检索结果-内蒙古大学图书馆

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷

作者： Wang, Jie Xu, Tingfa Song, Liqiang Ding, Lihe Li, Hui Jiang, Peng Han, Yuqi Li, Jianan School of Optics and Photonics Beijing Institute of Technology Beijing China Beijing Institute of Technology Beijing China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education Beijing Institute of Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology Chongqing China National Astronomical Observatories Chinese Academy of Sciences Chaoyang-qu China Beijing Key Laboratory of Embedded Real-time Information Processing Technique Beijing China

Fine-grained geometry, obtained through the assimilation of localized point features, is crucial in the realms of object recognition and scene comprehension within point cloud contexts. Traditional point cloud backbones predominantly utilize max pooling for the amalgamation of local features, a process that tends to overlook spatial interrelations among points, consequently leading to the potential loss of fine-grained geometric details. To overcome this limitation, we introduce an innovative operation termed Position Adaptive Pooling (PAPooling), which is designed to amalgamate local features while sensitively considering the spatial positions of points. This is achieved by employing a graph-based representation to explicitly model the spatial relationships of points. PAPooling involves two principal components: first, the local graph construction, which establishes a local graph for a set of points by linking a central point with its adjacent points, thereby transforming pairwise relative positions into channel-specific attention weights;second, the attentive feature aggregation, which adeptly takes into account the contribution of each node and simulates the inter-node relationships within the local graph, effectively extracting representations of local features through a Graph Convolution Network (GCN). PAPooling's simplicity and efficacy make it a versatile addition to widely used point-based backbones such as PointNet++ and DGCNN, offering a plug-and-play solution. Comprehensive experimental analysis demonstrates PAPooling's enhanced capability in capturing local geometry, contributing significantly across a spectrum of applications including 3D shape classification, part segmentation, scene segmentation, and corruption defense, all with minimal computational increase. Code will be public at https://***/Roywangj/PAPooling/. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

引用

Science China(information Sciences) 2017年第8期60卷 243-245页

作者： Tao ZENG Tiandong LIU Zegang DING Qi ZHANG Zhen WANG Teng LONG Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

Interferometric Synthetic Aperture Radar(InSAR)has been proposed as a technique for the reconstruction of the Digital Elevation Model(DEM),which is widely used in global terrain mapping mission[1].The DEM reconstruction methods of In SAR technique are usually based on the so-called phase unwrapping(PU)*** highly sloped terrain,the interferometric phase gradients(IPG)of the adjacent pixels are more thanπ.Therefore,the traditional PU methods

关键词： SAR In of DEM IPG on Figure LAPS A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

来源：评论

学校读者我要写书评

暂无评论

High-precision deformation monitoring algorithm for GBSAR system: rail determination phase error compensation

引用

Science China(information Sciences) 2016年第8期59卷 204-219页

作者： Cheng HU Mao ZHU Tao ZENG Weiming TIAN Cong MAO Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

In recent years, the repeat-pass GBSAR(ground based synthetic aperture radar) system has demonstrated its capacity to acquire deformation. Nevertheless, in a variety of applications, it needs to measure the deformation with the precision up to 0.1 mm, which could not be reached by utilizing the traditional PS(permanent scatterer) algorithm in most cases. Generally, one of the main reasons could be summarized into the phase error caused by the rail determination error, because the precision of rail determination might degrade during long working hours. However, the traditional PS algorithm could not compensate for the phase error caused by the rail determination error. In order to solve the problems, we modify the conventional PS ***, we deduced the transformation relationship between the rail determination error and its corresponding interferometric phase error. Then, the phase errors caused by the atmosphere and the rail determination error were jointly compensated. The experimental data, which were obtained in Fangshan District in beijing(China), were used to test and verify the performance of the new algorithm. After the comparison between the results processed by the new algorithm and those processed by the traditional algorithm, the proposed method demonstrated its ability to obtain high-precision deformation.

