Complex Synthetic Aperture Radar Images Research Articles

Vehicle Localization Method in Complex SAR Images Based on Feature Reconstruction and Aggregation.

Due to the small size of vehicle targets, complex background environments, and the discrete scattering characteristics of high-resolution synthetic aperture radar (SAR) images, existing deep learning networks face challenges in extracting high-quality vehicle features from SAR images, which impacts vehicle localization accuracy. To address this issue, this paper proposes a vehicle localization method for SAR images based on feature reconstruction and aggregation with rotating boxes. Specifically, our method first employs a backbone network that integrates the space-channel reconfiguration module (SCRM), which contains spatial and channel attention mechanisms specifically designed for SAR images to extract features. The network then connects a progressive cross-fusion mechanism (PCFM) that effectively combines multi-view features from different feature layers, enhancing the information content of feature maps and improving feature representation quality. Finally, these features containing a large receptive field region and enhanced rich contextual information are input into a rotating box vehicle detection head, which effectively reduces false alarms and missed detections. Experiments on a complex scene SAR image vehicle dataset demonstrate that the proposed method significantly improves vehicle localization accuracy. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method.

A Ghost and Attention Mechanism-Based Deep Learning Approach for SAR Small Target Image Detection

Sy nthetic aperture radar (SAR) images play an important role in the task of small target imaging and detection. However, due to its blurred target imaging, complex image background, and challenging feature representation, SAR detection is difficult to get high precision in a complex imaging environment. Therefore, by integrating the ghost model and the Attention-Mechanism (AM), this paper presents a new feature network model based on the improved YOLOv5s for detecting small targets in SAR images efficiently. The key is to design a Ghost_AM module by integrating the ghost bottleneck with the simple AM. This Ghost_AM module is introduced into to the YOLOv5s’ network for improving the YOLOv5s’ extraction performance for small target’s feature from a complex SAR image. Furthermore, to improve the YOLOv5s’ recognition ability for the features extracted from the Ghost_AM, a bidirectional feature pyramid network is use to replace the YOLOv5s’ feature fusion network and get a precise detection. The experiments using some SAR ship image datasets have demonstrated the presented model is better than some traditional SAR target detection algorithms and the original YOLOv5s. Moreover, the presented model’s parameters are reduced by 25.1% compared with the original YOLOv5s, which contributes to its simpler implementation.

Multi-Domain Joint Synthetic Aperture Radar Ship Detection Method Integrating Complex Information with Deep Learning

With the flourishing development of deep learning, synthetic aperture radar (SAR) ship detection based on this method has been widely applied across various domains. However, most deep-learning-based detection methods currently only use the amplitude information from SAR images. In fact, phase information and time-frequency features can also play a role in ship detection. Additionally, the background noise and the small size of ships also pose challenges to detection. Finally, satellite-based detection requires the model to be lightweight and capable of real-time processing. To address these difficulties, we propose a multi-domain joint SAR ship detection method that integrates complex information with deep learning. Based on the imaging mechanism of line-by-line scanning, we can first confirm the presence of ships within echo returns in the eigen-subspace domain, which can reduce detection time. Benefiting from the complex information of single-look complex (SLC) SAR images, we transform the echo returns containing ships into the time-frequency domain. In the time-frequency domain, ships exhibit distinctive features that are different from noise, without the limitation of size, which is highly advantageous for detection. Therefore, we constructed a time-frequency SAR image dataset (TFSID) using the images in the time-frequency domain, and utilizing the advantages of this dataset, we combined space-to-depth convolution (SPDConv) and Inception depthwise convolution (InceptionDWConv) to propose Efficient SPD-InceptionDWConv (ESIDConv). Using this module as the core, we proposed a lightweight SAR ship detector (LSDet) based on YOLOv5n. The detector achieves a detection accuracy of 99.5 with only 0.3 M parameters and 1.2 G operations on the dataset. Extensive experiments on different datasets demonstrated the superiority and effectiveness of our proposed method.

Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges

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

SwinYOLOv7: Robust ship detection in complex synthetic aperture radar images

Using satellite-based SAR (Synthetic Aperture Radar) imagery to detect and track ships is a formidable challenge. However, accurate analysis is hampered by inherent difficulties such as obscured edges, multiple targets, varying dimensions and complex backgrounds. These factors contribute to a poor signal-to-noise ratio. Various artificial intelligence models have been developed to improve these problems, especially with YOLO-based models. To overcome the above challenges and achieve robust performance, this study presents a model called SwinYOLOv7, a novel fusion of the YOLOv7 framework with the Features Pyramid Network and the Swin Transformer using ground-breaking anchor-free detection algorithms. This innovative method aims to increase the accuracy of vessel detection while reducing the impact of background clutter. The proposed model improved by YOLOv7 examined three different datasets in detail: SRSDD-v1.0, HRSID, and SSDD to optimize the performance of the model. The training process was consistently verified using superior recall, precision, and F1-score values, which can be easily compared with previous studies. The results show that the model using the Swin Transformer attention mechanism and using an image size of 640×640 achieves the highest accuracy of 96.59%. Alternative attention mechanisms, including the Squeeze-and-Excitation Network (SEnet), the Convolutional Block Attention Module (CBAM), Channel Attention (CA) and Efficient Channel Attention (ECA), deliver poorer accuracy rates. The combination of YOLOv7 and Swin Transformer yielded encouraging results that enabled the proposed model to outperform the current benchmarking models. Therefore, the proposed model provides a compelling solution to ensure accurate vessel identification in complex search and rescue scenarios.

A CFAR-Enhanced Ship Detector for SAR Images Based on YOLOv5s

Ship detection and recognition in Synthetic Aperture Radar (SAR) images are crucial for maritime surveillance and traffic management. Limited availability of high-quality datasets hinders in-depth exploration of ship features in complex SAR images. While most existing SAR ship research is primarily based on Convolutional Neural Networks (CNNs), and although deep learning advances SAR image interpretation, it often prioritizes recognition over computational efficiency and underutilizes SAR image prior information. Therefore, this paper proposes YOLOv5s-based ship detection in SAR images. Firstly, for comprehensive detection enhancement, we employ the lightweight YOLOv5s model as the baseline. Secondly, we introduce a sub-net into YOLOv5s, learning traditional features to augment ship feature representation of Constant False Alarm Rate (CFAR). Additionally, we attempt to incorporate frequency-domain information into the channel attention mechanism to further improve detection. Extensive experiments on the Ship Recognition and Detection Dataset (SRSDDv1.0) in complex SAR scenarios confirm our method’s 68.04% detection accuracy and 60.25% recall, with a compact 18.51 M model size. Our network surpasses peers in mAP, F1 score, model size, and inference speed, displaying robustness across diverse complex scenes.

URBAN 3D RECONSTRUCTION OF VHR SAR IMAGES USING ITERATIVE OPTIMIZATION ALGORITHM AND LAYOVER FIXED-ORDER MODEL

Abstract. Synthetic Aperture Radar (SAR) Tomography (TomoSAR) is a three-dimensional SAR imaging technique that uses multiple passes to process complex SAR images and obtain three-dimensional spatial scattering information to derive the elevation scattering distribution. Due to its own shortcomings, the elevation obtained by the traditional spectral estimation method has low resolution in the elevation direction and is affected by noise. The imaging algorithm based on compressed sensing can achieve super-resolution reconstruction in the elevation direction while reducing the number of observations. However, the CS algorithm still faces challenges when applied to real-world tomographic SAR imaging. In particular, it often requires numerous iterations to achieve satisfactory results, which significantly reduces its processing efficiency in large-scale tomography. To address the above issues, in this paper, we proposed an urban 3D reconstruction of VHR SAR images using an iterative optimization algorithm and layover fixed-order model. The iterative optimization algorithm and the layover fixed-order model consist of two parts: The TomoSAR imaging equation is solved by the two-step iterative shrinkage/thresholding (TwIST) algorithm, and the number of scatterers K is estimated by the Bayesian Information Criterion (BIC). In this paper, the effectiveness of TwIST-BIC in TomoSAR imaging in urban areas is verified with real TerraSARX data. By comparing with the OMP algorithm based on matching tracking and the FISTA algorithm based on gradient descent. The TWIST-BIC method is less complex, converges faster, and combines both execution speed and super-resolution, which can effectively solve the processing efficiency problem in large-area tomography and acquire high-resolution tomographic analysis.

