Pub Date : 2023-02-22DOI: 10.1109/JMASS.2023.3235675
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2023.3235675","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3235675","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 1","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/iel7/8253411/10050211/10050213.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49953253","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 : 2023-02-22DOI: 10.1109/JMASS.2023.3247586
Cheng Fang;Yumeng Song;Fangheng Guan;Feifei Liang;Lei Yang
Unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) plays an important role in modern remote sensing for its characteristics of all weather, all day-and-night, zero casualty, flying flexibility, and low cost. However, the atmospheric turbulence will cause motion errors to UAV SAR, resulting in unmodeled phase errors. The phase errors will degrade the focusing quality of the image and bring difficulties to the recognition task. Meanwhile, it is difficult for a convolution neural network (CNN) to extract and utilize the back-scattering information for target recognition. To this end, a novel defocusing adaptive complex CNN (DA-CCNN) is proposed, which can realize the overall computation of the network in the complex-valued data domain and effectively extract the phase history information of the complex-valued data. Furthermore, it is the first time that the image entropy metric is introduced into the fully complex deep neural network to improve the focusing quality of the image and the interpretability of the network. The experiment is carried out using the benchmark dataset of MSTAR 10. In order to simulate the defocused images generated by UAV SAR and certify the robustness to phase errors, datasets with the contamination are also applied. The results show that on the benchmark data, the recognition accuracy of DA-CCNN is comparable to that of the existing methods. On the data with phase errors, DA-CCNN shows stronger robustness and higher accuracy in terms of recognition than the reported networks.
{"title":"A Robust Complex-Valued Deep Neural Network for Target Recognition of UAV SAR Imagery","authors":"Cheng Fang;Yumeng Song;Fangheng Guan;Feifei Liang;Lei Yang","doi":"10.1109/JMASS.2023.3247586","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3247586","url":null,"abstract":"Unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) plays an important role in modern remote sensing for its characteristics of all weather, all day-and-night, zero casualty, flying flexibility, and low cost. However, the atmospheric turbulence will cause motion errors to UAV SAR, resulting in unmodeled phase errors. The phase errors will degrade the focusing quality of the image and bring difficulties to the recognition task. Meanwhile, it is difficult for a convolution neural network (CNN) to extract and utilize the back-scattering information for target recognition. To this end, a novel defocusing adaptive complex CNN (DA-CCNN) is proposed, which can realize the overall computation of the network in the complex-valued data domain and effectively extract the phase history information of the complex-valued data. Furthermore, it is the first time that the image entropy metric is introduced into the fully complex deep neural network to improve the focusing quality of the image and the interpretability of the network. The experiment is carried out using the benchmark dataset of MSTAR 10. In order to simulate the defocused images generated by UAV SAR and certify the robustness to phase errors, datasets with the contamination are also applied. The results show that on the benchmark data, the recognition accuracy of DA-CCNN is comparable to that of the existing methods. On the data with phase errors, DA-CCNN shows stronger robustness and higher accuracy in terms of recognition than the reported networks.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"175-185"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964259","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 : 2023-02-14DOI: 10.1109/JMASS.2023.3244848
Bai Zhu;Liang Zhou;Simiao Pu;Jianwei Fan;Yuanxin Ye
Over the past few decades, with the rapid development of global aerospace and aerial remote sensing technology, the types of sensors have evolved from the traditional monomodal sensors (e.g., optical sensors) to the new generation of multimodal sensors (e.g., multispectral, hyperspectral, light detection and ranging (LiDAR), and synthetic aperture radar (SAR) sensors). These advanced devices can dynamically provide various and abundant multimodal remote sensing images (MRSIs) with different spatial, temporal, and spectral resolutions according to different application requirements. Since then, it is of great scientific significance to carry out the research of MRSI registration, which is a crucial step for integrating the complementary information among multimodal data and making comprehensive observations and analysis of the Earth’s surface. In this work, we will present our own contributions to the field of multimodal image registration, summarize the advantages and limitations of existing multimodal image registration methods, and then discuss the remaining challenges and make a forward-looking prospect for the future development of the field.
