IEEE Transactions on Radar Systems最新文献

{"title":"Occluded Object Classification With mmWave MIMO Radar IQ Signals Using Dual-Stream Convolutional Neural Networks","authors":"Stefan Hägele;Fabian Seguel;Sabri Mustafa Kahya;Eckehard Steinbach","doi":"10.1109/TRS.2025.3571284","DOIUrl":"https://doi.org/10.1109/TRS.2025.3571284","url":null,"abstract":"The ability of millimeter-wave (mmWave) radar to penetrate lightweight materials and provide nonvisual insights into obscured areas represents a significant advantage over camera or LiDAR sensors. This capability enables mmWave radar to detect humans behind thin walls or identify occluded objects stored within luggage or packages. The latter capability is particularly valuable in industrial, logistics, and manufacturing applications, where the ability to “look inside the box without opening it” can greatly enhance the efficiency and security. However, the current state of the art in these applications relies on expensive custom-built large antenna array imaging scanners, coupled with image-based object detection algorithms, to detect and classify occluded or concealed objects. To address this challenge more efficiently, we propose a lightweight classification approach for detecting various occluded objects inside a cardboard box. We employ a standard off-the-shelf mmWave 4-D frequency-modulated continuous wave (FMCW) imaging radar. This is combined with a deep learning-based classification method in the form of a dual-stream convolutional neural network (CNN) approach to process complex in-phase and quadrature (IQ) radar signals. This approach reaches in our experiments an overall accuracy of 95.15% on average over a collection of ten different concealed objects.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"789-798"},"PeriodicalIF":0.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11007063","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analog In-Memory Computing for the Synthetic Aperture Radar Polar Format Algorithm","authors":"David K. Richardson;T. Patrick Xiao;R. Derek West;Christopher H. Bennett;Sapan Agarwal","doi":"10.1109/TRS.2025.3570977","DOIUrl":"https://doi.org/10.1109/TRS.2025.3570977","url":null,"abstract":"As the utility of synthetic aperture radar (SAR) systems increases in autonomous vehicles, satellites, and other power- and space-constrained edge applications, there is a growing need for processors that can form SAR images at low power. In recent years, analog in-memory compute (AIMC) has shown immense promise for accelerating neural networks and other matrix-vector multiplication (MVM) heavy workloads at the edge. In this work, we examine how the polar format algorithm (PFA), a popular SAR image formation algorithm, can be mapped to these AIMC systems. The PFA maps readily onto analog MVMs because it primarily consists of two linear operations: interpolation of frequency-domain data to a Cartesian grid, followed by a 2-D Fourier transform. This work presents two approaches to map the interpolation operation onto MVMs in analog hardware: a chirp transform and a modified form of sinc interpolation. These mappings introduce algorithmic errors, and their effect on the quality of SAR image formation is examined, both quantitatively and qualitatively. In addition, the impact of errors introduced by the analog hardware is explored to determine which approach is optimal under varying assumptions about the underlying analog memory devices and circuits.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"811-817"},"PeriodicalIF":0.0,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian Inverse Learning and Online Changepoint Detection of Cognitive Radar Strategies","authors":"C. V. Anoop;Anup Aprem","doi":"10.1109/TRS.2025.3551066","DOIUrl":"https://doi.org/10.1109/TRS.2025.3551066","url":null,"abstract":"In this article, we introduce an online electronic countermeasure framework for learning the strategies and detecting changes in the strategy of an adversarial cognitive radar (CR) in an inverse learning framework. We model the CR as a rational, constrained utility-maximizing agent and formulate the problem in the revealed preference setting. The utility of CR is modeled as a random direction vector, that follows the von Mises-Fisher distribution with unknown parameters, and we use Bayesian machine learning with revealed preference characterization to learn the radar’s utility, and extend it to the detection of changes in strategy in an online setting. The main contributions of the article are: 1) the development of Bayesian machine learning algorithms—HBOIL and HBOCPD, for inverse learning and detection of changes in strategies of an adversarial CR, respectively; 2) HBOIL and HBOCPD use a Hamiltonian Monte Carlo (HMC) sampling algorithm that exploits