检索结果-内蒙古大学图书馆

Adaptive Mainlobe Interference Suppression in Sparse Distributed Array Radar Based on Synthetic Wideband Signal 2nd

2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017

作者： Luo, Jian Zhang, Honggang Song, Yuanyuan Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783319734460

This paper proposes a mainlobe interference suppression method in distributed array radar (DAR) based on stepped frequency synthetic wideband signal. Due to the equivalent large aperture of DAR, it is possible to cancel the mainlobe interference without target signal suppression. The applying of stepped frequency synthetic wideband signal can avoid the different time delays arriving at each array compared with the traditional instantaneous wideband Chirp (linear frequency modulation) signal. Moreover, it can reduce the computational complexity. This method employs the narrowband adaptive processing to each sub-pulse of the stepped frequency signal, and then synthesizes the high resolution range profile (HRRP). As a result, mainlobe interference suppression under wideband signal is accomplished. Mainlobe interference suppression experiment is carried out by using an S-band experimental radar system, an S-band noise jammer and a target simulator. The measured data is processed employing the proposed method, and the result verifies the effectiveness of this algorithm. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Classification Based on Markov Random Field

Remote Sensing Image Classification Based on Markov Random F...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Tong Zhang Yin Zhuang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

With the continuous development of optical remote sensing technology, the segmentation of high resolution remote sensing images has become a hot research field. The high resolution and complex remote sensing images make the general natural image segmentation become a challenge task. Here, Markov random field (MRF) can well combine the spatial information of remote sensing image with the domain information between pixels for image segmentation, which is currently a hot research direction. In this paper, the wavelet and MRF are combined to achieve multi-scale analysis and produce more accurate segmentation results, the extensive experiments demonstrated that proposed method is more suitable for remote sensing image segmentation, and it provides a good boundary local mapping results and is robust with image non-stationary signal. In addition, in view of the disadvantage of fixed potential function parameters of traditional MRF, we put forward the method of variable weight. On this basis, Kullback-Leibler (KL) divergence is proposed to calculate the similarity between the segmented regions to further optimize the segmentation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Squint SAR Imaging for Noncooperative Moving Ship Target Based on High Velocity Motion Platform

High-Squint SAR Imaging for Noncooperative Moving Ship Targe...

引用

2018 China International SAR Symposium, CISS 2018

作者： Zhou, Zhichao Ding, Zegang Zhang, Tianyi Wang, Yan Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (纸本)9781538671931

For high velocity motion platform, it usually takes a shorter azimuth accumulation time to achieve high-squint synthetic aperture radar (SAR) imaging for noncooperative moving ship target with meter-level resolutions. In this case, three-dimensional relative motion of the ship target can be neglected approximately, mainly the translational motion should be considered. However, the magnitude and direction of the target's translational velocity are unknown. To solve the above problem, a two-step imaging method is proposed in this paper. Firstly, the entire scene is coarsely imaged by using the parameters provided by inertial navigation system. The position of the ship target can be judged by two-dimensional order statistics constant false alarm rate (OS-CFAR) detection and ship target pixel clustering. By constructing the band-pass filter in azimuth frequency domain, the data of the target can be obtained effectively, and to a certain extent, sea clutter and noise are suppressed. Then the motion parameters are estimated. Finally, the target is secondarily imaged with the estimated parameters to achieve precise focus. The results of simulation verify the correctness of the analysis and the validity of the proposed method. © 2018 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

The Analyses for Discretization behaviour of Line Segment Target in SAR Image

The Analyses for Discretization behaviour of Line Segment Ta...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yangkai Wei Tao Zeng Xinliang Chen Yujie Fan Yuhan Wen Zegang Ding Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing People's Republic of China Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Under the assumption of the point scattering model, traditional SAR imaging processing can depict the scattering features of the illuminated scene with a series of strong point scatterers. In the traditional SAR images, when the illuminated scene contains various line segment targets, only some line segment targets show line-segment-scattering features, whereas others are discretized into strong point scatterers. This discretization behaviour of line segment targets makes it difficult to interpret the factual geometrical structure of the line segment targets through SAR images. Unfortunately, neither the traditional point scattering model and imaging processing can provide a detailed analysis for the discretization behaviour of line segment targets. Hence, in this paper, we propose some detailed and comprehensible analyses for this problem from three aspects. First, by introducing the spatial spectrum analysis of SAR imaging, we provide an azimuth analysis for this problem from the perspective of the imaging system. Then, we analyse this problem from the range direction based on the high resolution range profile of received echo. Furthermore, through establishing a parametric model for the line segment targets, a comprehensive analysis for the problem is given based on the scattering features. Numerical simulation experiments demonstrate the effectiveness of our proposed analyses.

