检索结果-内蒙古大学图书馆

Spatio-Temporal Pruning for Training Ultra-Low-Latency Spiking Neural Networks in Remote Sensing Scene Classification

引用

REMOTE SENSING 2024年第17期16卷

作者： Li, Jiahao Xu, Ming Chen, He Liu, Wenchao Chen, Liang Xie, Yizhuang Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc T Beijing 100081 Peoples R China

In remote sensing scene classification (RSSC), restrictions on real-time processing on power consumption, performance, and resources necessitate the compression of neural networks. Unlike artificial neural networks (ANNs), spiking neural networks (SNNs) convey information through spikes, offering superior energy efficiency and biological plausibility. However, the high latency of SNNs restricts their practical application in RSSC. Therefore, there is an urgent need to research ultra-low-latency SNNs. As latency decreases, the performance of the SNN significantly deteriorates. To address this challenge, we propose a novel spatio-temporal pruning method that enhances the feature capture capability of ultra-low-latency SNNs. Our approach integrates spatial fundamental structures during the training process, which are subsequently pruned. We conduct a comprehensive evaluation of the impacts of these structures across classic network architectures, such as VGG and ResNet, demonstrating the generalizability of our method. Furthermore, we develop an ultra-low-latency training framework for SNNs to validate the effectiveness of our approach. In this paper, we successfully achieve high-performance ultra-low-latency SNNs with a single time step for the first time in RSSC. Remarkably, our SNN with one time step achieves at least 200 times faster inference time while maintaining a performance comparable to those of other state-of-the-art methods.

关键词： spiking neural networks ultra-low latency remote sensing scene classification

来源：评论

学校读者我要写书评

暂无评论

Satellite Component Detection Based Upon Searchable Multiview Features Mapping

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1-1页

作者： Zhang, Zipeng Wang, Wenzheng Deng, Chenwei Han, Yuqi Beijing Inst Technol Sch Informat & Elect Beijing Key Lab Embedded Real Time Informat Proc T Beijing 100081 Peoples R China

Satellite component detection (SCD) is one of the key technologies for on-orbit service (OOS) in space exploration. Unlike detection tasks on the ground, the single illumination in the space environment often leads to significant shadow occlusion when capturing satellite components from multiple viewing angles, resulting in the loss of component information. Existing component detection methods utilize this information to estimate their high-dimensional feature distributions and lack descriptions of the correlations between multiview features. To address this issue, we proposed an SCD based upon searchable multiview features mapping, which describes the distribution of satellite components by capturing both the discrimination between positive and negative samples and the commonality of intraclass components. Specifically, to enhance the connection of multiview features, orthogonal subspaces for different classes are constructed by the improved cosine distance between multiview features which is performed as a subspace metric to represent the discrimination and is used to cluster the mapped features. Besides, considering inherent errors in the mapping process, a loose constraint of the metric is introduced to search for common features, maintaining the local sparsity of multiview features. In the proposed dataset and the public dataset of satellite components, the proposed method achieved mean average precisions (mAP) of 0.878 and 0.862, respectively, outperforming existing state-of-the-art methods.

关键词： Loose constraint orthogonal subspaces satellite component detection (SCD) searchable multiview features Loose constraint orthogonal subspaces satellite component detection (SCD) searchable multiview features

来源：评论

学校读者我要写书评

暂无评论

Robust Estimation of Insect Morphological Parameters for Entomological Radar Using Multifrequency Echo Intensity- Independent Estimators

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1-1页

作者： Wang, Rui Wang, Jiangtao Li, Weidong Li, Muyang Zhang, Fan Hu, Cheng Beijing Inst Technol Radar Technol Res Inst Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Adv Technol Res Inst Jinan 250300 Peoples R China Beijing Inst Technol Key Lab Real Time Informat Proc Technol Embedded Beijing 100081 Peoples R China Beijing Inst Technol Radar Technol Res Inst Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Key Lab Real Time Informat Proc Technol Embedded Beijing 100081 Peoples R China

