Pub Date : 2023-12-13DOI: 10.1109/JMASS.2023.3342208
Waseem Sajjad;Arooj Shafique;Rehan Mahmood
Technological innovations in small satellites especially CubeSats have become attractive because of their low development cost and numerous applications, such as Earth remote sensing, rural connectivity, and space exploration. Like many satellites, CubeSats also entails the integration of different subsystems for successful execution of the mission(s) requirements. Among these subsystems, onboard computer (OBC) is one of the integral parts of the CubeSat and its failure could result in the loss of the entire mission. This article presents a study guide to design any mission-specific OBC for CubeSats with considerations to make it reliable while assessing performance and power consumption. Reliability is addressed by electronic components selection, architectural design, and fault-tolerant techniques at both hardware and software levels. A performance enhancement methodology is also discussed by coherent selection of storage devices, interfaces, and the processing unit. Then, different hardware and software level techniques are discussed to reduce OBC power consumption. Finally, an OBC architectural design is proposed for the National CubeSat of Pakistan (ICUBE-N) while considering its reliability, low-power consumption, and enhanced performance.
{"title":"Designing of Reliable, Low-Power, and Performance-Efficient Onboard Computer Architecture for CubeSats","authors":"Waseem Sajjad;Arooj Shafique;Rehan Mahmood","doi":"10.1109/JMASS.2023.3342208","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3342208","url":null,"abstract":"Technological innovations in small satellites especially CubeSats have become attractive because of their low development cost and numerous applications, such as Earth remote sensing, rural connectivity, and space exploration. Like many satellites, CubeSats also entails the integration of different subsystems for successful execution of the mission(s) requirements. Among these subsystems, onboard computer (OBC) is one of the integral parts of the CubeSat and its failure could result in the loss of the entire mission. This article presents a study guide to design any mission-specific OBC for CubeSats with considerations to make it reliable while assessing performance and power consumption. Reliability is addressed by electronic components selection, architectural design, and fault-tolerant techniques at both hardware and software levels. A performance enhancement methodology is also discussed by coherent selection of storage devices, interfaces, and the processing unit. Then, different hardware and software level techniques are discussed to reduce OBC power consumption. Finally, an OBC architectural design is proposed for the National CubeSat of Pakistan (ICUBE-N) while considering its reliability, low-power consumption, and enhanced performance.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 2","pages":"59-72"},"PeriodicalIF":0.0,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141091152","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 : 2023-12-04DOI: 10.1109/JMASS.2023.3338388
{"title":"2023 Index IEEE Journal on Miniaturization for Air and Space Systems Vol. 4","authors":"","doi":"10.1109/JMASS.2023.3338388","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3338388","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 4","pages":"438-449"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10339681","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138485013","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 : 2023-11-28DOI: 10.1109/JMASS.2023.3330206
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2023.3330206","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3330206","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 4","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10330796","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138454413","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 : 2023-11-17DOI: 10.1109/JMASS.2023.3334149
Yuwei Lan;Taoli Yang;Yong Wang
The gravity recovery and climate experiment (GRACE) sensors observe changes in the Earth’s mass distribution between water storage compartments, estimating the terrestrial water stage (TWS). Unfortunately, the estimation is affected by noise, characterized by primary north–south-oriented stripes. The noise impact is severe in tropical areas. Existing denoising algorithms remove the stripes, but the noise removal and signal preservation can be further improved. Thus, a new 2-D frequency-domain filtering algorithm is proposed, consisting of notch filter banks and a low-pass filter. Also, the relative sum absolute difference (RSAD) is proposed to evaluate noise removal and signal preservation effectiveness. The proposed algorithm removed stripe noise and preserved signal in simulated noisy GRACE Level-2 data. The denoised results were satisfactory qualitatively and quantitatively assessed by the RSAD. In addition, the proposed algorithm outperforms three existing denoising algorithms in noise removal and signal preservation.
