Pub Date : 2024-07-01DOI: 10.1109/JMASS.2024.3420893
Wentao Sun;Zan Li;Jia Shi;Zixuan Bai;Feng Wang;Tony Q. S. Quek
As an aerial base station (BS), uncrewed aerial vehicle (UAV) has been considered as a promising platform to provide wireless data service in future networks due to its flexible, swift, and low-cost features. However, since the suddenness and randomness of ground users’ (GUs’) data requirements, it is challenging for the UAV BSs to dynamically make decisions to provide real-time data services to GUs. In a multimode UAV-assisted wireless network, we formulate a multiobjective optimization problem to minimize the average peak age of information (APAoI) and energy consumption of UAVs and to maximize the accumulated service data (ASD) for GUs. Therefore, this article proposes the multiagent hybrid twin delayed deep deterministic policy gradient (MAHTD-DDPG) algorithm with hybrid action space design, which is empowered by the centralized training and distributed execution (CTDE) framework. In the proposed algorithm, the UAVs can cooperatively make decisions by sharing the GU status information, in a result of jointly optimizing the UAV trajectory, mode selection, and transmit power. Simulation results demonstrate that our proposed approach achieves 79.6% and 120.4% higher rewards than the multiagent DDPG algorithm and HTD-DDPG algorithm, respectively.
{"title":"MAHTD-DDPG-Based Multiobjective Resource Allocation for UAV-Assisted Wireless Network","authors":"Wentao Sun;Zan Li;Jia Shi;Zixuan Bai;Feng Wang;Tony Q. S. Quek","doi":"10.1109/JMASS.2024.3420893","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3420893","url":null,"abstract":"As an aerial base station (BS), uncrewed aerial vehicle (UAV) has been considered as a promising platform to provide wireless data service in future networks due to its flexible, swift, and low-cost features. However, since the suddenness and randomness of ground users’ (GUs’) data requirements, it is challenging for the UAV BSs to dynamically make decisions to provide real-time data services to GUs. In a multimode UAV-assisted wireless network, we formulate a multiobjective optimization problem to minimize the average peak age of information (APAoI) and energy consumption of UAVs and to maximize the accumulated service data (ASD) for GUs. Therefore, this article proposes the multiagent hybrid twin delayed deep deterministic policy gradient (MAHTD-DDPG) algorithm with hybrid action space design, which is empowered by the centralized training and distributed execution (CTDE) framework. In the proposed algorithm, the UAVs can cooperatively make decisions by sharing the GU status information, in a result of jointly optimizing the UAV trajectory, mode selection, and transmit power. Simulation results demonstrate that our proposed approach achieves 79.6% and 120.4% higher rewards than the multiagent DDPG algorithm and HTD-DDPG algorithm, respectively.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"70-81"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179171","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}
Pub Date : 2024-04-16DOI: 10.1109/JMASS.2024.3389097
Curtis Manore;Alan J. Fenn;Hanumant Singh
In suboptimal environments for satellite reception, an unmanned aerial system (UAS) can navigate to a higher vantage point to receive better quality satellite broadcasts. Small UAS platforms are constrained by weight and size, making VHF antenna implementation difficult for satellite reception onboard a UAS. This research designs, simulates, and implements a small form factor V-dipole antenna with matching circuit and low-noise amplifiers to receive high-quality National Oceanic and Atmospheric Administration (NOAA) satellite imagery and weather data from a custom DJI Matrice 100 UAS platform. A software-defined radio was used to filter and demodulate VHF satellite signals, and an Nvidia TX2-embedded computer processed the satellite images onboard the UAS. Performance was evaluated by the quality of the image reception and practicality of the antenna design in flight.
