Robust Target Recognition Research Articles

Robust target recognition in synthetic aperture radar images via correlation analysis and joint decision of multi-level bidimensional intrinsic mode functions by bidimensional variational mode decomposition

Robust target recognition in synthetic aperture radar images via correlation analysis and joint decision of multi-level bidimensional intrinsic mode functions by bidimensional variational mode decomposition

Capsule Broad Learning System Network for Robust Synthetic Aperture Radar Automatic Target Recognition with Small Samples

The utilization of deep learning in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) has witnessed a recent surge owing to its remarkable feature extraction capabilities. Nonetheless, deep learning methodologies are often encumbered by inadequacies in labeled data and the protracted nature of training processes. To address these challenges and offer an alternative avenue for accurately extracting image features, this paper puts forth a novel and distinctive network dubbed the Capsule Broad Learning System Network for robust SAR ATR (CBLS-SARNET). This novel strategy is specifically tailored to cater to small-sample SAR ATR scenarios. On the one hand, we introduce a United Division Co-training (UDC) Framework as a feature filter, adeptly amalgamating CapsNet and the Broad Learning System (BLS) to enhance network efficiency and efficacy. On the other hand, we devise a Parameters Sharing (PS) network to facilitate secondary learning by sharing the weight and bias of BLS node layers, thereby augmenting the recognition capability of CBLS-SARNET. Experimental results unequivocally demonstrate that our proposed CBLS-SARNET outperforms other deep learning methods in terms of recognition accuracy and training time. Furthermore, experiments validate the generalization and robustness of our novel method under various conditions, including the addition of blur, Gaussian noise, noisy labels, and different depression angles. These findings underscore the superior generalization capabilities of CBLS-SARNET across diverse SAR ATR scenarios.

SFC-Sup: Robust Two-Stage Underwater Acoustic Target Recognition Method Based on Supervised Contrastive Learning

SFC-Sup: Robust Two-Stage Underwater Acoustic Target Recognition Method Based on Supervised Contrastive Learning

Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training

Sufficient synthetic aperture radar (SAR) data is the key element in achieving excellent target recognition performance for most deep learning algorithms. It is unrealistic to obtain sufficient SAR data from the actual measurements, so SAR simulation based on electromagnetic scattering modeling has become an effective way to obtain sufficient samples. Simulated and measured SAR images are nonhomologous data. Due to the fact that the target geometric model of SAR simulation is not inevitably consistent with the real object, the SAR sensor model in SAR simulation may be different from the actual sensor, the background environment of the object is also inevitably different from that of SAR simulation, the error of electromagnetic modeling method itself, and so on. There are inevitable differences between the simulated and measured SAR images, which will affect the recognition performance. To address this problem, an SAR simulation method based on a high-frequency asymptotic technique and a discrete ray tracing technique is proposed in this paper to obtain SAR simulation images of ground vehicle targets. Next, various convolutional neural networks (CNNs) and AugMix data augmentation methods are proposed to train only on simulated data, and then target recognition on MSTAR measured data is performed. The experiments show that all the CNNs can achieve incredible recognition performance on the nonhomologous SAR data, and the RegNetX-3.2GF achieves state-of-the-art performance, up to 84.81%.

Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau

The development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult problem is how to quickly extract landslide information from extensive InSAR image data. Since the instance segmentation model (Mask R-CNN) in deep learning can provide highly robust target recognition, we select the landslide-prone eastern edge of the Tibetan Plateau as a specific test area. Introducing and optimizing this model achieves high-speed and accurate recognition of InSAR observations. First, the InSAR patch landslide instance segmentation dataset (SLD) is established by developing a common object in context (COCO) annotation format conversion code based on InSAR observations. The Mask R-CNN+++ is found by adding three functions of the ResNext module to increase the fineness of the network segmentation results and enhance the noise resistance of the model, the DCB (deformable convolutional block) to improve the feature extraction ability of the network for geometric morphological changes of landslide patches, and an attention mechanism to selectively enhance usefully and suppress features less valuable to the native Mask R-CNN network. The model achieves 92.94% accuracy on the test set, and the active landslide recognition speed based on this model under ordinary computer hardware conditions is 72.3 km2/s. The overall characteristics of the results of this study show that the optimized model effectively enhances the perceptibility of image morphological changes, thereby resulting in smoother recognition boundaries and further improvement of the generalization ability of segmentation detection. This result is expected to serve to identify and monitor active landslides in complex surface conditions on a large spatial scale. Moreover, active landslides of different geometric features, motion patterns, and intensities are expected to be further segmented.

