Pub Date : 2023-01-04DOI: 10.1109/JMASS.2023.3234076
Yangte Gao;Zhihao Che;Lin Li;Jianfeng Gao;Fukun Bi
Object detection in aerial images has received extensive attention in the field of computer vision. Different from natural images, the aerial objects are usually distributed in any direction. Therefore, the existing detector usually needs more parameters to encode the direction information, resulting in a large number of redundant calculations. In addition, because an ordinary convolution neural network (CNN) does not effectively model the direction change, a large amount of the rotated data is required for the aerial detector. To solve these problems, we propose a deep spatial feature transformation network (DSFT-Net), which includes a spatial feature extraction module and a feature selection module. Specifically, we add the rotation convolution kernel to the detector to extract the directional feature of the rotated target to accurately predict the direction of the model. Then, we build a dual pyramid to separate the features in the classification and regression tasks. Finally, the polarization function is proposed to construct the critical features that are suitable for their respective tasks, achieving feature selection and more refined detection. Experiments on public remote sensing benchmarks (e.g., DOTA, HRSC2016, and UCAS-AOD) have proved the effectiveness of our detector.
{"title":"Deep Spatial Feature Transformation for Oriented Aerial Object Detection","authors":"Yangte Gao;Zhihao Che;Lin Li;Jianfeng Gao;Fukun Bi","doi":"10.1109/JMASS.2023.3234076","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3234076","url":null,"abstract":"Object detection in aerial images has received extensive attention in the field of computer vision. Different from natural images, the aerial objects are usually distributed in any direction. Therefore, the existing detector usually needs more parameters to encode the direction information, resulting in a large number of redundant calculations. In addition, because an ordinary convolution neural network (CNN) does not effectively model the direction change, a large amount of the rotated data is required for the aerial detector. To solve these problems, we propose a deep spatial feature transformation network (DSFT-Net), which includes a spatial feature extraction module and a feature selection module. Specifically, we add the rotation convolution kernel to the detector to extract the directional feature of the rotated target to accurately predict the direction of the model. Then, we build a dual pyramid to separate the features in the classification and regression tasks. Finally, the polarization function is proposed to construct the critical features that are suitable for their respective tasks, achieving feature selection and more refined detection. Experiments on public remote sensing benchmarks (e.g., DOTA, HRSC2016, and UCAS-AOD) have proved the effectiveness of our detector.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"93-99"},"PeriodicalIF":0.0,"publicationDate":"2023-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964195","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}
Though many deep-learning-based trackers for visual object tracking have achieved state-of-the-art performance on multiple benchmarks, they still suffer from significant variations in object appearance and loss of the object. To capture variations of the object appearance, this article proposes a template matching network for object tracking, where deep reinforcement learning is introduced to learn how to update the template. Specifically, the template updating problem is modeled to a Markov decision process where the proximal policy optimization (PPO) algorithm is applied to learn the policy of updating the current template. The resultant template updating policy not only considers the variations of the object but also estimates the influence of current updating for the following frames. To further handle the sudden loss of the object, a two-class redetection discriminator is proposed to conclude whether the object is lost or not. If the object is believed to be lost, a global redetection will be launched to locate the target. Experimentally, the proposed method is compared with some representative methods on dataset OTB2015, and experimental results show that our method can get competitive performance on both accuracy and frame speed.