Preliminary Evaluation of Geometric Positioning Accuracy of C-SAR Images Based on Automatic Corner Reflectors

C-SAR/01 and C-SAR/02 serve as successors to the GF-3 satellite. They are designed to operate in tandem with GF-3, collectively forming a C-band synthetic aperture radar (SAR) satellite constellation. This constellation aims to achieve 1 m resolution imaging with a revisit rate of one day. It can effectively cater to various applications such as marine disaster prevention, monitoring marine dynamic environments, and supporting marine scientific research, disaster mitigation, environmental protection, and agriculture. Geometric correction plays a pivotal role in acquiring highly precise geographic location data for ground targets. The geometric positioning accuracy without control points signifies the SAR satellite’s geometric performance. However, SAR images do not exhibit a straightforward image-point–object-point correspondence, unlike optical images. In this study, we introduce a novel approach employing high-precision automatic trihedral corner reflectors as ground control points (GCPs) to assess the geometric positioning accuracy of SAR images. A series of satellite-ground synchronization experiments was conducted at the Xilinhot SAR satellite calibration and validation site to evaluate the geometric positioning accuracy of different C-SAR image modes. Firstly, we calculated the azimuth and elevation angles of the corner reflectors based on satellite orbit parameters. During satellite transit, these corner reflectors were automatically adjusted to align with the radar-looking direction. We subsequently measured the exact longitude and latitude coordinates of the corner reflector vertex in situ using a high-precision real-time kinematics instrument. Next, we computed the theoretical image coordinates of the corner reflectors using the rational polynomial coefficients (RPC) model. After that, we determined the accurate position of the corner reflector in the Single Look Complex (SLC) SAR image using FFT interpolation and the sliding window method. Finally, we evaluated and validated the geometric positioning accuracy of C-SAR images by comparing the two coordinates. The preliminary results indicate that the positioning accuracy varies based on the satellite, imaging modes, and orbital directions. Nevertheless, for most sample points, the range positioning accuracy was better than 60 m, and the azimuth positioning accuracy was better than 80 m. These findings can serve as a valuable reference for subsequent applications of C-SAR satellites.

Multitemporal Speckle Reduction With Self-Supervised Deep Neural Networks

Speckle filtering is generally a prerequisite to the analysis of synthetic aperture radar (SAR) images. Tremendous progress has been achieved in the domain of single-image despeckling. Latest techniques rely on deep neural networks to restore the various structures and textures peculiar to SAR images. The availability of time series of SAR images offers the possibility of improving speckle filtering by combining different speckle realizations over the same area. The supervised training of deep neural networks requires ground-truth speckle-free images. Such images can only be obtained indirectly through some form of averaging, by spatial or temporal integration, and are imperfect. Given the potential of very high-quality restoration reachable by multitemporal speckle filtering, the limitations of ground-truth images need to be circumvented. We extend a recent self-supervised training strategy for single-look complex (SLC) SAR images, called MERLIN, to the case of multitemporal filtering. This requires modeling the sources of statistical dependencies in the spatial and temporal dimensions as well as between the real and imaginary components of the complex amplitudes. Quantitative analysis on datasets with simulated speckle indicates a clear improvement of speckle reduction when additional SAR images are included. Our method is then applied to stacks of TerraSAR-X images and shown to outperform competing multitemporal speckle filtering approaches. The code of the trained models and supplementary results are made freely available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://gitlab.telecom-paris.fr/ring/multitemporal-merlin/</uri> .

Lightweight and anchor-free frame detection strategy based on improved CenterNet for multiscale ships in SAR images

Ship detection using synthetic aperture radar (SAR) images has important applications in military and civilian fields, but the different sizes of the ship downgrade the detection accuracy of multiscale ships. Aiming at the problem of the poor accuracy and low efficiency of multiscale ship detection in complex scenes, this paper proposes a lightweight and anchor-free frame detection strategy for multiscale ships in SAR images. First, to deal with the problems of limited training samples, different sizes, attitudes, and angles of the ships in SAR images, a data augmentation strategy suitable for SAR images is adopted to expand the training space, followed by multiscale training to enhance the model generalization ability for multiscale ship detection. Second, a lightweight and anchor-free ship detection model based on the improved CenterNet is proposed, which abandons the dense anchor frame generation and extracts the key point of the ships for detection and positioning. Compared with the anchor frame-based detection method, this proposed detection model does not need to use the post-processing method to remove redundant anchor frames, and can accurately locate the center point of the ships with a better detection performance. Third, to reduce the model size and simplify the model parameters, a more lightweight network design is adopted in combination with the characteristics of SAR images. Hence, a residual network (ResNet) with fewer convolutional layers is constructed as the backbone network, and the cross-stage partial network (CSPNet) and spatial pyramid pooling (SPP) network are designed as the bottleneck network. The shallow ResNet can fully extract the SAR image features and reduce the training overfitting, and CSPNet and SPP can effectively combine the low-level image features to obtain the high-level features, reducing the model computation while at the same time enhancing the feature extraction ability. Finally, the evaluation index of the common objects in the context dataset is introduced, which can provide higher-quality evaluation results for ship detection accuracy and provide comprehensive evaluation indicators for multiscale ship detection. Experimental results show that the proposed strategy has the advantages of high detection efficiency, strong detection ability, and good generalization performance, which can achieve real-time and high-precision detection of the multiscale ship in complex SAR images.

