首页 > 最新文献

2022 5th International Conference on Information Communication and Signal Processing (ICICSP)最新文献

英文 中文
Compatible Sliding-Windows Algorithm for Vessel Trajectory Compression 船舶轨迹压缩兼容滑动窗口算法
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050669
Li Hua, Zhang Xiaojun
With the development of marine economy and data positioning technology, A large amount of vessel trajectory data has been generated. Data compression has become the key issue in the research of vessel trajectory big data. Since the compression rate of the existing vessel trajectory compression algorithms was not adjustable, we proposed a vessel trajectory compression algorithm with adjustable compression rate based on Sliding-Windows(SW) algorithm. The main idea was to adjust the compression rate by dynamically updating the vertical Euclidean distance threshold. The proposed algorithm could adapt to the dynamic change of channel capacity by dynamically adjusting the compression rate in online compression. The simulation results showed that compared with the traditional SW algorithm, the proposed algorithm not only realized the dynamic adjustment of compression rate, but also the compression error was less than that of the SW algorithm. Meanwhile the increase of computational complexity was almost negligible. This algorithm could also be used for online compression of other kinds of trajectory data.
随着海洋经济和数据定位技术的发展,产生了大量的船舶轨迹数据。数据压缩已成为船舶轨迹大数据研究的关键问题。针对现有船舶轨迹压缩算法压缩率不可调的问题,提出了一种基于滑动窗口(SW)算法压缩率可调的船舶轨迹压缩算法。其主要思想是通过动态更新垂直欧氏距离阈值来调整压缩率。该算法通过动态调整在线压缩中的压缩率来适应信道容量的动态变化。仿真结果表明,与传统的SW算法相比,该算法不仅实现了压缩率的动态调节,而且压缩误差小于SW算法。同时,计算复杂度的增加几乎可以忽略不计。该算法也可用于其他类型轨迹数据的在线压缩。
{"title":"Compatible Sliding-Windows Algorithm for Vessel Trajectory Compression","authors":"Li Hua, Zhang Xiaojun","doi":"10.1109/ICICSP55539.2022.10050669","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050669","url":null,"abstract":"With the development of marine economy and data positioning technology, A large amount of vessel trajectory data has been generated. Data compression has become the key issue in the research of vessel trajectory big data. Since the compression rate of the existing vessel trajectory compression algorithms was not adjustable, we proposed a vessel trajectory compression algorithm with adjustable compression rate based on Sliding-Windows(SW) algorithm. The main idea was to adjust the compression rate by dynamically updating the vertical Euclidean distance threshold. The proposed algorithm could adapt to the dynamic change of channel capacity by dynamically adjusting the compression rate in online compression. The simulation results showed that compared with the traditional SW algorithm, the proposed algorithm not only realized the dynamic adjustment of compression rate, but also the compression error was less than that of the SW algorithm. Meanwhile the increase of computational complexity was almost negligible. This algorithm could also be used for online compression of other kinds of trajectory data.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116049951","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}
引用次数: 0
A Robust Interference Suppression Method Based on FDA-MIMO Radar 基于FDA-MIMO雷达的鲁棒干扰抑制方法
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050656
Zhixia Wu, Shengqi Zhu, Jingwei Xu, Lan Lan, Mengdi Zhang, Ximin Li
In the issue of interference suppression, the performance of traditional adaptive methods will decrease when mainlobe interference and sidelobe interference have angle error. To this end, a robust adaptive beamforming technique based on frequency diversity array (FDA) multiple-input multiple-output (MIMO) is proposed in this work. Firstly, preprocessing in data domain is adopted for mainlobe interference cancellation. Then, the sidelobe interference is suppressed in the receiving dimension. Finally, robust adaptive beamforming method is applied to suppress sidelobe interference. Simulation results show the effectiveness of the proposed algorithm.