the Afriat’s theorem in revealed preference as well as a subsetting structure that arises in the posterior, and hence is devoid of the computational burden of solving optimization problems in existing techniques; 3) numerical results demonstrate the ability to characterize and determine the changes in the beam allocation strategy of a CR in noise-free and noisy adversarial settings. HBOIL and HBOCPD are robust to observation noise compared to the existing approaches; 4) HBOIL outperforms classical machine learning approaches in predicting optimal radar responses; and 5) HBOCPD performs, on an average, five times faster compared to the classical offline generalized likelihood ratio (GLR) approach, while using less restrictive assumptions.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"562-575"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Localization of LOS and NLOS Targets With Clutter Mitigation via Multipath Exploitation Radar","authors":"Jiahui Chen;Xiaobo Yang;Chen Qiu;Zhihao Zhu;Peilun Wu;Zihan Xu;Shisheng Guo;Guolong Cui","doi":"10.1109/TRS.2025.3550023","DOIUrl":"https://doi.org/10.1109/TRS.2025.3550023","url":null,"abstract":"The development of nonline-of-sight target detection (NLOS-TD) technology has significantly enhanced the detection capabilities of radar systems, allowing them to monitor regions that are not within direct visual range. However, current NLOS-TD techniques mainly focus on scenarios involving only NLOS targets, without sufficiently addressing the more complex case where both line-of-sight (LOS) and NLOS targets are present. To address the problem, this article proposes a joint localization method that integrates clutter mitigation for both LOS and NLOS targets. Specifically, first, electromagnetic (EM) wave propagation in typical corner scenarios involving both LOS and NLOS targets is examined. Subsequently, the process of background clutter removal and target localization is formulated as an optimization problem, incorporating low-rank, sparsity, and group sparsity constraints. After that, a proximal gradient (PG)-based iterative method is developed, which suppresses clutter while simultaneously producing images of both LOS and NLOS targets. The efficiency of the method is demonstrated through both simulations and experimental results, confirming its ability to accurately localize LOS and NLOS targets.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"549-561"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"POMDP-Driven Cognitive Massive MIMO Radar: Joint Target Detection-Tracking in Unknown Disturbances","authors":"Imad Bouhou;Stefano Fortunati;Leila Gharsalli;Alexandre Renaux","doi":"10.1109/TRS.2025.3549239","DOIUrl":"https://doi.org/10.1109/TRS.2025.3549239","url":null,"abstract":"The joint detection and tracking of a moving target embedded in an unknown disturbance represents a key feature that motivates the development of the cognitive radar paradigm. Building upon recent advancements in robust target detection with multiple-input multiple-output (MIMO) radars, this work explores the application of a partially observable Markov decision process (POMDP) framework to enhance the tracking and detection tasks in a statistically unknown environment. In the POMDP setup, the radar system is considered as an intelligent agent that continuously senses the surrounding environment, optimizing its actions to maximize the probability of detection <inline-formula> <tex-math>$(P_{!D})$ </tex-math></inline-formula> and improve the target position and velocity estimation, all this while keeping a constant probability of false alarm <inline-formula> <tex-math>$(P_{text {FA}})$ </tex-math></inline-formula>. The proposed approach employs an online algorithm that does not require any a priori knowledge of the noise statistics, and it relies on a much more general observation model than the traditional range-azimuth-elevation model employed by conventional tracking algorithms. Simulation results clearly show substantial performance improvement of the POMDP-based algorithm compared to the state-action-reward-state-action (SARSA)-based one that has been recently investigated in the context of massive MIMO (MMIMO) radar systems.