High-resolution Target Research Articles

Two-Step Adaptive Target Detection Scheme Using Beam-Steering FMCW Radar Sensors

This letter proposes a two-stage adaptive target detection approach using a beam-steered frequency-modulated continuous wave (FMCW) radar sensor. In the first step, coarse estimation was performed using multiple sharped beams, where the presence of a target was determined using only a portion of the sampled beat signals. In the second step, a high-resolution range-Doppler (RD) map was generated using the entire information about the beat signal pertaining to the transmitted beams estimated to contain the target. Angle estimation was accomplished through digital beamforming based on the enhanced RD map. Furthermore, to verify the effectiveness of the proposed algorithm, high-resolution target detection experiments were conducted using a 24-GHz FMCW radar, while complexity reduction was evaluated in terms of the required memory size.

Self-learning based joint multi image super-resolution and sub-pixel registration

Multi Image Super-resolution (MISR) refers to the task of enhancing the spatial resolution of a stack of low-resolution (LR) images representing the same scene. Although many deep learning-based single image super-resolution (SISR) technologies have recently been developed, deep learning has not been widely exploited for MISR, even though it can achieve higher reconstruction accuracy because more information can be extracted from the stack of LR images. One of the primary obstacles encountered by deep networks when addressing the MISR problem is the variability in the number of LR images that act as input to the network. This impedes the feasibility of adopting an end-to-end learning approach, because the varying number of input images makes it difficult to construct a training dataset for the network. Another challenge arises from the requirement to align the LR input images to generate high-resolution (HR) image of high quality, which requires complex and sophisticated methods.In this paper, we propose a self-learning based method that can simultaneously perform super-resolution and sub-pixel registration of multiple LR images. The proposed method trains a neural network with only the LR images as input and without any true target HR images; i.e., the proposed method requires no extra training dataset. Therefore, it is easy to use the proposed method to deal with different numbers of input images. To our knowledge this is the first time that a neural network is trained using only LR images to perform a joint MISR and sub-pixel registration. Experimental results confirmed that the HR images generated by the proposed method achieved better results in both quantitative and qualitative evaluations than those generated by other deep learning-based methods.

The value analysis of high-resolution thin-layer CT in the identification of early lung adenocarcinoma: An observation study.

The aim of this study was to explore the clinical value of high-resolution thin-layer computed tomography (CT) for the identification of early lung adenocarcinoma. Ninety patients with early lung adenocarcinoma who were diagnosed and treated in our hospital were selected as study subjects and divided into noninvasive (NIG, n = 51) and invasive (IG, n = 39) groups according to their pathological findings. Both groups underwent high-resolution target scanning. Differences in lesion size, density, and distribution between the 2 groups were compared. Intergroup differences in the CT signs were examined. A receiver-operating characteristic curve was established to calculate the diagnostic efficacy of high-resolution, thin-layer CT for early lung adenocarcinoma infiltration. The maximum diameter and density of the tumors were significantly higher in the IG than in the NIG (P < .05). The proportions of CT signs of lobulation, spicule, and vessel convergence were higher in the IG patients compared to the NIG (P < .05). High-resolution thin-layer CT for the diagnosis of lung adenocarcinoma infiltration had an AUC of 0.6702 (P < .05), a diagnostic sensitivity of 64.10%, and a diagnostic specificity of 60.78%. High-resolution thin-layer CT had certain differential diagnostic efficacy for early lung adenocarcinoma, which clearly presents various CT signs of early lung adenocarcinoma lesions.