{"title":"Visual Tracking With Reinforced Template Updating and Redetection Discriminator","authors":"Shan Zhong;Yuya Sun;Shengrong Gong;Lifan Zhou;Gengsheng Xie","doi":"10.1109/JMASS.2022.3228339","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3228339","url":null,"abstract":"Though many deep-learning-based trackers for visual object tracking have achieved state-of-the-art performance on multiple benchmarks, they still suffer from significant variations in object appearance and loss of the object. To capture variations of the object appearance, this article proposes a template matching network for object tracking, where deep reinforcement learning is introduced to learn how to update the template. Specifically, the template updating problem is modeled to a Markov decision process where the proximal policy optimization (PPO) algorithm is applied to learn the policy of updating the current template. The resultant template updating policy not only considers the variations of the object but also estimates the influence of current updating for the following frames. To further handle the sudden loss of the object, a two-class redetection discriminator is proposed to conclude whether the object is lost or not. If the object is believed to be lost, a global redetection will be launched to locate the target. Experimentally, the proposed method is compared with some representative methods on dataset OTB2015, and experimental results show that our method can get competitive performance on both accuracy and frame speed.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"70-75"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953275","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}
We investigate the issue of combating interrupted-sampling repeater jamming (ISRJ). Due to the advantages of miniaturization, lightweight, and flexibility, the ISRJ poses a great menace to radar performance through the fast sampling and forwarding of radar signals. Given this problem, we propose an electronic counter-countermeasure (ECCM) system based on the time–frequency domain. The system mines the information of radar echoes using de-chirping processing and the short-time Fourier transform (STFT). We introduce a binarization algorithm to achieve noise suppression and utilize two different features to guarantee the correct rate of target signal extraction. Simulation experiments show that our system can be effective against ISRJ. Moreover, our system still exhibits good interference suppression performance under the condition of multiple jammers, which effectively enhances the anti-jamming capability of the radar.
{"title":"Interference Countermeasure System Based on Time–Frequency Domain Characteristics","authors":"Lining Duan;Siyu Du;Yinghui Quan;Qinzhe Lv;Shuai Li;Mengdao Xing","doi":"10.1109/JMASS.2022.3229499","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3229499","url":null,"abstract":"We investigate the issue of combating interrupted-sampling repeater jamming (ISRJ). Due to the advantages of miniaturization, lightweight, and flexibility, the ISRJ poses a great menace to radar performance through the fast sampling and forwarding of radar signals. Given this problem, we propose an electronic counter-countermeasure (ECCM) system based on the time–frequency domain. The system mines the information of radar echoes using de-chirping processing and the short-time Fourier transform (STFT). We introduce a binarization algorithm to achieve noise suppression and utilize two different features to guarantee the correct rate of target signal extraction. Simulation experiments show that our system can be effective against ISRJ. Moreover, our system still exhibits good interference suppression performance under the condition of multiple jammers, which effectively enhances the anti-jamming capability of the radar.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"76-84"},"PeriodicalIF":0.0,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953274","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 : 2022-12-06DOI: 10.1109/JMASS.2022.3226771
Gang Xu;Hao Pei;Mengjie Jiang;Jianlai Chen;Hui Wang;Hui Zhang;Yanyang Liu
Benefiting from the characteristics of low-cost, small-size, and high-resolution, the millimeter-wave (mmWave) radar has been gradually applied to automotive parking assistance. In this article, a novel algorithm of automotive synthetic aperture radar (SAR) imaging is proposed for the mapping of parking places. To deal with the motion error from the inaccurate speed of the radar platform, a parametric method of sparse Bayesian learning (SBL) is presented for well-focused and high-resolution SAR imaging. Then, a watershed-based SAR image segmentation algorithm is applied to detect the vehicles, which can indicate the locations of free parking spaces. Finally, the experimental analysis using 77-GHz automotive radar data is performed to confirm the effectiveness of the proposal.
{"title":"High-Resolution mmWave SAR Imagery for Automotive Parking Assistance","authors":"Gang Xu;Hao Pei;Mengjie Jiang;Jianlai Chen;Hui Wang;Hui Zhang;Yanyang Liu","doi":"10.1109/JMASS.2022.3226771","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3226771","url":null,"abstract":"Benefiting from the characteristics of low-cost, small-size, and high-resolution, the millimeter-wave (mmWave) radar has been gradually applied to automotive parking assistance. In this article, a novel algorithm of automotive synthetic aperture radar (SAR) imaging is proposed for the mapping of parking places. To deal with the motion error from the inaccurate speed of the radar platform, a parametric method of sparse Bayesian learning (SBL) is presented for well-focused and high-resolution SAR imaging. Then, a watershed-based SAR image segmentation algorithm is applied to detect the vehicles, which can indicate the locations of free parking spaces. Finally, the experimental analysis using 77-GHz automotive radar data is performed to confirm the effectiveness of the proposal.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"54-61"},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49986622","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 : 2022-12-06DOI: 10.1109/JMASS.2022.3227018
Wenjie Shen;Yun Lin;Yang Li;Wen Hong;Yanping Wang
Multiaspect SAR has the capability of providing a high-resolution image due to its long synthetic aperture feature. However, a moving target can generate long and complex signatures in a multiaspect SAR image, which may hamper the applications like image interpretation and target detection. In this article, two methods are proposed to remove the moving target signature in a single-channel multiaspect SAR image. The two methods are all based on logarithm background subtraction. The first one is a fast scheme with a cost of reduced resolution. While the second one focuses on preserving the high resolution, it takes more time than the previous one. The first method utilizes the fact of target signal position changes in subaperture image sequence to obtain the static background. The second method combines the detection results to exclude the moving target signal in each complex-valued subaperture image, then obtaining the high resolution of static background by coherent summation. The methods are validated by synthetic and real airborne SAR data.
