Target Recognition Using Pre-Trained Convolutional Neural Networks and Transfer Learning

Deep learning algorithms have found extensive utility in Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR). Despite this, conventional deep learning-based ATR models often lack in their performance when subjected to Extended Operating Conditions (EOCs). Significant variations in depression, noise interference, limited training data, and partial occlusion are primary factors in EOCs. In this paper, we proposed a deep neural network-based technique to recognize SAR targets for Standard Operating Conditions (SOC) and Extended Operating Conditions (EOC). The proposed approach comprises an encoder and decoder network. The encoder network integrates multiple dilated convolutions to address noise-induced recognition challenges for extracting multi-scale features. Furthermore, a feature refinement module is integrated within the multi-scale channels to enhance the extraction of discriminative and resilient features. Feature refinement selectively emphasizes informative features while suppressing irrelevant ones. Additionally, a salient attention block and a spatial feature learning module are introduced for feature selection. Selected features are then utilized in the top-level network layer of the encoder network to preserve spatial relationships among diverse features. This spatial feature learning module aids in recognition performance, particularly when training data is scarce. The decoder network consists of stacked transposed convolution layers, facilitating the encoder network's acquisition of discriminative image features. Experimental evaluations were conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset to validate the efficacy of the proposed methodology.

Many research efforts have been devoted to applying machine learning (ML) algorithms to the task of Automatic Target Recognition (ATR). In the 90’s, ML techniques such as Neural Networks were less popular due to various technological barriers and applications. Computational resources were scarce and expensive. Today, computational resources are not as expensive as in the past; however, an abundance of sensors and business data need to be analyzed in real-time. High performance computing (HPC) enables ML-based decision making in real-time or near real-time. This research explores the application of deep learning algorithms, specifically convolutional neural networks, to the task of ATR in synthetic aperture radar (SAR) imagery. We developed a Convolution Neural Networks (CNN) architecture for achieving ATR in SAR imagery and found that classification accuracy levels of 99% can be achieved through the application of neural networks. We used graphics processing units (GPU) to accomplish the computational tasks.

This tutorial presents a state-of-the-art survey of advanced applications of Synthetic Aperture Radar (SAR). Applications include: the detection and recognition of targets in SAR imagery, and the detection of targets under trees (and in the open) using change detection (coherent change detection, full-polarization change detection, etc). A fully polarimetric SAR sensor is described. Models of clutter and targets are developed from analysis of full-polarization SAR imagery. Algorithms for optimum (GLRT) processing of full-polarization data are derived, including the polarimetric whitening filter (PWF) and the polarimetric matched filter (PMF). Polarization-based discrimination features (polarization entropy, anisotropy, etc.) are developed and applied to SAR image terrain classification. Model-based and template-based target recognition systems are described and classifier performance results versus resolution and polarization are summarized for 10-and 20-target classifiers. Super-resolution algorithms are applied to SAR imagery and target recognition performance improvements demonstrated. Multi-polarization and multi-pass change detection algorithms are developed and demonstrated using UHF SAR imagery of targets under trees; fusion of multi-polarization coherent and non-coherent change detection algorithms is demonstrated. The effect of SAR image compression on change detection performance is quantified. Change detection performance using multi-pass VHF SAR imagery of targets under trees is demonstrated using data gathered by the Swedish CARABAS SAR system.

Synthetic Aperture Radar (SAR) imagery is available all the time and, in all weathers, due to its ability to penetrate through cloud cover, dust, haze except heavy rainfall. SAR imagery mainly characterizes structural properties of various earth objects and provides a data which is rich in spatial information. Processing of SAR data has been of great interest due to these advantages. However, due to coherent processing of SAR signal, imagery is corrupted by speckle noise which is multiplicative in nature. Reduction of speckle noise from SAR imagery is helpful for analysis and interpretation of SAR images. In this paper, performance of conventional speckle reduction filters, namely Lee, Enhanced Lee, Frost, Enhanced Frost and Gamma MAP are compared with wavelet-based filtering technique for RISAT-1 imagery. Results are compared visually and using quality metrics, Speckle Suppression Index (SSI), Equivalent Number of Looks (ENL) and Speckle Suppression and Mean Preservation Index (SMPI). From visual interpretation of de-speckled image, it is evident that wavelet-based filtering out performs the conventional filters in terms of edge and texture preservation.

