Pub Date : 2022-10-26DOI: 10.1109/JMASS.2022.3217278
Xinran Liu;Luoxiao Yang;Zhongju Wang;Long Wang;Chao Huang;Zijun Zhang;Xiong Luo
Unmanned aerial vehicle (UAV)-based autonomous equipment is increasingly employed by the Internet of Things (IoT) digital infrastructure of wind farms. Counting the number of wind turbines (WTs) of UAV-captured images can significantly improve the effectiveness of UAV inspection and the efficiency of wind farm operation and maintenance. However, existing counting methods generally require expensive object position annotations for instance-level supervision as well as a huge number of images to train models. In this article, we propose a two-stage algorithm that combines vision Transformer (ViT) and ensemble learning models to estimate the number of WTs of UAV-taken images. At the first stage, a ViT-based deep neural network is developed to automatically extract high-level features of input UAV images based on the self-attention mechanism. Next, at the second stage, an ensemble learning model, incorporating the deep forest and hist gradient boosting algorithms, is utilized to estimate the counts based on the extracted features. Experimental results show that the proposed algorithm can significantly improve the accuracy compared with the commonly considered and recently reported benchmarks.
{"title":"UAV-Assisted Wind Turbine Counting With an Image-Level Supervised Deep Learning Approach","authors":"Xinran Liu;Luoxiao Yang;Zhongju Wang;Long Wang;Chao Huang;Zijun Zhang;Xiong Luo","doi":"10.1109/JMASS.2022.3217278","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3217278","url":null,"abstract":"Unmanned aerial vehicle (UAV)-based autonomous equipment is increasingly employed by the Internet of Things (IoT) digital infrastructure of wind farms. Counting the number of wind turbines (WTs) of UAV-captured images can significantly improve the effectiveness of UAV inspection and the efficiency of wind farm operation and maintenance. However, existing counting methods generally require expensive object position annotations for instance-level supervision as well as a huge number of images to train models. In this article, we propose a two-stage algorithm that combines vision Transformer (ViT) and ensemble learning models to estimate the number of WTs of UAV-taken images. At the first stage, a ViT-based deep neural network is developed to automatically extract high-level features of input UAV images based on the self-attention mechanism. Next, at the second stage, an ensemble learning model, incorporating the deep forest and hist gradient boosting algorithms, is utilized to estimate the counts based on the extracted features. Experimental results show that the proposed algorithm can significantly improve the accuracy compared with the commonly considered and recently reported benchmarks.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"18-24"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953257","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 : 2022-10-25DOI: 10.1109/JMASS.2022.3216854
Rong Li;Xianming Xie
A Gaussian particle swarm optimization-based phase unwrapping (PU) technique is presented to recover unwrapped phases reflecting the deformation or height of the observed objects from measured interferograms composed of wrapped phases. First, the Gaussian particle swarm optimization strategy is exploited into PU for measured interferograms, and a robust PU program based on the Gaussian particle filter is constructed by combining a robust phase slope estimation technique demonstrated well previously. Second, an efficient path-following approach is exploited to route the paths of PU to improve the accuracy and efficiency in PU for interferograms. Finally, the performances of the proposed method are fully demonstrated with the experiments of PU for the simulated and measured interferograms, and the advantages of this method in the accuracy of PU for interferograms are also shown, with respect to some other traditional methods and representative methods.
{"title":"A Gaussian Particle Swarm Optimization-Based Phase Unwrapping Algorithm","authors":"Rong Li;Xianming Xie","doi":"10.1109/JMASS.2022.3216854","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3216854","url":null,"abstract":"A Gaussian particle swarm optimization-based phase unwrapping (PU) technique is presented to recover unwrapped phases reflecting the deformation or height of the observed objects from measured interferograms composed of wrapped phases. First, the Gaussian particle swarm optimization strategy is exploited into PU for measured interferograms, and a robust PU program based on the Gaussian particle filter is constructed by combining a robust phase slope estimation technique demonstrated well previously. Second, an efficient path-following approach is exploited to route the paths of PU to improve the accuracy and efficiency in PU for interferograms. Finally, the performances of the proposed method are fully demonstrated with the experiments of PU for the simulated and measured interferograms, and the advantages of this method in the accuracy of PU for interferograms are also shown, with respect to some other traditional methods and representative methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"9-17"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953256","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 : 2022-10-25DOI: 10.1109/JMASS.2022.3216815
Genwang Liu;Jie Zhang;Xi Zhang;Yi Zhang;Gui Gao;Junmin Meng;Yongjun Jia;Xiaochen Wang
Synthetic aperture radar (SAR) ship target detection under nonhomogeneous sea conditions is changeable. In this article, according to the characteristics of the target and ocean during SAR imaging, the polarization-time–frequency coherent optimal detector PTFO is constructed, and then the constant false alarm rate method is used to detect ship targets with a stable scattering in SAR images. Four quad-polarimetric RADARSAT-2 data are used to analyze the ship–clutter contrast enhancement capability of PTFO quantitatively, and the appropriate number of time–frequency decompositions is determined to be 3. The proposed method can obtain an FOM of 0.95, which is better than other classical methods to control the detection accuracy and suppress the appearance of false alarm targets.