在干扰抑制问题上,当主瓣干扰和副瓣干扰存在角度误差时,传统自适应方法的性能会下降。为此,本文提出了一种基于频率分集阵列(FDA)多输入多输出(MIMO)的鲁棒自适应波束形成技术。首先,对主瓣干扰进行数据域预处理。然后,在接收维上抑制副瓣干扰。最后,采用鲁棒自适应波束形成方法抑制副瓣干扰。仿真结果表明了该算法的有效性。
{"title":"A Robust Interference Suppression Method Based on FDA-MIMO Radar","authors":"Zhixia Wu, Shengqi Zhu, Jingwei Xu, Lan Lan, Mengdi Zhang, Ximin Li","doi":"10.1109/ICICSP55539.2022.10050656","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050656","url":null,"abstract":"In the issue of interference suppression, the performance of traditional adaptive methods will decrease when mainlobe interference and sidelobe interference have angle error. To this end, a robust adaptive beamforming technique based on frequency diversity array (FDA) multiple-input multiple-output (MIMO) is proposed in this work. Firstly, preprocessing in data domain is adopted for mainlobe interference cancellation. Then, the sidelobe interference is suppressed in the receiving dimension. Finally, robust adaptive beamforming method is applied to suppress sidelobe interference. Simulation results show the effectiveness of the proposed algorithm.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122796236","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}
引用次数: 0
Passive Detection Method Based on Non-cooperative Underwater Acoustic Pulse Signal 基于非合作水声脉冲信号的被动探测方法
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050665
Cheng Ken, Wang Fangyong, Du Shuanping
Non-cooperative passive detection is a new type of underwater acoustic detection technology, which originated in the field of radar. It detects the target scattered echoes through active signals emitted by non-cooperative sources. Since this mode can perform high-gain detection of long-distance targets without transmitting a detection signal, it has great development prospects. In this paper, a target detection method based on non-cooperative pulse signal is proposed, and the non-cooperative transmitted signal is reconstructed by fractional Fourier transform (FRFT) as a matched filter template. Taking the emission sound source as the positioning assistant point, the position of the assistant point is determined by using the dual-array positioning technology, and the target is measured by calculating the relative positional relationship between the assistant point and the target. The simulation experiments show that the non-cooperative target positioning technology used in this paper has obvious advantages compared with the traditional dual-array passive positioning technology. The mean positioning error of this method for passive targets at a distance of 15km is less than 5%.
非合作被动探测是一种新型的水声探测技术,起源于雷达领域。它通过非合作源发出的主动信号检测目标散射回波。由于该模式可以在不发射探测信号的情况下对远距离目标进行高增益探测,因此具有很大的发展前景。提出了一种基于非合作脉冲信号的目标检测方法,利用分数阶傅立叶变换(FRFT)作为匹配滤波模板重构非合作传输信号。以发射声源为定位辅助点,利用双阵列定位技术确定辅助点的位置,通过计算辅助点与目标的相对位置关系对目标进行测量。仿真实验表明,与传统的双阵列无源定位技术相比,本文采用的非合作目标定位技术具有明显的优势。该方法对15km范围内被动目标的平均定位误差小于5%。
{"title":"Passive Detection Method Based on Non-cooperative Underwater Acoustic Pulse Signal","authors":"Cheng Ken, Wang Fangyong, Du Shuanping","doi":"10.1109/ICICSP55539.2022.10050665","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050665","url":null,"abstract":"Non-cooperative passive detection is a new type of underwater acoustic detection technology, which originated in the field of radar. It detects the target scattered echoes through active signals emitted by non-cooperative sources. Since this mode can perform high-gain detection of long-distance targets without transmitting a detection signal, it has great development prospects. In this paper, a target detection method based on non-cooperative pulse signal is proposed, and the non-cooperative transmitted signal is reconstructed by fractional Fourier transform (FRFT) as a matched filter template. Taking the emission sound source as the positioning assistant point, the position of the assistant point is determined by using the dual-array positioning technology, and the target is measured by calculating the relative positional relationship between the assistant point and the target. The simulation experiments show that the non-cooperative target positioning technology used in this paper has obvious advantages compared with the traditional dual-array passive positioning technology. The mean positioning error of this method for passive targets at a distance of 15km is less than 5%.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122883224","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}
引用次数: 0
RIS-Assisted Radar NLOS Target Detection ris辅助雷达NLOS目标探测
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050582
Jun-qing Ye, Yi-Hao Peng, Peichang Zhang, Qiang Li, Lei Huang
Reconfigurable Intelligent surface (RIS) has been envisioned as a promising technique for the 6th generation (6G) communications. Generally, a RIS is consist of a number of reflective elements that collaboratively adjust the direction of incident signals, and is considered to have the advantages of combating fading and shadowing problems in communication systems. In this article, by exploiting these RIS advantages, we propose to utilize the concept of RIS for the non-line-of-sight (NLOS) target radar detection. More specifically, we opt for using semi-definite relaxing (SDR) to obtain the optimal phase shift of RIS for each detection angle to build a code-book for all the optimal phase shifts, which can then be used for detecting the direction of target. The Doppler frequency shift can also be obtained via processing the echo with maximum power. Simulation results show that RIS is capable of significantly improving the coverage of radar detection.