Spaceborne HRWS-SAR-GMTI System Design Method with Optimal Configuration

The spaceborne high-resolution and wide-swath synthetic aperture radar (HRWS-SAR) system combined with the ground moving target indication (GMTI) mode provides a promising prospect in the realization of wide-area target surveying and high-resolution target imaging. In this paper, a system design method is proposed for an HRWS-SAR-GMTI system with ideal reconstruction configuration. In the proposed method, the whole azimuth receiving channels are uniformly divided into multiple groups, where HRWS-SAR imaging is implemented in each sub-group and then GMTI processing is performed based on the reconstructed SAR images. Then, an optimal candidate PRF is properly selected with respect to the optimal reconstruction configuration. After that, the digital beam forming scanning on receive (DBF-SCORE) technique is applied to further enlarge the range swath and improve the noise equivalent scattering coefficient (NESZ). Based on the predesigned system, HRWS-SAR image-based GMTI processing can finally be accomplished. The effectiveness of the proposed method is validated by simulated experiments.

Sub2Full: split spectrum to boost optical coherence tomography despeckling without clean data.

Optical coherence tomography (OCT) suffers from speckle noise, causing the deterioration of image quality, especially in high-resolution modalities such as visible light OCT (vis-OCT). Here, we proposed an innovative self-supervised strategy called Sub2Full (S2F) for OCT despeckling without clean data. This approach works by acquiring two repeated B-scans, splitting the spectrum of the first repeat as a low-resolution input, and utilizing the full spectrum of the second repeat as the high-resolution target. The proposed method was validated on vis-OCT retinal images visualizing sublaminar structures in the outer retina and demonstrated superior performance over state-of-the-art Noise2Noise (N2N) and Noise2Void (N2V) schemes.

Noise-Free Optimization in Early Training Steps for Image Super-resolution

Recent deep-learning-based single image super-resolution (SISR) methods have shown impressive performance whereas typical methods train their networks by minimizing the pixel-wise distance with respect to a given high-resolution (HR) image. However, despite the basic training scheme being the predominant choice, its use in the context of ill-posed inverse problems has not been thoroughly investigated. In this work, we aim to provide a better comprehension of the underlying constituent by decomposing target HR images into two subcomponents: (1) the optimal centroid which is the expectation over multiple potential HR images, and (2) the inherent noise defined as the residual between the HR image and the centroid. Our findings show that the current training scheme cannot capture the ill-posed nature of SISR and becomes vulnerable to the inherent noise term, especially during early training steps. To tackle this issue, we propose a novel optimization method that can effectively remove the inherent noise term in the early steps of vanilla training by estimating the optimal centroid and directly optimizing toward the estimation. Experimental results show that the proposed method can effectively enhance the stability of vanilla training, leading to overall performance gain. Codes are available at github.com/2minkyulee/ECO.

FRACTAL GEOMETRY-BASED RESOURCE ALLOCATION FOR MIMO RADAR

The netted Collocated Multiple-Input Multiple-Output (C-MIMO) radar systems have attracted widespread attention due to their high resolution and excellent target detection capabilities. The self-similarity and spatial filling properties of fractal geometry enable antenna layouts to function effectively across multiple scales and frequency bands, which helps improve the overall performance and resource utilization of systems. In this paper, a radar array element model based on the Fudgeflake fractal is used to establish a target localization performance model directly related to power bandwidth allocation. Based on the model, a three-step solving strategy was designed with the Sequence Quadratic Program (SQP) algorithm as the foundation to achieve optimized allocation of power and bandwidth while maximizing overall performance. Experimental results demonstrate that under this algorithm, the use of power bandwidth resources is optimized through fractal geometry-based design.

A General Spatial-Frequency Learning Framework for Multimodal Image Fusion.