Synthetic Aperture Radar (SAR) images are prone to be contaminated by noise, which makes it very difficult to perform target recognition in SAR images. Inspired by great success of very deep convolutional neural networks (CNNs), this paper proposes a robust feature extraction method for SAR image target classification by adaptively fusing effective features from different CNN layers. First, YOLOv4 network is fine-tuned to detect the targets from the respective MF SAR target images. Second, a very deep CNN is trained from scratch on the moving and stationary target acquisition and recognition (MSTAR) database by using small filters throughout the whole net to reduce the speckle noise. Besides, using small-size convolution filters decreases the number of parameters in each layer and, therefore, reduces computation cost as the CNN goes deeper. The resulting CNN model is capable of extracting very deep features from the target images without performing any noise filtering or pre-processing techniques. Third, our approach proposes to use the multi-canonical correlation analysis (MCCA) to adaptively learn CNN features from different layers such that the resulting representations are highly linearly correlated and therefore can achieve better classification accuracy even if a simple linear support vector machine is used. Experimental results on the MSTAR dataset demonstrate that the proposed method outperforms the state-of-the-art methods.

Feature extraction is a crucial step for any automatic target recognition process, especially in the interpretation of synthetic aperture radar (SAR) imagery. In order to obtain distinctive features, this paper proposes a feature fusion algorithm for SAR target recognition based on a stacked autoencoder (SAE). The detailed procedure presented in this paper can be summarized as follows: firstly, 23 baseline features and Three-Patch Local Binary Pattern (TPLBP) features are extracted. These features can describe the global and local aspects of the image with less redundancy and more complementarity, providing richer information for feature fusion. Secondly, an effective feature fusion network is designed. Baseline and TPLBP features are cascaded and fed into a SAE. Then, with an unsupervised learning algorithm, the SAE is pre-trained by greedy layer-wise training method. Capable of feature expression, SAE makes the fused features more distinguishable. Finally, the model is fine-tuned by a softmax classifier and applied to the classification of targets. 10-class SAR targets based on Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset got a classification accuracy up to 95.43%, which verifies the effectiveness of the presented algorithm.

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.

This paper proposes an automatic target recognition (ATR) method for synthetic aperture radar (SAR) images based on information-decoupled representation. A typical SAR image of a ground target can be divided into three parts: target region, shadow and background. From the aspect of SAR target recognition, the target region and shadow contain discriminative information. However, they also include some confusing information because of the similarities of different targets. The background mainly contains redundant information, which has little contribution to the target recognition. Because the target segmentation may impair the discriminative information in the target region, the relatively simpler shadow segmentation is performed to separate the shadow region for information decoupling. Then, the information-decoupled representations are generated, i.e., the target image, shadow and original image. The background is retained in the target image, which represents the coupling of target backscattering and background. The original image and generated target image are classified using the sparse representation-based classification (SRC). Then, their classification results are combined by a score-level fusion for target recognition. The shadow image is not used because of its lower discriminability and possible segmentation errors. To evaluate the performance of the proposed method, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under both standard operating condition (SOC) and various extended operating conditions (EOCs). The proposed method can correctly classify 10 classes of targets with the percentage of correct classification (PCC) of 94.88% under SOC. With the PCCs of 93.15% and 75.03% under configuration variance and 45° depression angle, respectively, the superiority of the proposed is demonstrated in comparison with other methods. The robustness of the proposed method to both uniform and nonuniform shadow segmentation errors is validated with the PCCs over 93%. Moreover, with the maximum average precision of 0.9580, the proposed method is more effective than the reference methods on outlier rejection.

Synthetic Aperture Radar (SAR) imagery have been one of the important tools to support earth observations and topographic measurements. It means SAR imagery are essentially rich in structures and some important target categories are difficult to recognize. Optical imagery contains rich and clear spectral information which has a good influence on semantic image segmentation. The success of deep neural networks for semantic segmentation heavily depends on large-scale and well-labeled data sets, which are hard to collect in practice. In this paper, we consider deep transfer learning for semantic segmentation, we propose a deep novel transfer learning method, which transfers a semantically segment model from SAR imagery to SAR and optical fusion imagery. The experimental results show that the method proposed achieves higher mean Intersection over Union (mIoU) with less training time compared with other methods.