可重构智能表面(RIS)已被设想为第六代(6G)通信的一种有前途的技术。通常,RIS由许多反射元件组成,这些反射元件协同调整入射信号的方向,并且被认为具有对抗通信系统中的衰落和阴影问题的优点。在本文中,通过利用RIS的这些优势,我们建议将RIS的概念用于非视距(NLOS)目标雷达探测。更具体地说,我们选择使用半确定松弛(SDR)来获得每个探测角度下RIS的最优相移,并为所有最优相移构建代码本,然后用于目标方向的检测。用最大功率处理回波也可以得到多普勒频移。仿真结果表明,RIS能够显著提高雷达探测的覆盖范围。
{"title":"RIS-Assisted Radar NLOS Target Detection","authors":"Jun-qing Ye, Yi-Hao Peng, Peichang Zhang, Qiang Li, Lei Huang","doi":"10.1109/ICICSP55539.2022.10050582","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050582","url":null,"abstract":"Reconfigurable Intelligent surface (RIS) has been envisioned as a promising technique for the 6th generation (6G) communications. Generally, a RIS is consist of a number of reflective elements that collaboratively adjust the direction of incident signals, and is considered to have the advantages of combating fading and shadowing problems in communication systems. In this article, by exploiting these RIS advantages, we propose to utilize the concept of RIS for the non-line-of-sight (NLOS) target radar detection. More specifically, we opt for using semi-definite relaxing (SDR) to obtain the optimal phase shift of RIS for each detection angle to build a code-book for all the optimal phase shifts, which can then be used for detecting the direction of target. The Doppler frequency shift can also be obtained via processing the echo with maximum power. Simulation results show that RIS is capable of significantly improving the coverage of radar detection.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122944245","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}
引用次数: 0
A Sparse Real Time Acoustic Holography Method for Nonstationary Acoustic Source Reconstruction 一种用于非平稳声源重建的稀疏实时声全息方法
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050652
Xingguo Chen, Lin Geng, Geoffrey J. Zhang
A sparse real-time near-field acoustic holography method is proposed to precisely and stably reconstruct a transient sound field. In the proposed method, by using a time-domain impulse response function, a time domain convolution equation between the time-wavenumber pressure spectra on the hologram and reconstruction planes is first established. Then, for obtaining the time-wavenumber pressure spectrum on the reconstruction plane, a smoothed $ell_{0}$ -norm optimization algorithm is applied to solve the serious ill-conditioned problem in the inverse process. The key of solving this problem is to approximate replace the discontinuous $ell_{0}$ -norm by using a suitable continuous Gaussian function family, and the steepest ascent algorithm is introduced to minimize the continuous function for obtaining the optimal solution. Finally, the pressure time-wavenumber spectra on the reconstruction plane at all wavenumbers for all times are solved, and the corresponding time-dependent pressures are acquired by the two-dimensional inverse Fourier transform. A numerical simulation with a baffled planar piston is conducted to observe the performance of the proposed method. The simulation results prove that the proposed method can accurately reconstruct the transient sound field. The reconstruction results are also compared to those of real-time near-field acoustic holography with Tikhonov regularization and YALL1 modal to verify the superiority of the proposed method.