在卫星接收不理想的环境中，无人机系统（UAS）可以导航到更高的有利位置，以接收质量更好的卫星广播。小型无人机系统平台受到重量和尺寸的限制，因此很难在无人机系统上实施甚高频天线来接收卫星。本研究设计、模拟并实现了一种小型 V 型偶极子天线，该天线配有匹配电路和低噪声放大器，可从定制的大疆 Matrice 100 无人机系统平台接收高质量的美国国家海洋和大气管理局（NOAA）卫星图像和气象数据。软件定义无线电用于过滤和解调甚高频卫星信号，Nvidia TX2-嵌入式计算机在无人机系统上处理卫星图像。通过图像接收质量和飞行中天线设计的实用性对性能进行了评估。
{"title":"Design of Active V-Dipole Antenna on UAS for Receiving NOAA Polar Satellite Imagery","authors":"Curtis Manore;Alan J. Fenn;Hanumant Singh","doi":"10.1109/JMASS.2024.3389097","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3389097","url":null,"abstract":"In suboptimal environments for satellite reception, an unmanned aerial system (UAS) can navigate to a higher vantage point to receive better quality satellite broadcasts. Small UAS platforms are constrained by weight and size, making VHF antenna implementation difficult for satellite reception onboard a UAS. This research designs, simulates, and implements a small form factor V-dipole antenna with matching circuit and low-noise amplifiers to receive high-quality National Oceanic and Atmospheric Administration (NOAA) satellite imagery and weather data from a custom DJI Matrice 100 UAS platform. A software-defined radio was used to filter and demodulate VHF satellite signals, and an Nvidia TX2-embedded computer processed the satellite images onboard the UAS. Performance was evaluated by the quality of the image reception and practicality of the antenna design in flight.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"165-174"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041372","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}
Pub Date : 2024-04-04DOI: 10.1109/JMASS.2024.3385699
Suchitra Tiwari;Amit K. Singh;Ankit Dubey
A highly efficient low-profile binary metasurface lens (BMSL) antenna is designed and developed to achieve wide-angle beamsteering at the millimeter-wave band of fifth-generation (5G) aerospace communication systems. First, a subwavelength-sized phase-shift element (meta-element) with a crossed-arrow geometry having two-line symmetry structure is designed possessing special characteristics of insensitivity to polarization as well as the oblique angle of incidence, wide-band transmission, and compactness. Further, 1-bit quantized radial phase-graded metasurface lens is designed by arranging the proposed elements in $19times19$ array resulting in an aperture area of $33.6~lambda _{0}^{2}$ . To realize beamsteering along 0°, ±15°, ±30°, ±45°, and ±60°, BMSLs with distinct phase-quantization are designed and spatially fed through antipodal Vivaldi antenna (AVA) which acts as a primary feed source positioned at optimum focal point thereby radiating highly concentrated beams in the intended directions. The complete BMSL antenna system is then fabricated and characterized in an ideal free-space environment achieving a measured peak gain of up to 20.8 dBi in broadside direction and 1.6 dB of maximum scan loss for ±60° steering. The proposed BMSL antenna achieves an aperture efficiency of 28.4 % at 28 GHz and a −3-dB gain bandwidth of 16.5 %. Thus, the proposed BMSL antenna is a promising contender for facilitating terrestrial (air) as well as nonterrestrial (space) communication links between low-Earth orbit satellites and 5G base stations.
{"title":"Wide-Band Wide-Angle Beamsteerable Meta-Lens Antenna for Terrestrial/Nonterrestrial 5G Communication Systems","authors":"Suchitra Tiwari;Amit K. Singh;Ankit Dubey","doi":"10.1109/JMASS.2024.3385699","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3385699","url":null,"abstract":"A highly efficient low-profile binary metasurface lens (BMSL) antenna is designed and developed to achieve wide-angle beamsteering at the millimeter-wave band of fifth-generation (5G) aerospace communication systems. First, a subwavelength-sized phase-shift element (meta-element) with a crossed-arrow geometry having two-line symmetry structure is designed possessing special characteristics of insensitivity to polarization as well as the oblique angle of incidence, wide-band transmission, and compactness. Further, 1-bit quantized radial phase-graded metasurface lens is designed by arranging the proposed elements in \u0000<inline-formula> <tex-math>$19times19$ </tex-math></inline-formula>\u0000 array resulting in an aperture area of \u0000<inline-formula> <tex-math>$33.6~lambda _{0}^{2}$ </tex-math></inline-formula>\u0000. To realize beamsteering along 0°, ±15°, ±30°, ±45°, and ±60°, BMSLs with distinct phase-quantization are designed and spatially fed through antipodal Vivaldi antenna (AVA) which acts as a primary feed source positioned at optimum focal point thereby radiating highly concentrated beams in the intended directions. The complete BMSL antenna system is then fabricated and characterized in an ideal free-space environment achieving a measured peak gain of up to 20.8 dBi in broadside direction and 1.6 dB of maximum scan loss for ±60° steering. The proposed BMSL antenna achieves an aperture efficiency of 28.4 % at 28 GHz and a −3-dB gain bandwidth of 16.5 %. Thus, the proposed BMSL antenna is a promising contender for facilitating terrestrial (air) as well as nonterrestrial (space) communication links between low-Earth orbit satellites and 5G base stations.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"117-124"},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091131","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}
Multibaseline phase unwrapping (MBPU) is a key procedure of interferometric synthetic aperture radar (InSAR). However, phase noise is a factor still challenging the MBPU accuracy. This article presents a refined pure integer programming (RPIP)-based MBPU method. In this method, a new parameter is introduced through considering the statistical information of the interferometric phase, which is adopted to improve the tolerance of phase noise. We also provide an effective path for searching of the ambiguity set. Theoretical analysis and experimental results show that, compared with the PIP method, unwrapping errors of the RPIP method is reduced by 60%.