关键词： permanent scatterer(PS) synthetic aperture radar(SAR) ground-based SAR deformation monitoring radar

来源：评论

学校读者我要写书评

暂无评论

A high-precision phase-derived range and velocity measurement method based on synthetic wideband pulse Doppler radar

引用

Science China(information Sciences) 2017年第8期60卷 151-162页

作者： Huayu FAN Lixiang REN Teng LONG Erke MAO Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Radar Research Laboratory Beijing Institute of Technology

Development of radar technology needs to address the two-dimensional high resolution of range and velocity simultaneously for high-speed targets. Taking advantage of the superior coherent performance of synthetic wideband pulse Doppler radar, this paper elaborates the principles of phase-derived range and velocity measurements. Moreover, this paper explores the key technologies of unwrapping phase ambiguity, and discusses the phase unwrapping strategy at a low signal-to-noise ratio(SNR). The proposed method can be applied to the conditions of low SNR and has comparatively strong practicality in engineering. Both the ejection ball and civil aircraft experiments have validated the correctness and feasibility of the proposed method. In particular,the experimental results reveal that the accuracy of phase-derived range and velocity measurement has reached a level of submillimeter or millimeter and centimeter/second or submillimeter/second, respectively.

关键词： synthetic wideband PD radar phase-derived range measurement phase-derived velocity measurement unwrapping phase ambiguity track filtering minimum entropy method

来源：评论

学校读者我要写书评

暂无评论

Robust and fast iterative sparse recovery method for space-time adaptive processing

引用

Science China(information Sciences) 2016年第6期59卷 199-211页

作者： Xiaopeng YANG Yuze SUN Tao ZENG Teng LONG Beijing Key Laboratory of Embedded Real-time Information Processing Technology School of Information and Electronics Beijing Institute of Technology

Conventional space-time adaptive processing(STAP) requires large numbers of independent and identically distributed(i.i.d) training samples to ensure the performance of clutter suppression, which is hard to be achieved in practical complex nonhomogeneous environment. In order to improve the performance of clutter suppression with small training sample support, a robust and fast iterative sparse recovery method for STAP is proposed in this paper. In the proposed method, the sparse recovery of clutter spatial-temporal spectrum and the calibration of space-time overcomplete dictionary are achieved iteratively. Firstly, the robust solution of sparse recovery is derived by regularized processing, which can be calculated recursively based on the block Hermitian matrix property, afterwards the mismatch of space-time overcomplete dictionary is calibrated by minimizing the cost function. The proposed method can not only alleviate the effect of noise and dictionary mismatch, but also reduce the computational cost caused by direct matrix inversion. Finally, the proposed method is verified based on the simulated and the actual airborne phased array radar data, which shows that the proposed method is suitable for practical complex nonhomogeneous environment and provides better performance compared with conventional STAP methods.

关键词： space-time adaptive processing(STAP) sparse recovery robust iteration computational complexity

来源：评论

学校读者我要写书评

暂无评论

An Anti-background Interference Object Detection Method for Complex Remote Sensing Images

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Tang, Wei Zhao, Xidong Zhang, Qingjun Wang, Wenzheng Zhao, Baojun China Academy of Space Technology Shandong Institute of Space Electronic Technology Yantai 264003 China Changfeng Electromechanical Technology Research and Design Institute Beijing 100086 China Remote Sensing General Department of China Academy of Space Technology Beijing 100086 China Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-Time Information Processing Technology School of Information and Electronics Beijing 100081 China

Object detection in remote sensing images differs from general object detection in that it faces numerous challenges such as false alarm interference. However, conventional object detection methods primarily focus on scale and orientation variations, insufficiently addressing issues such as object blurring and false alarms, which frequently occur in large-scale Earth observation scenarios. To address this issue, this paper proposes an anti-interference object-detection algorithm based on mask guidance and adaptive margin loss, termed MG2ADet. Specifically, we devise a mask guidance module that leverages pseudo-mask labels to guide network features towards focusing on foreground regions, thereby enhancing the discriminability of object features and suppressing background noise interference. Besides, to further differentiate object and background features, we designed an adaptive margin classification loss function that guides the detection model in learning strongly discriminative features. This classification loss adaptively adjusts the angular margin penalty based on the image quality score of samples, assigning varying weights to different difficult samples, and ultimately improving the detection model's ability to discriminate between blurred objects and similar distractors. Extensive experiments on public remote sensing datasets demonstrated the excellent detection performance of our algorithm in comparison with numerous existing detectors (both one-stage and two-stage detectors). © 2008-2012 IEEE.