为了精确稳定地重建瞬态声场,提出了一种稀疏实时近场声全息方法。该方法首先利用时域脉冲响应函数,建立了全息图上的时间波数压力谱与重建面之间的时域卷积方程。然后,为了获得重构平面上的时间波数压力谱,采用光滑的$ell_{0}$范数优化算法解决逆过程中的严重病态问题。解决该问题的关键是用合适的连续高斯函数族近似代替不连续的$ell_{0}$ -范数,并引入最陡上升算法对连续函数进行最小化,从而得到最优解。最后,对重构平面上各时刻各波数下的压力时间波数谱进行求解,并通过二维傅里叶反变换得到相应的随时间变化的压力。最后以平面折板活塞为例进行了数值模拟,验证了该方法的有效性。仿真结果表明,该方法能够准确地重建瞬态声场。并将重建结果与Tikhonov正则化和YALL1模态实时近场声全息的重建结果进行了比较,验证了所提方法的优越性。
{"title":"A Sparse Real Time Acoustic Holography Method for Nonstationary Acoustic Source Reconstruction","authors":"Xingguo Chen, Lin Geng, Geoffrey J. Zhang","doi":"10.1109/ICICSP55539.2022.10050652","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050652","url":null,"abstract":"A sparse real-time near-field acoustic holography method is proposed to precisely and stably reconstruct a transient sound field. In the proposed method, by using a time-domain impulse response function, a time domain convolution equation between the time-wavenumber pressure spectra on the hologram and reconstruction planes is first established. Then, for obtaining the time-wavenumber pressure spectrum on the reconstruction plane, a smoothed $ell_{0}$ -norm optimization algorithm is applied to solve the serious ill-conditioned problem in the inverse process. The key of solving this problem is to approximate replace the discontinuous $ell_{0}$ -norm by using a suitable continuous Gaussian function family, and the steepest ascent algorithm is introduced to minimize the continuous function for obtaining the optimal solution. Finally, the pressure time-wavenumber spectra on the reconstruction plane at all wavenumbers for all times are solved, and the corresponding time-dependent pressures are acquired by the two-dimensional inverse Fourier transform. A numerical simulation with a baffled planar piston is conducted to observe the performance of the proposed method. The simulation results prove that the proposed method can accurately reconstruct the transient sound field. The reconstruction results are also compared to those of real-time near-field acoustic holography with Tikhonov regularization and YALL1 modal to verify the superiority of the proposed method.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124884517","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}
引用次数: 0
High-Resolution Imaging from Gapped Data Based on Fast Sparse Bayesian Learning 基于快速稀疏贝叶斯学习的缺口数据高分辨率成像
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050620
Yuanyuan Wang, Haosheng Fu, Fengzhou Dai
High-resolution imaging from gapped data has become a research hotspot in radar imaging field. Among many imaging algorithms, sparse Bayesian learning (SBL) is more robust and has greater estimation accuracy, which attracts active interest from researchers. Unfortunately, the inversion and multiplying operations are involved in each iteration of SBL lead to heavy computational complexity when they are implemented directly. In this paper, we propose a fast Fourier dictionary (FD)-based SBL algorithm to solve high-resolution imaging from gapped data, greatly reducing the calculation cost. Finally, the experimental results verify the effectiveness of the proposed method.