Adversarial Self-Supervised Learning for Robust SAR Target Recognition

Synthetic aperture radar (SAR) can perform observations at all times and has been widely used in the military field. Deep neural network (DNN)-based SAR target recognition models have achieved great success in recent years. Yet, the adversarial robustness of these models has received far less academic attention in the remote sensing community. In this article, we first present a comprehensive adversarial robustness evaluation framework for DNN-based SAR target recognition. Both data-oriented metrics and model-oriented metrics have been used to fully assess the recognition performance under adversarial scenarios. Adversarial training is currently one of the most successful methods to improve the adversarial robustness of DNN models. However, it requires class labels to generate adversarial attacks and suffers significant accuracy dropping on testing data. To address these problems, we introduced adversarial self-supervised learning into SAR target recognition for the first time and proposed a novel unsupervised adversarial contrastive learning-based defense method. Specifically, we utilize a contrastive learning framework to train a robust DNN with unlabeled data, which aims to maximize the similarity of representations between a random augmentation of a SAR image and its unsupervised adversarial example. Extensive experiments on two SAR image datasets demonstrate that defenses based on adversarial self-supervised learning can obtain comparable robust accuracy over state-of-the-art supervised adversarial learning methods.

Multi-Aspect SAR Target Recognition Based on Prototypical Network with a Small Number of Training Samples.

At present, synthetic aperture radar (SAR) automatic target recognition (ATR) has been deeply researched and widely used in military and civilian fields. SAR images are very sensitive to the azimuth aspect of the imaging geomety; the same target at different aspects differs greatly. Thus, the multi-aspect SAR image sequence contains more information for classification and recognition, which requires the reliable and robust multi-aspect target recognition method. Nowadays, SAR target recognition methods are mostly based on deep learning. However, the SAR dataset is usually expensive to obtain, especially for a certain target. It is difficult to obtain enough samples for deep learning model training. This paper proposes a multi-aspect SAR target recognition method based on a prototypical network. Furthermore, methods such as multi-task learning and multi-level feature fusion are also introduced to enhance the recognition accuracy under the case of a small number of training samples. The experiments by using the MSTAR dataset have proven that the recognition accuracy of our method can be close to the accruacy level by all samples and our method can be applied to other feather extraction models to deal with small sample learning problems.

Robust Target Recognition and Tracking of Self-Driving Cars With Radar and Camera Information Fusion Under Severe Weather Conditions

Radar and camera information fusion sensing methods are used to solve the inherent shortcomings of the single sensor in severe weather. Our fusion scheme uses radar as the main hardware and camera as the auxiliary hardware framework. At the same time, the Mahalanobis distance is used to match the observed values of the target sequence. Data fusion based on the joint probability function method. Moreover, the algorithm was tested using actual sensor data collected from a vehicle, performing real-time environment perception. The test results show that radar and camera fusion algorithms perform better than single sensor environmental perception in severe weather, which can effectively reduce the missed detection rate of autonomous vehicle environment perception in severe weather. The fusion algorithm improves the robustness of the environment perception system and provides accurate environment perception information for the decision-making system and control system of autonomous vehicles.