{"title":"Moving Targets Artifacts Removal in Multiaspect SAR Imagery Based on Logarithm Background Subtraction","authors":"Wenjie Shen;Yun Lin;Yang Li;Wen Hong;Yanping Wang","doi":"10.1109/JMASS.2022.3227018","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3227018","url":null,"abstract":"Multiaspect SAR has the capability of providing a high-resolution image due to its long synthetic aperture feature. However, a moving target can generate long and complex signatures in a multiaspect SAR image, which may hamper the applications like image interpretation and target detection. In this article, two methods are proposed to remove the moving target signature in a single-channel multiaspect SAR image. The two methods are all based on logarithm background subtraction. The first one is a fast scheme with a cost of reduced resolution. While the second one focuses on preserving the high resolution, it takes more time than the previous one. The first method utilizes the fact of target signal position changes in subaperture image sequence to obtain the static background. The second method combines the detection results to exclude the moving target signal in each complex-valued subaperture image, then obtaining the high resolution of static background by coherent summation. The methods are validated by synthetic and real airborne SAR data.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"62-69"},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49986621","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 : 2022-11-30DOI: 10.1109/JMASS.2022.3225766
Presents the 2022 author/subject index for this issue of the publication.
给出了本期出版物的2022年作者/主题索引。
{"title":"2022 Index IEEE Journal on Miniaturization for Air and Space Systems Vol. 3","authors":"","doi":"10.1109/JMASS.2022.3225766","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3225766","url":null,"abstract":"Presents the 2022 author/subject index for this issue of the publication.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"302-311"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8253411/9961123/09966946.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948498","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 : 2022-11-23DOI: 10.1109/JMASS.2022.3219013
Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
列出本刊的编辑委员会、理事会、现任工作人员、委员会成员和/或社团编辑。
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2022.3219013","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3219013","url":null,"abstract":"Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8253411/9961123/09961126.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948740","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 : 2022-11-10DOI: 10.1109/JMASS.2022.3221277
Shang-You Chiu;Katherine A. Kim
For low-Earth orbit nanosatellite development, small volume and high reliability are of primary concern. The electrical power system (EPS) is a critical subsystem that generates, stores, and distributes power within the nanosatellite. An EPS is typically made up of multiple power converters that are designed independently and then connected together. However, if the impedance interactions of the power converters are not properly analyzed, the converters can interact adversely in some conditions, leading to instability. Analyses using the impedance interaction factor and the extra element theorem are applied to the EPS. A design procedure and analysis tool, developed in MATLAB, is presented to ensure a robust EPS without converter interaction stability problems. A CubeSat EPS hardware prototype with four buck converters powered by photovoltaic panels is tested to verify the impedance analysis and stable system operation of the nanosatellite EPS.