{"title":"A 2-D Frequency-Domain Algorithm to Remove GRACE Stripe Noise","authors":"Yuwei Lan;Taoli Yang;Yong Wang","doi":"10.1109/JMASS.2023.3334149","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3334149","url":null,"abstract":"The gravity recovery and climate experiment (GRACE) sensors observe changes in the Earth’s mass distribution between water storage compartments, estimating the terrestrial water stage (TWS). Unfortunately, the estimation is affected by noise, characterized by primary north–south-oriented stripes. The noise impact is severe in tropical areas. Existing denoising algorithms remove the stripes, but the noise removal and signal preservation can be further improved. Thus, a new 2-D frequency-domain filtering algorithm is proposed, consisting of notch filter banks and a low-pass filter. Also, the relative sum absolute difference (RSAD) is proposed to evaluate noise removal and signal preservation effectiveness. The proposed algorithm removed stripe noise and preserved signal in simulated noisy GRACE Level-2 data. The denoised results were satisfactory qualitatively and quantitatively assessed by the RSAD. In addition, the proposed algorithm outperforms three existing denoising algorithms in noise removal and signal preservation.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"51-55"},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139942773","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 : 2023-11-17DOI: 10.1109/JMASS.2023.3333833
Daylon Hester;Seokhee Han;Mark Adams
This article presents a streamlined design methodology for single-feed circularly polarized antenna arrays for CubeSats. The presented method was created with student-led teams in mind and employs a geometrically simple approach, opting for circular patches and ring-shaped feed networks instead of complex geometries. High- and low-impedance radiating elements are designed, and design restrictions are introduced such that all other geometries may be solved through a set of simple cascading equations. These deliberate choices minimize the number of design parameters and simplify the design process. Circular polarization is achieved through a multilevel implementation of sequentially arranged linearly polarized circular patches fed in a series-parallel fashion by ring-shaped feed lines of constant impedance. This article also demonstrates a $4times 4$ right-hand circularly polarized (RHCP) CubeSat downlink array antenna designed for operation in the 8025–8400-MHz Earth exploration satellite band which was developed using the proposed methodology. The antenna comprises four sequentially rotated RHCP subarrays, each consisting of four sequentially rotated linearly polarized circular patches. The antenna’s boresight RHCP gain exceeds 16.19 dBic at 8.389 GHz with a simulated 27.9% 3-dB axial ratio bandwidth, a 20° half-power beamwidth, and an aperture efficiency of 53%. The antenna has a sub-2 VSWR bandwidth of 26.6%, and its radiation efficiency ranges from 60% to 82% across the target band. Its compact size of 9 cm $times $ 9 cm enables it to fit on one face of a 10 cm $times $ 10 cm CubeSat unit.
{"title":"Design Methodology for Single-Feed Circularly Polarized X-Band Antenna Arrays for CubeSats Using Multilevel Sequential Rotation","authors":"Daylon Hester;Seokhee Han;Mark Adams","doi":"10.1109/JMASS.2023.3333833","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3333833","url":null,"abstract":"This article presents a streamlined design methodology for single-feed circularly polarized antenna arrays for CubeSats. The presented method was created with student-led teams in mind and employs a geometrically simple approach, opting for circular patches and ring-shaped feed networks instead of complex geometries. High- and low-impedance radiating elements are designed, and design restrictions are introduced such that all other geometries may be solved through a set of simple cascading equations. These deliberate choices minimize the number of design parameters and simplify the design process. Circular polarization is achieved through a multilevel implementation of sequentially arranged linearly polarized circular patches fed in a series-parallel fashion by ring-shaped feed lines of constant impedance. This article also demonstrates a \u0000<inline-formula> <tex-math>$4times 4$ </tex-math></inline-formula>\u0000 right-hand circularly polarized (RHCP) CubeSat downlink array antenna designed for operation in the 8025–8400-MHz Earth exploration satellite band which was developed using the proposed methodology. The antenna comprises four sequentially rotated RHCP subarrays, each consisting of four sequentially rotated linearly polarized circular patches. The antenna’s boresight RHCP gain exceeds 16.19 dBic at 8.389 GHz with a simulated 27.9% 3-dB axial ratio bandwidth, a 20° half-power beamwidth, and an aperture efficiency of 53%. The antenna has a sub-2 VSWR bandwidth of 26.6%, and its radiation efficiency ranges from 60% to 82% across the target band. Its compact size of 9 cm \u0000<inline-formula> <tex-math>$times $ </tex-math></inline-formula>\u0000 9 cm enables it to fit on one face of a 10 cm \u0000<inline-formula> <tex-math>$times $ </tex-math></inline-formula>\u0000 10 cm CubeSat unit.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"42-50"},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139942845","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}