Insect morphological parameters, including mass and length, are crucial for species identification. Entomological radar can estimate morphological parameters by establishing mappings from insect radar cross section (RCS) estimators to them. Current high-accuracy methods relying on absolute RCS estimators are sensitive to echo intensity. When applied to radars without angle measurement capability, these methods may underestimate morphological parameters. This underestimation arises from the inability of such radars to compensate for reduced echo intensity caused by insects deviating from the beam center. A method using single-frequency echo intensity-independent estimators (EIIEs) was attempted;however, it could only estimate the mass of insects below 200 mg with limited accuracy. This article explores the use of multifrequency EIIEs (MFEIIEs) to enhance the estimation of insect mass and length. Based on the multifrequency scattering dataset for 159 insects measured in an anechoic chamber, the insect multifrequency scattering matrix (SM) was studied. The study revealed that four EIIEs, including the amplitude ratio and phase difference of SM eigenvalues, and two relative RCS features related to the shape of the insect polarization pattern, were correlated with insect mass and length with varied correlations with frequency. Subsequently, morphological parameter estimation was achieved by establishing the mappings from MFEIIEs to mass and length using a random forest algorithm. The presented dataset demonstrated that this method was suitable for insects below 1000 mg. Finally, the method's effectiveness and robustness were demonstrated through field measurements on 160 insects, which yielded mean relative estimation errors of 21.82% for mass and 13.18% for length.

关键词： Insects Radar cross-sections Accuracy Estimation Scattering Length measurement Frequency estimation Echo intensity-independent estimator (EIIE) entomological radar insect morphological parameter estimation radar cross section (RCS)

来源：评论

学校读者我要写书评

暂无评论

An ARM-FPGA Hybrid Acceleration and Fault Tolerant Technique for Phase Factor Calculation in Spaceborne Synthetic Aperture Radar Imaging

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 5059-5072页

作者： Xie, Yu Zhong, Zhihui Li, Bingyi Xie, Yizhuang Chen, Liang Chen, He Beijing Inst Technol Sch Informat & Elect Beijing Key Lab Embedded Real Time Informat Proc T Beijing 100081 Peoples R China Beijing Inst Radio Measurement Beijing 100854 Peoples R China

In the realm of real-time spaceborne synthetic aperture radar (SAR) imaging, the accurate and swift phase factors calculation (PFC) holds significant importance. This article introduces an innovative advanced RISC machines (ARM) field-programmable gate array (FPGA) hybrid acceleration technique designed to expedite the phase factor computation process of SAR imaging. By combing the strengths of ARM and FPGA, our approach achieves optimal performance. The proposed methodology strategically allocates the initial and intermediate calculations to ARM, while delegating the intricate exponential functions to FPGA. By incorporating a parallel four-channel coordinated rotation digital computer (CORDIC) structure and redundancy-based fault tolerant modules with error correction codes, the protection of soft errors is realized and the reliability is improved. By utilizing a modified three-tiered reconfigurable processing elements exchange network for fault tolerant CORDIC processors, the acceleration of computing time is realized and hardware overhead is reduced. A comprehensive prototype verification illustrates the method's efficacy for PFC in spaceborne SAR imaging. The evaluation of computational time and resource utilization unveils ARM's suitability for the initial two levels, while the complexities and precision of the third level warrant FPGA computing acceleration. Overall, this research advances a novel ARM-FPGA hybrid strategy that elevates phase factor computation in spaceborne SAR imaging, opening up avenues for efficient and dependable radar imaging applications.

关键词： Field programmable gate arrays Program processors Radar polarimetry Hardware Fault tolerant systems Fault tolerance Termination of employment Fault tolerance (FT) field programmable gate arrays (FPGA) hybrid integrated circuits (HICS) phase factor calculation (PFC) synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Learning a Robust Topological Relationship for Online Multiobject Tracking in UAV Scenarios

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷

作者： Deng, Chenwei Wu, Jiapeng Han, Yuqi Wang, Wenzheng Chanussot, Jocelyn Sch Informat & Elect Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc T Beijing 100081 Peoples R China Univ Grenoble Alpes CNRS Grenoble INP GIPSAlab F-38000 Grenoble France