{"title":"Advances and Challenges in Multimodal Remote Sensing Image Registration","authors":"Bai Zhu;Liang Zhou;Simiao Pu;Jianwei Fan;Yuanxin Ye","doi":"10.1109/JMASS.2023.3244848","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3244848","url":null,"abstract":"Over the past few decades, with the rapid development of global aerospace and aerial remote sensing technology, the types of sensors have evolved from the traditional monomodal sensors (e.g., optical sensors) to the new generation of multimodal sensors (e.g., multispectral, hyperspectral, light detection and ranging (LiDAR), and synthetic aperture radar (SAR) sensors). These advanced devices can dynamically provide various and abundant multimodal remote sensing images (MRSIs) with different spatial, temporal, and spectral resolutions according to different application requirements. Since then, it is of great scientific significance to carry out the research of MRSI registration, which is a crucial step for integrating the complementary information among multimodal data and making comprehensive observations and analysis of the Earth’s surface. In this work, we will present our own contributions to the field of multimodal image registration, summarize the advantages and limitations of existing multimodal image registration methods, and then discuss the remaining challenges and make a forward-looking prospect for the future development of the field.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"165-174"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964260","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 : 2023-02-07DOI: 10.1109/JMASS.2023.3243110
Xiaomao Chen;Ying Huang;Chao He;Xianming Xie
In this article, we proposed a phase unwrapping (PU) method which combines with unscented Kalman filter, pixel classification, and an efficient path-following strategy. The characteristics of the proposed method are summarized as: 1) the path-following strategy speeds up the process of PU without decreasing the accuracy; 2) the reliability of each pixel will be graded according to the position of residue and pixel classification strategy; and 3) different from the traditional methods, the proposed method can perform filtering and PU at the same time to prevent global propagation of error. In addition, we also introduce a signal model which can obtain a similar correlation map by only using a wrapped phase image when without the primary-secondary image. The results on synthetic data and real data show that the proposed method can obtain better results.
{"title":"An Efficient Phase Unwrapping Method Based on Unscented Kalman Filter","authors":"Xiaomao Chen;Ying Huang;Chao He;Xianming Xie","doi":"10.1109/JMASS.2023.3243110","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3243110","url":null,"abstract":"In this article, we proposed a phase unwrapping (PU) method which combines with unscented Kalman filter, pixel classification, and an efficient path-following strategy. The characteristics of the proposed method are summarized as: 1) the path-following strategy speeds up the process of PU without decreasing the accuracy; 2) the reliability of each pixel will be graded according to the position of residue and pixel classification strategy; and 3) different from the traditional methods, the proposed method can perform filtering and PU at the same time to prevent global propagation of error. In addition, we also introduce a signal model which can obtain a similar correlation map by only using a wrapped phase image when without the primary-secondary image. The results on synthetic data and real data show that the proposed method can obtain better results.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"157-164"},"PeriodicalIF":0.0,"publicationDate":"2023-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964261","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 : 2023-02-06DOI: 10.1109/JMASS.2023.3242304
Xiangwei Bu;Baoxu Jiang
In this article, a fragility-free prescribed performance control (PPC) approach is proposed for unknown disturbed nonaffine systems with application to flight control of waverider aerocraft (WA). The main improvement is to develop a prescribed funnel containing additional readjusting terms, which is able to autonomously readjust its shape, such that the tracking error, whose value may increase due to parametric perturbations and external disturbances, is always constrained within the prescribed funnel, capable of guaranteeing, for any initial system condition, 1) avoidance of security fragility problem associated with the existing PPC; 2) finite-time prescribed performance concerning tracking errors; and 3) independent of affine model formulation and function approximation. Finally, the addressed design is applied to WA, and compared simulations with practical examples are presented to show the superiority.
