Target Recognition Applications Research Articles

Passive underwater acoustic barcodes using Rayleigh wave resonance

Passive underwater acoustic markers are promising in terms of applications in underwater target recognition, positioning, and navigation. In this paper, a passive underwater acoustic marker composed of acrylic sphere combinations is designed for acoustic coding based on the subsonic Rayleigh wave resonance phenomenon, where strong backscattering resonance peaks appear when an acrylic sphere is excited by a broadband pulse. Due to the fact that the resonance frequencies are dependent on the Rayleigh wave velocity and the radius of the sphere, the backscattering response of markers can be regulated by changing the radius of a sphere or combining spheres with different radii. Each marker has a unique acoustic signature for a selected frequency band, akin to acoustic barcodes. The feasibility of this acoustic coding method has been evaluated by comparing the numerical results and experimental results. Compared with active acoustic markers, passive acoustic markers naturally operate in a wider frequency band, have a longer lifetime, and lower cost.

Physical-Related Feature Extraction From Simulated SAR Image Based on the Adversarial Encoding Network for Data Augmentation

The synthetic aperture radar automatic target recognition (SAR ATR) application based on the deep convolutional network often faces data scarcity. SAR image simulation based on electromagnetic and geometric calculations can provide a large amount of data that contains interpretable physical features, such as shadow and contour. However, there is a big difference between the simulated SAR image and the real image, and it is difficult to directly use it for data augmentation. This letter proposes the adversarial encoding network to extract the physical-related features, which can be understood as the common features between the simulated and real data. By designing the adversarial learning between an encoder and a discriminator, the encoder can extract real features from the simulated images. The encoded features are sent to a classifier to ensure the correct category information. A decoder is used to reconstruct the encoded features into the input image so that the encoded feature retains the image information as much as possible. Ablation experiments and comparative experiments are used to verify the ability of each module and the performance of the proposed method. The results show that the proposed model can achieve 98.55% accuracy, especially when the real data are insufficient for classification, which verifies that the proposed method is effective for data augmentation.

Water Target Recognition Method and Application for Unmanned Surface Vessels

Water target recognition is a critical challenge for the perception technology of unmanned surface vessels (USVs). In the application of USV, detection accuracy and the inference time both matter, while it is tough to strike a balance and single-frame water target detection behaves unstable in the video detection. To solve these problems, many strategies are applied to increase YOLOv4’s performance, including network pruning, the focal loss function, blank label training, and preprocessing with histogram normalization. The optimized detection method achieves a mean average precision (mAP) of 81.74% and a prediction speed of 26.77 frames per second (FPS), which meets the USV navigation requirements. To build the integrated USV-based system for water target recognition, a water target dataset containing 9936 images is created from offshore USV experiments in which the human-in-the-loop annotation and mosaic data augmentation methods are used. The issues of miss detection and false alarm can be considerably mitigated by cascading the Siamese-RPN tracking network, and the major color of a water target can be retrieved using a local contrast saliency color detection scheme. The system being tested is called “ME120” includes an embedded edge computing platform (Nvidia Jetson AGX Xavier). Finally, online dataset learning demonstrates the improved YOLOv4 achieves an increase of 66.98% in FPS at the cost of a decrease of 0.79% in mAP when compared with the original YOLOv4 and offline navigation experiments validate that our system achieves high recognition capability while maintaining a high degree of robustness.

Surrounding Prototype Loss for Radar HRRP Open Set Target Recognition

The open set recognition model can identify the known and unknown samples simultaneously. In the radar automatic target recognition application, open set recognition meets better practical requirements than closed set recognition. Theoretically, an overlap usually exists between the known and unknown features, which makes it difficult for the model to identify unknown samples. Therefore, we explore the distribution of the known and unknown features, and find that the unknown features are usually smaller and closer to the center region in the feature space than the known features. Based on this phenomenon, we propose a novel loss function that improves the open set recognition performance by controlling the known features distributed to the surrounding area of the feature space. In addition, extensive experiments are carried out on measured HRRP data. Thus, we verify the effectiveness of the proposed method.

Application of artificial intelligence in COVID-19 medical area: a systematic review.

