检索结果-内蒙古大学图书馆

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Gong, Weishuang Wang, Qi Li, Yachao Xidian University Xidian University Hangzhou Institute of Technology Hangzhou China Xidian University National Key Laboratory of Radar Signal Processing Xi'an China

ISBN: (纸本)9798350355581

This paper proposes a unified localization method based on the time difference of arrival (TDOA) and the frequency difference of arrival (FDOA), which can estimate the position and velocity of the target when it is in the near-field, or the direction of the target when it is in the far-field. We use the modified polar representation (MPR) to unify the far-field and near-field models to construct an optimal localization problem with two constraints and propose an algebraic solution. The method first uses the least squares method to find the initial value without considering the constraints. Then the constraints are used to build an optimization equation to reduce the error of the initial value and obtain the precise value. Simulation results show that the proposed algorithm is close to the Cramer-Rao lower bound (CRLB), verifying the performance. © 2024 IEEE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Target Location in Distributed MIMO radar based on Coherent processing 2

Target Location in Distributed MIMO radar based on Coherent ...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Wei, Fa Yan, Shi Zhu, Shengqi Lan, Lan Li, Ximin Qi, Jiawei Ma, Runlong Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China Beijing Institute of Remote Sensing Device Beijing100854 China

ISBN: (纸本)9798331515669

In this paper, the problem of target location is investigated in the distributed multiple-input multiple-output (MIMO) radar based on coherent processing. At the modelling stage, the distributed MIMO radar is divided into three separated subarrays, where both transmit and receive functions are used in subarrays 1 and 3, while only receive function is adopted in subarray 2. Furthermore, a small frequency increment is introduced among different antenna elements in the subarray 1, in the meantime, a phase modulating operation is performed for various antenna elements in the subarray 3. In this respect, the target location performance can be improved significantly by means of the transmit modulation in subarrays 1 and 3. Under the circumstances, the model of target location is established, and a two-step estimation technology is shown, where a small location sector with respect to targets are firstly obtained, and the accurate location are further estimated. Specifically, in order to reduce the computational cost required by the multi-dimensional search procedures, an alternating procedure is developed by a sequence of 1-D searches obtained alternating between the optimization over each variable keeping the other fixed. Numerical results corroborate the effectiveness of the developed methods for the target location with distributed MIMO radar based on coherent processing. © 2024 IEEE.

关键词： Phase modulation

来源：评论

学校读者我要写书评

暂无评论

MDFNet: Multimodal Feature Decomposition and Fusion Network for Multimodal Remote Sensing Image Semantic Segmentation 2

MDFNet: Multimodal Feature Decomposition and Fusion Network ...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Wei, Tianyu Chen, He Wang, Jue Liu, Wenchao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

The semantic segmentation of multimodal remote sensing (RS) images, utilizing optical and synthetic aperture radar (SAR) data, has raised attention in recent studies. Advanced studies adaptively modeled and fused modality-share and modality-specific information beneficial for segmentation and achieved competitive performance. However, in challenging scenarios such as low image contrast or blurred textures in optical images and speckle noises or foreshortening in SAR images, modality-specific information may lost. This study proposed a multimodal feature decomposition and fusion network (MDFNet) designed for multimodal RS image semantic segmentation using optical and SAR images. By decomposing multimodal features into modality-share and modality-difference features and applying gradient descent on modality-difference features, modality-specific information beneficial for segmentation can be retained. Specifically, we designed a MDF decoder with MDF blocks. MDF block maps multimodal features into the same feature space and calculates the difference of multimodal features to obtain modality-share and modality-difference features respectively, then fuses these features. MDF decoder optimizes modality-difference features by gradient descent using adaptive modeling, thereby retaining modality-specific information that is beneficial for segmentation. Comprehensive experiments conducted on the DFC20 dataset demonstrated that the proposed MDFNet surpasses representative methods. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of the Impacts of Temporal-Spatial Variant Troposphere on Ground-Based SAR Imaging of Asteroids