Complex-Valued Sparse SAR-Image-Based Target Detection and Classification

It is known that synthetic aperture radar (SAR) images obtained by typical matched filtering (MF)-based algorithms always suffer from serious noise, sidelobes and clutter. However, the improvement in image quality means that the complexity of SAR systems will increase, which affects the applications of SAR images. The introduction of sparse signal processing technologies into SAR imaging proposes a new way to solve this problem. Sparse SAR images obtained by sparse recovery algorithms show better image performance than typical complex SAR images with lower sidelobes and higher signal-to-noise ratios (SNR). As the most widely applied fields of SAR images, target detection and target classification rely on SAR images with high quality. Therefore, in this paper, a target detection framework based on sparse images recovered by complex approximate message passing (CAMP) algorithm and a novel classification network via sparse images reconstructed by the new iterative soft thresholding (BiIST) algorithm are proposed. Experimental results show that sparse SAR images have better performance whether for target classification or for target detection than the images recovered by MF-based algorithms, which validates the huge application potentials of sparse images.

Spaceborne SAR image formation enhancement using MOCO techniques

Synthetic aperture radar (SAR) is considered a prevailing tool for remote sensing. It benefits working with high efficiency in all weather and all-day circumstances, making SAR is very confident compared to other types of remote sensing. The SAR platform moves with constant velocity and height, with a linear path for ideal situations. However, this assumption is not realized in satellite movement, which is an elliptical orbiting that worsens the quality of the focused image. This paper introduces a methodology of motion compensation for motion errors due to satellite elliptical orbiting and perturbations in an orbital path. It represents two major contributions applied on a low earth orbit (LEO) spaceborne SAR. First, motion errors analysis in the range and azimuth directions. Second, an algorithm for motion error compensation (MOCO) combined with a chirp scaling algorithm (CSA) is performed. Moreover, a validation for the formulated algorithm is executed using sentinel-1 level-0 real raw data input, and the result is compared with the sentinel-1 level-1 single look complex (SLC) SAR image. The validation is performed using two different metrics. First, image quality measurement by sharpness, contrast, and entropy. Second, measuring the peak-sidelobe-ratio (PSLR), impulse-response-width (IRW), and integrated-sidelobe-ratio (ISLR) for five high power reflecting points in the scene area.

HTC+ for SAR Ship Instance Segmentation

Existing instance segmentation models mostly pay less attention to the targeted characteristics of ships in synthetic aperture radar (SAR) images, which hinders further accuracy improvements, leading to poor segmentation performance in more complex SAR image scenes. To solve this problem, we propose a hybrid task cascade plus (HTC+) for better SAR ship instance segmentation. Aiming at the specific SAR ship task, seven techniques are proposed to ensure the excellent performance of HTC+ in more complex SAR image scenes, i.e., a multi-resolution feature extraction network (MRFEN), an enhanced feature pyramid net-work (EFPN), a semantic-guided anchor adaptive learning network (SGAALN), a context ROI extractor (CROIE), an enhanced mask interaction network (EMIN), a post-processing technique (PPT), and a hard sample mining training strategy (HSMTS). Results show that each of them offers an observable accuracy gain, and the instance segmentation performance in more complex SAR image scenes becomes better. On two public datasets SSDD and HRSID, HTC+ surpasses the other nine competitive models. It achieves 6.7% higher box AP and 5.0% higher mask AP than HTC on SSDD. These are 4.9% and 3.9% on HRSID.