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"539-548"},"PeriodicalIF":0.0,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Motion Compensation Radar Imaging Based on Bi-XLSTM and BP Algorithm","authors":"Xuemei Ren;Xiaoyong Li;Pengshuai Rong;Wanting Zhou;Lei Liu;Xueru Bai;Feng Zhou","doi":"10.1109/TRS.2025.3567548","DOIUrl":"https://doi.org/10.1109/TRS.2025.3567548","url":null,"abstract":"Advances in high-speed digital acquisition and storage technologies have enabled the sampling of radar echoes at intermediate frequencies. Precise gate control and recording techniques facilitate translational compensation based on echo coherence, enabling robust imaging even in low signal-to-noise ratio (SNR) conditions. Despite these advancements, existing approaches face inefficiencies in parameter estimation and encounter significant difficulties in azimuth focusing when increasing imaging resolution at large angles. To address these challenges, a novel joint motion compensation imaging algorithm that integrates bidirectional extended long short-term memory (Bi-XLSTM) networks with back projection (BP) is proposed. This approach initiates with the development of a comprehensive joint motion echo model for the target to reduce cumulative errors, thereby establishing a solid foundation for further joint motion compensation. Next, Bi-XLSTM is utilized for the efficient extraction of motion parameters from coherent echoes. The Adam optimization algorithm is then applied during the BP imaging process to jointly optimize motion and rotation parameters, targeting optimal image quality and resulting in highly focused images. Experiments conducted on point simulations, electromagnetic simulations, and real data confirm that this technique outperforms traditional methods.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"738-755"},"PeriodicalIF":0.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144125645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"5G-Based Passive Radar Utilizing Channel Response Estimated via Reference Signals","authors":"Marek Wypich;Radoslaw Maksymiuk;Tomasz P. Zielinski","doi":"10.1109/TRS.2025.3547245","DOIUrl":"https://doi.org/10.1109/TRS.2025.3547245","url":null,"abstract":"In this article, the possibilities of using the signal of 5G cellular networks for passive radar are investigated. In contrast to the traditional approach, i.e., the passive coherent location (PCL), in which the cross-ambiguity function (CAF) between the transmitted and received signal is calculated, in the presented method, known from the automotive industry, the channel frequency response (CFR) is first estimated, and then, the channel impulse response (CIR) is computed and spectrally analyzed to obtain a range-velocity map. It is shown that CFR/CIR-based 5G radar, known as an orthogonal frequency-division multiplexing (OFDM)-based radar, outperforms CAF-based 5G radar in some aspects, e.g., ease of implementation and lower complexity, while maintaining comparable measurement accuracy. In this article, CFR/CIR is estimated using standard 5G channel state information reference signals (CSI-RSs) or some additional radar-on-demand (RoD) OFDM symbols that could be offered by mobile network operators as an extra paid service. Different time and frequency densities of RoD OFDM symbols are tested. The results are compared with the application of CAF and 5G positioning reference-like signals (PRSs). This article shows that even rare CSI-RS pilots can make a low-cost radar device from a 5G receiver. It is demonstrated that slightly irregular sampling of the CIR taps, caused by using cyclic prefixes of different lengths in 5G, does not lead to major velocity estimation errors.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"511-519"},"PeriodicalIF":0.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generating Counterfactual Explanations for Misclassification of Automotive Radar Targets","authors":"Neeraj Pandey;Devansh Mathur;Debojyoti Sarkar;Shobha Sundar Ram","doi":"10.1109/TRS.2025.3566222","DOIUrl":"https://doi.org/10.1109/TRS.2025.3566222","url":null,"abstract":"Prior studies have demonstrated that the inverse synthetic aperture radar (ISAR) images of automotive targets at millimeter-wave (mmW) frequencies provide useful information regarding the target’s shape, size, and trajectory and serve as excellent classification features for deep neural networks. However, the classification performance is limited by environmental conditions, such as multipath, clutter, and occlusion, even when the radar receivers have a high signal-to-noise ratio (SNR). Therefore, for the widespread adoption of deep learning-based ISAR classification in real-world advanced driver assistance systems (ADASs), it is essential to provide a framework for explaining the physics-based phenomena responsible for misclassification and building trust among end users. In this work, we use the deep learning-based generative framework that introduces minimal perturbations on ISAR images belonging to one class to synthesize counterfactual realistic ISAR images that are misclassified as belonging to a second class of automotive vehicles. The networks are specifically trained to emulate occlusions of parts of the target vehicles from the radar. Due to the requirement of controlled experiments for occluding specific parts of the vehicle, simulation radar data are adopted to generate ISAR images. Our results show that the analyses of the counterfactual images generated through this process provide valuable insights into the physics-based causes of misclassification.