Semantic segmentation of unmanned aerial vehicle (UAV) remote sensing images is a recent research hotspot, offering technical support for diverse types of UAV remote sensing missions. However, unlike general scene images, UAV remote sensing images present inherent challenges. These challenges include the complexity of backgrounds, substantial variations in target scales, and dense arrangements of small targets, which severely hinder the accuracy of semantic segmentation. To address these issues, we propose a convolutional neural network (CNN) and transformer hybrid network for semantic segmentation of UAV remote sensing images. The proposed network follows an encoder–decoder architecture that merges a transformer-based encoder with a CNN-based decoder. First, we incorporate the Swin transformer as the encoder to address the limitations of CNN in global modeling, mitigating the interference caused by complex background information. Second, to effectively handle the significant changes in target scales, we design the multiscale feature integration module (MFIM) that enhances the multiscale feature representation capability of the network. Finally, the semantic feature fusion module (SFFM) is designed to filter the redundant noise during the feature fusion process, which improves the recognition of small targets and edges. Experimental results demonstrate that the proposed method outperforms other popular methods on the UAVid and Aeroscapes datasets.
{"title":"Hybrid CNN and Transformer Network for Semantic Segmentation of UAV Remote Sensing Images","authors":"Xuanyu Zhou;Lifan Zhou;Shengrong Gong;Haizhen Zhang;Shan Zhong;Yu Xia;Yizhou Huang","doi":"10.1109/JMASS.2023.3332948","DOIUrl":"10.1109/JMASS.2023.3332948","url":null,"abstract":"Semantic segmentation of unmanned aerial vehicle (UAV) remote sensing images is a recent research hotspot, offering technical support for diverse types of UAV remote sensing missions. However, unlike general scene images, UAV remote sensing images present inherent challenges. These challenges include the complexity of backgrounds, substantial variations in target scales, and dense arrangements of small targets, which severely hinder the accuracy of semantic segmentation. To address these issues, we propose a convolutional neural network (CNN) and transformer hybrid network for semantic segmentation of UAV remote sensing images. The proposed network follows an encoder–decoder architecture that merges a transformer-based encoder with a CNN-based decoder. First, we incorporate the Swin transformer as the encoder to address the limitations of CNN in global modeling, mitigating the interference caused by complex background information. Second, to effectively handle the significant changes in target scales, we design the multiscale feature integration module (MFIM) that enhances the multiscale feature representation capability of the network. Finally, the semantic feature fusion module (SFFM) is designed to filter the redundant noise during the feature fusion process, which improves the recognition of small targets and edges. Experimental results demonstrate that the proposed method outperforms other popular methods on the UAVid and Aeroscapes datasets.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"33-41"},"PeriodicalIF":0.0,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135759026","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 : 2023-11-03DOI: 10.1109/JMASS.2023.3330014
Wei Shi;Mingliang Chen;Junchao Zhang
Small and dim target detection is a longstanding challenge in computer vision because of conditions, such as target scale variations and strong clutter. This article provides an innovative and efficient algorithm for detecting small targets. By utilizing a novel approach, our algorithm achieves superior performance in the presence of challenging environmental conditions, it suppresses the background and enhances the target via gradient features guided local contrast (GFLC). To begin, we leverage the gradient properties of the image to mitigate the background noise. Subsequently, local contrast features are utilized to accentuate the target area in the original image. The fusion map is then computed by combining the above features. Finally, the targets are efficiently extracted from the fusion map via segmentation. The findings indicate that the algorithm we presented achieves outstanding accuracy in detecting targets in images with intricate backgrounds and low contrast, and it effectively suppresses background noise.