Extended convolutional capsule network with application on SAR automatic target recognition

Deep learning-based algorithms have a wide range of applications in synthetic aperture radar (SAR) automatic target recognition (ATR). However, most deep learning-based ATR algorithms perform poorly under extended operation conditions (EOCs), such as large depression variation, noise corruption, limited training samples, partial occlusion, and etc. This paper presents a novel deep neural network named extended convolutional capsule network to achieve robust SAR target recognition under EOCs. The proposed method is composed of an encoder network and a decoder network. Specifically, to mitigate the impact of noise on recognition, we first adopt multiple dilated convolutions to extract multi-scale features in the encoder network. Secondly, a feature refinement module is embedded in the multi-scale channels, which aims to extract discriminative and robust features by adaptively highlighting informative features and suppressing useless ones. Finally, we deploy capsule unit-based feature pose preserving layers to retain the spatial relationship among different features in the top-level network layer of the encoder network, which is very useful for improving the recognition performance under limited training samples. The decoder network is formed by stacking transposed convolutional layers to encourage the encoder network to learn discriminative image features. Experiments on the moving and stationary target acquisition and recognition (MSTAR) data demonstrate the effectiveness of the proposed method.

Feature Extraction and Target Recognition of Moving Image Sequences

The detection and recognition of moving objects in image sequence images involve many aspects, such as pattern recognition, image processing, and computer vision. The main difficulties of target detection and recognition are complex background interference, local occlusion, real-time recognition, illumination changes, target size type changes, etc. However, it is very difficult to solve these problems in practical applications. This article introduces image pre-processing for the pre-processing of image sequences. Selectively we highlight the visually obvious features that are helpful for target detection in the image, weaken the image background and features that are not related to the target, and improve the quality of the image sequence. A multi-information integrated probability density estimation kernel integrating gray scale, spatial relationship and local standard deviation information is designed, and the multi-information integrated kernel is used to extract the feature of the moving target. In terms of moving target recognition, Naive Bayes is used as a weak learner. In order to avoid the over-fitting of the classifier caused by high-noise moving image sequence features, the regularized Adaboost recognition model is introduced as a moving target recognition classifier. In order to completely separate the target and the background, we propose a moving target extraction method based on multi-information kernel density estimation, and input relevant target feature description vectors into the regularized Adaboost-based moving target recognition framework. Robust target recognition performance is obtained, and the reliability of target recognition under high noise data is improved.

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.

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

In this paper, a robust synthetic aperture radar (SAR) automatic target recognition (ATR) method is proposed by combining the global and local filters, especially aiming to improve the recognition performance under various extended operating conditions (EOCs). Due to the cleanness of the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, which is the prevalent benchmark for SAR ATR, extremely high performance has been reported in many literatures. However, in the real-world scenarios, there exist many types of EOCs such as noise corruption, partial occlusion, sensor variation, etc. Therefore, this study focuses on the SAR ATR problem under several typical EOCs. The intensities of the test image to be classified is taken as the global filter. The spatial correlation between the test image and its corresponding template is calculated as the global response, which describes the global consistency. To depict the local properties of the target, the attributed scattering centers (ASCs) are employed as local filters. Each ASC of the test image is matched with its counterpart from the template ASC set. Then, the local response is evaluated based on the attributes’ differences. The global response and local responses are linearly combined using a random weight matrix. Afterwards, a judgment variable is designed as the measure for target recognition. Experiments are conducted on the MSTAR dataset under the standard operating condition (SOC) and various EOCs including configuration variance, depression angle variance, noise corruption, resolution variance, and partial occlusion. Compared with several state-of-the-art SAR ATR methods, the validity and robustness of the proposed method is fully demonstrated.

Joint sparse representation of complementary components in SAR images for robust target recognition

An automatic target recognition (ATR) method of synthetic aperture radar (SAR) images is proposed by joint sparse representation (JSR) of the complementary components from the original SAR image. The shadow and target image are generated from the original image. A simple but effective segmentation algorithm is designed to separate out the shadow region. By replacing the shadow region with randomly selected background pixels in the original image, the target image is generated. Afterwards, the two components together with the original image are jointly classified based on JSR. Due to the extended operating conditions (EOCs) in SAR ATR, the shadow or target region may be corrupted. In this case, the sole use of the original image may bring some interference caused by the corruption. As a remedy, the joint use of the three components can effectively improve the robustness of the ATR method to various EOCs by complementing each other. To quantitatively evaluate the proposed method, experiments are conducted on the moving and stationary target acquisition and recognition dataset under various conditions. The results demonstrate the effectiveness and robustness of the proposed method.