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"724-737"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CPM-Based Tunable Phase-Attached Radar–Communications (PARC)","authors":"Cenk Sahin;Patrick M. McCormick;Justin G. Metcalf;John Jakabosky;Shannon D. Blunt;Erik S. Perrins;Jonathan Owen","doi":"10.1109/TRS.2025.3546216","DOIUrl":"https://doi.org/10.1109/TRS.2025.3546216","url":null,"abstract":"Motivated by the increasing need for efficient use of the electromagnetic spectrum (EMS) in congested and contested environments, a codesigned dual-function radar-communication (DFRC) waveform framework was introduced, which combines the desirable features of a pulsed radar transmission (i.e., constant amplitude and continuous phase) with the ability to embed information in the phase of the waveform via continuous-phase modulation (CPM). This CPM-based phase-attached radar-communication (PARC) waveform operates in a pulse-agile mode, which introduces a coupling of the fast- and slow-time dimensions through what is known as range-sidelobe modulation (RSM). The flexibility of CPM-based PARC via its multiple tunable parameters provides the ability to control this radar performance degradation at the expense of bit error rate (BER) and/or data throughput. Furthermore, the severity of RSM can likewise be mitigated via mismatched filter pulse compression on receive to reduce the variance of the pulse compression responses. Here, we evaluate the radar and communication performance trade space as a function of the CPM-based PARC parameters when assuming both matched and mismatched filter pulse compression at the radar receiver. The efficacy of the CPM-based PARC framework for both radar and communications is experimentally validated in an open-air environment using a radar in a quasi-monostatic configuration and a communication receiver in the field of view of the radar.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"520-538"},"PeriodicalIF":0.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Log-Normal Complex-Amplitude Likelihood Ratio-Based TBD Method With Soft Orbit-Information Constraints for Tracking Space Targets With Space-Based Radar","authors":"Shuyu Zheng;Dongsheng Li;Qingwei Yang;Yingjian Zhao;Libing Jiang;Zhuang Wang","doi":"10.1109/TRS.2025.3546213","DOIUrl":"https://doi.org/10.1109/TRS.2025.3546213","url":null,"abstract":"Space-based radars (SBRs) systems are able to provide an unobstructed field of view for space target detection and tracking. However, the large temperature dynamic range and poor heat dissipation performance of the SBR system cause severe thermal noise, leading to deficiency in distant or dim space target detection tasks. In essence, the challenges above can be categorized as typical low signal-to-noise ratio (SNR) problems, and the track before detect (TBD) processing scheme is applied to solve them in this article. Nevertheless, the typical TBD methods reckon without the following aspects and thus are not well compatible with space target surveillance tasks via the SBR system. First, the typical TBD methods discard the phase information of radar raw data in constructing the likelihood ratio. In addition, most existing work merely considers modeling the amplitude fluctuation as Swerling types, which is not accurate enough for space targets when compared with the log-normal distribution (LND) model. Moreover, orbital space targets follow the orbital dynamic principle while most existing TBD methods neglect this important information, which will cause space targets filtering estimation bias. To address the aforementioned problems, we propose a TBD method based on the complex-amplitude likelihood ratio (CLR) of the LND model and soft orbit-information constraint (OC). In this article, with the aim of acquiring a more accurate likelihood ratio, we first derive the closed mathematical form of the amplitude likelihood ratio (ALR) and the CLR of the LND model. Meanwhile, some approximations are proposed to alleviate the integral computation. Then, the proposed ALR and CLR of the LND model are utilized to be implemented into the TBD scheme. Finally, we design elegant soft OC strategies to modify the associated weights corresponding with birth particles in sequential Monte Carlo (SMC) implementation. Simulation results are provided to validate the effectiveness of the proposed soft OC-CLR-TBD method.","PeriodicalId":100645,"journal":{"name":"IEEE Transactions on Radar Systems","volume":"3 ","pages":"467-482"},"PeriodicalIF":0.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}