空白数据的高分辨率成像已成为雷达成像领域的研究热点。在众多成像算法中,稀疏贝叶斯学习算法(SBL)鲁棒性强,估计精度高,引起了研究人员的广泛关注。遗憾的是,SBL的每次迭代都涉及到反转和乘法运算,直接实现时计算复杂度很高。本文提出了一种基于快速傅立叶字典(FD)的SBL算法,从间隙数据中求解高分辨率成像,大大降低了计算成本。最后,通过实验验证了所提方法的有效性。
{"title":"High-Resolution Imaging from Gapped Data Based on Fast Sparse Bayesian Learning","authors":"Yuanyuan Wang, Haosheng Fu, Fengzhou Dai","doi":"10.1109/ICICSP55539.2022.10050620","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050620","url":null,"abstract":"High-resolution imaging from gapped data has become a research hotspot in radar imaging field. Among many imaging algorithms, sparse Bayesian learning (SBL) is more robust and has greater estimation accuracy, which attracts active interest from researchers. Unfortunately, the inversion and multiplying operations are involved in each iteration of SBL lead to heavy computational complexity when they are implemented directly. In this paper, we propose a fast Fourier dictionary (FD)-based SBL algorithm to solve high-resolution imaging from gapped data, greatly reducing the calculation cost. Finally, the experimental results verify the effectiveness of the proposed method.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125077154","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}
引用次数: 0
Adaptive Altitude Measurement Based on Digital Elevation Model in VHF Array Radar 基于数字高程模型的甚高频阵雷达自适应高度测量
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050571
Xu Jin, Zhu Wei, Ding Shengyao, Hu Kunjiao
The multi-path signal and the direct signal, lying within a beam-width of the receiving antenna, are highly correlated, which cause badly effect to the performance of low-angle altitude measurement for very high frequency (VHF) radar. A novel adaptive altitude measurement is proposed. Combine digital elevation model (DEM) with distributed sources model, a multipath signal model was constructed which is much closer to the practical rough reflection surface. The height of target was obtained through multi-dimension alternating projection and synthesized vector maximum likelihood algorithm. Simulation results and the measured data processing demonstrate the validity and feasibility of the proposed method.
接收天线波束宽度范围内的多径信号与直接信号高度相关,严重影响甚高频雷达低角度测高性能。提出了一种新的自适应高度测量方法。将数字高程模型(DEM)与分布式源模型相结合,构建了更接近实际粗糙反射面的多径信号模型。通过多维交替投影和合成向量极大似然算法获得目标高度。仿真结果和实测数据处理验证了该方法的有效性和可行性。
{"title":"Adaptive Altitude Measurement Based on Digital Elevation Model in VHF Array Radar","authors":"Xu Jin, Zhu Wei, Ding Shengyao, Hu Kunjiao","doi":"10.1109/ICICSP55539.2022.10050571","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050571","url":null,"abstract":"The multi-path signal and the direct signal, lying within a beam-width of the receiving antenna, are highly correlated, which cause badly effect to the performance of low-angle altitude measurement for very high frequency (VHF) radar. A novel adaptive altitude measurement is proposed. Combine digital elevation model (DEM) with distributed sources model, a multipath signal model was constructed which is much closer to the practical rough reflection surface. The height of target was obtained through multi-dimension alternating projection and synthesized vector maximum likelihood algorithm. Simulation results and the measured data processing demonstrate the validity and feasibility of the proposed method.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121986634","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}
引用次数: 0
Multi-scale Attention Adaptive Network for Object Detection in Remote Sensing Images 基于多尺度注意力自适应网络的遥感图像目标检测
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050627
Qixi Tan, W. Xie, Haojin Tang, Yanshan Li
Remote sensing images (RSI) have a large range of variations in the aspect of inter- and intra-class size variability across objects. As a key technology in the field of RSI processing, RSI object detection has been widely applied. Multilevel features fusion network is commonly used to improve the performance of object detection. However, the existing multilevel feature fusion networks for RSI lack the ability to combine global information. Aiming at this problem, A multi-scale attention adaptive network (MA2Net) is proposed to object detection in RSI. The main contributions of this paper are twofold. Firstly, a multi-scale attention adaptive network is designed to adaptively integrate the multilevel features. This network is composed of integrating (IG) block, channel self-attention (CS) block, and adaptive fusion (AF) block. Specifically, IG is designed to transform the multi-level features into an intermediate size. The CS block is an embedded gaussian self-attention module used to model the relationship between the feature channels. AF is developed to learn the multilevel expression of self-attention features to obtain multi-scale feature maps. Secondly, to achieve a balance between multi-task and higher accuracy, a feature align head is utilized to correctly locate and classify objects. The experimental results on DIOR show that our network can achieve higher detection accuracy than the state-of-the-art RSI object detector.