Many existing multiobject tracking (MOT) methods tend to model each object's feature individually. However, under acute viewpoint variation and occlusion, there may exist significant differences between the current and historical features of objects, which easily leads to object loss. To alleviate these issues, the topological relationships (i.e., geometric shapes formed by objects) should be modeled as a supplement to individual object features to maintain stability. In this article, we propose a novel MOT framework, which consists of a frame graph and association graph, to leverage the topological relationships both spatially and temporally. Technically, the frame graph models distance and angle among objects to resist viewpoint change, while the association graph utilizes the interframe temporal consistency of topological features to recover occluded objects. Extensive experiments on mainstream datasets demonstrate the effectiveness.

关键词： Trajectory Feature extraction Shape Autonomous aerial vehicles Cameras Accuracy Topology Feature association graph neural networks multiobject tracking (MOT) topological features unmanned aerial vehicle

来源：评论

学校读者我要写书评

暂无评论

Space Target Detection Based on DBF and GRFT for Ground-Based Distributed Radar

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1-5页

作者： Li, Zhe Ding, Zegang Wang, Yinzi Sun, Yufei Li, Linghao Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing Key Lab Embedded Real Time Informat Proc T Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401331 Peoples R China

Ground-based distributed radar is a potential technique for space target detection. However, in the case of a low signal-to-noise ratio (SNR), it is difficult to achieve long-term integration due to the limited ephemeris guidance accuracy and complex motion model. To solve this problem, a space target detection algorithm based on digital beamforming (DBF) and generalized radon-Fourier transform (GRFT) is proposed in this letter. To avoid the gain loss caused by ephemeris errors, small-scale beam-searching is conducted through the DBF technique, which also enables the measurement of target angle and even angular velocity. Besides, transforming the problem of energy accumulation into parameterized model matching, the GRFT process can achieve long-term integration effectively in the case of complex motion models. The effectiveness of the algorithm is verified via real data experiments based on a ground-based distributed radar. By showing an effective 30-s integration and a computational efficiency improvement of 40%, the validation of the proposed algorithm has been proved.

关键词： Digital beamforming (DBF) generalized radon-Fourier transform (GRFT) space target detection

来源：评论

学校读者我要写书评

暂无评论

MULTI-GRAINED GLOBAL-LOCAL SEMANTIC FEATURE FUSION FOR FEW SHOT REMOTE SENSING SCENE CLASSIFICATION

MULTI-GRAINED GLOBAL-LOCAL SEMANTIC FEATURE FUSION FOR FEW S...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Liu, Yuqing Zhang, Tong Zhuang, Yin Wang, Guanqun Chen, He Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

ISBN: (纸本)9798350320107

Few-shot remote sensing scene classification aims to classify unseen scenes by using only a few labeled samples. Hence, how to set up a more effective feature description according to a few labeled samples, becomes an important issue. In this paper, in view of more complicated remote sensing scenes containing several hierarchical and coupled spatial relations (e.g., internal and external spatial contexts), which severely hinder the feature extraction under few-shot learning scenarios, a multi-grained global-local semantic feature fusion (MGGL-SFF) method is proposed for few-shot remote sensing scene classification, which can better combine the global discriminative spatial semantic features with local transferable fragment features to set a powerful prototype representation up for few shot learning. Finally, experiments are carried out on defined few-shot remote sensing scene classification benchmark, and results proved the proposed MGGL-SFF can achieve a new state-of-the-art performance.

关键词： Few-shot learning remote sensing multi-grained scene classification global-local semantic feature fusion

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain-Adaptive Object Detection via Localization Regression Alignment

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第11期35卷 15170-15181页

作者： Piao, Zhengquan Tang, Linbo Zhao, Baojun Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Adv Technol Res Inst Jinan 250300 Peoples R China Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China

