. The low-dimensional feature is further improved based on the generalized optimization of norm-constrained RBM. Finally, by a regularized Softmax which can classify the targets and obtain output results. The experimental results show that the SAR target recognition algorithm based on the guided reconstruction and weighted constrained deep confidence network not only improves the target recognition performance and generalization ability, but also reduces the output feature dimension and network training times, and the recognition performance of the algorithm is further improved.