{"title":"Ship Detection in Nonhomogeneous Sea Clutter Based on Polarization-Time–Frequency Optimal Using Polarimetric SAR","authors":"Genwang Liu;Jie Zhang;Xi Zhang;Yi Zhang;Gui Gao;Junmin Meng;Yongjun Jia;Xiaochen Wang","doi":"10.1109/JMASS.2022.3216815","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3216815","url":null,"abstract":"Synthetic aperture radar (SAR) ship target detection under nonhomogeneous sea conditions is changeable. In this article, according to the characteristics of the target and ocean during SAR imaging, the polarization-time–frequency coherent optimal detector PTFO is constructed, and then the constant false alarm rate method is used to detect ship targets with a stable scattering in SAR images. Four quad-polarimetric RADARSAT-2 data are used to analyze the ship–clutter contrast enhancement capability of PTFO quantitatively, and the appropriate number of time–frequency decompositions is determined to be 3. The proposed method can obtain an FOM of 0.95, which is better than other classical methods to control the detection accuracy and suppress the appearance of false alarm targets.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"2-8"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953255","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 : 2022-10-20DOI: 10.1109/JMASS.2022.3215982
Yuqi Wang;Wenlong Dong;Guang-Cai Sun;Zijing Zhang;Mengdao Xing;Xiaoniu Yang
In passive localization, the received signal may come from multiple signal sources with different modulations. The modulations are usually resolved by high-order spectrum (HOS) processing. However, the processing causes multiple intersignal cross terms, resulting in a degradation of localization performance. To resolve the problem, this article proposes a CLEAN-based synthetic aperture passive positioning algorithm for multiple signal sources. The main idea is to locate the same modulated signal by focusing and then filtering out the located signal. Signals with the same modulation are located through the synthetic aperture passive localization method. Then, the located signals are removed and the remaining signals are recovered through inverse focusing. The multiple signals are focused, extracted, and separated according to the modulation. The effect of cross terms and multiplicative noise in the HOS is dramatically reduced. The simulation experiments show that the proposed algorithm can effectively improve localization accuracy.
{"title":"A CLEAN-Based Synthetic Aperture Passive Localization Algorithm for Multiple Signal Sources","authors":"Yuqi Wang;Wenlong Dong;Guang-Cai Sun;Zijing Zhang;Mengdao Xing;Xiaoniu Yang","doi":"10.1109/JMASS.2022.3215982","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3215982","url":null,"abstract":"In passive localization, the received signal may come from multiple signal sources with different modulations. The modulations are usually resolved by high-order spectrum (HOS) processing. However, the processing causes multiple intersignal cross terms, resulting in a degradation of localization performance. To resolve the problem, this article proposes a CLEAN-based synthetic aperture passive positioning algorithm for multiple signal sources. The main idea is to locate the same modulated signal by focusing and then filtering out the located signal. Signals with the same modulation are located through the synthetic aperture passive localization method. Then, the located signals are removed and the remaining signals are recovered through inverse focusing. The multiple signals are focused, extracted, and separated according to the modulation. The effect of cross terms and multiplicative noise in the HOS is dramatically reduced. The simulation experiments show that the proposed algorithm can effectively improve localization accuracy.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"294-301"},"PeriodicalIF":0.0,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948497","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}
Study on sea clutter is highly important in the field of maritime surveillance. The physical mechanism of sea clutter is complex and there are many influencing factors, among which the grazing angle is one of the most important. To address the problem of determining the suitability of models of sea clutter, this study performed a comprehensive goodness-of-fit (GoF) analysis of six sea clutter models using five methods at different grazing angles, bands, and azimuths. Furthermore, to improve the description of sea clutter amplitude, we proposed a new parameter representation method. The proposed new parameters can be used to analyze the characteristics of sea clutter amplitude and evaluate the GoF of sea clutter models at different grazing angles. Experimental data were obtained using airborne radar at a low grazing angle and spaceborne synthetic-aperture radar at medium–high grazing angles. The results indicate that the characteristics of sea clutter amplitude are various with different azimuths and grazing angles, whereas there are no significant differences between the ${X}$ and ${C}$ bands. In detail, ${K}$ distribution and generalized gamma distribution ( $text{G}Gamma text{D}$ ) are recommended in side-looking, while ${G}^{0}$ and ${K}$ distributions are recommended in forward-looking at low grazing angle; at medium–high grazing angle, ${K}$ , $text{G}Gamma text{D}$ , and Weibull distributions are recommended for the ${X}$ band, while ${K}$ and ${G} ^{0}$ distributions are recommended for the ${C}$ band. Compared with mean-square error, Kullback–Leibler, Bhattacharyya distance, threshold error, and graphical GoF methods, the proposed method was demonstrated to be simple and efficient in evaluating the GoF of sea clutter models.