Multitask Learning-Based for SAR Image Superpixel Generation

Most of the existing synthetic aperture radar (SAR) image superpixel generation methods are designed based on the raw SAR images or artificially designed features. However, such methods have the following limitations: (1) SAR images are severely affected by speckle noise, resulting in unstable pixel distance estimation. (2) Artificially designed features cannot be well-adapted to complex SAR image scenes, such as the building regions. Aiming to overcome these shortcomings, we propose a multitask learning-based superpixel generation network (ML-SGN) for SAR images. ML-SGN firstly utilizes a multitask feature extractor to extract deep features, and constructs a high-dimensional feature space containing intensity information, deep semantic informantion, and spatial information. Then, we define an effective pixel distance measure based on the high-dimensional feature space. In addition, we design a differentiable soft assignment operation instead of the non-differentiable nearest neighbor operation, so that the differentiable Simple Linear Iterative Clustering (SLIC) and multitask feature extractor can be combined into an end-to-end superpixel generation network. Comprehensive evaluations are performed on two real SAR images with different bands, which demonstrate that our proposed method outperforms other state-of-the-art methods.

An RCS Measurement Method Using Sparse Imaging Based 3-D SAR Complex Image

Three-dimensional (3-D) synthetic aperture radar (SAR) near-field imaging provides a novel radar cross section (RCS) measurement method, which has been widely concerned in the microwave field. However, the accuracy of RCS measurement based on image is easily affected by sidelobes of matching filtering (MF) imaging and background clutter. Although the existing observation-matrix-based sparse SAR imaging algorithm can suppress sidelobes and clutter, it requires huge computational cost. To solve the above problems, an RCS measurement method using sparse imaging based 3-D SAR complex image is proposed. First, 3-D sparse imaging based complex image is used to suppress sidelobe and clutter of MF image. After that, the far-field RCS of the target is obtained by the compensation factor. Compared with the observation-matrix-based sparse SAR imaging algorithm, the proposed algorithm can reduce the computation time while retain the phase information of scene distribution. Compared with the RCS measurement based on MF image, the RCS measurement performance of the proposed method is improved. The simulation and real data of the system results validate the proposed method.

Target Recognition in Single-Channel SAR Images Based on the Complex-Valued Convolutional Neural Network With Data Augmentation

In recent years, with the rapid development of deep learning theory, real-valued convolutional neural networks have achieved significant success in the field of synthetic aperture radar (SAR) target recognition. However, different from natural images, the SAR images have complex information due to their special imaging mechanism. Traditional deep learning methods for SAR target recognition only employ the amplitude information and ignore the phase portion, which may sacrifice some useful information in the original complex SAR data. Moreover, the number of samples of SAR images is very limited. This is undoubtedly a huge challenge for the traditional real-valued convolutional neural networks (CNNs) which require numerous labeled data for training. Especially, since the single-channel SAR image contains only one channel, it has less available information than the multiple-channel SAR image. To deal with the above problems, a complex-valued convolutional neural network (CV-Net), for target recognition in single-channel SAR images is proposed in this paper. The amplitude and phase information in the complex SAR data are fully utilized for target recognition. In addition, to alleviate the problem of small samples, this paper also proposed a data augmentation method based on the complex SAR images. The experimental results based on the measured SAR data demonstrate that the proposed algorithm has better performance than the traditional real-valued convolutional neural networks.

Target Detection Based on Edge-Aware and Cross-Coupling Attention for SAR Images

Due to the existence of speckle noise, background clutter, backscattering points, and geometric distortion of some targets in synthetic aperture radar (SAR) images, extracting multiscale and multilocation targets accurately is still a great challenge. To tackle these problems, a novel target detection method based on edge-aware and cross-coupling attention for SAR images is proposed in this paper. By enhancing the depend-encies between targets in different locations, bridging the gap between different feature maps, and assisting the targets’ detec-tion through cross-coupling with the edge-aware network, the performance of detecting multiscale targets in complex SAR im-ages can be improved significantly. Specifically, residual spatial pyramid pooling (RSPP) and mixed pooling module based con-volution block attention module (MCBAM) are combined in the decoding part to promote coupling between networks. Besides, the semi-dense connection is adopted in the encoding part based on residual convolution block (RCB), which can improve the ability of multiscale feature extraction and promote the acquirement of high-resolution features with strong semantic information. Ex-periments are conducted on the SAR oil tank dataset (OTD) and SAR residential area dataset (RAD). We compare our model with a traditional method and CNN-based algorithms. The experi-mental results verify that our model outperforms the competing models in both pixel level and geometric segmentation accuracy.