{"title":"Multibaseline Phase Unwrapping With a Refined Parametric Pure Integer Programming for Noise Suppression","authors":"Jiawei Yue;Qihuan Huang;Hui Liu;Ziqi He;Hanwen Zhang","doi":"10.1109/JMASS.2024.3385026","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3385026","url":null,"abstract":"Multibaseline phase unwrapping (MBPU) is a key procedure of interferometric synthetic aperture radar (InSAR). However, phase noise is a factor still challenging the MBPU accuracy. This article presents a refined pure integer programming (RPIP)-based MBPU method. In this method, a new parameter is introduced through considering the statistical information of the interferometric phase, which is adopted to improve the tolerance of phase noise. We also provide an effective path for searching of the ambiguity set. Theoretical analysis and experimental results show that, compared with the PIP method, unwrapping errors of the RPIP method is reduced by 60%.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"156-164"},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10492469","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041439","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}
Pub Date : 2024-03-29DOI: 10.1109/JMASS.2024.3406783
Bin Gao;Anna Song;Hanwen Xu;Zenan Zhang;Wenhui Lian;Lei Yang
Low-rank matrix decomposition is effective for sparse recovery. However, the conventions are limited in accuracy for high-resolution synthetic aperture radar (SAR) imagery due to the shrinkage effect in the cost function, which leads to biased estimates. To this end, an enhanced-low rank matrix decomposition (E-LRMD) SAR imaging algorithm is proposed, which employs a factor group-sparse regularization (FGSR) to approximate the intended cost function, so that the low-rank features can be represented. Since, the constructed regularization function is factorized, the singular value decomposition is avoided, and the computational burden can be reduced accordingly. Furthermore, $ell _{1}$ -norm is incorporated to encode the sparse feature. To incorporate with the enhancement of multiple features, the alternating direction method of multipliers (ADMM) framework is utilized. Therefore, both the low-rank and sparse features can be accurately recovered and enhanced, cooperatively, where the error propagation between the enhancement of multiple features is minimized. In the experiments, the effectiveness and robustness of the algorithm are verified by the simulated data and practical UAV-SAR data, respectively. Also, a phase transition diagram (PTD) experiment is carried out to analyse the advantages of the proposed algorithm in terms of quantitative aspects compared with the conventional methods.