Exploiting Multi-View SAR Images for Robust Target Recognition

The exploitation of multi-view synthetic aperture radar (SAR) images can effectively improve the performance of target recognition. However, due to the various extended operating conditions (EOCs) in practical applications, some of the collected views may not be discriminative enough for target recognition. Therefore, each of the input views should be examined before being passed through to multi-view recognition. This paper proposes a novel structure for multi-view SAR target recognition. The multi-view images are first classified by sparse representation-based classification (SRC). Based on the output residuals, a reliability level is calculated to evaluate the effectiveness of a certain view for multi-view recognition. Meanwhile, the support samples for each view selected by SRC collaborate to construct an enhanced local dictionary. Then, the selected views are classified by joint sparse representation (JSR) based on the enhanced local dictionary for target recognition. The proposed method can eliminate invalid views for target recognition while enhancing the representation capability of JSR. Therefore, the individual discriminability of each valid view as well as the inner correlation among all of the selected views can be exploited for robust target recognition. Experiments are conducted on the moving and stationary target acquisition recognition (MSTAR) dataset to demonstrate the validity of the proposed method.

Target recognition in SAR images by exploiting the azimuth sensitivity

ABSTRACTAzimuth sensitivity is a significant characteristic of synthetic aperture radar (SAR) images. Most of the previous SAR target recognition algorithms try to cope with the property by pose estimation or training classifiers which are not sensitive to azimuth. Actually, the azimuth sensitivity can provide discriminative information for target recognition as a supplement to the original spatial image (SI). This letter describes the azimuth sensitivity by the azimuth sensitivity image (ASI) which is constructed by comparing the sub-aperture images of the SI. Then the SI and ASI are classified by the sparse representation-based classification (SRC), respectively. Afterwards, a score-level fusion is employed to combine the two results for robust target recognition. Extensive experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset and the performance is compared with several state-of-the-art methods. The experimental results show that the ASI can complement the SI for effective and robust target recognition.

Local structure preserving sparse coding for infrared target recognition.

Sparse coding performs well in image classification. However, robust target recognition requires a lot of comprehensive template images and the sparse learning process is complex. We incorporate sparsity into a template matching concept to construct a local sparse structure matching (LSSM) model for general infrared target recognition. A local structure preserving sparse coding (LSPSc) formulation is proposed to simultaneously preserve the local sparse and structural information of objects. By adding a spatial local structure constraint into the classical sparse coding algorithm, LSPSc can improve the stability of sparse representation for targets and inhibit background interference in infrared images. Furthermore, a kernel LSPSc (K-LSPSc) formulation is proposed, which extends LSPSc to the kernel space to weaken the influence of the linear structure constraint in nonlinear natural data. Because of the anti-interference and fault-tolerant capabilities, both LSPSc- and K-LSPSc-based LSSM can implement target identification based on a simple template set, which just needs several images containing enough local sparse structures to learn a sufficient sparse structure dictionary of a target class. Specifically, this LSSM approach has stable performance in the target detection with scene, shape and occlusions variations. High performance is demonstrated on several datasets, indicating robust infrared target recognition in diverse environments and imaging conditions.

Classification of Birds and UAVs Based on Radar Polarimetry

This letter aims to show the potential of using polarimetric parameters to distinguish between large birds and unmanned aerial vehicles (UAVs) of comparable size in the context of a modern long-range air defense radar. Time is a critical resource in such systems, and techniques for robust noncooperative target recognition not relying on spatial resolution or long dwell times are highly desired. Furthermore, methods less dependent on target micromotion are, in many cases, required. Methods exploiting polarimetric features are shown to have potential in both cases. An experiment in S-band shows that a simple nearest-neighbor classifier can achieve good separation between UAVs and birds both with and without detectable micromotion based on a set of polarimetric parameters alone.

Cu-Au alloy nanostructures coated with aptamers: a simple, stable and highly effective platform for in vivo cancer theranostics.