引用

Journal of Beijing institute of Technology 2023年第6期32卷 727-739页

作者： Tingting Fu Yuanhao Li Zhiyang Chen Zheng Wu Cheng Hu Radar Research Laboratory School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081China Beijing Key Laboratory of Embedded Real-time Information Processing Technology the Chongqing Institute of Meteorological Sciences Chongqing 401147China

The near-Earth asteroid collisions could cause catastrophic disasters to humanity and the Earth,so it is crucial to monitor ***-based synthetic aperture radar(SAR)is an observation technique for high resolution imaging of *** ground-based SAR requires a long integration time to achieve a large synthetic aperture,and the echo signal will be seriously affected by temporal-spatial variant *** spatiotemporal freezing tropospheric models are *** cope with this,this paper models and analyses the impacts of temporal-spatial variant troposphere on ground-based SAR imaging of *** the background tropo-sphere,a temporal-spatial variant ray tracing method is proposed to trace the 4D(3D spatial+temporal)refractive index network provided by the numerical weather model,and calculate the error of the background *** the tropospheric turbulence,the Andrew power spectral model is used in conjunction with multiphase screen theory,and varying errors are obtained by tracking the changing position of the pierce point on the phase *** simulation,the impact of temporal-spatial variant tropospheric errors on image quality is analyzed,and the simulation results show that the X-band echo signal is seriously affected by the troposphere and the echo signal must be compensated.

关键词： near-Earth asteroids ground-based SAR troposphere ray tracing

来源：评论

学校读者我要写书评

暂无评论

Image Editing based on Diffusion Model for Remote Sensing Image Change Captioning 2

Image Editing based on Diffusion Model for Remote Sensing Im...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Cai, Miaoxin Chen, He Li, Can Gan, Shuyu Chen, Liang Zhuang, Yin Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

Remote Sensing Image Change Captioning (RSICC) is a task that utilizes natural language to describe changes in remote sensing images of the same area captured at different times. However, the significant temporal intervals between multi-temporal images, the infrequency of observable changes, and the limitations on observation locations make it difficult to acquire and annotate a large and diverse dataset for analyzing change in multi-temporal images. The scarcity of labeled data hinders the training of RSICC models, leading to poor generalization. Compared to annotated registered bi-temporal image, single-temporal data is easier to obtain. Therefore, to tackle the issue of poor generalization of RSICC models under limited annotated sample conditions, a text-guided image pairs generation (TGIPG) method is proposed to create synthetic RSICC datasets from single-temporal data and randomly sampled text instructions via a diffusion-based controllable image editing model. This approach generates more valid pairs of multi-temporal samples to address the constraints of limited change information. Specifically, this method utilizes language instructions to introduce change information into the diffusion process, gradually transforming the pre-phase image into the post-phase image. Our experiments on the LEVIR-CC dataset show that synthetic data can significantly enhance the performance of any RSICC model, with a restricted number of training samples, by employing this plug-and-play TGIPG method. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Efficient On-board Remote Sensing Scene Classification Using FPGA With Ternary Weight 2

Efficient On-board Remote Sensing Scene Classification Using...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Qi, Guijie Qiao, Tingting Yu, Jingchi Xie, Yizhuang Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

Remote Sensing Scene Classification (RSSC) is essential for applications such as environmental monitoring and catastrophe management, which often have stringent time constraints requiring real-time processing. On-board processing significantly enhances real-time performance but is challenged by limited computational resources and strict power requirements. To address these challenges, this study proposes an FPGA-based accelerator designed for Ternary Weight Networks (TWNs), which use ternary values {+1, 0, -1} for weights. By adopting TWNs, the multiplication operations in convolution are eliminated, resulting in a significant reduction in computing and power needs. Experimental results show that TWNs significantly reduce network parameters while retaining classification accuracy comparable to Full-precision Weight Networks (FPWNs). The FPGA-based accelerator achieves an energy-efficiency ratio of 434.11 GOP/W, outperforming most existing CNN accelerators, hence meeting the requirements for on-board RSSC. © 2024 IEEE.