multimodal image fusion involves tasks like pan-sharpening and depth super-resolution. Both tasks aim to generate high-resolution target images by fusing the complementary information from the texture-rich guidance and low-resolution target counterparts. They are inborn with reconstructing high-frequency information. Despite their inherent frequency domain connection, most existing methods only operate solely in the spatial domain and rarely explore the solutions in the frequency domain. This study addresses this limitation by proposing solutions in both the spatial and frequency domains. We devise a Spatial-Frequency Information Integration Network, abbreviated as SFINet for this purpose. The SFINet includes a core module tailored for image fusion. This module consists of three key components: a spatial-domain information branch, a frequency-domain information branch, and a dual-domain interaction. The spatial-domain information branch employs the spatial convolution-equipped invertible neural operators to integrate local information from different modalities in the spatial domain. Meanwhile, the frequency-domain information branch adopts a modality-aware deep Fourier transformation to capture the image-wide receptive field for exploring global contextual information. In addition, the dual-domain interaction facilitates information flow and the learning of complementary representations. We further present an improved version of SFINet, SFINet++, that enhances the representation of spatial information by replacing the basic convolution unit in the original spatial domain branch with the information-lossless invertible neural operator. We conduct extensive experiments to validate the effectiveness of the proposed networks and demonstrate their outstanding performance against state-of-the-art methods in two representative multimodal image fusion tasks: pan-sharpening and depth super-resolution. The source code is publicly available at https://github.com/manman1995/Awaresome-pansharpening.

Multi-branch stacking remote sensing image target detection based on YOLOv5

Optical remote sensing is crucial in land management, maritime safety, and rescue operations. Currently, high resolution target detection faces the problems including feature loss, false detection, and limited network robustness. To tackle the aforementioned issues, this study introduces a novel MBS-NET model, which is built upon the YOLOv5 structure. The proposed model presents a multi-branch stacking module structure to precisely capture deep target feature information. By introducing a dual-channel attention mechanism module (EGCA) at the model's neck, the proposed method ensures discriminative feature acquisition in crowded objects and vast spatial scenes. Prior to network training, introduce an improved data augmentation strategy to accommodate the multi-scale and directional variations in remote sensing objectives for model detection. Experimental results on the large-scale public DIOR dataset demonstrate that the MBS-NET model introduced in this paper displays exceptional performance and remarkable interpretability in remote sensing scenarios at a large scale. MBS-NET model outperforms YOLOv5 and YOLOv7 models by increasing the accuracy by 5% and 2% respectively. In addition, the recall rate and F1 Score index of MBS-NET model is superior to those of other methods, resulting in significant improvement of detection accuracy and robustness in large scenes.

Self-supervised depth super-resolution with contrastive multiview pre-training

Many low-level vision tasks, including guided depth super-resolution (GDSR), struggle with the issue of insufficient paired training data. Self-supervised learning is a promising solution, but it remains challenging to upsample depth maps without the explicit supervision of high-resolution target images. To alleviate this problem, we propose a self-supervised depth super-resolution method with contrastive multiview pre-training. Unlike existing contrastive learning methods for classification or segmentation tasks, our strategy can be applied to regression tasks even when trained on a small-scale dataset and can reduce information redundancy by extracting unique features from the guide. Furthermore, we propose a novel mutual modulation scheme that can effectively compute the local spatial correlation between cross-modal features. Exhaustive experiments demonstrate that our method attains superior performance with respect to state-of-the-art GDSR methods and exhibits good generalization to other modalities.

Performance analysis of the coherent FMCW photonic radar system under the influence of solar noise

The real-time high-resolution target detection in radar applications has increased the demand for photonic radar systems due to their higher bandwidth and faster processing capabilities over conventional microwave radar. Additionally, photonic-based radar technology can revolutionize the limited performance of conventional microwave radar caused by various atmospheric attenuations. This article presents a frequency-modulated continuous-wave photonic radar system using coherent detection. The performance of the proposed system is theoretically investigated under the effect of various real-time atmospheric weather attenuations and the influence of solar background noise, which is further verified on the simulation platform. This study is conducted under different atmospheric weather conditions, such as clear, haze, and fog, to highlight the practical limitation of free-space links in the presence of solar background noise. The detected signal at different target ranges with and without solar noise is measured and then compared in terms of signal-to-noise ratio. Furthermore, the impact of solar noise on the system performance when the Sun is under different sky conditions and zenithal angles is also analyzed. The results presented here provide insights into designing photonic radar systems for practical applications like autonomous vehicle radar systems, self-traffic control, and navigation.