{"title":"Modeling and Parameter Representation of Sea Clutter Amplitude at Different Grazing Angles","authors":"Chenghui Cao;Jie Zhang;Xi Zhang;Gui Gao;Yi Zhang;Junmin Meng;Genwang Liu;Zhenhua Zhang;Qianqian Han;Yongjun Jia;Xiaochen Wang","doi":"10.1109/JMASS.2022.3213170","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3213170","url":null,"abstract":"Study on sea clutter is highly important in the field of maritime surveillance. The physical mechanism of sea clutter is complex and there are many influencing factors, among which the grazing angle is one of the most important. To address the problem of determining the suitability of models of sea clutter, this study performed a comprehensive goodness-of-fit (GoF) analysis of six sea clutter models using five methods at different grazing angles, bands, and azimuths. Furthermore, to improve the description of sea clutter amplitude, we proposed a new parameter representation method. The proposed new parameters can be used to analyze the characteristics of sea clutter amplitude and evaluate the GoF of sea clutter models at different grazing angles. Experimental data were obtained using airborne radar at a low grazing angle and spaceborne synthetic-aperture radar at medium–high grazing angles. The results indicate that the characteristics of sea clutter amplitude are various with different azimuths and grazing angles, whereas there are no significant differences between the \u0000<inline-formula> <tex-math>${X}$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>${C}$ </tex-math></inline-formula>\u0000 bands. In detail, \u0000<inline-formula> <tex-math>${K}$ </tex-math></inline-formula>\u0000 distribution and generalized gamma distribution (\u0000<inline-formula> <tex-math>$text{G}Gamma text{D}$ </tex-math></inline-formula>\u0000) are recommended in side-looking, while \u0000<inline-formula> <tex-math>${G}^{0}$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>${K}$ </tex-math></inline-formula>\u0000 distributions are recommended in forward-looking at low grazing angle; at medium–high grazing angle, \u0000<inline-formula> <tex-math>${K}$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$text{G}Gamma text{D}$ </tex-math></inline-formula>\u0000, and Weibull distributions are recommended for the \u0000<inline-formula> <tex-math>${X}$ </tex-math></inline-formula>\u0000 band, while \u0000<inline-formula> <tex-math>${K}$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>${G} ^{0}$ </tex-math></inline-formula>\u0000 distributions are recommended for the \u0000<inline-formula> <tex-math>${C}$ </tex-math></inline-formula>\u0000 band. Compared with mean-square error, Kullback–Leibler, Bhattacharyya distance, threshold error, and graphical GoF methods, the proposed method was demonstrated to be simple and efficient in evaluating the GoF of sea clutter models.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"284-293"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948496","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 : 2022-10-10DOI: 10.1109/JMASS.2022.3212880
Xi Zhang;Quanfang Zhao;Gui Gao;Jie Zhang;Meng Bao;Junmin Meng
Satellite radar altimeters (RAs) can measure sea-ice thickness on a large scale. According to the assumption of isostatic equilibrium, knowing the density of water, snow, and ice is crucial to estimating the thickness of sea ice from altimeters. Therefore, using inaccurate density values to estimate sea-ice thickness from RAs will lead to unreliable results. This article proposes a method to evaluate and correct density ( $rho $ ) ratios, $rho _{w}/{(}rho _{w}-rho _{i}{)}$ and $rho _{s}/{(}rho _{w}-rho _{i}{)}$ , where subscripts ${i}$ , ${w}$ , and ${s}$ represent sea ice, water, and snow, respectively, by using sea ice freeboard of CryoSat-2 (CS-2) and Sentinel-3A (S3), Operational IceBridge ice thickness, and modified climatological snow depth data. In addition to comparing the calculated density ratio (DR) with the DR commonly used in the previous studies, we also investigate how input density parameters affect the accuracy of freeboard-to-thickness conversion of the satellite RA. Our results indicate that the $rho _{i}$ of first-year ice (FYI) region used by the ESA sea ice climate change initiative product (ESA SICCI) is generally large, whereas $rho _{s}$ is significantly small. For a more accurate inversion of Arctic sea-ice thickness, $rho _{w}/{(}rho _{w}-rho _{i}{)} = 9.01$ and $rho _{s}/{(}rho _{w}-rho _{i}{)} = 3.52$ can be used for FYI, and $rho _{w}/{(}rho _{w}-rho _{i}{)} = 7.20$ and $rho _{s}/(rho _{w}-rho _{i}) =2.30$ can be used for multiyear ice (MYI) region. Because $rho _{w}$ is relatively stable and easy to observe, the proposed method also can be used to invert sea ice density $rho _{i}$ and snow layer density $rho _{s}$ from estimated DRs.