{"title":"Dim and Small Target Detection Method via Gradient Features Guided Local Contrast","authors":"Wei Shi;Mingliang Chen;Junchao Zhang","doi":"10.1109/JMASS.2023.3330014","DOIUrl":"10.1109/JMASS.2023.3330014","url":null,"abstract":"Small and dim target detection is a longstanding challenge in computer vision because of conditions, such as target scale variations and strong clutter. This article provides an innovative and efficient algorithm for detecting small targets. By utilizing a novel approach, our algorithm achieves superior performance in the presence of challenging environmental conditions, it suppresses the background and enhances the target via gradient features guided local contrast (GFLC). To begin, we leverage the gradient properties of the image to mitigate the background noise. Subsequently, local contrast features are utilized to accentuate the target area in the original image. The fusion map is then computed by combining the above features. Finally, the targets are efficiently extracted from the fusion map via segmentation. The findings indicate that the algorithm we presented achieves outstanding accuracy in detecting targets in images with intricate backgrounds and low contrast, and it effectively suppresses background noise.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"27-32"},"PeriodicalIF":0.0,"publicationDate":"2023-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134981548","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 : 2023-10-31DOI: 10.1109/JMASS.2023.3328879
Yunjie Liu;Anne Bettens;Xiaofeng Wu
Vision-based pose estimation is fundamental for close proximity satellite operations, especially for on-orbit service missions. While neural network methods for pose estimation are becoming more widespread, traditional computer vision techniques still offer unique benefits in terms of efficiency and reliability. This article presents an algorithm that uses feature point detection and random sample consensus (RANSAC) as a solution for satellite pose estimation. The proposed algorithm requires no initialization, previous pose, or motion state information, which significantly reduces processing time. A comparison was conducted between the proposed algorithm and neural-network-based approaches. It was found that the proposed method only needs minimal training samples and memory to produce high-precision pose estimation, making it appropriate for use on small satellite platforms, such as CubeSats. Moreover, the satellite pose estimation implementation was achieved through hardware/software (HW/SW) co-design, by implementing the feature point detection module on a field-programmable gate array (FPGA). This approach takes full advantage of an FPGA’s pipeline structure and the ability for parallel operation of software and hardware. Consequently, it offers an efficient solution for satellite pose estimation with improved operational efficiency, resource utilization, and low power consumption.
{"title":"Hardware/Software Co-Design of a Feature-Based Satellite Pose Estimation System","authors":"Yunjie Liu;Anne Bettens;Xiaofeng Wu","doi":"10.1109/JMASS.2023.3328879","DOIUrl":"10.1109/JMASS.2023.3328879","url":null,"abstract":"Vision-based pose estimation is fundamental for close proximity satellite operations, especially for on-orbit service missions. While neural network methods for pose estimation are becoming more widespread, traditional computer vision techniques still offer unique benefits in terms of efficiency and reliability. This article presents an algorithm that uses feature point detection and random sample consensus (RANSAC) as a solution for satellite pose estimation. The proposed algorithm requires no initialization, previous pose, or motion state information, which significantly reduces processing time. A comparison was conducted between the proposed algorithm and neural-network-based approaches. It was found that the proposed method only needs minimal training samples and memory to produce high-precision pose estimation, making it appropriate for use on small satellite platforms, such as CubeSats. Moreover, the satellite pose estimation implementation was achieved through hardware/software (HW/SW) co-design, by implementing the feature point detection module on a field-programmable gate array (FPGA). This approach takes full advantage of an FPGA’s pipeline structure and the ability for parallel operation of software and hardware. Consequently, it offers an efficient solution for satellite pose estimation with improved operational efficiency, resource utilization, and low power consumption.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"16-26"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262846","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 : 2023-10-26DOI: 10.1109/JMASS.2023.3327721
Yujuan Cui
To solve the task assignment problem of heterogeneous multi-unmanned aerial vehicle (UAV) with different loads, an improved monkey swarm algorithm is proposed. First, the complex combat tasks are divided into three types of subtasks, and the multi-UAV task assignment model is established based on the performance of UAVs with specific loads. Second, an improved chaotic self-adapting monkey algorithm (ICSAMA) is proposed by introducing chaos optimization into the monkey swarm algorithm through the adaptive mechanism. The optimization ability of the improved algorithm is verified by the classical benchmark function containing single/multipeaks. Finally, taking the actual heterogeneous multi-UAV task planning problem as an example, ICSAMA is applied to solve it. The simulation results show that ICSAMA has higher convergence accuracy and robustness than the standard monkey swarm algorithm.