{"title":"Fragility-Free Prescribed Performance Control Without Approximation Applied to Waverider Aerocraft","authors":"Xiangwei Bu;Baoxu Jiang","doi":"10.1109/JMASS.2023.3242304","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3242304","url":null,"abstract":"In this article, a fragility-free prescribed performance control (PPC) approach is proposed for unknown disturbed nonaffine systems with application to flight control of waverider aerocraft (WA). The main improvement is to develop a prescribed funnel containing additional readjusting terms, which is able to autonomously readjust its shape, such that the tracking error, whose value may increase due to parametric perturbations and external disturbances, is always constrained within the prescribed funnel, capable of guaranteeing, for any initial system condition, 1) avoidance of security fragility problem associated with the existing PPC; 2) finite-time prescribed performance concerning tracking errors; and 3) independent of affine model formulation and function approximation. Finally, the addressed design is applied to WA, and compared simulations with practical examples are presented to show the superiority.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"146-156"},"PeriodicalIF":0.0,"publicationDate":"2023-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964188","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 : 2023-02-01DOI: 10.1109/JMASS.2023.3241566
Ao Li;Shuaizheng Liu;Xiaoxiang Hu;Rui Guo
In this article, an improved model predictive static programming (MPSP)-based fault-tolerant control (FTC) scheme is proposed to solve the attitude tracking control problem of the hypersonic vehicle (HSV). In the field of HSV, the MPSP technique has been applied successfully to solve guidance problems of its high computational efficiency. While we try to address the attitude control problem directly using it. The attitude model of HSV with uncertainty and disturbance, together with the fault model of aircraft body injury, is constructed first. The actuator of HSV is suffering from input constraints. Then, a feasible attitude control trajectory is generated by the improved MPSP method. The methodological innovation in this article extends the MPSP technique to the direct control of the attitude of HSV both in the fixed and flexible final time. By utilizing the improved MPSP technique, the complexity of processing multiple constraints and the computation is reduced. The effectiveness of the designed FTC scheme is demonstrated through simulation under different cases with actuator constraints.
{"title":"Fault-Tolerant Attitude Control for Hypersonic Flight Vehicle Subject to Actuators Constraint: A Model Predictive Static Programming Approach","authors":"Ao Li;Shuaizheng Liu;Xiaoxiang Hu;Rui Guo","doi":"10.1109/JMASS.2023.3241566","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3241566","url":null,"abstract":"In this article, an improved model predictive static programming (MPSP)-based fault-tolerant control (FTC) scheme is proposed to solve the attitude tracking control problem of the hypersonic vehicle (HSV). In the field of HSV, the MPSP technique has been applied successfully to solve guidance problems of its high computational efficiency. While we try to address the attitude control problem directly using it. The attitude model of HSV with uncertainty and disturbance, together with the fault model of aircraft body injury, is constructed first. The actuator of HSV is suffering from input constraints. Then, a feasible attitude control trajectory is generated by the improved MPSP method. The methodological innovation in this article extends the MPSP technique to the direct control of the attitude of HSV both in the fixed and flexible final time. By utilizing the improved MPSP technique, the complexity of processing multiple constraints and the computation is reduced. The effectiveness of the designed FTC scheme is demonstrated through simulation under different cases with actuator constraints.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"136-145"},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964189","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 : 2023-01-30DOI: 10.1109/JMASS.2023.3240892
Fraj Hariz;Yassine Bouslimani;Mohsen Ghribi
Nowadays, most of the mobile mapping systems (MMSs) use global navigation satellite system (GNSS)/inertial navigation system positioning technology and 2-D sensors to construct maps, self-localize, and gather environmental information, as well. Several problems can arise with traditional architectures of these systems, especially in situations where the GNSS signal is unavailable or multiple paths are involved, such as reliability issues and poor accuracy. Moreover, their cost of up to U.S. $$ $ 2 million still poses a significant challenge for the development of new geographical information system applications. This article proposes a new design of an MMS that incorporates a 1.5-cm accurate 3-D light detection and ranging sensor and a high-accuracy positioning system based on synchronous position attitude and navigation (SPAN)/TerraStar C-PRO technologies. The extended Kalman filter was used in this research to reduce the impact of GNSS signal loss by combining the simultaneous localization and mapping (SLAM) method with SPAN/TerraStar C-PRO technologies. In the experiments, the concept of our mobile mapping platform was validated using the simulation environment Gazebo. So as to evaluate the proposed platform, a real dataset was collected from a complex environment where the GNSS signal is rarely available, exactly, from the campus of Moncton—Université de Moncton. The obtained results disclosed that the proposed platform proves its performance in terms of accuracy and reliability. Due to the integration of the SLAM algorithm with SPAN/TerraStarC-PRO technologies, the generated 3-D point cloud map includes a number of 285 million points with a mean accuracy 0.28 m even in the case of GNSS signal loss.