{"title":"System Analysis and Design for Multiconverter Electrical Power Systems in Nanosatellites","authors":"Shang-You Chiu;Katherine A. Kim","doi":"10.1109/JMASS.2022.3221277","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3221277","url":null,"abstract":"For low-Earth orbit nanosatellite development, small volume and high reliability are of primary concern. The electrical power system (EPS) is a critical subsystem that generates, stores, and distributes power within the nanosatellite. An EPS is typically made up of multiple power converters that are designed independently and then connected together. However, if the impedance interactions of the power converters are not properly analyzed, the converters can interact adversely in some conditions, leading to instability. Analyses using the impedance interaction factor and the extra element theorem are applied to the EPS. A design procedure and analysis tool, developed in MATLAB, is presented to ensure a robust EPS without converter interaction stability problems. A CubeSat EPS hardware prototype with four buck converters powered by photovoltaic panels is tested to verify the impedance analysis and stable system operation of the nanosatellite EPS.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"41-53"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49986623","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 : 2022-11-01DOI: 10.1109/JMASS.2022.3218578
Wenlong Dong;Yuqi Wang;Guang-Cai Sun;Mengdao Xing
The frequency hopping (FH) signal has received much research interest due to its low interception probability. In the FH signal localization, the variation of signal frequency introduces error into localization methods involving phase or frequency information. In order to deal with the problem of positioning measurement estimation for unknown FH signal emitters, this article proposes a synthetic aperture passive positioning method. Baseband modulation of received signals is compensated by the time difference method. Then, the de-chirp method is introduced for carrier frequency estimation. The Doppler frequency of each pulse is compensated by a Doppler frequency compensation matrix, and the cost function related to the emitter position is constructed by 2-D focus results of the received signal at all frequencies. The emitter position is obtained through a gird search. Simulation and experimental data show that the proposed method is superior to several existing positioning methods especially when the signal-to-noise ratio (SNR) is low.
{"title":"Passive Localization for Frequency Hopping Signal Emitter Based on Synthetic Aperture Principle","authors":"Wenlong Dong;Yuqi Wang;Guang-Cai Sun;Mengdao Xing","doi":"10.1109/JMASS.2022.3218578","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3218578","url":null,"abstract":"The frequency hopping (FH) signal has received much research interest due to its low interception probability. In the FH signal localization, the variation of signal frequency introduces error into localization methods involving phase or frequency information. In order to deal with the problem of positioning measurement estimation for unknown FH signal emitters, this article proposes a synthetic aperture passive positioning method. Baseband modulation of received signals is compensated by the time difference method. Then, the de-chirp method is introduced for carrier frequency estimation. The Doppler frequency of each pulse is compensated by a Doppler frequency compensation matrix, and the cost function related to the emitter position is constructed by 2-D focus results of the received signal at all frequencies. The emitter position is obtained through a gird search. Simulation and experimental data show that the proposed method is superior to several existing positioning methods especially when the signal-to-noise ratio (SNR) is low.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"33-40"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953251","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}
The lidar reflective tomography (LRT) system transmits a laser signal and obtains laser reflection projections of the target, which shows great potential for further long-distance noncooperative target detection. However, the received projections are normally in an incomplete view state. Hence, in this article, an improved algebraic reconstruction technique (ART) utilizing the sparse regularization model and nonlocal means (NLMs) algorithm is introduced and proposed for LRT reconstruction to restore incomplete signals or projections. By using the designed LRT outfield system, the comparative experiments are carried out to validate the effectiveness of the proposed method. By considering different investigation states, the improved NLM-ART sparse method shows great capability for LRT of noncooperative targets in long distance.
{"title":"Lidar Reflective Tomography of the Target Under Incomplete View State","authors":"Rui Guo;Zhihan Jin;Wenbo Zhang;Yihua Hu;Zheyi Jiang;Bo Zang","doi":"10.1109/JMASS.2022.3217310","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3217310","url":null,"abstract":"The lidar reflective tomography (LRT) system transmits a laser signal and obtains laser reflection projections of the target, which shows great potential for further long-distance noncooperative target detection. However, the received projections are normally in an incomplete view state. Hence, in this article, an improved algebraic reconstruction technique (ART) utilizing the sparse regularization model and nonlocal means (NLMs) algorithm is introduced and proposed for LRT reconstruction to restore incomplete signals or projections. By using the designed LRT outfield system, the comparative experiments are carried out to validate the effectiveness of the proposed method. By considering different investigation states, the improved NLM-ART sparse method shows great capability for LRT of noncooperative targets in long distance.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"25-32"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953258","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：