BackgroundCoronavirus disease 2019 (COVID-19) has caused a large-scale global epidemic, impacting international politics and the economy. At present, there is no particularly effective medicine and treatment plan. Therefore, it is urgent and significant to find new technologies to diagnose early, isolate early, and treat early. Multimodal data drove artificial intelligence (AI) can potentially be the option. During the COVID-19 Pandemic, AI provided cutting-edge applications in disease, medicine, treatment, and target recognition. This paper reviewed the literature on the intersection of AI and medicine to analyze and compare different AI model applications in the COVID-19 Pandemic, evaluate their effectiveness, show their advantages and differences, and introduce the main models and their characteristics.MethodsWe searched PubMed, arXiv, medRxiv, and Google Scholar through February 2020 to identify studies on AI applications in the medical areas for the COVID-19 Pandemic.ResultsWe summarize the main AI applications in six areas: (I) epidemiology, (II) diagnosis, (III) progression, (IV) treatment, (V) psychological health impact, and (VI) data security. The ongoing development in AI has significantly improved prediction, contact tracing, screening, diagnosis, treatment, medication, and vaccine development for the COVID-19 Pandemic and reducing human intervention in medical practice.DiscussionThis paper provides strong advice for using AI-based auxiliary tools for related applications of human diseases. We also discuss the clinicians’ role in the further development of AI. They and AI researchers can integrate AI technology with current clinical processes and information systems into applications. In the future, AI personnel and medical workers will further cooperate closely.

Laser fuze specific target recognition based on grey system theory

Existing target recognition methods are difficult to implement on a low-cost and small-volume fuze platform. This paper proposes a rapid typical target recognition algorithm tailored to small sample sizes. A laser line scanning model is used to complete the target two-dimensional (2D) scanning, and the distance value of the target to be recognized is obtained to form a sample sequence matrix of the recognition algorithm. The ground recognition algorithm, which properly incorporates the ground effect and the uncertain direction of motion of the recognized target is used to reduce the influence of ground effect, a coordinated conversion model of the recognized target is established; a typical target recognition model based on grey system theory and fuzzy mathematics theory is established accordingly. The algorithm resolves the uncertainty in target recognition under lean information conditions. The recognition algorithm is proven capable of recognizing specific targets under small sample size. The results presented here may provide a reference for future low-cost laser imaging fuze target recognition applications.

Three-Dimensional Interferometric ISAR Imaging Algorithm Based on Cross Coherence Processing.

Interferometric inverse synthetic aperture radar (InISAR) has received significant attention in three-dimensional (3D) imaging due to its applications in target classification and recognition. The traditional two-dimensional (2D) ISAR image can be interpreted as a filtered projection of a 3D target’s reflectivity function onto an image plane. Such a plane usually depends on unknown radar-target geometry and dynamics, which results in difficulty interpreting an ISAR image. Using the L-shape InISAR imaging system, this paper proposes a novel 3D target reconstruction algorithm based on Dechirp processing and 2D interferometric ISAR imaging, which can jointly estimate the effective rotation vector and the height of scattering center. In order to consider only the areas of the target with meaningful interferometric phase and mitigate the effects of noise and sidelobes, a special cross-channel coherence-based detector (C3D) is introduced. Compared to the multichannel CLEAN technique, advantages of the C3D include the following: (1) the computational cost is lower without complex iteration and (2) the proposed method, which can avoid propagating errors, is more suitable for a target with multi-scattering points. Moreover, misregistration and its influence on target reconstruction are quantitatively discussed. Theoretical analysis and numerical simulations confirm the suitability of the algorithm for 3D imaging of multi-scattering point targets with high efficiency and demonstrate the reliability and effectiveness of the proposed method in the presence of noise.

A new evidential similarity measurement based on Tanimoto measure and its application in multi-sensor data fusion

Dempster–Shafer evidence theory is a powerful fusion approach for reasoning under uncertain circumstances. However, unreasonable results will generate when utilizing Dempster’s combination rule to fuse highly conflicting evidence. How to accurately measure the conflict degree between two pieces of evidence is still a problem to be solved. To date, the method of conflict measurement has been proposed by many authors. Unfortunately, the effectiveness of these approaches is limited. In this paper, a new method of evidential similarity measurement is devised in the light of Tanimoto measurement to describe the inconsistency between bodies of evidence. Then, a novel evidential conflict measurement approach is presented in accordance with the evidential similarity measurement to quantify the conflict degree between bodies of evidence. It is analyzed and proved that the novel approach of evidential conflict measurement satisfies the property of conflict measures. Some numerical examples are given to demonstrate the efficacy and superiority of the proposed approach. Moreover, the validity of the proposed approach is evaluated by the application of target recognition.