{"title":"Enhanced Low-Rank Matrix Decomposition for High-Resolution UAV-SAR Imagery","authors":"Bin Gao;Anna Song;Hanwen Xu;Zenan Zhang;Wenhui Lian;Lei Yang","doi":"10.1109/JMASS.2024.3406783","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3406783","url":null,"abstract":"Low-rank matrix decomposition is effective for sparse recovery. However, the conventions are limited in accuracy for high-resolution synthetic aperture radar (SAR) imagery due to the shrinkage effect in the cost function, which leads to biased estimates. To this end, an enhanced-low rank matrix decomposition (E-LRMD) SAR imaging algorithm is proposed, which employs a factor group-sparse regularization (FGSR) to approximate the intended cost function, so that the low-rank features can be represented. Since, the constructed regularization function is factorized, the singular value decomposition is avoided, and the computational burden can be reduced accordingly. Furthermore, \u0000<inline-formula> <tex-math>$ell _{1}$ </tex-math></inline-formula>\u0000-norm is incorporated to encode the sparse feature. To incorporate with the enhancement of multiple features, the alternating direction method of multipliers (ADMM) framework is utilized. Therefore, both the low-rank and sparse features can be accurately recovered and enhanced, cooperatively, where the error propagation between the enhancement of multiple features is minimized. In the experiments, the effectiveness and robustness of the algorithm are verified by the simulated data and practical UAV-SAR data, respectively. Also, a phase transition diagram (PTD) experiment is carried out to analyse the advantages of the proposed algorithm in terms of quantitative aspects compared with the conventional methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"187-199"},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041442","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}
Terahertz (THz) radar imaging has been getting a lot more attention in recent years because it has a faster frame rate and better resolution. However, nonlinear phase errors resulting from the immaturity and instability of THz devices inevitably affect the transmitted signal of THz radar imaging systems, causing the range image to blur. In this work, we present an adaptive correction approach for improving the imaging quality of THz radar by the elimination of nonlinear phase error. First, the nonparametric model is created with high accuracy; this model accounts for nonlinear phase errors introduced by the signal source and other broadband hardware devices like the frequency multiplier. After that, the suggested technique employs nonlinear phase error estimates and compensation by iterative optimization, with the picture contrast of multiple pulse compression serving as the evaluation criterion. The proposed method has been validated through the use of both synthetic data and field data gathered with a 0.22-THz airborne synthetic aperture radar equipment. The experimental results further highlight the suggested method’s high robustness, low computational cost, and several potential uses.
{"title":"An Adaptive Nonlinear Phase Error Estimation and Compensation Method for Terahertz Radar Imaging System","authors":"Mengyang Zhan;Jiawei Wu;Yinwei Li;Gang Xu;Yiming Zhu","doi":"10.1109/JMASS.2024.3382942","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3382942","url":null,"abstract":"Terahertz (THz) radar imaging has been getting a lot more attention in recent years because it has a faster frame rate and better resolution. However, nonlinear phase errors resulting from the immaturity and instability of THz devices inevitably affect the transmitted signal of THz radar imaging systems, causing the range image to blur. In this work, we present an adaptive correction approach for improving the imaging quality of THz radar by the elimination of nonlinear phase error. First, the nonparametric model is created with high accuracy; this model accounts for nonlinear phase errors introduced by the signal source and other broadband hardware devices like the frequency multiplier. After that, the suggested technique employs nonlinear phase error estimates and compensation by iterative optimization, with the picture contrast of multiple pulse compression serving as the evaluation criterion. The proposed method has been validated through the use of both synthetic data and field data gathered with a 0.22-THz airborne synthetic aperture radar equipment. The experimental results further highlight the suggested method’s high robustness, low computational cost, and several potential uses.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"108-116"},"PeriodicalIF":0.0,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091213","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}
Ground subsidence is a representative geohazard in mining areas that threatens human safety and infrastructure. Interferometric synthetic aperture radar (InSAR) was used to measure ground subsidence related to mining activities. However, mining areas are often subjected to severe temporal and geometric decorrelation problems, resulting in sparse persistent scatterers (PSs) and lower measurement accuracy. To improve deformation measurements, a robust multitemporal InSAR (MT-InSAR) method that jointly detects PS and distributed scatterers (DSs) in a two-tier network was utilized here. To solve the mismatch in the traditional linear velocity model, a logistic model was introduced for MT-InSAR processing. Forty-four Sentinel-1A SAR images acquired between 1 January 2020 and 30 June 2021 were used to measure ground subsidence in Zhoutaizi Village, Chengde City, Hebei Province, China, which endured geohazards induced and exacerbated by mining activities. We observed that more measurement points were produced using the logistic model (11 607) compared with the constant velocity model (10 980) in the mining areas with an increase of 5.7%, while the mean value of the standard deviation of the estimated residuals reduced from 1.45 to 1.13 with a decrease of 22%. Results are beneficial for geohazard assessment and management in mining areas.