Super-resolution of 2D ultrasound images and videos

This paper proposes a novel deep-learning framework for super-resolution ultrasound images and videos in terms of spatial resolution and line reconstruction. To this end, we up-sample the acquired low-resolution image through a vision-based interpolation method; then, we train a learning-based model to improve the quality of the up-sampling. We qualitatively and quantitatively test our model on different anatomical districts (e.g., cardiac, obstetric) images and with different up-sampling resolutions (i.e., 2X, 4X). Our method improves the PSNR median value with respect to SOTA methods of 1.7% on obstetric 2X raw images, 6.1% on cardiac 2X raw images, and 4.4% on abdominal raw 4X images; it also improves the number of pixels with a low prediction error of 9.0% on obstetric 4X raw images, 5.2% on cardiac 4X raw images, and 6.2% on abdominal 4X raw images. The proposed method is then applied to the spatial super-resolution of 2D videos, by optimising the sampling of lines acquired by the probe in terms of the acquisition frequency. Our method specialises trained networks to predict the high-resolution target through the design of the network architecture and the loss function, taking into account the anatomical district and the up-sampling factor and exploiting a large ultrasound data set. The use of deep learning on large data sets overcomes the limitations of vision-based algorithms that are general and do not encode the characteristics of the data. Furthermore, the data set can be enriched with images selected by medical experts to further specialise the individual networks. Through learning and high-performance computing, the proposed super-resolution is specialised to different anatomical districts by training multiple networks. Furthermore, the computational demand is shifted to centralised hardware resources with a real-time execution of the network’s prediction on local devices.Graphical abstract

RIS-aided integrated sensing and communication: a mini-review

Integrating sensing and communication (ISAC) is a cutting-edge technology aimed at achieving high-resolution target sensing and high data-rate communications using a shared spectrum. This innovative approach optimizes the usage of the radio spectrum with no or minimal level of mutual interference. The capability of reconfigurable intelligent surface (RIS) to control the environment and provide additional degrees of freedom is driving the development of RIS-aided ISAC. In this mini-review, we provide an overview of the current state-of-the-art of RIS-aided ISAC technology, including various system configurations, approaches, and signal processing techniques.

Spatiotemporal Evolution of Orbital Angular Momentum (OAM) Beams Based on a Uniform Circular Frequency Diverse Array (UC-FDA)

Radar imaging based on orbital angular momentum (OAM) beams has become a significant approach to realize high resolution and multidimensional target detection. The irradiation of a target area with OAM beams with different modes has been proven to be a feasible solution to improve the azimuthal resolution of the target. This article is the first to propose and validate novel spatiotemporal OAM beams generated by a uniform circular frequency diverse array (UC-FDA). Unlike the conventional uniform circular array (UCA), signals with frequency intervals need to be fed to the antennas in the UC-FDA structure. The mode of the spatiotemporal OAM beam can be switched automatically with spatial transmission, which enhances the flexibility of mode switching and reduces the switching time. The evolution characteristics of the OAM beam are fully demonstrated. Meanwhile, the intrinsic spatiotemporal evolution rules and influence parameters are analyzed and summarized. Furthermore, an optimized dynamic decomposition (DMD) algorithm is proposed and used to implement mode detection. Finally, the spatiotemporal evolution of OAM beams is applied to a rudimentary exploration of radar imaging. The measured results indicate that azimuth imaging of targets can be successfully accomplished. Spatiotemporal OAM beams may unlock promising potential for new-tech radar scenarios.