{"title":"High-Resolution Mobile Mapping Platform Using 15-mm Accuracy LiDAR and SPAN/TerraStar C-PRO Technologies","authors":"Fraj Hariz;Yassine Bouslimani;Mohsen Ghribi","doi":"10.1109/JMASS.2023.3240892","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3240892","url":null,"abstract":"Nowadays, most of the mobile mapping systems (MMSs) use global navigation satellite system (GNSS)/inertial navigation system positioning technology and 2-D sensors to construct maps, self-localize, and gather environmental information, as well. Several problems can arise with traditional architectures of these systems, especially in situations where the GNSS signal is unavailable or multiple paths are involved, such as reliability issues and poor accuracy. Moreover, their cost of up to U.S. \u0000<inline-formula> <tex-math>$$ $ </tex-math></inline-formula>\u00002 million still poses a significant challenge for the development of new geographical information system applications. This article proposes a new design of an MMS that incorporates a 1.5-cm accurate 3-D light detection and ranging sensor and a high-accuracy positioning system based on synchronous position attitude and navigation (SPAN)/TerraStar C-PRO technologies. The extended Kalman filter was used in this research to reduce the impact of GNSS signal loss by combining the simultaneous localization and mapping (SLAM) method with SPAN/TerraStar C-PRO technologies. In the experiments, the concept of our mobile mapping platform was validated using the simulation environment Gazebo. So as to evaluate the proposed platform, a real dataset was collected from a complex environment where the GNSS signal is rarely available, exactly, from the campus of Moncton—Université de Moncton. The obtained results disclosed that the proposed platform proves its performance in terms of accuracy and reliability. Due to the integration of the SLAM algorithm with SPAN/TerraStarC-PRO technologies, the generated 3-D point cloud map includes a number of 285 million points with a mean accuracy 0.28 m even in the case of GNSS signal loss.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"122-135"},"PeriodicalIF":0.0,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964190","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 : 2023-01-13DOI: 10.1109/JMASS.2023.3236765
Mou Ma;Shasha Xu;Junzheng Jiang
A distributed iterative method is proposed to solve the problem of node (sensor) localization for large-scale wireless sensor network (WSN), by leveraging the graph topology decomposition and gradient descent method. First, the undirected graph representing the WSN is divided into several overlapping subgraphs. Based on the decomposition subgraphs, the localization problem is splitting into a series of subproblems each of which resides on one subgraph. The iterative procedure is proceeded on the subgraphs and each iteration consists of two operators. The first operator is solving the subproblem in every subgraph by using the gradient descent method which possesses light computational cost, and the second operator is to fuse and average the local positions of nodes in the overlapping region of adjacent subgraphs. In order to enrich the available information of localization, the positions of the target nodes with high localization accuracy are used as the (pseudo) anchor nodes for the subsequent iteration. Owing to that the operators are accomplished on subgraphs with small sizes, the proposed distributed iterative method possesses low computational cost, making it suitable for large-scale WSN. Numerical results are included to demonstrate the effectiveness of the proposed localization method.
{"title":"A Distributed Gradient Descent Method for Node Localization on Large-Scale Wireless Sensor Network","authors":"Mou Ma;Shasha Xu;Junzheng Jiang","doi":"10.1109/JMASS.2023.3236765","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3236765","url":null,"abstract":"A distributed iterative method is proposed to solve the problem of node (sensor) localization for large-scale wireless sensor network (WSN), by leveraging the graph topology decomposition and gradient descent method. First, the undirected graph representing the WSN is divided into several overlapping subgraphs. Based on the decomposition subgraphs, the localization problem is splitting into a series of subproblems each of which resides on one subgraph. The iterative procedure is proceeded on the subgraphs and each iteration consists of two operators. The first operator is solving the subproblem in every subgraph by using the gradient descent method which possesses light computational cost, and the second operator is to fuse and average the local positions of nodes in the overlapping region of adjacent subgraphs. In order to enrich the available information of localization, the positions of the target nodes with high localization accuracy are used as the (pseudo) anchor nodes for the subsequent iteration. Owing to that the operators are accomplished on subgraphs with small sizes, the proposed distributed iterative method possesses low computational cost, making it suitable for large-scale WSN. Numerical results are included to demonstrate the effectiveness of the proposed localization method.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"114-121"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964191","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 : 2023-01-12DOI: 10.1109/JMASS.2023.3236302
Xinrun Tian;Shuisheng Zhou;Tiantian Meng
Matrix completion aims to recover a matrix from an incomplete matrix with many unknown elements and has wide applications in optical image recovery and machine learning, in which the popular method is to formulate it as a general low-rank matrix approximation problem. However, the traditional optimization model for matrix completion is less robust. This article proposes a robust matrix completion method in which the truncated nuclear norm regularization (TNNR) is used as the approximation of the rank function and the sum of absolute values of the row difference, which is called the total row difference, is used to constrain the oscillations of the missing matrix. By minimizing the value of the total row difference in the objective, the proposed model controls the oscillation and reduces the impact of missing parts in the process of matrix completion continuously. Furthermore, we propose a two-step iterative algorithm framework and design an ADMM algorithm for the subproblem model that includes minimizing the total row difference. Experiments show that the proposed algorithm has more stable performance and better recovery effect and obviously reduces the sensitivity of the traditional TNNR models to the truncated rank parameter.