Oil Spill Contextual and Boundary-Supervised Detection Network Based on Marine SAR Images

Oil spills have caused serious harm to the marine environment. Remote sensing technology is one of the important tools for marine environment monitoring. Synthetic aperture radar (SAR) has become an important technology for detecting marine pollution. Identifying dark spots is essential for oil spill detection based on SAR images. Dark spots’ detection can be achieved using image segmentation techniques. However, natural phenomena, such as waves and currents, can also cause dark spots, resulting in consistently uneven intensity, high noise, and blurred boundaries in oil spill images. In addition, existing oil spill detection models often perform well for large targets but have poor detection accuracy for small targets. To solve the above problems, the oil spill contextual and boundary-supervised detection network (CBD-Net) is proposed to extract refined oil spill regions by fusing multiscale features. To improve the internal consistency of oil spill regions, the spatial and channel squeeze excitation (scSE) block is introduced. In CBD-Net, boundary details are enhanced with optimized edge supervision. In addition, a manually labeled dataset is proposed, Deep-SAR Oil Spill (SOS) dataset, aiming to solve the problem of insufficient existing oil spill detection dataset. Experimental results demonstrate that CBD-Net outperforms other comparative models and is able to extract robust and accurate oil spill regions from complex SAR images. The highest mIoU of 83.42% and the highest F1 score of 87.87% were achieved on the SOS dataset. The CBD-Net model proposed in this article can play a guiding role in the marine oil spill decision support system.

Refocusing on SAR Ship Targets With Three-Dimensional Rotating Based on Complex-Valued Convolutional Gated Recurrent Unit

This letter proposes a complex-valued convolutional gated recurrent unit (CV-ConvGRU) network for the three-dimensional rotation refocusing task of a synthetic aperture radar (SAR) ship target. To take advantage of the amplitude and phase information of complex SAR images, all elements of CV-ConvGRU, including the convolutional layer, activation function, update gate and reset gate, are extended to the complex domain. Based on CV-ConvGRU, a complex-valued SAR ship refocusing network (CV-SSRN) architecture is designed for refocusing experiments. To verify the robustness of the proposed CV-ConvGRU over ConvGRU on information perception, this letter also raises a real-valued SAR ship refocusing network (RV-SSRN), which has the same degree of freedom as CV-SSRN. Finally, experiments are carried out, and all results show the superiority of the proposed method on refocusing accuracy.

Amplitude-Phase CNN-Based SAR Target Classification via Complex-Valued Sparse Image

It is known that a synthetic aperture radar (SAR) image obtained by matched filtering (MF)-based algorithms always suffers from serious noise, sidelobes, and clutters. However, the improvement of the image quality means the complexity of the SAR system will increase, which affects the application of the SAR image. The introduction of the sparse signal processing technique into SAR imaging proposes a new way to solve this problem. Sparse SAR image obtained by sparse recovery algorithms shows a better image performance than the typical complex SAR image with lower sidelobes and higher signal-to-noise ratio. As the most widely applied field of the SAR image, target classification relies on the SAR image with high quality. Therefore, a novel target classification model based on the amplitude and phase information of the sparse SAR image is introduced in this article. First, complex sparse image dataset is constructed by a novel iterative soft thresholding (BiIST) algorithm. Compared with typical regularization-based sparse recovery algorithms, BiIST not only can improve the quality of recovered image, but also can obtain a nonsparse solution with retaining phase information and background statistical distribution of the SAR image. Then, targets are classified by the proposed amplitude-phase convolutional neural network (AP-CNN). Typical SAR target classification networks imitate those on optical image, just using amplitude data. However, considering the particularity of the SAR image, the AP-CNN uses both amplitude and phase for training, which theoretically improves the classification accuracy. Experimental results show that the AP-CNN outperforms the typical amplitude-based CNN in target classification, both under standard operating conditions (SOCs) and extended operating conditions (EOCs). Results under SOC demonstrate that the AP-CNN improves the classification accuracy by 11.46&#x0025; with only 1000 training samples. Even under EOC, the accuracy gap between the AP-CNN and CNN can reach 6.6&#x0025; in the case of 800 training samples. This means that even if the number of samples is limited, the AP-CNN can obtain optimal classification result.