In the field of synthetic aperture radar (SAR) automatic target recognition (ATR), deep learning-driven methods perform well when numerous training samples are available. However, in practical SAR application scenarios, the number of available training samples is often scarce due to the limitation of observation conditions, which leads to major challenges for deep learning-driven methods in real-world deployment. Currently, the problem of ATR with only a few training samples has attracted much attention in the SAR field. In this article, we put forward an ATR method called azimuth-guided feature embedding network with dual inference mechanism (AGFEN-DIM) to achieve fewshot SAR target recognition. To be specific, the feature extraction model, i.e. azimuth-guided feature embedding network (AGFEN) is composed of the azimuth embedding module (AEM) and the dynamic feature embedding module (DFEN). Among them, AEM resorts to a set of azimuth-parameterized convolution kernels, aiming to make full use of information relevant to the current radar imaging environment. The proposed DFEN is capable of dynamically extracting the discriminative features of the target according to the input image under the guidance of azimuth-parameterized convolutional kernels. The dual inference mechanism (DIM) effectively integrates the inference results of improved prototype classification and label propagation strategy to boost the reliability and robustness of the recognition model for few-shot SAR target recognition tasks. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate that the proposed AGFEN-DIM surpasses many state-of-the-art SAR ATR methods in various application scenarios.

Automatic targets recognition (ATR) for synthetic aperture radar (SAR) image is very important. ATR can be used in traffic management, national frontier safety, and so on. Traditional algorithms for SAR ATR is composed of extraction features and training classifier. The features are essential for the classification accuracy. However, choosing good features by hand is a hard task. The deep convolutional neural networks (CNNs) which can learn features automatically have got a great performance in natural images. However, the CNNs have many parameters and need a lot of data to train such networks. The remote-sensing data of SAR is limited. Then, the authors need a simple network which needs not much data and easy to train. The principal component analysis network (PCANet) is a shallow network that performs well in the recognition task and needs no hand features choosing. Though this network has produced a wide application in the natural images, it is rarely used in the SAR images. The experimental result of the moving and stationary target acquisition and recognition (MSTAR) dataset shows that the PCANet can achieve over 99% accuracy on ten-class targets. This result is better than traditional algorithms and is very close to the results of deep-learning methods.

DARPA/Air Force Research Laboratory Moving and Stationary Target Acquisition and Recognition (MSTAR) program is developing state-of-the-art model based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The model-based approach requires using off-line developed target models in an on-line hypothesize-and-test manner to compare predicted target signatures with image data and output target reports. Central to this model-based ATR is the PEMS (Predict-Extract-Match-Search) subsystem. The Search module is critical to PEMS by providing intelligent control to traverse the hypothesis feature space. A major MSTAR goal is to demonstrate robust ATR for variations in targets including partially hidden targets. This paper will provide an update on the technology being developed under MSTAR and the status of this model based ATR research, specifically concentrating on the Search Module.

Combination of global and local filters for robust SAR target recognition under various extended operating conditions

ABSTRACTAutomatic Target Recognition (ATR) based on Synthetic Aperture Radar (SAR) images plays a key role in military applications. However, there are difficulties with this traditional recognition method. Principally, it is a challenge to design robust features and classifiers for different SAR images. Although Convolutional Neural Networks (CNNs) are very successful in many image classification tasks, building a deep network with limited labeled data remains a problem. The topologies of CNNs like the fully connected structure will lead to redundant parameters and the negligence of channel-wise information flow. A novel CNNs approach, called Group Squeeze Excitation Sparsely Connected Convolutional Networks (GSESCNNs), is therefore proposed as a solution. The group squeeze excitation performs dynamic channel-wise feature recalibration with less parameters than squeeze excitation. Sparsely connected convolutional networks are a more efficient way to operate the concatenation of feature maps from different layers. Experimental results on Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR images, demonstrate that this approach achieves, at 99.79%, the best prediction accuracy, outperforming the most common skip connection models, such as Residual Networks and Densely Connected Convolutional Networks, as well as other methods reported in the MSTAR dataset.

In order to improve synthetic aperture radar (SAR) target recognition performance, this paper proposes a novel method using multi-level deep features. The multi-level deep features are learned by the convolutional neural network (CNN), which are capable of describing the target characteristics from different aspects. In order to make full use of the discrimination contained in the multi-level deep features, the joint sparse representation (JSR) is used as the basic classifier, which performs the multi-task learning to jointly classify the multi-level deep features. It could not only represent each feature properly but also consider the correlations between different levels of features. Based on the solutions from JSR, the target label is classified as the training class with the minimum reconstruction error. By fully exploiting the discriminative information contained in the multi-level deep features, the proposed method could effectively enhance SAR target recognition performance. The moving and stationary target acquisition and recognition (MSTAR) dataset is employed in the experiments. The results show that the proposed method could achieve a significantly high recognition rate of 99.38% for classifying 10 classes of targets under the standard operating condition (SOC), which is higher than those from some reference methods drawn from current literatures. Under different types of extended operating conditions (EOCs), the overall performance of the proposed method keeps superior over the reference methods. In addition, the outlier rejection capability of the proposed method is also better than the compared methods. All these experimental results validate the high effectiveness of the proposed method.