遥感图像(RSI)在不同对象的类间和类内大小变异性方面具有很大的变化范围。作为RSI处理领域的一项关键技术,RSI目标检测得到了广泛的应用。多层次特征融合网络是提高目标检测性能的常用方法。然而,现有的RSI多层特征融合网络缺乏整合全局信息的能力。针对这一问题,提出了一种多尺度注意力自适应网络(MA2Net)用于RSI中的目标检测。本文的主要贡献有两个方面。首先,设计了一个多尺度注意力自适应网络,自适应整合多层次特征;该网络由集成(IG)块、信道自关注(CS)块和自适应融合(AF)块组成。具体来说,IG旨在将多层次特征转换为中等大小。CS块是一个嵌入式高斯自注意模块,用于对特征通道之间的关系进行建模。为了学习自注意特征的多层次表达,获得多尺度特征图,开发了自动识别。其次,为了在多任务和更高精度之间取得平衡,利用特征对齐头对目标进行正确定位和分类。DIOR上的实验结果表明,我们的网络可以达到比目前最先进的RSI目标检测器更高的检测精度。
{"title":"Multi-scale Attention Adaptive Network for Object Detection in Remote Sensing Images","authors":"Qixi Tan, W. Xie, Haojin Tang, Yanshan Li","doi":"10.1109/ICICSP55539.2022.10050627","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050627","url":null,"abstract":"Remote sensing images (RSI) have a large range of variations in the aspect of inter- and intra-class size variability across objects. As a key technology in the field of RSI processing, RSI object detection has been widely applied. Multilevel features fusion network is commonly used to improve the performance of object detection. However, the existing multilevel feature fusion networks for RSI lack the ability to combine global information. Aiming at this problem, A multi-scale attention adaptive network (MA2Net) is proposed to object detection in RSI. The main contributions of this paper are twofold. Firstly, a multi-scale attention adaptive network is designed to adaptively integrate the multilevel features. This network is composed of integrating (IG) block, channel self-attention (CS) block, and adaptive fusion (AF) block. Specifically, IG is designed to transform the multi-level features into an intermediate size. The CS block is an embedded gaussian self-attention module used to model the relationship between the feature channels. AF is developed to learn the multilevel expression of self-attention features to obtain multi-scale feature maps. Secondly, to achieve a balance between multi-task and higher accuracy, a feature align head is utilized to correctly locate and classify objects. The experimental results on DIOR show that our network can achieve higher detection accuracy than the state-of-the-art RSI object detector.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124037913","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}
引用次数: 0
Data Processing of Noise Flight Test for Large Civil Aircraft Type Certification 大型民机型式审定噪声飞行试验数据处理
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050622
Chen Ling, Li Qiang, Zhang Zhen
Civil aircraft noise is the main source of the airport and its surrounding areas, in recent years, with the continuous development of the air transport industry, aircraft noise is more and more concerned by the public, according to the International Civil Aviation Convention Annex 16 Volume I and China Civil Aviation Regulations CCAR36 Aircraft Type and Airworthiness Certification Noise Regulations. The noise limit requirements for transport aircraft are put forward. According to the requirements of the regulations, it is the key to determine that the aircraft meets the requirements of the regulations to obtain the noise data through flight test and to obtain the equivalent perceived noise level through data processing. In this paper, the noise data processing process and the key points are analyzed.
