检索结果-内蒙古大学图书馆

IET International Radar Conference 2018, IRC 2018

作者： Zhou, Hao-Tian Chen, Liang Fu, Bo Shi, Hao Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing100081 China 95894 PLA Troops No. 5805 Mail-box Changping District Beijing102211 China

The coherent nature of radar illumination causes the speckle effect, which gives the synthetic aperture radar (SAR) image its noisy appearance. The probability distribution of speckle noise is multiplicative rather than additive, which makes the interpretation and processing of SAR imagery more difficult. A novel SAR image denoising method is proposed. First the multiplicative noise is transformed into additive-like noise by logarithmic transformation. After that, a novel object function is proposed which combines a pre-trained dictionary model to deal with the image. Finally, exponential transform is employed to recover the image. Experimental results show that the proposed method can effectively remove the noise of SAR images, and indicate good performance compared with other state-of-the-art methods. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Radar HRRP target recognition based on stacked denosing sparse autoencoder

Radar HRRP target recognition based on stacked denosing spar...

引用

IET International Radar Conference 2018, IRC 2018

作者： Tai, Guangxing Wang, Yanhua Li, Yang Hong, Wei Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing Institute of Technology Beijing100081 China Beijing Racobit Electronic Information Technology Co. Ltd. Beijing100081 China

An end-to-end radar high-resolution range profile recognition method is proposed based on stacked denosing sparse autoencoder which stacks several denosing sparse autoencoders and uses softmax as the classifier. The training process consists of two steps. The first is layer-by-layer pre-training and the second is fine tuning using the pre-training results for initialisations. The two-step training process makes this model converge faster and more likely to converge to the global optimal point than directly training the joint network. Experimental result shows that the proposed method achieves higher recognition accuracy than state-of-art methods. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Resolution analysis for geostationary spaceborne-airborne bistatic forward-looking SAR

Resolution analysis for geostationary spaceborne-airborne bi...

引用

IET International Radar Conference 2018, IRC 2018

作者： Ke, Meng Yin, Wei Zhang, Tianyi Yang, Yanjiao Ding, Zegang Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Radar Research Lab School of Information and Electronics Beijing Institute of Technology China No. 589 Zhongshan West road Shijiazhuang China Beijing Electro-Mechanical Engineering Institute Beijing China

Owing to the spatial separation of transmitter and receiver, bistatic SAR is able to image the area in front of the moving direction of transmitter or receiver, but the geometry model is more complex than that of monostatic SAR, which brings great difficulties to system design and imaging process. Besides, the special geometry configuration of geostationary spaceborne-airborne bistatic forward-looking SAR results in non-orthogonal and non-uniform ground resolution, which is not considered in the traditional range and azimuth resolution. To solve this problem, the resolution ellipse based on the generalised ambiguity function (GAF) is used to maintain the best and worst ground resolution in the resolution cell. The receiver's flight direction is designed to obtain the optimal uniform ground resolution distribution, which has great value for system design and the receiver's path planning. Finally, the accuracy of the resolution ellipse and correctness of the deduced formulas are verified by simulation. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Deep forest for radar HRRP recognition

Deep forest for radar HRRP recognition

引用

IET International Radar Conference 2018, IRC 2018

作者： Wang, Yanhua Bi, Xuejie Chen, Wei Li, Yang Chen, Qiao Long, Teng Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China Beijing Racobit Radar Technology Research Institute Co. Ltd. Beijing China

High-resolution range profile (HRRP) has received intensive attention in the radar automatic target recognition filed. Here, deep forest is applied to the recognition of HRRP. The deep forest is a deep learning method, which is a cascade of ensemble learners. In each layer, there are various ensemble learners. The input of each layer is the combination of the previous layer output and the original input data. The number of cascade levels can be adaptively determined such that the model complexity can be automatically set. Experiments based on measured data show that deep forest is feasible and achieves highly competitive performance for HRRP recognition. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An improved Chinese text multi-label classification method based on CNN 13

An improved Chinese text multi-label classification method b...

引用

2020 13th International Conference on Computer and Electrical Engineering, ICCEE 2020

作者： Xin, Yuanxia Zhang, Zhi Collage of Computer Science and Technology Wuhan University of Science and Technology WuhanHubei430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System WuhanHubei430065 China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology WuhanHubei430065 China

Text multi-label classification technology can accurately and quickly classify text information into related categories or topics, and help people quickly locate the required content in massive information resources, which is of great significance in application. As the traditional classification algorithm is faced with the problems of low classification accuracy due to the low correlation of data labels, unbalanced label data and few short text feature words, this paper firstly performs hierarchical pre-processing on label data to transform multi-label classification into hierarchical text multi-classification. At the same time, an improved multi-label classification algorithm Multi-label Convolutional Neural Networks (ML-CNN) is proposed. Based on the TensorFlow framework, a CNN model is designed and different training models are constructed for each level of label classification. According to the number of classification levels, the output of the upper level label is stitched to the original input tail as the next level of input. Experiments on the description information of 500,000 Chinese products with labels, show that the improved algorithm will significantly improve the classification accuracy and the accuracy of each level can reach more than 88%, which proves the feasibility and effectiveness of the algorithm. © Published under licence by IOP Publishing Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Slow-time MIMO Radar Clutter Mitigation Based on Robust Pulse-to-Pulse Coding

Slow-Time MIMO Radar Clutter Mitigation Based on Robust Puls...