{"title":"An Improved Chaotic Self-Adapting Monkey Algorithm for Multi-UAV Task Assignment","authors":"Yujuan Cui","doi":"10.1109/JMASS.2023.3327721","DOIUrl":"10.1109/JMASS.2023.3327721","url":null,"abstract":"To solve the task assignment problem of heterogeneous multi-unmanned aerial vehicle (UAV) with different loads, an improved monkey swarm algorithm is proposed. First, the complex combat tasks are divided into three types of subtasks, and the multi-UAV task assignment model is established based on the performance of UAVs with specific loads. Second, an improved chaotic self-adapting monkey algorithm (ICSAMA) is proposed by introducing chaos optimization into the monkey swarm algorithm through the adaptive mechanism. The optimization ability of the improved algorithm is verified by the classical benchmark function containing single/multipeaks. Finally, taking the actual heterogeneous multi-UAV task planning problem as an example, ICSAMA is applied to solve it. The simulation results show that ICSAMA has higher convergence accuracy and robustness than the standard monkey swarm algorithm.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 1","pages":"9-15"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134884344","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}
Recently, inverse synthetic aperture radar (ISAR) image recognition using deep learning (DL) technology is developed rapidly. However, the imaging and recognition processing is independent of each other, and the recognition network cannot fully capture target features from the radar data. Accordingly, this article proposes an integrated convolution network for ISAR imaging and target recognition, named IITR-Net. In the scheme, a DL imaging module is designed for ISAR imaging instead of using the traditional imaging algorithms, which can be cascaded with the recognition network. Thus, the proposed IITR-Net can realize the end-to-end training using the echo data as input. Moreover, the joint backpropagation process is derived for learnable parameters of the imaging module. In the experimental analysis, the proposed IITR-Net can achieve higher classification accuracy than current recognition frameworks. It implies that the IITR-Net can learn more deep features of the target, which improves the performance of recognition.
{"title":"Integrated Convolution Network for ISAR Imaging and Target Recognition","authors":"Haoze Du;Peishuang Ni;Jianlai Chen;Shuai Ma;Hui Zhang;Gang Xu","doi":"10.1109/JMASS.2023.3325526","DOIUrl":"10.1109/JMASS.2023.3325526","url":null,"abstract":"Recently, inverse synthetic aperture radar (ISAR) image recognition using deep learning (DL) technology is developed rapidly. However, the imaging and recognition processing is independent of each other, and the recognition network cannot fully capture target features from the radar data. Accordingly, this article proposes an integrated convolution network for ISAR imaging and target recognition, named IITR-Net. In the scheme, a DL imaging module is designed for ISAR imaging instead of using the traditional imaging algorithms, which can be cascaded with the recognition network. Thus, the proposed IITR-Net can realize the end-to-end training using the echo data as input. Moreover, the joint backpropagation process is derived for learnable parameters of the imaging module. In the experimental analysis, the proposed IITR-Net can achieve higher classification accuracy than current recognition frameworks. It implies that the IITR-Net can learn more deep features of the target, which improves the performance of recognition.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 4","pages":"431-437"},"PeriodicalIF":0.0,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135009516","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}
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：