{"title":"Impact and Correction of Sea Ice, Snow, and Seawater Density on Arctic Sea-Ice Thickness Retrieval From Ku-Band SAR Altimeters","authors":"Xi Zhang;Quanfang Zhao;Gui Gao;Jie Zhang;Meng Bao;Junmin Meng","doi":"10.1109/JMASS.2022.3212880","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3212880","url":null,"abstract":"Satellite radar altimeters (RAs) can measure sea-ice thickness on a large scale. According to the assumption of isostatic equilibrium, knowing the density of water, snow, and ice is crucial to estimating the thickness of sea ice from altimeters. Therefore, using inaccurate density values to estimate sea-ice thickness from RAs will lead to unreliable results. This article proposes a method to evaluate and correct density (\u0000<inline-formula> <tex-math>$rho $ </tex-math></inline-formula>\u0000) ratios, \u0000<inline-formula> <tex-math>$rho _{w}/{(}rho _{w}-rho _{i}{)}$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$rho _{s}/{(}rho _{w}-rho _{i}{)}$ </tex-math></inline-formula>\u0000, where subscripts \u0000<inline-formula> <tex-math>${i}$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>${w}$ </tex-math></inline-formula>\u0000, and \u0000<inline-formula> <tex-math>${s}$ </tex-math></inline-formula>\u0000 represent sea ice, water, and snow, respectively, by using sea ice freeboard of CryoSat-2 (CS-2) and Sentinel-3A (S3), Operational IceBridge ice thickness, and modified climatological snow depth data. In addition to comparing the calculated density ratio (DR) with the DR commonly used in the previous studies, we also investigate how input density parameters affect the accuracy of freeboard-to-thickness conversion of the satellite RA. Our results indicate that the \u0000<inline-formula> <tex-math>$rho _{i}$ </tex-math></inline-formula>\u0000 of first-year ice (FYI) region used by the ESA sea ice climate change initiative product (ESA SICCI) is generally large, whereas \u0000<inline-formula> <tex-math>$rho _{s}$ </tex-math></inline-formula>\u0000 is significantly small. For a more accurate inversion of Arctic sea-ice thickness, \u0000<inline-formula> <tex-math>$rho _{w}/{(}rho _{w}-rho _{i}{)} = 9.01$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$rho _{s}/{(}rho _{w}-rho _{i}{)} = 3.52$ </tex-math></inline-formula>\u0000 can be used for FYI, and \u0000<inline-formula> <tex-math>$rho _{w}/{(}rho _{w}-rho _{i}{)} = 7.20$ </tex-math></inline-formula>\u0000 and \u0000<inline-formula> <tex-math>$rho _{s}/(rho _{w}-rho _{i}) =2.30$ </tex-math></inline-formula>\u0000 can be used for multiyear ice (MYI) region. Because \u0000<inline-formula> <tex-math>$rho _{w}$ </tex-math></inline-formula>\u0000 is relatively stable and easy to observe, the proposed method also can be used to invert sea ice density \u0000<inline-formula> <tex-math>$rho _{i}$ </tex-math></inline-formula>\u0000 and snow layer density \u0000<inline-formula> <tex-math>$rho _{s}$ </tex-math></inline-formula>\u0000 from estimated DRs.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"276-283"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948495","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 : 2022-10-04DOI: 10.1109/JMASS.2022.3211496
Biao Shen;Tao Liu;Weijian Liu;Gui Gao
The acquisition and utilization of polarization information is an open topic because polarization plays a significant role in many fields, such as radar target detection, classification, recognition, synthetic aperture radar (SAR) imaging, anti-jamming, etc. Inspired by the bat sound waveform and combined with the properties of the stepped linear frequency modulation (SLFM) signal, in this article, a novel polarization waveform, namely, simultaneous SLFM (SSLFM), which can be used for small airborne and spaceborne polarimetric SAR (PolSAR) platform, is proposed. Moreover, a method based on the SSLFM signal is proposed to realize simultaneous polarization measurement and double high-resolution imaging. It is demonstrated that the method can better make use of the polarization information of echoes and obtain a better imaging effect. The feasibility of the proposed method is verified by simulation experiments.