Analysis of target surface polarization characteristics and inversion of complex refractive index based on three-component model optimization

Traditional imaging detection techniques are used to collect intensity information and spectral information of the target to generate high-resolution target images, but the imaging system is susceptible to external environmental factors, resulting in system instability and image quality degradation. Polarization detection techniques use the polarization properties of light to determine the polarization state and spatial profile of a target, thereby improving the contrast of the target in the image. In this study, the reflection process of the target surface is investigated from a microscopic perspective. A polarization characteristics model was developed to illustrate the link between the properties of the target surface and the degree of polarization of the reflected light. The results show that the degree of polarization is strongly related to the detection of zenith and azimuth angles. Experimental data are used to invert the complex refractive index of the target. The polarization of the target is greatest in the direction of specular reflection and smallest in the direction of light source incidence. This suggests that the established Polarimatric Bidirectional Reflectance Distribution Function (pBRDF) model can provide theoretical support for the analysis of the polarization properties of the target surface. Targets of different materials have different polarization properties and the extinction coefficient can effectively classify the targets.

A bidirectional semantic segmentation method for remote sensing image based on super-resolution and domain adaptation

ABSTRACT Image semantic segmentation methods based on convolutional neural networks rely on supervised learning with labels, and their performance often drops significantly when applied to unlabelled datasets from different sources. The domain adaptation methods can reduce the inconsistency of feature distribution between the unlabelled target domain data used for testing and the labelled source domain data used for training, thus improve the segmentation performance and have more practical applications. However, in the field of remote sensing image processing, if the spatial resolutions of the source domain and the target domain are different and this problem is not to be solved, the performance of the transferred model will be affected. In this paper, we propose a bidirectional semantic segmentation method based on super-resolution and domain adaption (BSSM-SRDA), which is suitable for the transfer learning task of a semantic segmentation model from a low-resolution source domain data to a high-resolution target domain data. BSSM-SRDA mainly consists of three parts: a shared feature extraction network; a super-resolution image translation module, which incorporates a super-resolution approach to reduce spatial resolution differences and visual style differences of the two domains; a domain-adaptive semantic segmentation module, which combines an adversarial domain adaptation approach to reduce differences at the output level. At the same time, we design a new bidirectional self-supervised learning algorithm for BSSM-SRDA that facilitates mutually beneficial learning of the super-resolution image translation module and the domain-adaptive semantic segmentation module. The experiments demonstrate the superiority of the proposed method over other state-of-the-art methods on two remote-sensing image datasets, with mIoU improvements of 2.5% and 3.2%, respectively. Code: https://github.com/mageliang/BSSM-SRDA.git

MStrain: strain-level identification of Yersinia pestis using metagenomic data.

High-resolution target pathogen detection using metagenomic sequencing data represents a major challenge due to the low concentration of target pathogens in samples. We introduced mStrain, a novel Yesinia pestis strain/lineage-level identification tool that utilizes metagenomic data. mStrain successfully identified Y. pestis at the strain/lineage level by extracting sufficient information regarding single-nucleotide polymorphisms (SNPs), which can therefore be an effective tool for identification and source tracking of Y. pestis based on metagenomic data during a plague outbreak. . Assigning the reads in the metagenomic sequencing data to an exactly known or most closely representative Y. pestis strain. Assigning the reads in the metagenomic sequencing data to a specific lineage on the phylogenetic tree. The unique and typical SNPs present in all representative strains. An SNP is defined as the ancestor state when consistent with the allele of Yersinia pseudotuberculosis strain IP32953; otherwise, the SNP is defined as the derived state. The code for running mStrain, the test dataset, and instructions for running the code can be found at the following GitHub repository: https://github.com/xwqian1123/mStrain.