As a star material in cancer theranostics, photoresponsive gold (Au) nanostructures may still have drawbacks, such as low thermal conductivity, irradiation-induced melting effect and high cost. To solve the problem, copper (Cu) with a much higher thermal conductivity and lower cost was introduced to generate a novel Cu-Au alloy nanostructure produced by a simple, gentle and one-pot synthetic method. Having the good qualities of both Cu and Au, the irregularly-shaped Cu-Au alloy nanostructures showed several advantages over traditional Au nanorods, including a broad and intense near-infrared (NIR) absorption band from 400 to 1100 nm, an excellent heating performance under laser irradiation at different wavelengths and even a notable photostability against melting. Then, via a simple conjugation of fluorophore-labeled aptamers on the Cu-Au alloy nanostructures, active targeting and signal output were simultaneously introduced, thus constructing a theranostic platform based on fluorophore-labeled, aptamer-coated Cu-Au alloy nanostructures. By using human leukemia CCRF-CEM cancer and Cy5-labeled aptamer Sgc8c (Cy5-Sgc8c) as the model, a selective fluorescence imaging and NIR photothermal therapy was successfully realized for both in vitro cancer cells and in vivo tumor tissues. It was revealed that Cy5-Sgc8c-coated Cu-Au alloy nanostructures were not only capable of robust target recognition and stable signal output for molecular imaging in complex biological systems, but also killed target cancer cells in mice with only five minutes of 980 nm irradiation. The platform was found to be simple, stable, biocompatible and highly effective, and shows great potential as a versatile tool for cancer theranostics.

A Robust and Efficient Algorithm for Tool Recognition and Localization for Space Station Robot

This paper studies a robust target recognition and localization method for a maintenance robot in a space station, and its main goal is to solve the target affine transformation caused by microgravity and the strong reflection and refraction of sunlight and lamplight in the cabin, as well as the occlusion of other objects. In this method, an Affine Scale Invariant Feature Transform (Affine-SIFT) algorithm is proposed to extract enough local feature points with a fully affine invariant, and the stable matching point is obtained from the above point for target recognition by the selected Random Sample Consensus (RANSAC) algorithm. Then, in order to localize the target, the effective and appropriate 3D grasping scope of the target is defined, and we determine and evaluate the grasping precision with the estimated affine transformation parameters presented in this paper. Finally, the threshold of RANSAC is optimized to enhance the accuracy and efficiency of target recognition and localization, and the scopes of illumination, vision distance and viewpoint angle for robot are evaluated to obtain effective image data by Root-Mean-Square Error (RMSE). An experimental system to simulate the illumination environment in a space station is established. Enough experiments have been carried out, and the experimental results show both the validity of the proposed definition of the grasping scope and the feasibility of the proposed recognition and localization method.

INFORMATION BLENDING IN VIRTUAL ASSOCIATIVE NETWORKS: A NEW PARADIGM FOR SENSOR INTEGRATION

Research reported in this article is motivated, in part, by current U.S. military programs aimed at the development of efficient data integration and sensor management methods capable of handling large sensor suites and achieving robust target recognition performance in real time scenarios. Modern sensor systems have shown good recognition abilities against a few isolated targets. However, these capabilities decline steeply when multiple sensors are acting against large target groups under realistic conditions requiring dynamic allocation of the sensor resources and efficient on-line integration and disambiguation of multiple sensor outputs. Neural networks and other sensor integration technologies have been inspired by cognitive models attributing human perceptual integration to parallel processing and convergence of simultaneous data streams. This article explores a different model emphasizing serial processing and association of consecutive memory traces in the Long Term Memory (LTM) into a globally connected memory structure called a Virtual Associative Network (VAN). Information integration in VAN is called blending. Target representation is constructed dynamically from the segments of virtual net matched serially against the input segments in the Short Term Memory (STM). This article will elaborate the concept of blending, reference its biological foundations, explain the difference between information blending and conventional sensor fusion techniques, and demonstrate blending applications in a large scale sensor management task.