{"title":"Simultaneous Polarization Measurement and High-Resolution Imaging Algorithm Inspired by Bat Sound Waveform","authors":"Biao Shen;Tao Liu;Weijian Liu;Gui Gao","doi":"10.1109/JMASS.2022.3211496","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3211496","url":null,"abstract":"The acquisition and utilization of polarization information is an open topic because polarization plays a significant role in many fields, such as radar target detection, classification, recognition, synthetic aperture radar (SAR) imaging, anti-jamming, etc. Inspired by the bat sound waveform and combined with the properties of the stepped linear frequency modulation (SLFM) signal, in this article, a novel polarization waveform, namely, simultaneous SLFM (SSLFM), which can be used for small airborne and spaceborne polarimetric SAR (PolSAR) platform, is proposed. Moreover, a method based on the SSLFM signal is proposed to realize simultaneous polarization measurement and double high-resolution imaging. It is demonstrated that the method can better make use of the polarization information of echoes and obtain a better imaging effect. The feasibility of the proposed method is verified by simulation experiments.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"264-275"},"PeriodicalIF":0.0,"publicationDate":"2022-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948494","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 : 2022-10-03DOI: 10.1109/JMASS.2022.3211436
Yanan Guan;Jie Zhang;Xi Zhang;Gui Gao;Junmin Meng;Genwang Liu;Chenghui Cao;Xiaochen Wang
The automatic identification system (AIS) provides detailed information about vessel movement that has gained wide application in areas such as ship behavior analysis over the past decade. Based on the AIS data in January and February of the lunar calendar in 2019 and 2020, this study analyzed the number and size of ships, the spatial distribution characteristics, such as ship position and density, ship speed, as well as the temporal characteristics of daily and monthly changes of ship flow, and then evaluated the impact of the COVID-19 epidemic on ship activities in Dongying Port waters. The results show that the number of tankers declined to a lesser extent compared to fishing and cargo ships after the outbreak of the COVID-19 epidemic. Because berthing activities would require extra operating time due to the epidemic, ships may require longer turnaround times. In general, tankers in Dongying Port waters were less affected by the epidemic than cargo and fishing ships.
{"title":"Impacts of the COVID-19 Epidemic on Ship Activity in Dongying Port Waters","authors":"Yanan Guan;Jie Zhang;Xi Zhang;Gui Gao;Junmin Meng;Genwang Liu;Chenghui Cao;Xiaochen Wang","doi":"10.1109/JMASS.2022.3211436","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3211436","url":null,"abstract":"The automatic identification system (AIS) provides detailed information about vessel movement that has gained wide application in areas such as ship behavior analysis over the past decade. Based on the AIS data in January and February of the lunar calendar in 2019 and 2020, this study analyzed the number and size of ships, the spatial distribution characteristics, such as ship position and density, ship speed, as well as the temporal characteristics of daily and monthly changes of ship flow, and then evaluated the impact of the COVID-19 epidemic on ship activities in Dongying Port waters. The results show that the number of tankers declined to a lesser extent compared to fishing and cargo ships after the outbreak of the COVID-19 epidemic. Because berthing activities would require extra operating time due to the epidemic, ships may require longer turnaround times. In general, tankers in Dongying Port waters were less affected by the epidemic than cargo and fishing ships.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"256-263"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948493","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 : 2022-10-03DOI: 10.1109/JMASS.2022.3211256
Chi Zhang;Xi Zhang;Jie Zhang;Gui Gao;Jingke Zhang;Genwang Liu;Yongjun Jia;Xiaochen Wang;Yi Zhang;Yongshou Dai
In recent years, researchers have started to apply neural networks to ship detection of synthetic aperture radar (SAR). However, SAR images are difficult to acquire and interpret manually. Sufficient training samples cannot be obtained, which limits the performance of ship detection. Therefore, data enhancement has become an active means to handle the issue of insufficient samples. To evaluate the performance of diverse data enhancement methods, a variety of data enhancement methods is used to expand the ship samples in the SAR ship detection dataset, including rotation, shift, mirror, brightening, etc. Moreover, we used the combination of diverse data enhancement methods for experiments. Experiments were performed using the SSDD dataset. Based on the experimental results, we analyze the characteristics of diverse data enhancement methods.
