Iet Radar Sonar and Navigation最新文献_第2页

DetDSHAP: Explainable Object Detection for Uncrewed and Autonomous Drones With Shapley Values DetDSHAP：具有Shapley值的无人和自主无人机的可解释目标检测

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-18 DOI: 10.1049/rsn2.70042

Maxwell Hogan, Nabil Aouf

{"title":"DetDSHAP: Explainable Object Detection for Uncrewed and Autonomous Drones With Shapley Values","authors":"Maxwell Hogan, Nabil Aouf","doi":"10.1049/rsn2.70042","DOIUrl":"https://doi.org/10.1049/rsn2.70042","url":null,"abstract":"Automatic object detection onboard drones is essential for facilitating autonomous operations. The advent of deep learning techniques has significantly enhanced the efficacy of object detection and recognition systems. However, the implementation of deep networks in real-world operational settings for autonomous decision-making presents several challenges. A primary concern is the lack of transparency in deep learning algorithms, which renders their behaviour unreliable to both practitioners and the general public. Additionally, deep networks often require substantial computational resources, which may not be feasible for many compact portable platforms. This paper aims to address these challenges and promote the integration of deep object detectors in drone applications. We present a novel interpretative framework, DetDSHAP, designed to elucidate the predictions generated by the YOLOv5 detector. Furthermore, we propose utilising the contribution scores derived from our explanatory model as an innovative pruning technique for the YOLOv5 network, thereby achieving enhanced performance while minimising computational demands. Lastly, we provide performance evaluations of our approach demonstrating its efficiency across various datasets, including real data collected from drone-mounted cameras and established public benchmark datasets.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70042","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Grating Lobe Suppression of Non-Periodic Geometric Formations Based on Modified Particle Swarm Optimization 基于改进粒子群优化的非周期几何形状光栅瓣抑制

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-14 DOI: 10.1049/rsn2.70046

Lin Qiu, Huijie Liu, Juan Chen, Hao Huang, Andrew W. H. Ip, Kai Leung Yung

{"title":"Grating Lobe Suppression of Non-Periodic Geometric Formations Based on Modified Particle Swarm Optimization","authors":"Lin Qiu, Huijie Liu, Juan Chen, Hao Huang, Andrew W. H. Ip, Kai Leung Yung","doi":"10.1049/rsn2.70046","DOIUrl":"https://doi.org/10.1049/rsn2.70046","url":null,"abstract":"For the issue of configuration difficulty in maintaining linear formations based on the same orbital plane for distributed space-based coherent aperture radar (DSCAR), it is necessary to modify the linear formation model into an arc formation model. This article derives the steering vector and joint pattern expressions for DSCAR based on uniform arc formation, and designs a segmented inertial factor (IF) particle swarm optimization (PSO) to seek the optimal solution for non-uniform spacing and random yaw angle in non-periodic geometric distribution. Simulation analysis shows that the combination of non-uniform spacing and random yaw angle in non-periodic geometric formations can achieve lower peak side lobe level (PSLL) compared to single non-uniform spacing and single random yaw angle but with wider beamwidth spread. Additionally, the segmented IF PSO proposed in this article balances convergence more quickly in the early stage of the search process and improves convergence speed to approach the optimal value (OV) in later stage. Compared with other IF PSO, it has better convergence speed and accuracy.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70046","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributed Shipborne HFHSSWR Localisation Method Based on Gaussian Markov Fields 基于高斯马尔可夫场的分布式舰载HFHSSWR定位方法

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-13 DOI: 10.1049/rsn2.70045

Longyuan Xu, Peng Tong, Yinsheng Wei, Mingkai Ding

引用次数: 0

Machine Learning Doppler-Tolerant One-Bit Radar Detectors 机器学习容忍多普勒位雷达探测器

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-13 DOI: 10.1049/rsn2.70011

Kyle P. Wensell, Changshi Zhou, Alexander M. Haimovich, Abdallah Khreishah, Brent Lozneanu, Brandon Cannizzo, Evan A. Young, Lam T. Vo

{"title":"Machine Learning Doppler-Tolerant One-Bit Radar Detectors","authors":"Kyle P. Wensell, Changshi Zhou, Alexander M. Haimovich, Abdallah Khreishah, Brent Lozneanu, Brandon Cannizzo, Evan A. Young, Lam T. Vo","doi":"10.1049/rsn2.70011","DOIUrl":"https://doi.org/10.1049/rsn2.70011","url":null,"abstract":"Doppler-tolerant waveforms are some of the most common radar waveforms used in practice. However, their deterministic and repetitive nature impedes control of mutual interference when multiple radars operate in close proximity. Noise radar technology may address this problem but is not Doppler tolerant. In this study, we design a machine learning radar detector capable of Doppler-tolerant performance with noise waveforms. The detector is implemented as a feedforward multilayer neural network. We show that the detector may be trained to operate with one-bit data. Further, to evaluate the proposed detector's performance, we derive a closed-form expression of the receiver operating characteristic (ROC) for one-bit detection of a Swerling 1 target using the square-law detector under the assumption of low signal-to-noise ratio (SNR). Numerical results demonstrate that the proposed machine learning detector, when suitably trained, is capable of operating with Doppler tolerance over a wide range of Doppler shifts.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Depth Estimation Method for Continuous Acoustic Signal Targets in Shallow Water Using a Linear Array 基于线性阵列的浅水连续声信号目标深度估计方法