关键词： SAR line segment discretization behaviour parametric model

来源：评论

学校读者我要写书评

暂无评论

Weight-based Channel-model Matrix Framework provides a reasonable solution for EEG-based cross-dataset emotion recognition

arXiv

引用

arXiv 2022年

作者： Chen, Huayu He, Huanhuan Zhu, Jing Sun, Shuting Li, Jianxiu Shao, Xuexiao Li, Junxiang Li, Xiaowei Hu, Bin Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University Lanzhou China Brain Health Engineering Laboratory School of Medical Technology Beijing Institute of Technology Beijing China School of Information Science and Engineering Inner Mongolia University Inner Mongolia China Shandong Academy of Intelligent Computing Technology Jinan China Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Shanghai China Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University Institute of Semiconductors Chinese Academy of Sciences Lanzhou China Open Source Software and Real-Time System Lanzhou University Ministry of Education Lanzhou China

Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which makes the universal models yield unsatisfactory results. Facing the situation that lacks EEG information decoding research, we first analyzed the impact of different EEG information(individual, session, emotion and trial) for emotion recognition by sample space visualization, sample aggregation phenomena quantification, and energy pattern analysis on five public datasets. Based on these phenomena and patterns, we provided the processing methods and interpretable work of various EEG differences. Through the analysis of emotional feature distribution patterns, the Individual Emotional Feature Distribution Difference(IEFDD) was found, which was also considered as the main factor of the stability for emotion recognition. After analyzing the limitations of traditional modeling approach suffering from IEFDD, the Weight-based Channel-model Matrix Framework(WCMF) was proposed. To reasonably characterize emotional feature distribution patterns, four weight extraction methods were designed, and the optimal was the correction T-test(CT) weight extraction method. Finally, the performance of WCMF was validated on cross-dataset tasks in two kinds of experiments that simulated different practical scenarios, and the results showed that WCMF had more stable and better emotion recognition ability. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Spatial Enhanced-SSD For Multiclass Object Detection in Remote Sensing Images

Spatial Enhanced-SSD For Multiclass Object Detection in Remo...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Guanqun Wang Yin Zhuang Zhiru Wang He Chen Hao Shi Liang Chen Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China

Accurate multiclass object detection in remote sensing images is a challenging task, especially for small objects. Since the scales of objects in remote sensing images have a great variance, almost all of the advanced detection methods have shortcomings. Consequently, improving the accuracy of multiclass objects detection has always been the direction of researchers' efforts. In this paper, a spatial enhanced-Single Shot MultiBox Detector (SE-SSD) is proposed. First, to enhance the spatial information, we enlarge the input image channels with embedding oriented-gradients feature maps. Second, the multiple output layers in the backbone network are changed to reduce one pooling operation. Finally, we design a context module to enhance the receptive field for feature layer description in SE-SSD framework. Experimental results on DOTA dataset demonstrate that Spatial Enhanced-SSD method reaches a much higher mean average precision (mAP) than Faster R-CNN, SSD and other classic detection network.

关键词： Feature extraction Object detection Remote sensing Convolution Sports Detectors

来源：评论

学校读者我要写书评

暂无评论

Fast Digital Beamforming for Conformal Array

Fast Digital Beamforming for Conformal Array

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yiling Lu Yin Xiang Yikun Zhao Zegang Ding School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

The conventional digital beam forming (DBF) for conformal array needs to scan a series of look angles with small angular separation to obtain a high-resolution pattern. Inspired by the fast back projection algorithm (FBP)[3] for SAR imaging, a fast DBF algorithm for the conformal array is proposed in this paper. Firstly, the conformal array is divided into several subarrays, and the pattern of each subarray is formed in a coarse resolution. Then, the pattern of each subarray is interpolated to a high resolution one by FFT. Finally, all subarrays' high-resolution pattern is added together to form the pattern of the whole array. The simulation results have proved the efficiency and accuracy of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method For Fast Remote Sensing Images Classification

A Method For Fast Remote Sensing Images Classification

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Fengjiao Li Donglin Jing Fukun Bi Hao Shi Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China School of Information Science and Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Due to the characteristic of high score remote sensing images, such as large file, chaotic content and complex information, the demand for image classification speed and accuracy is increasing. In this paper, we combine the convolutional neural network and octave convolution to extract the complex high-order statistical properties of the image. We first analyze the more classical convolutional neural network, and use the octave convolution to make full use of the fine details of the changes of the high-frequency information of the remote sensing image. The memory and computing resources consumed are greatly reduced, and network optimization is performed. The test proves that the result is effective for speed and accuracy improvements.

关键词： Remote sensing image Convolutional neural network Image frequency Octave convolution

来源：评论

学校读者我要写书评

暂无评论

Optical Remote Sensing Image Waters Extraction technology Based on Deep Learning Context-Unet

Optical Remote Sensing Image Waters Extraction Technology Ba...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Ruoda Yan Shan Dong Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China Engineering Center of Digital Audio and Video Communication University of China Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

The optical remote sensing images are used to sea-land segmentation which is a difficult task. Due to general deep learning based methods required a large number of refined annotation, however, a large scale optical remote sensing images annotation is very expensive. Therefore, the Context-Unet is proposed to produce accurate sea-land segmentation results by a few annotated training samples. In this paper, we apply the Context-Unet network to the watershed extraction. On the basis of this, we re-compile the loss function to improve the accuracy of watershed extraction. Example: Finally, the date collected from Google Earth service is used to train and test this paper proposed Context-Unet and state-o-the-art methods. The experiments proved that the proposed method outperforms than other methods, and it can achieve 98% precision and 97% recall ratios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel word length optimization method for radix-2k fixed-point FFT

引用

Science China(information Sciences) 2018年第2期61卷 278-282页

作者： Chen YANG Yizhuang XIE He CHEN Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology

Dear editor,Fast Fourier transform(FFT)is one of the most fundamental algorithms used in digital signal *** applications such as orthogonal frequency division multiplexing(OFDM),long term

关键词： A novel word length optimization method for radix-2~k fixed-point FFT length

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：