关键词： Aerial image Complex Scenes Deep learning Object Detection

来源：评论

学校读者我要写书评

暂无评论

A novel subsidence monitoring technique based on space-surface bistatic differential interferometry using GNSS as transmitters

引用

Science China(information Sciences) 2015年第6期58卷 68-83页

作者： ZENG Tao ZHANG Tian TIAN WeiMing HU Cheng Beijing Key Laboratory of Embedded Real-time Information Processing Technology Radar Research Laboratory School of Information and ElectronicsBeijing Institute of Technology

Synthetic Aperture Radar Differential Interferometry(DIn SAR) technique is an effective tool with large coverage and high spatial accuracy for subsidence monitoring. Nevertheless, the temporal resolution is usually poor so that rapid deformation cannot be measured due to the long revisit time of radar *** SAR Differential Interferometry technique using Global Navigation Satellite System(GNSS) as illuminator has a shorter revisit time, whereas the measurement accuracy is constrained by low signal power, narrow bandwidth and atmospheric delay error. To cope with these problems, in this paper, we propose a novel subsidence monitoring technique based on Space-Surface bistatic Differential Interferometry(SS-DI) with GNSS transmitters, where two stations consist of a reference one and a measurement one that are deployed on the ground. First, we applied a space differential processing between two stations to cancel identical errors such as tropospheric and ionospheric errors etc. Then we used a long time coherent integration to improve the signal noise ratio. Subsequently, we also utilized a time differential processing to construct double differential equations with respect to unknown deformation variables. Finally, we solved the equations to obtain a highly accurate estimation of three dimension deformation. Furthermore, an SS-DI experiment using Beidou-2 as transmitters was carried out to validate the proposed method, where a high accuracy(0.01 mm) device was utilized to simulate subsidence deformation. The experimental results reveal that the proposed method has better performance of spatial measurement accuracy of 0.53 mm compared with differential GPS method.

关键词： differential interferometry subsidence monitoring Beidou-2/Compass-2 space-surface bistatic radar differential GPS

来源：评论

学校读者我要写书评

暂无评论

Multi-scale object detection by top-down and bottom-up feature pyramid network

引用

Journal of Systems Engineering and Electronics 2019年第1期30卷 1-12页

作者： ZHAO Baojun ZHAO Boya TANG Linbo WANG Wenzheng WU Chen School of Information and Electronics Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

While moving ahead with the object detection technology, especially deep neural networks, many related tasks, such as medical application and industrial automation, have achieved great success. However, the detection of objects with multiple aspect ratios and scales is still a key problem. This paper proposes a top-down and bottom-up feature pyramid network(TDBU-FPN),which combines multi-scale feature representation and anchor generation at multiple aspect ratios. First, in order to build the multi-scale feature map, this paper puts a number of fully convolutional layers after the backbone. Second, to link neighboring feature maps, top-down and bottom-up flows are adopted to introduce context information via top-down flow and supplement suboriginal information via bottom-up flow. The top-down flow refers to the deconvolution procedure, and the bottom-up flow refers to the pooling procedure. Third, the problem of adapting different object aspect ratios is tackled via many anchor shapes with different aspect ratios on each multi-scale feature map. The proposed method is evaluated on the pattern analysis, statistical modeling and computational learning visual object classes(PASCAL VOC)dataset and reaches an accuracy of 79%, which exhibits a 1.8% improvement with a detection speed of 23 fps.

关键词： convolutional neural network (CNN) feature pyramid network (FPN) object detection deconvolution.

来源：评论

学校读者我要写书评

暂无评论

Impacts of ionospheric scintillation on geosynchronous SAR focusing: preliminary experiments and analysis

引用

Science China(information Sciences) 2015年第10期58卷 191-193页

作者： LI YuanHao HU Cheng DONG XiChao TIAN WeiMing LONG Teng Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

Dear editor,Geosynchronous Synthetic Aperture Radar(GEO SAR)has significant potential when applied to hazard and disaster monitoring because of its short revisit time of approximately 24 h and its wide coverage of app... 详细信息

关键词： SAR Impacts of ionospheric scintillation on geosynchronous SAR focusing GEO PSLR Figure preliminary experiments and analysis than

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of inclined geosynchronous SAR focusing using Beidou IGSO signals

引用

Science China Earth Sciences 2016年第12期59卷 240-242页

作者： Xichao DONG Cheng HU Weiming TIAN Tian ZHANG Yuanhao LI Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

Dear editor,Geosynchronous synthetic aperture radar(GEO SAR)[1,2]has an inclined geosynchronous orbit of around 36000 km,which leads to its short revisit time of around 24 hours and a wide coverage of up to approximately one third of the Earth *** long integration time guarantees the fine ***,GEO SAR owns the promising capability of providing images with the high resolution,

关键词：倾斜地球同步轨道 SAR 北斗聚焦信号

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：