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-07 DOI: 10.1049/rsn2.70034

Siqi Du, Dong Han, Ning Li

{"title":"Depth Estimation Method for Continuous Acoustic Signal Targets in Shallow Water Using a Linear Array","authors":"Siqi Du, Dong Han, Ning Li","doi":"10.1049/rsn2.70034","DOIUrl":"https://doi.org/10.1049/rsn2.70034","url":null,"abstract":"To overcome the limitations of existing methods in processing continuous acoustic signals—particularly issues related to modal aliasing and the constraints of Pekeris waveguide applications—this study proposes a depth estimation approach for continuous acoustic targets using hydrophone linear arrays. A horizontal linear array, designed to meet the resolution requirements of the F–K transform, is deployed to receive continuous acoustic signals. Environmental parameters are incorporated to fit the sound speed profile, and modal time-delay differences are calculated based on normal mode propagation models. Temporal compensation is then applied to each modal component of the received signals across array elements. The corrected signal matrix undergoes a bidirectional F–K transform transformation into the frequency–wavenumber domain, allowing for clear separation of the normal modes of continuous signals. Frequency–wavenumber curves are characterised based on the sound speed profile, and binary mask filters are designed to extract modal energy. Finally, a depth estimation matching function is constructed to facilitate energy search and matching. Simulation results indicate that the proposed method achieves depth estimation errors of less than 5% for 10-s broadband acoustic signals under negative sound speed profiles and real shallow-sea waveguide conditions. The method demonstrates improved stability and applicability in variable sound speed environments, offering greater practical value for real-world shallow-sea scenarios.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144237290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Passive Target Motion Analysis With Own-Ship Location Uncertainty in the Presence of Non-Gaussian Sensor Noise 非高斯传感器噪声存在下具有自船位置不确定性的被动目标运动分析

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-05 DOI: 10.1049/rsn2.70043

Rohit Kumar Singh, Shreya Das, Shovan Bhaumik

{"title":"Passive Target Motion Analysis With Own-Ship Location Uncertainty in the Presence of Non-Gaussian Sensor Noise","authors":"Rohit Kumar Singh, Shreya Das, Shovan Bhaumik","doi":"10.1049/rsn2.70043","DOIUrl":"https://doi.org/10.1049/rsn2.70043","url":null,"abstract":"Passive target motion analysis (TMA) is traditionally performed using angle-only measurements, which requires the own-ship to execute a manoeuvre to make the tracking system observable. These manoeuvres are burdensome for the naval community. In contrast, this work explores underwater TMA by incorporating time delay and Doppler frequency measurements along with angle data, eliminating the need for own-ship manoeuvre and improving estimation accuracy. Measurement noises are assumed to follow a non-Gaussian distribution, and maximum correntropy (MC)-based Bayesian filtering framework is adopted to solve the problem. Furthermore, the own-ship's position is inherently uncertain due to navigation errors, and this work addresses the uncertainty by modifying the measurement noise covariance matrix within the estimation framework. Simulation results demonstrate that the proposed methodology achieves improved tracking performance in terms of root mean square error (RMSE) and <math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>%</mi>\u0000 </mrow>\u0000 <annotation> $%$</annotation>\u0000 </semantics></math> track loss compared to existing state-of-the-art MC Kalman filtering approaches.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70043","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144220000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Area Controllable Suppression Jamming Method Against SAR Based on Two-Dimensional Phase Mismatch 基于二维相位失配的SAR多区域可控抑制干扰方法

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-05 DOI: 10.1049/rsn2.70040

Guangyuan Li, GuiKun Liu, Zhenyang Xu, Haoming Xu, Zhengshuai Li, Peng Wang, Yueyang Zhang, Liang Li

{"title":"Multi-Area Controllable Suppression Jamming Method Against SAR Based on Two-Dimensional Phase Mismatch","authors":"Guangyuan Li, GuiKun Liu, Zhenyang Xu, Haoming Xu, Zhengshuai Li, Peng Wang, Yueyang Zhang, Liang Li","doi":"10.1049/rsn2.70040","DOIUrl":"https://doi.org/10.1049/rsn2.70040","url":null,"abstract":"In the imaging process of SAR, the secondary phase mismatch can cause image defocusing. In this paper, a suppression jamming method against SAR based on two-dimensional (2D) phase mismatch is proposed through a designed jammer system. By extracting and resampling the intercepted radar signal through the designed jammer, the bandwidth of the linear frequency modulation (LFM) signal can be changed, which causes defocusing in the range dimension after matching filtering. Azimuth phase mismatch is achieved through velocity mismatch, which leads to azimuth defocusing after azimuth matching filtering. Efficient coverage of multiple dispersed important regions can be achieved by adjusting the parameters of jamming targets reasonably, such as modulation bandwidth, azimuth velocity, jamming positions and jamming power. Theoretical analysis is conducted on the implementation of the algorithm and its 2-D controllability in terms of jamming location and jamming area, as well as the required jamming power. The correctness of the theoretical model is verified by simulation results of spaceborne SAR. This method is quite simple to implement and can achieve efficient coverage of multiple dispersed targets, providing a basis for the implementation and application of SAR jamming in active radar responders.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144220001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