引用

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Feng Xu Junqi Xue Xiaopeng Yang Fawei Yang Zhanze Wang Beijing Key Laboratory of Embedded Real-time Information Processing Technology School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Slow-time MIMO radar is investigated to deal with some cost sensitive applications like UAVs detection to avoid the use of arbitrary waveform generators and digital receivers. But this method suffers from the deterioration of Signal to Noise Ratio (SNR) caused by superposition of clutter. To solve this problem, a robust pulse-to-pulse coding method is proposed to mitigate clutter as well as suppress the sidelobe level in Doppler domain. In our proposed method, the problem of optimizing weighting vector is transformed into a typical MVDR problem and the design of new weighting vector is obtained by the combination of MVDR solution and a sequence of weight coefficients which are calculated by Fourier inversion. This proposed method can mitigate the clutter adaptively while the sidelobe is suppressed. Both simulation and experiments results validate the reliability and effectiveness of this method.

关键词： Clutter Doppler effect MIMO communication MIMO radar Transmitters Encoding Demodulation

来源：评论

学校读者我要写书评

暂无评论

Novel acceleration compensation method for highly squint mode SAR with curve trajectory

引用

The Journal of Engineering 2019年第20期2019卷 6527-6532页

作者： Zhichao Zhou Zegang Ding Tao Zeng Gen Li Linghao Li School of Information and Electronics Beijing Institute Technology Beijing People's Republic of China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing People's Republic of China

Due to the influence of air currents and the control of the platform's own power system, acceleration is often present in the motion platform equipped with synthetic aperture radar (SAR) system, which causes the actual trajectory of the platform to be curved. When the acceleration is large or the azimuth accumulation time is long, a large envelope error or phase error will be caused. This problem will be more obvious in highly squint mode SAR. On the other hand, the acceleration may also cause the situation where the absolute value of the Doppler frequency rate is extremely small, resulting in the azimuthal time-bandwidth product that is too small to satisfy the requirements of the stationary phase principle. To solve the above problems, a novel acceleration compensation method based on inertial navigation information is proposed in this article. By integrating the acceleration and velocity information provided by the inertial navigation system, the position information of maneuvering platform is obtained. Then the actual trajectory of the platform is constructed. On this basis, the envelope and phase errors caused by the acceleration are estimated. The results of real data processing verify the correctness of the analysis and the effectiveness of the proposed method.

关键词： inertial navigation radar imaging synthetic aperture radar compensation real data processing position information acceleration information velocity information power system control phase errors maneuvering platform inertial navigation system inertial navigation information stationary phase principle azimuthal time-bandwidth product Doppler frequency rate envelope error azimuth accumulation time synthetic aperture radar system motion platform air currents curve trajectory highly squint mode SAR novel acceleration compensation method

来源：评论

学校读者我要写书评

暂无评论

Polarised HRRP scattering centre estimation via atomic norm minimisation

Polarised HRRP scattering centre estimation via atomic norm ...

引用

IET International Radar Conference 2018, IRC 2018

作者： Liu, Haibo Xi, Ying Wang, Yanhua Li, Yang Zhao, Tong Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Racobit Radar Technology Research Institute Co. Ltd. Beijing100081 China

The combination of polarisation and high-resolution technology is a promising research direction for radar automatic target recognition. Fusing the polarisation information into the scattering centre model is able to refine the scattering structural information. This study proposes a fully-polarised radar high range resolution profile (HRRP) scattering centre estimation method based on a multiple measurement vector atomic norm minimisation model. The estimation is performed in a continuous domain, thus avoids the basis mismatch problem. The experimental results demonstrate the superiorities of the proposed method in terms of accuracy and robustness. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Cloud detection from visual band of satellite image based on variance of fractal dimension

引用

Journal of Systems Engineering and Electronics 2019年第3期30卷 485-491页

作者： TIAN Pingfang GUANG Qiang LIU Xing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Intelligent Information Processing and Real-Time Industrial System in Hubei Province Wuhan 430065 China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Rich-Media Knowledge Organization and Service of Digital Publishing Content National Press and Publication Administration Beijing 100038 China

Cover ratio of cloud is a very important factor which affects the quality of a satellite image, therefore cloud detection from satellite images is a necessary step in assessing the image quality. The study on cloud detection from the visual band of a satellite image is developed. Firstly, we consider the differences between the cloud and ground including high grey level, good continuity of grey level, area of cloud region, and the variance of local fractal dimension (VLFD) of the cloud region. A single cloud region detection method is proposed. Secondly, by introducing a reference satellite image and by comparing the variance in the dimensions corresponding to the reference and the tested images, a method that detects multiple cloud regions and determines whether or not the cloud exists in an image is described. By using several Ikonos images, the performance of the proposed method is demonstrated.

关键词： cloud detection visual image satellite image variance of local fractal dimension (VLFD)

来源：评论

学校读者我要写书评

暂无评论

A Network Pruning Method for Remote Sensing Image Scene Classification

A Network Pruning Method for Remote Sensing Image Scene Clas...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Qi, Baogui Chen, He Zhuang, Yin Liu, Shaorong Chen, Liang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China School of Electronic Engineering and Computer Science Peking University Beijing100087 China Beijing Institute of Spacecraft System Engineering Beijing100094 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

Deep convolutional neural networks have been widely used to improve remote sensing image scene classification performance. However, most of these networks include many parameters and need many computational resources. Which hinders the applications of these networks when facing the satellite, plane or other mobile platforms. In this paper, we introduce a network pruning framework which can reduce the size of the network model and maintain the classification accuracy. In this framework, we train the pruned model using both the original unpruned model's output and training dataset. Which can learn more information than retrain using dataset only. In our experiments, we evaluate our method for remote sensing scene classification on NWPU-RESISC45 dataset. The results demonstrate that our method was effective and maintained the model classification accuracy. © 2019 IEEE.

关键词： Remote sensing

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：