{"title":"Robust Matrix Completion Method Based on TNNR and Total Row Difference for Recovering Optical Image","authors":"Xinrun Tian;Shuisheng Zhou;Tiantian Meng","doi":"10.1109/JMASS.2023.3236302","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3236302","url":null,"abstract":"Matrix completion aims to recover a matrix from an incomplete matrix with many unknown elements and has wide applications in optical image recovery and machine learning, in which the popular method is to formulate it as a general low-rank matrix approximation problem. However, the traditional optimization model for matrix completion is less robust. This article proposes a robust matrix completion method in which the truncated nuclear norm regularization (TNNR) is used as the approximation of the rank function and the sum of absolute values of the row difference, which is called the total row difference, is used to constrain the oscillations of the missing matrix. By minimizing the value of the total row difference in the objective, the proposed model controls the oscillation and reduces the impact of missing parts in the process of matrix completion continuously. Furthermore, we propose a two-step iterative algorithm framework and design an ADMM algorithm for the subproblem model that includes minimizing the total row difference. Experiments show that the proposed algorithm has more stable performance and better recovery effect and obviously reduces the sensitivity of the traditional TNNR models to the truncated rank parameter.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"105-113"},"PeriodicalIF":0.0,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964192","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 : 2023-01-04DOI: 10.1109/JMASS.2023.3234099
Jianhu Liang;Jiayi Sun;Xumei Zhang;Mingming Bian;Fukun Bi
Target tracking based on satellite platforms in remote sensing images plays a critical role in military and civilian fields. However, most of the traditional algorithms are still aimed at natural scenes and are difficult to be directly applied to complex satellite images with large fields of view and weak contrast. Therefore, the method of tracking satellite videos based on a multidimensional enhancement mechanism is proposed. For the problem that the complex background in satellite images, which makes the target difficult to be correctly captured and identified, the triplet attention module is introduced to enhance the significance of the target in an efficient way, thereby improving the performance of the tracking network; because of the large computational complexity of a deep convolution network, the network structure with the ghost feature is adopted, and some traditional convolution operations are replaced by simple linear operations, which improves the speed of the network. Finally, with the support of satellite remote sensing datasets, the effectiveness of this method is verified through qualitative and quantitative experiments.
{"title":"Lightweight Tracking of Satellite Video Object Based on Saliency Enhancement Mechanism","authors":"Jianhu Liang;Jiayi Sun;Xumei Zhang;Mingming Bian;Fukun Bi","doi":"10.1109/JMASS.2023.3234099","DOIUrl":"https://doi.org/10.1109/JMASS.2023.3234099","url":null,"abstract":"Target tracking based on satellite platforms in remote sensing images plays a critical role in military and civilian fields. However, most of the traditional algorithms are still aimed at natural scenes and are difficult to be directly applied to complex satellite images with large fields of view and weak contrast. Therefore, the method of tracking satellite videos based on a multidimensional enhancement mechanism is proposed. For the problem that the complex background in satellite images, which makes the target difficult to be correctly captured and identified, the triplet attention module is introduced to enhance the significance of the target in an efficient way, thereby improving the performance of the tracking network; because of the large computational complexity of a deep convolution network, the network structure with the ghost feature is adopted, and some traditional convolution operations are replaced by simple linear operations, which improves the speed of the network. Finally, with the support of satellite remote sensing datasets, the effectiveness of this method is verified through qualitative and quantitative experiments.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"4 2","pages":"100-104"},"PeriodicalIF":0.0,"publicationDate":"2023-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49964194","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：