XAI-Driven Resilient Image Classification in the Presence of Adversarial Perturbations 存在对抗性扰动的xai驱动的弹性图像分类

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-06-04 DOI: 10.1049/rsn2.70041

Amir Hosein Oveis, Elisa Giusti, Alessandro Cantelli-Forti, Marco Martorella

{"title":"XAI-Driven Resilient Image Classification in the Presence of Adversarial Perturbations","authors":"Amir Hosein Oveis, Elisa Giusti, Alessandro Cantelli-Forti, Marco Martorella","doi":"10.1049/rsn2.70041","DOIUrl":"https://doi.org/10.1049/rsn2.70041","url":null,"abstract":"Deep learning (DL) architectures, although being employed in widespread applications, often raise concerns about their trustworthiness due to their opacity in their decision-making processes. Explainable AI (XAI) emerges as a promising solution to mitigate these concerns by providing interpretable rationales for DL network outputs. In domains where risk tolerance is minimal, ensuring trustworthy predictions is essential. This study introduces expmax, a new classifier rooted in XAI principles, designed for multiclass classification problems using convolutional neural network (CNN) architectures. The key strength of expmax, compared to the conventional softmax, lies in its ability to evaluate the model's focus on salient features of targets rather than being distracted by unrelated patterns from the background. This characteristic allows expmax for increased resilience, especially in scenarios with adversarial samples, where conventional classifiers may fail to correctly recognise the target class. The methodology behind expmax is based on fitting a regressor with features that are extracted from the training dataset using the SHapley Additive exPlanations (SHAP) algorithm, along with a target mask area detection algorithm. By using the SHAP-based extracted features, expmax reduces vulnerabilities to perturbations introduced by adversarial inputs. The method is validated on the MTARSI dataset for aircraft recognition in remote sensing images.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70041","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Radar Anti-Jamming Performance Evaluation: A Novel Model Based on Measurement Error and RCS Distributions 雷达抗干扰性能评估：一种基于测量误差和RCS分布的新模型

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-30 DOI: 10.1049/rsn2.70038

Linqi Zhao, Liang Yan, Xiaojun Duan, Zhengming Wang, Yike Xiao

{"title":"Radar Anti-Jamming Performance Evaluation: A Novel Model Based on Measurement Error and RCS Distributions","authors":"Linqi Zhao, Liang Yan, Xiaojun Duan, Zhengming Wang, Yike Xiao","doi":"10.1049/rsn2.70038","DOIUrl":"https://doi.org/10.1049/rsn2.70038","url":null,"abstract":"The growing complexity of the electromagnetic environment makes accurate radar anti-jamming performance evaluation essential for assessing the effectiveness of electronic countermeasure systems. In jamming scenarios, smaller measurement errors in range indicate a radar's enhanced ability to counteract interference. This paper presents a novel approach to radar anti-jamming performance evaluation based on statistical models of radar cross-section (RCS) fluctuations. Assuming that the RCS follows one of several distributions—Swerling I–II, Swerling III–IV, or Rayleigh—we derive the corresponding distributions of radar parameter measurement errors. In our model, the measurement error is assumed to follow a conditional Gaussian distribution, with its standard deviation modelled as a random variable dependent on both the RCS and the signal-to-interference ratio (SIR). This formulation establishes a quantitative relationship between measurement error, SIR, and RCS, and enables derivation of the error's probability density function (PDF). Consequently, we obtain a novel expression for the radar anti-jamming rate. We compare this model to two conventional approaches: one that assumes a constant error variance across all target ranges and another that assumes a fixed variance that varies with target ranges but without incorporating distributional uncertainty. The proposed Error Distribution Estimation (EDE) model leverages the full probability distribution of measurement errors together with real-time parameter error data fusion. This integration provides a more continuous and nuanced evaluation of radar anti-jamming performance, potentially leading to more reliable assessments under a range of operating conditions.","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Software-Defined Sonar for Unmanned Underwater System 无人水下系统软件定义声纳

IF 1.4 4区管理学

Iet Radar Sonar and Navigation Pub Date : 2025-05-27 DOI: 10.1049/rsn2.70037

Hongkun Zhou, Xiyun Ge, Ningyang Wei, Yuhang Gao, Xinyu Liu

引用次数: 0