A High-Quality Multicategory SAR Images Generation Method With Multiconstraint GAN for ATR

The high-quality training data sets are often insufficient in synthetic aperture radar (SAR) automatic target recognition (ATR) applications. The generative adversarial network (GAN) provides a way for SAR data augmentation. It is necessary to ensure the diversity, similarity, and correct category of the generated images so that these images can be served as the supplementary data set. In this letter, the multiconstraint GAN (MCGAN) is proposed to generate high-quality multicategory SAR images. First, an encoder is used to learn the features of the real images to enhance the similarity. Then, the encoded features are mixed with noise and category labels as the input of the generator to improve the diversity and category correctness. The generated images will be sent to a pretrained classifier to ensure the correct category. Finally, the improved Wasserstein loss with the gradient penalty is extended to the model to further improve the diversity and similarity of the generated images. The MSTAR data set is used to validate the proposed method on generation. The quality evaluation and classification tests are performed on the generated images, and the results show that the MCGAN can provide high-quality images, which could assist in achieving good classification accuracy.

An improved expression for information quality of basic probability assignment and its application in target recognition

An improved expression for information quality of basic probability assignment and its application in target recognition

Conflict Management for Target Recognition Based on PPT Entropy and Entropy Distance

Conflicting evidence affects the final target recognition results. Thus, managing conflicting evidence efficiently can help to improve the belief degree of the true target. In current research, the existing approaches based on belief entropy use belief entropy itself to measure evidence conflict. However, it is not convincing to characterize the evidence conflict only through belief entropy itself. To solve this problem, we comprehensively consider the influences of the belief entropy itself and mutual belief entropy on conflict measurement, and propose a novel approach based on an improved belief entropy and entropy distance. The improved belief entropy based on pignistic probability transformation function is named pignistic probability transformation (PPT) entropy that measures the conflict between evidences from the perspective of self-belief entropy. Compared with the state-of-the-art belief entropy, it can measure the uncertainty of evidence more accurately, and make full use of the intersection information of evidence to estimate the degree of evidence conflict more reasonably. Entropy distance is a new distance measurement method and is used to measure the conflict between evidences from the perspective of mutual belief entropy. Two measures are mutually complementary in a sense. The results of numerical examples and target recognition applications demonstrate that our proposed approach has a faster convergence speed, and a higher belief degree of the true target compared with the existing methods.

Oriented Perovskite Growth Regulation Enables Sensitive Broadband Detection and Imaging of Polarized Photons Covering 300–1050 nm

Photodetectors selective to the polarization empower breakthroughs in sensing technology for target identification. However, the realization of polarization-sensitive photodetectors based on intrinsically anisotropic crystal structure or extrinsically anisotropic device pattern requires complicated epitaxy and etching processes, which limit scalable production and application. Here, solution-processed PEA2 MA4 (Sn0.5 Pb0.5 )5 I16 (PEA= phenylethylammonium, MA= methylammonium) polycrystalline film is probed as photoactive layer toward sensing polarized photon from 300 to 1050nm. The growth of the PEA2 MA4 (Sn0.5 Pb0.5 )5 I16 crystal occurs in confined crystallographic orientation of the (202) facet upon the assistance of NH4 SCN and NH4 Cl, enhancing anisotropic photoelectric properties. Therefore, the photodetector achieves a polarization ratio of 0.41 and dichroism ratio (Imax /Imin ) of 2.4 at 900nm. At 520nm, the Imax /Imin even surpasses the one of the perovskite crystalline films, 1.8 and ≈1.2, respectively. It is worth noting that the superior figure-of-merits possess a response width of 900kHz, Ion /Ioff ratio of ≈3 × 108 , linear dynamic range from 0.15 nW to 12mW, noise current of 8.28 × 10-13 A × Hz-0.5 , and specific detectivity of 1.53 × 1012 Jones, which demonstrate high resolution and high speed for weak signal sensing and imaging. The proof of concept in polarized imaging confirms that the polarization-sensitive photodetector meets the requirements for practical application in target recognition.