民用飞机噪声是机场及其周边地区的主要噪声源,近年来,随着航空运输业的不断发展,飞机噪声越来越受到公众的关注,根据《国际民用航空公约》附件16卷一和《中国民用航空规则》CCAR36飞机机型和适航审定噪声规定。提出了运输飞机噪声限值要求。根据法规的要求,通过飞行试验获取噪声数据,并通过数据处理获得等效感知噪声级,是确定飞机是否符合法规要求的关键。本文对噪声数据的处理过程和处理要点进行了分析。
{"title":"Data Processing of Noise Flight Test for Large Civil Aircraft Type Certification","authors":"Chen Ling, Li Qiang, Zhang Zhen","doi":"10.1109/ICICSP55539.2022.10050622","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050622","url":null,"abstract":"Civil aircraft noise is the main source of the airport and its surrounding areas, in recent years, with the continuous development of the air transport industry, aircraft noise is more and more concerned by the public, according to the International Civil Aviation Convention Annex 16 Volume I and China Civil Aviation Regulations CCAR36 Aircraft Type and Airworthiness Certification Noise Regulations. The noise limit requirements for transport aircraft are put forward. According to the requirements of the regulations, it is the key to determine that the aircraft meets the requirements of the regulations to obtain the noise data through flight test and to obtain the equivalent perceived noise level through data processing. In this paper, the noise data processing process and the key points are analyzed.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128988107","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}
引用次数: 0
Propagation of the Vector Sound Field in the Bottom-Reflected Zone in Deep Water 深水底反射区矢量声场的传播
Pub Date : 2022-11-26 DOI: 10.1109/ICICSP55539.2022.10050616
Mei Sun
The propagation properties of the vector sound field with a shallow receiver in the bottom-reflected zone of a shallow source in deep water are studied in this paper. Firstly, the properties of the sound rays arriving at the receiver position are studied. Secondly, theoretical analysis of the propagation property of the vector sound field is conducted by using the ray model. Thirdly, transmission losses of the sound pressure, the horizontal particle velocity and the vertical particle velocity are calculated by the RAM-PE model. The theoretical analysis and the simulation results show that the energy and the transmission losses of the horizontal particle velocity and the vertical particle velocity are closely related with the grazing angles of the eigenrays. The transmission loss difference between the vertical particle velocity and the horizontal particle velocity increases with the increase of the range from the source to the receiver, and satisfies Eq. (19) in this paper.
本文研究了深水中浅源底反射带浅接收器矢量声场的传播特性。首先,对到达接收机位置的声射线的特性进行了研究。其次,利用射线模型对矢量声场的传播特性进行了理论分析。第三,利用RAM-PE模型计算声压、水平粒子速度和垂直粒子速度的传递损失;理论分析和仿真结果表明,水平粒子速度和垂直粒子速度的能量和传输损失与特征射线的掠掠角密切相关。垂直粒子速度与水平粒子速度的传输损耗差随着源到接收端距离的增加而增大,满足本文式(19)。
{"title":"Propagation of the Vector Sound Field in the Bottom-Reflected Zone in Deep Water","authors":"Mei Sun","doi":"10.1109/ICICSP55539.2022.10050616","DOIUrl":"https://doi.org/10.1109/ICICSP55539.2022.10050616","url":null,"abstract":"The propagation properties of the vector sound field with a shallow receiver in the bottom-reflected zone of a shallow source in deep water are studied in this paper. Firstly, the properties of the sound rays arriving at the receiver position are studied. Secondly, theoretical analysis of the propagation property of the vector sound field is conducted by using the ray model. Thirdly, transmission losses of the sound pressure, the horizontal particle velocity and the vertical particle velocity are calculated by the RAM-PE model. The theoretical analysis and the simulation results show that the energy and the transmission losses of the horizontal particle velocity and the vertical particle velocity are closely related with the grazing angles of the eigenrays. The transmission loss difference between the vertical particle velocity and the horizontal particle velocity increases with the increase of the range from the source to the receiver, and satisfies Eq. (19) in this paper.","PeriodicalId":281095,"journal":{"name":"2022 5th International Conference on Information Communication and Signal Processing (ICICSP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132500847","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}
引用次数: 0
期刊
2022 5th International Conference on Information Communication and Signal Processing (ICICSP)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1