Unsupervised domain-adaptive object detection uses labeled source domain data and unlabeled target domain data to alleviate the domain shift and reduce the dependence on the target domain data labels. For object detection, the features responsible for classification and localization are different. However, the existing methods basically only consider classification alignment, which is not conducive to cross-domain localization. To address this issue, in this article, we focus on the alignment of localization regression in domain-adaptive object detection and propose a novel localization regression alignment (LRA) method. The idea is that the domain-adaptive localization regression problem can be transformed into a general domain-adaptive classification problem first, and then adversarial learning is applied to the converted classification problem. Specifically, LRA first discretizes the continuous regression space, and the discrete regression intervals are treated as bins. Then, a novel binwise alignment (BA) strategy is proposed through adversarial learning. BA can further contribute to the overall cross-domain feature alignment for object detection. Extensive experiments are conducted on different detectors in various scenarios, and the state-of-the-art performance is achieved;these results demonstrate the effectiveness of our method. The code will be available at: https://***/zqpiao/LRA.

关键词： Location awareness Object detection Detectors Task analysis Feature extraction Training Data models Adversarial learning localization regression neural networks object detection unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

A Diverse Space Target Dataset With Multidebris and realistic On-Orbit Environment

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 9102-9114页

作者： Zhang, Zipeng Deng, Chenwei Deng, Zhiyuan Beijing Inst Technol Sch Informat & Elect Beijing Key Lab Embedded Real Time Informat Proc Beijing 100811 Peoples R China

As the number of space targets increases year by year, space situational awareness plays an important role in satellite security. To keep satellite secure, we use space target monitoring, removal, and avoidance to complete space situational awareness. These tasks usually use space target classification algorithms, and the algorithms should be compared fairly with a space target dataset. But at present, real data collection is difficult, and the existing simulation datasets lack some space models. These incomplete space target datasets limit the sustainable development of this field. Therefore, this article proposes a space target dataset to make up for the shortcomings of the existing space target dataset. 1) More realistic. Our dataset considers the real distribution and operation of space targets and counts their real number and orbital position. We simulate the real space target environment to ensure that the dataset can be migrated to practical applications. 2) More diverse. Our dataset includes 11 classes of satellites and 35 classes of space debris. In addition, we use a large number of lighting angles and shooting orbits for each model. 3) More reliable. In order to reduce artificial data bias, we count the attributes of the dataset to analyze the consistent distribution of attributes such as the resolution and contrast of space target images in different classes. Then, we made some targeted modifications. In addition, we propose a feature-based quantitative evaluation method for reliability, which calculates the distribution among different classes in the space target dataset.

关键词： Space vehicles Satellites Task analysis Space debris Classification algorithms Reliability Sparks Quantitative reliability evaluation space debris models space target datasets

来源：评论

学校读者我要写书评

暂无评论

A Coupled Error Self-Calibration Method for High-Speed Space Target Imaging in Stepped-Frequency Radar Based on Minimum Entropy

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第1期61卷 1090-1103页

作者： Li, Pucheng Li, Linghao Lv, Linhan Dong, Zehua Wang, Zhen Ding, Zegang Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing 10081 Peoples R China Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc T Radar Res Lab Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401331 Peoples R China

Stepped-frequency chirp radar achieves range high resolution through wideband synthesis, yet it harbors systemic errors. These errors coupled with the motion errors of high-speed space target, render error calibration more challenging and compromise the quality of imaging. To tackle this problem, this article proposes the coupled error self-calibration method for high-speed space target imaging in stepped-frequency based on minimum entropy. First, a parameterized model of echo signals incorporating complex coupled errors is established. This model not only takes into account the errors introduced by the amplitude-phase response characteristics of the stepped-frequency radar system, but also considers errors arising from the motion of high-speed targets. Then, analytical relationships between entropy and errors after range pulse compression of subband data, after 2-D imaging of subband data, and after high-resolution synthesis of all subband images are constructed. This stepwise processing strategy decomposed complex errors into three distinct components. Subsequently, employing an adaptive matrix estimation method to separately estimate and calibrate the three decoupled error components ensures a gradual improvement in imaging quality. Finally, the effectiveness of the proposed method is verified through computer simulation and a real experiment.

关键词： Radar imaging Radar Imaging Chirp Entropy Calibration Wideband Coupling error self-calibration high-speed space target imaging minimum entropy stepped-frequency chirp radar

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：