The integrated sigma-max system and its application in target recognition

Randomness and fuzziness are two fundamental kinds of uncertain phenomena, which can be handled respectively by probability theory (sigma system) and possibility theory (max system). For many practical problems of information processing, random uncertainty may often co-exist with fuzzy uncertainty, which reminds us to look for a novel mechanism called sigma-max hybrid uncertainty inference. This mechanism can cope with randomness and fuzziness jointly and achieve a direct fusion of heterogeneous information modeled by probability or possibility. Specifically, we are interested in two typical forms of uncertainty inference, i.e., uncertainty update equation combining heterogeneous information as well as composition rule of heterogeneous relations. Such an objective is achieved by the adoption of joint description of a random variable and a fuzzy variable, i.e., hybrid distribution of probability and possibility, which lays the foundation for connecting the two uncertainty systems of probability and possibility, and results in the integrated sigma-max system. The hybrid distribution, other than joint probability (or possibility) distribution, has a couple of special normalization requirements that are order-dependent with respective to “addition” operation over random variable and “max’ operation over fuzzy variable. The derived sigma-max inference is applied to target recognition, an example of which is simulated to demonstrate the merit of the proposed method over the classic Bayesian classifier when randomness and fuzziness are both involved.

Echo characteristics of laser beams reflected from rough targets with a finite size in atmospheric turbulence

Based on the extended Huygens-Fresnel principle, echo characteristics of the plane and spherical waves reflected from a rough target with a finite size in atmospheric turbulence were studied. The expressions of the intensity variance, covariance functions and scintillation index of the plane and spherical waves reflected from a rough target in double-path propagation through atmospheric turbulence were proposed considering the turbulence perturbations. The expressions were numerically calculated, and the results show that the intensity fluctuation caused by turbulence decreases with increasing target size. It is also found that under weak turbulence, it is mainly the log-amplitude fluctuations that affect the second-order statistical properties of the received beam intensity. Results obtained can potentially provide theoretical and technical guidance for the future applications of laser target detection and target recognition in space.

Speckle characteristics of vortex beams scattered from rough targets in turbulent atmosphere

In this study, the echo speckle characteristics of the Laguerre-Gauss (LG) vortex beams scattered from random rough surface targets were examined based on the Rytov Approximation Theory. In addition, the expressions of the intensity correlation and coherence functions, along with the normalized intensity variances of the speckle fields, were derived. The coherent lengths and scintillation indexes of the speckle fields were then numerically simulated, and the speckle characteristics of the Laguerre-Gauss vortex beam were compared with those of the Gaussian beams. The effects of the topological charges, rough target radii, initial beam radii, turbulence intensities, and roughness degrees of the targets on the speckle characteristics of the LG vortex beams were analyzed. This study's results showed that in the weak turbulence regions, the target characteristics were the main influencing factors of the speckle fields. Meanwhile, in the strong turbulence regions, the turbulence effects were the main influencing factors of the speckle fields. The influence effects of turbulent atmosphere and target characteristics on the coherent lengths and scintillation effects of the vortex beam echoes were observed to be less than those of the Gaussian beams. In addition, the influence effects of the turbulent atmosphere on coherent lengths and scintillation effects of the vortex beams echoes with small topology were found to be minimal. Therefore, this study's results can potentially provide theoretical and technical guidance for the future applications of laser target detection, target recognition, and speckle measurement processes in space.

An improved Gaussian laser beam probability distribution simulation based on Monte Carlo method

Research on target recognition in random media by Monte Carlo method has made rapid progress. However, the commonly used probability sampling function of the emitted photons’ directions is not suitable for simulating the radial cross-sectional distribution of a beam. This sampling has little effect on the simulated laser transmission in clouds, but if the laser range profile (LRP) of a target is simulated, it will cause serious distortion because the common sampling method cannot well represent the radial two-dimensional intensity distribution of the beam. In this paper, the traditional sampling method is improved through rigorous derivation, and the superiority of the method is illustrated by simulation data. The simulation results show that the Monte Carlo model of LRP based on the improved sampling method plays well in profile shape of ideal targets identification. This research can bring more reference and significance to target recognition application.