Zero-Shot Blind Learning for Single-Image Super-Resolution

Deep convolutional neural networks (DCNNs) have manifested significant performance gains for single-image super-resolution (SISR) in the past few years. Most of the existing methods are generally implemented in a fully supervised way using large-scale training samples and only learn the SR models restricted to specific data. Thus, the adaptation of these models to real low-resolution (LR) images captured under uncontrolled imaging conditions usually leads to poor SR results. This study proposes a zero-shot blind SR framework via leveraging the power of deep learning, but without the requirement of the prior training using predefined imaged samples. It is well known that there are two unknown data: the underlying target high-resolution (HR) images and the degradation operations in the imaging procedure hidden in the observed LR images. Taking these in mind, we specifically employed two deep networks for respectively modeling the priors of both the target HR image and its corresponding degradation kernel and designed a degradation block to realize the observation procedure of the LR image. Via formulating the loss function as the approximation error of the observed LR image, we established a completely blind end-to-end zero-shot learning framework for simultaneously predicting the target HR image and the degradation kernel without any external data. In particular, we adopted a multi-scale encoder–decoder subnet to serve as the image prior learning network, a simple fully connected subnet to serve as the kernel prior learning network, and a specific depthwise convolutional block to implement the degradation procedure. We conducted extensive experiments on several benchmark datasets and manifested the great superiority and high generalization of our method over both SOTA supervised and unsupervised SR methods.

Matrix-Assisted Laser Desorption/Ionization (MALDI) Mass Spectrometry Imaging of L-4-Phenylalanineboronic Acid (BPA) in a Brain Tumor Model Rat for Boron Neutron Capture Therapy (BNCT).

Boron neutron capture therapy (BNCT) is a cell-selective particle therapy for cancer using boron containing drugs. Boron compounds are accumulated in high concentration of tens ppm level of boron in target tumors to cause lethal damage to tumor tissue. The examination of boron distribution in target tumor and normal tissue is important to evaluate the efficiency of therapy. The matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) is a powerful tool to visualize the distribution of target analyte in biological samples. In this manuscript, we report a trial to visualize the distribution of a typical BNCT drug, L-4-phenylalanine boronic acid (BPA) in a brain tumor model rat using MALDI-MSI technique. We performed a MALDI-MSI with high mass resolution targeting to [BPA+H]+ at m/z 210 in a BPA-treated rat brain section using a spiral orbit-type time of flight (SpiralTOF) mass spectrometer. Several BPA ion species, [BPA+H]+, [BPA-H2O+Na]+, [BPA+DHB-2H2O+Na]+ and [BPA+DHB-2H2O+K]+ were detected separate from peaks originated from biomolecules or matrix reagent by achieving the mass resolving power of approximately 20,000 (full width at half maximum; FWHM) at m/z 210. The mass images with 60 μm spatial resolution obtained from these BPA ion species in a mass window of 0.02 Da revealed their localization in the tumor region. Additionally, the mass image obtained from [BPA+H]+ also likely showed the distribution of BPA inside the tumor. MALDI-MSI with high mass resolution targeting to [BPA+H]+ has a great potential to visualize the distribution of BPA in brain tissue with tumor.

PointNet+LSTM for Target List-Based Gesture Recognition With Incoherent Radar Networks

Radar-based gesture recognition can provide autonomous electronic systems with a reliable way to infer a human's intention, e.g., in traffic environments involving vulnerable road users. Particularly in complex scenarios, algorithms operating on radar target lists derived from constant false-alarm rate outputs present an attractive solution, as they not only enable the filtering of relevant targets, but can also make full use of the diverse, high-resolution target parameters provided by modern radar sensors. Therefore, this article proposes PointNet+long short-term memory (LSTM) for the enhanced target list-based recognition of challenging traffic gestures, combining per-frame feature extraction with PointNet and learning from sequences with a LSTM. The approach is generalized to facilitate the use of multistatic radar data from sensor networks to exploit slightly different viewing angles, which is particularly helpful for motions with low radial velocity. The proposed method is validated on a comprehensive dataset comprising eight traffic gestures and data recorded from 35 participants. Measurements are conducted both indoors and outdoors with an incoherent radar sensor network comprising three chirp sequence–multiple-input multiple-output sensors. On this challenging dataset, our approach clearly outperforms a reference convolutional neural network, reaching up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$92.2 \%$</tex-math></inline-formula> cross-validation accuracy.