关键词： Image thinning

来源：评论

学校读者我要写书评

暂无评论

SC-DVNet: A Dual-Branch Recognition Network for Synthetic Aperture radar Images Based on Scattering Features 2

SC-DVNet: A Dual-Branch Recognition Network for Synthetic Ap...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Chen, Fan Shi, Hao He, Jingfei Yin, Yifei Meng, Fanyu Chen, Liang Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

Ship classification using Synthetic Aperture radar (SAR) images is a crucial component in marine monitoring. With the rise of deep neural networks (DNN), the abstract feature maps obtained by CNN-based methods have significantly improved classification performance. However, most current DNN-based methods are predominantly inherited from optical imagery, designed only for SAR intensity images, which may present challenges for further improving recognition performance. Therefore, this paper proposes using the point Scattering Center (SC) model for scattering feature extraction combined with graph convolutional networks for ship classification tasks. Comprehensive ablation experiments were carried out to demonstrate the efficacy of the proposed approach. Finally, experimental results on OpenSARShip1.0 dataset verify that the performance of the suggested approach notably outperforms DNN-driven techniques. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Advanced Scale-aware Attention for Enhanced Tiny Object Detection in Remote Sensing 2

Advanced Scale-aware Attention for Enhanced Tiny Object Dete...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Qiao, Tingting Chen, He Chai, Bingqian Liu, Wenchao Qi, Guijie Xie, Yizhuang Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

Recent advancements in remote sensing object detection have progressed, but distinguishing objects from complex backgrounds remains difficult, especially for tiny objects. To address this, we introduce the Advanced Scale-Aware Attention (ASA) module, which retains key channel information while minimizing computational cost. This module reorganizes channels into the batch dimension and splits them into multiple sub-features. The ASA module contains three branches: the first encodes weights based on scale and channel relationships. The second and third branches use different convolution kernel sizes to capture features across various receptive fields. These branches collaborate to enhance pixel-level relationships, improving foreground-background contrast. On the AI-TOD dataset, our method improved AP50 by 8.6% over state-of-the-art approaches. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Digital Coding Technology for Harmonic Control of Meta-Atoms

Digital Coding Technology for Harmonic Control of Meta-Atoms

引用

2024 IEEE International Conference on Computational Electromagnetics, ICCEM 2024

作者： Hou, Xinan Xi, Rui Liao, Guisheng Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China Hangzhou Institute of Technology Xidian University Hangzhou311200 China

ISBN: (纸本)9798350383317

With the progress of meta - atoms, digital coding technology has become an important branch of this research field with its advantage in establishing the connection between digital information and meta-atoms, which greatly simplifies the metaatom design. In this paper, a digital coding technique for harmonic generation and regulation is introduced. Firstly, the harmonic number is modified by changing the phase slope, and then the corresponding harmonic amplitude and phase are regulated by designing the coding control. The introduced digital coding technique gets rid of the problem of harmonic crosstalk existing in the traditional multi-frequency control technology, and at the same time make the beam control more flexible, which greatly improves the efficiency of communication. © 2024 IEEE.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of High-Capacity Colorful QR Code with Multi-Code Combination 4

Design and Implementation of High-Capacity Colorful QR Code ...

引用

4th International Conference on Neural Networks, information and Communication Engineering, NNICE 2024

作者： Zhang, Xia Cao, Peng Beijing Institute of Graphic Communication Beijing Key Laboratory of High-end Printing Equipment Signal and Information Processing Beijing China

ISBN: (纸本)9798350394375

Compared with the traditional QR code, the color QR code has the outstanding advantages of large information capacity, ease of implementation, multi-code integration, etc. Therefore, it has been generally valued at home and abroad, and various color QR codes have been developed. In this paper, based on the needs of multi-code integration, automatic identification, anti-counterfeiting traceability, and other functional applications, a new color QR code is designed according to the basic principle of QR code grey threshold discrimination reading. Adopts the printing CMYK four-color information loading and grey scale segmentation method, which has the outstanding advantages of multi-code composite, both plain code and hidden codes, universal decoding function, and anti-counterfeiting traceability. Through experimental tests, the color QR code can read the plain code by direct code scanning, and can further read or authorize to read 1-2 hidden codes by app or mini program, which can be used to meet the requirements of printing anti-counterfeiting labels, traceability of commodity information and other fields, and has a good value of promotion and application. © 2024 IEEE.

关键词： Color

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：