Object-oriented detection of building shadow in TripleSat-2 remote sensing imagery

The projection of objects on the earth’s surface caused by the sunlight produces shadows. They are inevitable in high-spatial-resolution satellite remote sensing images and reduce the accuracy of change detection, land cover classification, target recognition, and many more applications. Dark-colored land covers in these satellite images, such as water bodies, road, and soil, appear with similar spectral properties as those of shadows and often result in difficulty in shadow detection, especially in complex urban settings. We propose an object-oriented building shadow extraction method and tested it using six selected study areas from TripleSat-2 satellite imagery with 3.2-m spatial resolution. The method’s main steps include (1) selecting six image features that can highlight the shadow information and then segment the image based on edge; (2) extracting shadow region based on multiple object features; and (3) masking nonbuilding shadow regions by the shadow and dark object separation index, image features including spectral, textural, and geometric features, and contextual information. The average precision, recall, and F1-score of the shadow detection were 85.6%, 88.6%, and 87.0%, respectively, and the ranges were 73.0% to 91.0%, 76.6% to 94.1%, and 74.7% to 91.2%, respectively. Compared with multiscale segmentation, edge-based segmentation is more efficient and helpful to completely and accurately extract shadows.

A SAR Image Target Recognition Approach via Novel SSF-Net Models.

With the wide application of high-resolution radar, the application of Radar Automatic Target Recognition (RATR) is increasingly focused on how to quickly and accurately distinguish high-resolution radar targets. Therefore, Synthetic Aperture Radar (SAR) image recognition technology has become one of the research hotspots in this field. Based on the characteristics of SAR images, a Sparse Data Feature Extraction module (SDFE) has been designed, and a new convolutional neural network SSF-Net has been further proposed based on the SDFE module. Meanwhile, in order to improve processing efficiency, the network adopts three methods to classify targets: three Fully Connected (FC) layers, one Fully Connected (FC) layer, and Global Average Pooling (GAP). Among them, the latter two methods have less parameters and computational cost, and they have better real-time performance. The methods were tested on public datasets SAR-SOC and SAR-EOC-1. The experimental results show that the SSF-Net has relatively better robustness and achieves the highest recognition accuracy of 99.55% and 99.50% on SAR-SOC and SAR-EOC-1, respectively, which is 1% higher than the comparison methods on SAR-EOC-1.

A Dynamic multi-sensor data fusion approach based on evidence theory and WOWA operator

Multi-sensor data fusion (MSDF) problems have attracted widespread attention recently. However, it is still an open issue about how to make the fusion process effectively even if the collected data conflict due to several unpredictable reasons. Moreover, most existing approaches mainly concentrated on the distinction of evidence sources, which cannot well consider the feature of individual belief degree and the associated preference of decision-makers. To address such an issue, a dynamic MSDF method based on evidence theory and weighted ordered weighted averaging (WOWA) operator is proposed in this study. A numerical example is analyzed to demonstrate its whole calculation procedure. Two simulation experiments, composed of a motor rotor fault diagnosis and an insulator string target recognition application, are also mentioned to illustrate its effectiveness and applied value. The results show that the proposed methodology can enhance the fusion accuracy in the constrained scenarios with the consideration of preference relation.

Inherent limitation of digital imagery: spatial-phase vacillations and the ambiguity function

The spatial relationship of a scene image upon a pixilated focal-plane-array can temporally change due to scene or camera motion, microjitter of camera line-of-sight, etc. It was found that degradation caused by subpixel spatial-phase vacillations (SPV) upon the performance of matched filters was unexpectedly significant. Subpixel spatial-phase vacillations can cause degradations in matched filter performance to detect desired objects and discriminate other objects. SPV appear to be an inherent limitation of digital imagery when processed using matched filter methodology and can negatively impact the performance of systems. Mitigation of this degradation was found to be possible by utilizing one of several matched filter constructions such as a multi-filter enhanced matched filter (EMF) bank and a single-filter EMF. A significant conclusion of this investigation is that, for automatic target recognition applications, improved overall task performance should be realized by the use of an EMF bank. Dramatic reduction in computational resources for image matching multispectral imagery was accomplished by spectrally-collapsing multispectral imagery to form pseudoimages with the spectral information appearing as a texture in a grayscale image. The pattern recognition ambiguity function, which sets the fundamental performance limit of an image processing system, is introduced.