{"title":"Performance Evaluation of Data Enhancement Methods in SAR Ship Detection","authors":"Chi Zhang;Xi Zhang;Jie Zhang;Gui Gao;Jingke Zhang;Genwang Liu;Yongjun Jia;Xiaochen Wang;Yi Zhang;Yongshou Dai","doi":"10.1109/JMASS.2022.3211256","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3211256","url":null,"abstract":"In recent years, researchers have started to apply neural networks to ship detection of synthetic aperture radar (SAR). However, SAR images are difficult to acquire and interpret manually. Sufficient training samples cannot be obtained, which limits the performance of ship detection. Therefore, data enhancement has become an active means to handle the issue of insufficient samples. To evaluate the performance of diverse data enhancement methods, a variety of data enhancement methods is used to expand the ship samples in the SAR ship detection dataset, including rotation, shift, mirror, brightening, etc. Moreover, we used the combination of diverse data enhancement methods for experiments. Experiments were performed using the SSDD dataset. Based on the experimental results, we analyze the characteristics of diverse data enhancement methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"249-255"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948667","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 : 2022-09-30DOI: 10.1109/JMASS.2022.3208624
Ruya Xiao;Xiufeng He;Zhuang Gao;Fengyu Yao
Decorrelation is a major obstacle to the application of multitemporal interferometric synthetic aperture radar (InSAR) in areas with low coherence. Distributed scatterers (DSs) with similar backscattering in the spatial neighborhood are the key to improving the observational density and accuracy of deformation estimation in fast decorrelation regions. Phase series estimation from all possible interferograms is expected to improve the signal-to-noise ratio (SNR) and further enhance the sensitivity of deformation measurement. The coherence bias and the efficiency of the phase estimation raise concerns. In this article, we propose a computationally attractive algorithm for the interferometric phase estimation, namely alternating projection (AP), which is a combination of the alternating maximization and the projection matrix decomposition methods. The homogenous pixel selection and coherence estimation bias correction are conducted by the FaSHPS algorithm and DSIpro software toolbox. Results of simulations and real SAR data show that the proposed AP method could reconstruct credible phase series comparable to the quasi-Newton optimization algorithm [Broyden–Fletcher–Goldfarb–Shanno (BFGS)] while having three times the efficiency gain.
{"title":"Phase Estimation for Distributed Scatterers by Alternating Projection","authors":"Ruya Xiao;Xiufeng He;Zhuang Gao;Fengyu Yao","doi":"10.1109/JMASS.2022.3208624","DOIUrl":"https://doi.org/10.1109/JMASS.2022.3208624","url":null,"abstract":"Decorrelation is a major obstacle to the application of multitemporal interferometric synthetic aperture radar (InSAR) in areas with low coherence. Distributed scatterers (DSs) with similar backscattering in the spatial neighborhood are the key to improving the observational density and accuracy of deformation estimation in fast decorrelation regions. Phase series estimation from all possible interferograms is expected to improve the signal-to-noise ratio (SNR) and further enhance the sensitivity of deformation measurement. The coherence bias and the efficiency of the phase estimation raise concerns. In this article, we propose a computationally attractive algorithm for the interferometric phase estimation, namely alternating projection (AP), which is a combination of the alternating maximization and the projection matrix decomposition methods. The homogenous pixel selection and coherence estimation bias correction are conducted by the FaSHPS algorithm and DSIpro software toolbox. Results of simulations and real SAR data show that the proposed AP method could reconstruct credible phase series comparable to the quasi-Newton optimization algorithm [Broyden–Fletcher–Goldfarb–Shanno (BFGS)] while having three times the efficiency gain.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"3 4","pages":"204-210"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49948662","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：