{"title":"Mining-Related Subsidence Measurements Using a Robust Multitemporal InSAR Method and Logistic Model","authors":"Peifeng Ma;Chang Yu;Zherong Wu;Zhanze Wang;Jiehong Chen","doi":"10.1109/JMASS.2024.3381788","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3381788","url":null,"abstract":"Ground subsidence is a representative geohazard in mining areas that threatens human safety and infrastructure. Interferometric synthetic aperture radar (InSAR) was used to measure ground subsidence related to mining activities. However, mining areas are often subjected to severe temporal and geometric decorrelation problems, resulting in sparse persistent scatterers (PSs) and lower measurement accuracy. To improve deformation measurements, a robust multitemporal InSAR (MT-InSAR) method that jointly detects PS and distributed scatterers (DSs) in a two-tier network was utilized here. To solve the mismatch in the traditional linear velocity model, a logistic model was introduced for MT-InSAR processing. Forty-four Sentinel-1A SAR images acquired between 1 January 2020 and 30 June 2021 were used to measure ground subsidence in Zhoutaizi Village, Chengde City, Hebei Province, China, which endured geohazards induced and exacerbated by mining activities. We observed that more measurement points were produced using the logistic model (11 607) compared with the constant velocity model (10 980) in the mining areas with an increase of 5.7%, while the mean value of the standard deviation of the estimated residuals reduced from 1.45 to 1.13 with a decrease of 22%. Results are beneficial for geohazard assessment and management in mining areas.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"149-155"},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041370","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}
Pub Date : 2024-03-26DOI: 10.1109/JMASS.2024.3381974
Rui Guo;Xiaopeng Zhao;Liang Guo;Ruiqi Xu;Yi Liang
In recent years, complex-valued convolutional neural networks (CNNs) have emerged as a promising approach for polarimetric synthetic aperture radar (PolSAR) image segmentation by utilizing both amplitude and phase information in PolSAR data. This article introduces a complex-valued network for PolSAR image segmentation termed as complex-valued Lovász-softmax loss optimization synthetic aperture radar network (CV-LoSARNet), which is in fact a complex-valued Lovász-softmax loss optimization framework. The bilateral structure of CV-LoSARNet provides efficient feature extraction, while the complex-valued network adapting to PolSAR data can improve feature extraction capabilities. The introduced loss function combines both the Lovász-softmax loss and cross-entropy loss, which can improve the optimization objective of the segmentation. Comparative experiments conducted on E-SAR data and AIRSAR data demonstrate the superiority of the proposed network over the classical full CNN and the classic bilateral networks. Compared with the classic bilateral network, the CV-LoSARNet has improved the mean intersection over union and mean pixel accuracy of E-SAR data sets by 2.37% and 2.29%, for AIRSAR data sets, the improvement is 12.95% and 6.70%. Moreover, the segmentation performance of the proposed network on different polarimetric modes is discussed.
{"title":"A Complex-Valued PolSAR Image Segmentation Network With Lovász-Softmax Loss Optimization","authors":"Rui Guo;Xiaopeng Zhao;Liang Guo;Ruiqi Xu;Yi Liang","doi":"10.1109/JMASS.2024.3381974","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3381974","url":null,"abstract":"In recent years, complex-valued convolutional neural networks (CNNs) have emerged as a promising approach for polarimetric synthetic aperture radar (PolSAR) image segmentation by utilizing both amplitude and phase information in PolSAR data. This article introduces a complex-valued network for PolSAR image segmentation termed as complex-valued Lovász-softmax loss optimization synthetic aperture radar network (CV-LoSARNet), which is in fact a complex-valued Lovász-softmax loss optimization framework. The bilateral structure of CV-LoSARNet provides efficient feature extraction, while the complex-valued network adapting to PolSAR data can improve feature extraction capabilities. The introduced loss function combines both the Lovász-softmax loss and cross-entropy loss, which can improve the optimization objective of the segmentation. Comparative experiments conducted on E-SAR data and AIRSAR data demonstrate the superiority of the proposed network over the classical full CNN and the classic bilateral networks. Compared with the classic bilateral network, the CV-LoSARNet has improved the mean intersection over union and mean pixel accuracy of E-SAR data sets by 2.37% and 2.29%, for AIRSAR data sets, the improvement is 12.95% and 6.70%. Moreover, the segmentation performance of the proposed network on different polarimetric modes is discussed.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"100-107"},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091153","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}
Pub Date : 2024-03-23DOI: 10.1109/JMASS.2024.3397068
{"title":"IEEE Journal on Miniaturization for Air and Space Systems Special Issue on Network Intelligence for Unmanned Aerial Vehicles","authors":"","doi":"10.1109/JMASS.2024.3397068","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3397068","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"125-126"},"PeriodicalIF":0.0,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10538083","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091139","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}
Pub Date : 2024-03-23DOI: 10.1109/JMASS.2024.3397026
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2024.3397026","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3397026","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10538073","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091159","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：